From c08e31299651410bb39c203a76ab2e853e2ce056 Mon Sep 17 00:00:00 2001 From: Xenia Date: Fri, 19 Jun 2026 13:31:17 +0200 Subject: [PATCH 01/12] Add SameStr workflow --- .../samestr-workflow/.dockstore.yml | 13 + .../microbiome/samestr-workflow/CHANGELOG.md | 5 + ...Galaxy-Workflow-SameStr_Workflow-tests.yml | 81 + .../Galaxy-Workflow-SameStr_Workflow.ga | 2266 +++++++++++++++++ .../microbiome/samestr-workflow/README.md | 21 + 5 files changed, 2386 insertions(+) create mode 100644 workflows/microbiome/samestr-workflow/.dockstore.yml create mode 100644 workflows/microbiome/samestr-workflow/CHANGELOG.md create mode 100644 workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow-tests.yml create mode 100644 workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow.ga create mode 100644 workflows/microbiome/samestr-workflow/README.md diff --git a/workflows/microbiome/samestr-workflow/.dockstore.yml b/workflows/microbiome/samestr-workflow/.dockstore.yml new file mode 100644 index 0000000000..6c74e2f764 --- /dev/null +++ b/workflows/microbiome/samestr-workflow/.dockstore.yml @@ -0,0 +1,13 @@ +version: 1.2 +workflows: +- name: main + subclass: Galaxy + publish: true + primaryDescriptorPath: /Galaxy-Workflow-SameStr_Workflow.ga + testParameterFiles: + - /Galaxy-Workflow-SameStr_Workflow-tests.yml + authors: + - name: 'Xenia ' + familyName: "Morera Mart\xEDnez" + - name: 'Saim ' + familyName: Momin diff --git a/workflows/microbiome/samestr-workflow/CHANGELOG.md b/workflows/microbiome/samestr-workflow/CHANGELOG.md new file mode 100644 index 0000000000..e558ca3732 --- /dev/null +++ b/workflows/microbiome/samestr-workflow/CHANGELOG.md @@ -0,0 +1,5 @@ +# Changelog + +## [0.1] - 2026-06-18 + +First release. diff --git a/workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow-tests.yml b/workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow-tests.yml new file mode 100644 index 0000000000..af2ad9d45b --- /dev/null +++ b/workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow-tests.yml @@ -0,0 +1,81 @@ +- doc: Test outline for SameStr-Workflow + job: + Raw Reads: + class: Collection + collection_type: list:paired + elements: + - class: Collection + type: paired + identifier: 28C + elements: + - class: File + identifier: forward + galaxy_id: "26c75dcccb616ac82be854397f71b1c9" + - class: File + identifier: reverse + galaxy_id: "26c75dcccb616ac8e428a378a8fe9c34" + - class: Collection + type: paired + identifier: 28B + elements: + - class: File + identifier: forward + galaxy_id: "26c75dcccb616ac8fb1de12482e3da71" + - class: File + identifier: reverse + galaxy_id: "26c75dcccb616ac8bf67f112ed1e99a0" + - class: Collection + type: paired + identifier: 28A + elements: + - class: File + identifier: forward + galaxy_id: "26c75dcccb616ac83af14439b6619568" + - class: File + identifier: reverse + galaxy_id: "26c75dcccb616ac83b3c1acd5116120b" + Run mOTUs: false + Run MetaPhlAn: true + outputs: + stats_file_metaphlan: + element_tests: + t__SGB15299: + asserts: + has_text: + text: "28B" + t__SGB4285: + asserts: + has_text: + text: "28B" + t__SGB6362: + asserts: + has_text: + text: "28B" + taxon_counts_metaphlan: + asserts: + has_text: + text: "28A" + has_text: + text: "28B" + has_text: + text: "28C" + strain_events_metaphlan: + asserts: + has_text: + text: "t__SGB15299" + has_text: + text: "t__SGB4285" + has_text: + text: "t__SGB6362" + has_text: + text: "28B" + has_text: + text: "28C" + cooccurrences_metaphlan: + asserts: + has_text: + text: "28A" + has_text: + text: "28B" + has_text: + text: "28C" diff --git a/workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow.ga b/workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow.ga new file mode 100644 index 0000000000..a8d30eef8c --- /dev/null +++ b/workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow.ga @@ -0,0 +1,2266 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "This workflow performs strain-level metagenomic analysis of shotgun sequencing data, enabling taxonomic profiling, strain identification, and shared strain detection across samples.", + "comments": [ + { + "child_steps": [ + 3, + 4 + ], + "color": "yellow", + "data": { + "title": "Preprocessing Steps" + }, + "id": 1, + "position": [ + 316.5, + 43.9 + ], + "size": [ + 516, + 356 + ], + "type": "frame" + }, + { + "child_steps": [ + 0 + ], + "color": "red", + "data": { + "title": "Inputs" + }, + "id": 0, + "position": [ + 0, + 101.4 + ], + "size": [ + 240, + 121.2 + ], + "type": "frame" + }, + { + "color": "none", + "data": { + "size": 2, + "text": "
" + }, + "id": 2, + "position": [ + 259.2, + 646 + ], + "size": [ + 0, + 0 + ], + "type": "text" + } + ], + "creator": [ + { + "class": "Person", + "familyName": "Morera Mart\u00ednez", + "name": "Xenia " + }, + { + "class": "Person", + "familyName": "Momin", + "name": "Saim " + } + ], + "format-version": "0.1", + "license": "MIT", + "name": "SameStr Workflow", + "report": { + "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" + }, + "outputs": [ + { + "label": "stats_file_metaphlan", + "output_name": "stats_file_metaphlan" + }, + { + "label": "taxon_counts_metaphlan", + "output_name": "taxon_counts_metaphlan" + }, + { + "label": "strain_events_metaphlan", + "output_name": "strain_events_metaphlan" + }, + { + "label": "cooccurrences_metaphlan", + "output_name": "cooccurrences_metaphlan" + }, + { + "label": "stats_file_motus", + "output_name": "stats_file_motus" + }, + { + "label": "taxon_counts_motus", + "output_name": "taxon_counts_motus" + }, + { + "label": "strain_events_motus", + "output_name": "strain_events_motus" + }, + { + "label": "cooccurrences_motus", + "output_name": "cooccurrences_motus" + } + ], + "steps": { + "0": { + "annotation": "Raw paired-end sequencing reads in FASTQ format. ", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "Raw paired-end sequencing reads in FASTQ format. ", + "name": "Raw Reads" + } + ], + "label": "Raw Reads", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 19.99998512403619, + "top": 141.40169542817313 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "d5cfa62b-9d85-497b-8ad3-a5a3e48d21ad", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "Run mOTUs subworkflow for shared strain detection.", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "Run mOTUs subworkflow for shared strain detection.", + "name": "Run mOTUs" + } + ], + "label": "Run mOTUs", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 987.6423524333857, + "top": 0.1667327880859375 + }, + "tool_id": null, + "tool_state": "{\"default\": false, \"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "9d41f03f-7ed3-4f25-a75d-72d900fc8a43", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "Run MetaPhlAn subworkflow for shared strain detection.", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "Run MetaPhlAn subworkflow for shared strain detection.", + "name": "Run MetaPhlAn" + } + ], + "label": "Run MetaPhlAn", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 992.4084167480469, + "top": 440.3083190917969 + }, + "tool_id": null, + "tool_state": "{\"default\": true, \"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "3750ea2c-d863-44f0-942f-6086a93f0162", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "Quality trimming and host read removal", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/kneaddata/kneaddata/0.12.1+galaxy1", + "errors": null, + "id": 3, + "input_connections": { + "read_type|paired_collection": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool KneadData", + "name": "read_type" + } + ], + "label": "Trimming and Host Removal", + "name": "KneadData", + "outputs": [ + { + "name": "paired_output", + "type": "input" + }, + { + "name": "unmatched_paired", + "type": "input" + }, + { + "name": "trimmed_paired", + "type": "input" + }, + { + "name": "unmatched_trimmed_paired", + "type": "input" + }, + { + "name": "log_file", + "type": "txt" + } + ], + "position": { + "left": 347.21852281613917, + "top": 79.24585125852026 + }, + "post_job_actions": { + "HideDatasetActiontrimmed_paired": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "trimmed_paired" + }, + "HideDatasetActionunmatched_trimmed_paired": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "unmatched_trimmed_paired" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/kneaddata/kneaddata/0.12.1+galaxy1", + "tool_shed_repository": { + "changeset_revision": "10f8abc1fbdf", + "name": "kneaddata", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"alignment\": {\"alignment_tool\": {\"tool_choice\": \"bowtie2\", \"__current_case__\": 0, \"bowtie2_db\": \"hg19\"}, \"save_contaminants\": false}, \"fastqc\": {\"fastqc_report\": {\"select_fastqc\": \"no_fastqc\", \"__current_case__\": 1}, \"run_trim_repetitive\": false}, \"log_level\": \"INFO\", \"read_type\": {\"select_read_type\": \"paired\", \"__current_case__\": 1, \"save_unmatched\": true, \"paired_collection\": {\"__class__\": \"ConnectedValue\"}}, \"tandem\": {\"trf_step\": {\"trf_bool\": \"skip\", \"__current_case__\": 1}}, \"trimmomatic\": {\"trimmomatic_step\": {\"decide_trimmomatic\": \"run_trimmomatic\", \"__current_case__\": 0, \"sequencer\": \"NexteraPE\"}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.12.1+galaxy1", + "type": "tool", + "uuid": "82d77df5-b99a-4f75-b0f3-7fbb15801f2f", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "Merge paired-end and orphaned reads from KneadData output", + "content_id": "__MERGE_COLLECTION__", + "errors": null, + "id": 4, + "input_connections": { + "inputs_0|input": { + "id": 3, + "output_name": "paired_output" + }, + "inputs_1|input": { + "id": 3, + "output_name": "unmatched_paired" + } + }, + "inputs": [], + "label": "Merge Collections", + "name": "Merge collections", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 612.5937791206638, + "top": 101.86172339925348 + }, + "post_job_actions": {}, + "tool_id": "__MERGE_COLLECTION__", + "tool_state": "{\"advanced\": {\"conflict\": {\"duplicate_options\": \"keep_first\", \"__current_case__\": 3}}, \"inputs\": [{\"__index__\": 0, \"input\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"input\": {\"__class__\": \"ConnectedValue\"}}], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.0", + "type": "tool", + "uuid": "a5e4be2f-5314-4af7-a08e-7e9e2f416710", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "Taxonomic profiling with mOTUs", + "id": 5, + "input_connections": { + "Raw Inputs": { + "id": 4, + "input_subworkflow_step_id": 0, + "output_name": "output" + }, + "when": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "Taxonomic profiling with mOTUs", + "name": "mOTUs Subworkflow" + } + ], + "label": "mOTUs Subworkflow", + "name": "mOTUs Subworkflow", + "outputs": [], + "position": { + "left": 1266.5750427246094, + "top": 0 + }, + "subworkflow": { + "a_galaxy_workflow": "true", + "annotation": "", + "comments": [ + { + "child_steps": [ + 20 + ], + "color": "green", + "data": { + "title": "SameStr Output" + }, + "id": 3, + "position": [ + 2971.1, + 65.1 + ], + "size": [ + 247, + 417 + ], + "type": "frame" + }, + { + "child_steps": [ + 19 + ], + "color": "green", + "data": { + "title": "SameStr Output" + }, + "id": 2, + "position": [ + 2779.8, + 514.5 + ], + "size": [ + 241, + 216 + ], + "type": "frame" + }, + { + "child_steps": [ + 13, + 12, + 7, + 14 + ], + "color": "turquoise", + "data": { + "title": "SameStr Strain-level Analysis" + }, + "id": 1, + "position": [ + 1226.1, + 104.8 + ], + "size": [ + 1265.7, + 311.9 + ], + "type": "frame" + }, + { + "child_steps": [ + 6, + 5 + ], + "color": "orange", + "data": { + "title": "Taxonomic Profiling and Marker-Based AlignmentFrame" + }, + "id": 0, + "position": [ + 866.9, + 0 + ], + "size": [ + 241.1, + 367 + ], + "type": "frame" + } + ], + "creator": [ + { + "class": "Person", + "familyName": "Morera Mart\u00ednez", + "name": "Xenia" + }, + { + "class": "Person", + "familyName": "Momin", + "name": "Saim" + } + ], + "format-version": "0.1", + "license": "MIT", + "name": "mOTUs Subworkflow", + "report": { + "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" + }, + "steps": { + "0": { + "annotation": "Merged paired-end and orphaned reads", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "Merged paired-end and orphaned reads", + "name": "Raw Inputs" + } + ], + "label": "Raw Inputs", + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 0, + "top": 128.73394695351277 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "15ed0dc8-e3e6-46a7-93c5-9fb6494fb49b", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "", + "content_id": "__EXTRACT_DATASET__", + "errors": null, + "id": 1, + "input_connections": { + "input": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": "Extract Forward Reads 2", + "name": "Extract dataset", + "outputs": [ + { + "name": "output", + "type": "data" + } + ], + "position": { + "left": 275.5362707054305, + "top": 45.50926482270616 + }, + "post_job_actions": {}, + "tool_id": "__EXTRACT_DATASET__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"which\": {\"which_dataset\": \"by_index\", \"__current_case__\": 2, \"index\": \"0\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.2", + "type": "tool", + "uuid": "5ac92002-0fb0-4d49-a457-80139e51f8bc", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "", + "content_id": "__EXTRACT_DATASET__", + "errors": null, + "id": 2, + "input_connections": { + "input": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": "Extract Reverse Reads 2", + "name": "Extract dataset", + "outputs": [ + { + "name": "output", + "type": "data" + } + ], + "position": { + "left": 273.55029717097636, + "top": 182.63944336940284 + }, + "post_job_actions": {}, + "tool_id": "__EXTRACT_DATASET__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"which\": {\"which_dataset\": \"by_index\", \"__current_case__\": 2, \"index\": \"1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.2", + "type": "tool", + "uuid": "7996854f-77ba-4f82-995d-653abd62a079", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", + "errors": null, + "id": 3, + "input_connections": { + "input_list": { + "id": 1, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Collapse Collection", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 552.0248259632644, + "top": 39.9230628562196 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", + "tool_shed_repository": { + "changeset_revision": "90981f86000f", + "name": "collapse_collections", + "owner": "nml", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"filename\": {\"add_name\": false, \"__current_case__\": 1}, \"input_list\": {\"__class__\": \"ConnectedValue\"}, \"one_header\": false, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "5.1.0", + "type": "tool", + "uuid": "7a97b520-d68d-4d9a-a34d-6475f40d8a56", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", + "errors": null, + "id": 4, + "input_connections": { + "input_list": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Collapse Collection", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 550.9437432540947, + "top": 196.2375242685519 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", + "tool_shed_repository": { + "changeset_revision": "90981f86000f", + "name": "collapse_collections", + "owner": "nml", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"filename\": {\"add_name\": false, \"__current_case__\": 1}, \"input_list\": {\"__class__\": \"ConnectedValue\"}, \"one_header\": false, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "5.1.0", + "type": "tool", + "uuid": "c3305f5a-681c-4449-a38e-4d1b9d2447f9", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "Profile microbial community composition using universal marker genes", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_profiler/3.1.0+galaxy1", + "errors": null, + "id": 5, + "input_connections": { + "inputs|input_type|reads_type|forward_reads": { + "id": 3, + "output_name": "output" + }, + "inputs|input_type|reads_type|reverse_reads": { + "id": 4, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "mOTUs_profiler", + "outputs": [ + { + "name": "output_motus", + "type": "txt" + } + ], + "position": { + "left": 885.1262385199572, + "top": 65.75285272023278 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_profiler/3.1.0+galaxy1", + "tool_shed_repository": { + "changeset_revision": "b2b7a3897ef6", + "name": "motus", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"algorithm_advanced_options\": {\"advanced_options\": {\"customize_algorithm_options\": \"default_options\", \"__current_case__\": 1}}, \"all_taxonomic_level\": false, \"biom_format\": false, \"cami_format_option\": {\"cami_options\": \"no\", \"__current_case__\": 1}, \"full_rank_taxonomy\": false, \"full_species_name\": false, \"inputs\": {\"input_type\": {\"selector\": \"reads\", \"__current_case__\": 0, \"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}}, \"sample_name\": null, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": \"db_from_2026-04-27T094930Z\"}}, \"ncbi_taxonomy_ids\": false, \"ref_motus\": false, \"result_as_counts\": false, \"save_bam\": false, \"save_mgc\": false, \"taxonomic_level_option\": {\"taxonomic_option\": \"no\", \"__current_case__\": 1}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "3.1.0+galaxy1", + "type": "tool", + "uuid": "696af434-1636-458f-ba0d-5abda5f7a622", + "when": null, + "workflow_outputs": [] + }, + "6": { + "annotation": "Map reads to mOTUs marker gene database for SNV calling", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_map_snv/3.1.0+galaxy0", + "errors": null, + "id": 6, + "input_connections": { + "inputs|reads_type|forward_reads": { + "id": 3, + "output_name": "output" + }, + "inputs|reads_type|reverse_reads": { + "id": 4, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Map SNV", + "outputs": [ + { + "name": "bam_output", + "type": "bam" + } + ], + "position": { + "left": 886.8530294435432, + "top": 224.19755572219503 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_map_snv/3.1.0+galaxy0", + "tool_shed_repository": { + "changeset_revision": "b2b7a3897ef6", + "name": "motus", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"algorithm_advanced_options\": {\"verbosity_level_selection\": \"3\", \"minimum_alignment_len\": \"75\"}, \"inputs\": {\"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": \"db_from_2026-04-27T094930Z\"}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "3.1.0+galaxy0", + "type": "tool", + "uuid": "c88518b5-264a-4743-9945-4a06e116d669", + "when": null, + "workflow_outputs": [] + }, + "7": { + "annotation": "Convert BAM to SNV profiles for SameStr analysis", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", + "errors": null, + "id": 7, + "input_connections": { + "alignment": { + "id": 6, + "output_name": "bam_output" + }, + "profile": { + "id": 5, + "output_name": "output_motus" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Convert", + "outputs": [ + { + "name": "npz_files", + "type": "input" + }, + { + "name": "stats_file", + "type": "tabular" + } + ], + "position": { + "left": 1261.8275092603064, + "top": 158.33909953778584 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": \"db_from_2026-04-27T094930Z\", \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "56abb72c-8e85-40ff-b4e2-1e392e80f6ce", + "when": null, + "workflow_outputs": [] + }, + "8": { + "annotation": "Flatten collection to allow cross-sample SNV profile comparison. Note: this modifies element identifiers by adding an underscore, which makes naming afterwards unstable for SameStr", + "content_id": "__FLATTEN__", + "errors": null, + "id": 8, + "input_connections": { + "input": { + "id": 7, + "output_name": "npz_files" + } + }, + "inputs": [], + "label": null, + "name": "Flatten collection", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 1137.183961831004, + "top": 548.5279972044827 + }, + "post_job_actions": {}, + "tool_id": "__FLATTEN__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"join_identifier\": \"_\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.0", + "type": "tool", + "uuid": "c3e62419-c72d-41e8-8efc-d4f124b982d7", + "when": null, + "workflow_outputs": [] + }, + "9": { + "annotation": "Extract element identifiers from flattened collection to prepare for renaming", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", + "errors": null, + "id": 9, + "input_connections": { + "input_collection": { + "id": 8, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Extract element identifiers", + "outputs": [ + { + "name": "output", + "type": "txt" + } + ], + "position": { + "left": 1442.2054905379298, + "top": 561.7634317296073 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", + "tool_shed_repository": { + "changeset_revision": "3e27acfa4830", + "name": "collection_element_identifiers", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"input_collection\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.0.3", + "type": "tool", + "uuid": "1dcc573e-640d-4d59-a571-cdbd85f5dc46", + "when": null, + "workflow_outputs": [] + }, + "10": { + "annotation": "Clean element identifiers after flattening to restore compatible naming for downstream tools", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", + "errors": null, + "id": 10, + "input_connections": { + "input": { + "id": 9, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Regex Find And Replace", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 1720.0195463093285, + "top": 569.6499661192393 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", + "tool_shed_repository": { + "changeset_revision": "503bcd6ebe4b", + "name": "regex_find_replace", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"checks\": [{\"__index__\": 0, \"pattern\": \"^[^_]+_\", \"replacement\": \"\"}], \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.3", + "type": "tool", + "uuid": "cff1e2ca-8a4a-4440-b31f-e13fdbff9200", + "when": null, + "workflow_outputs": [] + }, + "11": { + "annotation": "Rename cleaned identifiers to match SameStr expected format", + "content_id": "__RELABEL_FROM_FILE__", + "errors": null, + "id": 11, + "input_connections": { + "how|labels": { + "id": 10, + "output_name": "out_file1" + }, + "input": { + "id": 8, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Relabel identifiers", + "name": "how" + } + ], + "label": null, + "name": "Relabel identifiers", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2016.8126786335886, + "top": 548.8749942290515 + }, + "post_job_actions": {}, + "tool_id": "__RELABEL_FROM_FILE__", + "tool_state": "{\"how\": {\"how_select\": \"txt\", \"__current_case__\": 0, \"labels\": {\"__class__\": \"ConnectedValue\"}, \"strict\": false}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "63710c7f-f0c1-4110-b701-83d3e1920c6d", + "when": null, + "workflow_outputs": [] + }, + "12": { + "annotation": "Merge SNV profiles from multiple samples for cross-sample strain comparison", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", + "errors": null, + "id": 12, + "input_connections": { + "input_files": { + "id": 11, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Merge", + "outputs": [ + { + "name": "npz_files", + "type": "input" + }, + { + "name": "sample_name", + "type": "input" + } + ], + "position": { + "left": 1627.4833264469337, + "top": 181.20514913656223 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"clade\": null, \"database\": \"db_from_2026-04-27T094930Z\", \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "71266426-6068-484c-891c-934ebbc7c3e7", + "when": null, + "workflow_outputs": [] + }, + "13": { + "annotation": "Filter SNV profiles to retain high confidence variants for strain analysis", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", + "errors": null, + "id": 13, + "input_connections": { + "input_names": { + "id": 12, + "output_name": "sample_name" + }, + "input_snvs": { + "id": 12, + "output_name": "npz_files" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool SameStr Filter", + "name": "sample_filtering" + } + ], + "label": null, + "name": "SameStr Filter", + "outputs": [ + { + "name": "filtered_profile", + "type": "npz" + }, + { + "name": "sample_names", + "type": "tabular" + } + ], + "position": { + "left": 1993.7006647946978, + "top": 172.32397552702548 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": \"db_from_2026-04-27T094930Z\", \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "63048b47-0099-4866-b51f-897324b1a499", + "when": null, + "workflow_outputs": [] + }, + "14": { + "annotation": "Compare SNV profiles across samples to identify shared strains", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", + "errors": null, + "id": 14, + "input_connections": { + "input_names": { + "id": 13, + "output_name": "sample_names" + }, + "input_snvs": { + "id": 13, + "output_name": "filtered_profile" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Compare", + "outputs": [ + { + "name": "overlap_file", + "type": "tabular" + }, + { + "name": "close_file", + "type": "tabular" + }, + { + "name": "fraction_file", + "type": "tabular" + } + ], + "position": { + "left": 2271.7786830381865, + "top": 144.78305330970247 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"database\": \"db_from_2026-04-27T094930Z\", \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "b44c7357-4903-485d-8c5c-fc9b0563aa04", + "when": null, + "workflow_outputs": [] + }, + "15": { + "annotation": "empty datasets with insufficient coverage or no SNVs detected", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 15, + "input_connections": { + "input": { + "id": 13, + "output_name": "filtered_profile" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2496.1663411369873, + "top": 435.7383376287588 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "6d907258-064b-4399-b470-a1a1255702a1", + "when": null, + "workflow_outputs": [] + }, + "16": { + "annotation": "empty datasets with insufficient coverage or no SNVs detected", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 16, + "input_connections": { + "input": { + "id": 13, + "output_name": "sample_names" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2499.049389896233, + "top": 609.799429971278 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "850e77e8-2159-4029-90e0-c99668f52d7b", + "when": null, + "workflow_outputs": [] + }, + "17": { + "annotation": "empty datasets with insufficient coverage or no SNVs detected", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 17, + "input_connections": { + "input": { + "id": 14, + "output_name": "fraction_file" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2674.136469674208, + "top": 32.28881158568977 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "c6084e15-55eb-4a8e-ad31-1cfdbeab0df5", + "when": null, + "workflow_outputs": [] + }, + "18": { + "annotation": "empty datasets with insufficient coverage or no SNVs detected", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 18, + "input_connections": { + "input": { + "id": 14, + "output_name": "overlap_file" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2684.140946034504, + "top": 214.49601656615144 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "c2aa3a79-6f1d-43ba-a3db-5b1ede2b003b", + "when": null, + "workflow_outputs": [] + }, + "19": { + "annotation": "Generate summary statistics of SNV profiles per sample", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", + "errors": null, + "id": 19, + "input_connections": { + "input_names": { + "id": 16, + "output_name": "output" + }, + "input_snvs": { + "id": 15, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Stats", + "outputs": [ + { + "name": "stats_file", + "type": "tabular" + } + ], + "position": { + "left": 2799.761534585506, + "top": 554.5036623080092 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"database\": \"db_from_2026-04-27T094930Z\", \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "e0f8fb96-7c7b-46b6-b609-5d5e7e3618c9", + "when": null, + "workflow_outputs": [ + { + "label": "stats_file_motus", + "output_name": "stats_file", + "uuid": "5d7e7125-1ea5-46ad-9d3c-a1aefbb1e489" + } + ] + }, + "20": { + "annotation": "Summarize strain sharing results across all sample pairs", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", + "errors": null, + "id": 20, + "input_connections": { + "overlaps": { + "id": 18, + "output_name": "output" + }, + "similarities": { + "id": 17, + "output_name": "output" + }, + "tax_profiles": { + "id": 5, + "output_name": "output_motus" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Summarize", + "outputs": [ + { + "name": "cooccurrences", + "type": "tabular" + }, + { + "name": "strain_events", + "type": "tabular" + }, + { + "name": "taxon_counts", + "type": "tabular" + } + ], + "position": { + "left": 2991.083575513044, + "top": 105.97949575129569 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": \"db_from_2026-04-27T094930Z\", \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "7fe1a149-9d24-48b7-a81c-f9548eddfea7", + "when": null, + "workflow_outputs": [ + { + "label": "cooccurrences_motus", + "output_name": "cooccurrences", + "uuid": "a4ae9512-dee1-48e7-92c3-6be570af50dc" + }, + { + "label": "strain_events_motus", + "output_name": "strain_events", + "uuid": "85a78d13-bf76-4dad-b072-89a88ee5d01d" + }, + { + "label": "taxon_counts_motus", + "output_name": "taxon_counts", + "uuid": "9009bfe0-75d3-455d-b932-1ccef119da77" + } + ] + } + }, + "tags": [], + "uuid": "2cb7814e-4e14-4697-b5c4-ab2d4c41e052" + }, + "tool_id": null, + "type": "subworkflow", + "uuid": "0841c539-6ebb-4406-b3b0-e3e9a6d6bf9f", + "when": "$(inputs.when)", + "workflow_outputs": [ + { + "label": "strain_events_motus", + "output_name": "strain_events_motus", + "uuid": "8e255eab-cb55-472c-bb47-65eb3a6920cc" + }, + { + "label": "stats_file_motus", + "output_name": "stats_file_motus", + "uuid": "f88720e9-5001-4e0c-9df6-a2dd1c5a07bb" + }, + { + "label": "cooccurrences_motus", + "output_name": "cooccurrences_motus", + "uuid": "fb239d56-1750-4007-89ef-f40602df8307" + }, + { + "label": "taxon_counts_motus", + "output_name": "taxon_counts_motus", + "uuid": "adf9d1e7-368f-4277-a701-d82d7d4ae0e7" + } + ] + }, + "6": { + "annotation": "Taxonomic profiling with MetaPhlAn ", + "id": 6, + "input_connections": { + "0:Input dataset collection": { + "id": 4, + "input_subworkflow_step_id": 0, + "output_name": "output" + }, + "when": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "Taxonomic profiling with MetaPhlAn ", + "name": "Metaphlan Subworkflow" + } + ], + "label": "Metaphlan Subworkflow", + "name": "Metaphlan Subworkflow", + "outputs": [], + "position": { + "left": 1262.2417907714844, + "top": 321.0083923339844 + }, + "subworkflow": { + "a_galaxy_workflow": "true", + "annotation": "", + "comments": [ + { + "child_steps": [ + 16 + ], + "color": "green", + "data": { + "title": "SameStr Output" + }, + "id": 3, + "position": [ + 2877.7875, + 89 + ], + "size": [ + 245, + 479 + ], + "type": "frame" + }, + { + "child_steps": [ + 9, + 8, + 3, + 10 + ], + "color": "turquoise", + "data": { + "title": "SameStr Strain-level Analysis" + }, + "id": 1, + "position": [ + 1092.0875, + 117.30000000000001 + ], + "size": [ + 1284, + 298 + ], + "type": "frame" + }, + { + "child_steps": [ + 15 + ], + "color": "green", + "data": { + "title": "SameStr Output" + }, + "id": 2, + "position": [ + 2447.3875, + 512.4 + ], + "size": [ + 243, + 222 + ], + "type": "frame" + }, + { + "child_steps": [ + 1 + ], + "color": "orange", + "data": { + "title": "Taxonomic Profiling and Marker-Based Alignment" + }, + "id": 0, + "position": [ + 358.3875, + 0 + ], + "size": [ + 240, + 284.4 + ], + "type": "frame" + } + ], + "format-version": "0.1", + "name": "Metaphlan Subworkflow", + "report": { + "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" + }, + "steps": { + "0": { + "annotation": "Merged paired-end and orphaned reads", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [], + "label": null, + "name": "Input dataset collection", + "outputs": [], + "position": { + "left": 0, + "top": 23.475 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", + "tool_version": null, + "type": "data_collection_input", + "uuid": "3517c677-41a8-4963-b760-60c3e79dd9d1", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "Generate taxonomic profiles and marker gene alignments for SameStr", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/metaphlan/metaphlan/4.2.4+galaxy0", + "errors": null, + "id": 1, + "input_connections": { + "inputs|in|raw_in|in": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool MetaPhlAn", + "name": "analysis" + } + ], + "label": null, + "name": "MetaPhlAn", + "outputs": [ + { + "name": "output_file", + "type": "tabular" + }, + { + "name": "mapout", + "type": "tabular" + }, + { + "name": "sam_output_file", + "type": "sam" + } + ], + "position": { + "left": 378.3625183105469, + "top": 54.387506103515626 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/metaphlan/metaphlan/4.2.4+galaxy0", + "tool_shed_repository": { + "changeset_revision": "56ff60ec416d", + "name": "metaphlan", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"analysis\": {\"analysis_type\": {\"t\": \"rel_ab\", \"__current_case__\": 0, \"tax_lev\": {\"tax_lev\": \"a\", \"__current_case__\": 0, \"split_levels\": false}}, \"min_alignment_len\": null, \"organism_profiling\": null, \"stat\": \"tavg_g\", \"stat_q\": \"0.2\", \"perc_nonzero\": \"0.33\", \"ignore_markers\": {\"__class__\": \"RuntimeValue\"}, \"avoid_disqm\": true}, \"inputs\": {\"in\": {\"selector\": \"raw\", \"__current_case__\": 0, \"raw_in\": {\"selector\": \"paired_collection\", \"__current_case__\": 2, \"in\": {\"__class__\": \"ConnectedValue\"}}, \"read_min_len\": \"70\", \"mapping\": {\"bt2_ps\": \"very-sensitive\", \"min_mapq_val\": \"5\"}}, \"db\": {\"db_selector\": \"cached\", \"__current_case__\": 0, \"cached_db\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"viral_analysis\": {\"profile_vsc\": \"\", \"__current_case__\": 1}}}, \"out\": {\"sample_id_key\": \"SampleID\", \"sample_id\": \"Metaphlan_Analysis\", \"use_group_representative\": false, \"CAMI_format_output\": false, \"skip_unclassified_estimation\": false, \"biom_format_output\": false, \"krona_output\": false}, \"subsample\": {\"selector\": \"no\", \"__current_case__\": 0}, \"test\": \"false\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "4.2.4+galaxy0", + "type": "tool", + "uuid": "2024124c-b74b-4851-843e-2119d8824dec", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "Convert SAM to BAM format", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samtools_view/samtools_view/1.22+galaxy2", + "errors": null, + "id": 2, + "input_connections": { + "input": { + "id": 1, + "output_name": "sam_output_file" + } + }, + "inputs": [], + "label": null, + "name": "Samtools view", + "outputs": [ + { + "name": "outputsam", + "type": "input" + } + ], + "position": { + "left": 754.0375671386719, + "top": 273.9250122070313 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samtools_view/samtools_view/1.22+galaxy2", + "tool_shed_repository": { + "changeset_revision": "5cf9fcc93508", + "name": "samtools_view", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"addref_cond\": {\"addref_select\": \"no\", \"__current_case__\": 0}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"mode\": {\"outtype\": \"all_reads\", \"__current_case__\": 0, \"output_options\": {\"reads_report_type\": \"retained\", \"__current_case__\": 0, \"adv_output\": {\"readtags\": [], \"collapsecigar\": false}, \"output_format\": {\"oformat\": \"bam\", \"__current_case__\": 2}}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.22+galaxy2", + "type": "tool", + "uuid": "4166154d-3177-470a-af56-aaadc1a39165", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "Convert BAM to SNV profiles for SameStr analysis", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", + "errors": null, + "id": 3, + "input_connections": { + "alignment": { + "id": 2, + "output_name": "outputsam" + }, + "profile": { + "id": 1, + "output_name": "output_file" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Convert", + "outputs": [ + { + "name": "npz_files", + "type": "input" + }, + { + "name": "stats_file", + "type": "tabular" + } + ], + "position": { + "left": 1112.0749816894531, + "top": 165.487451171875 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "f63a91e2-40b5-4d61-b398-21016209f9af", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "Flatten collection to allow cross-sample SNV profile comparison. Note: this modifies element identifiers by adding an underscore, which makes naming afterwards unstable for SameStr", + "content_id": "__FLATTEN__", + "errors": null, + "id": 4, + "input_connections": { + "input": { + "id": 3, + "output_name": "npz_files" + } + }, + "inputs": [], + "label": null, + "name": "Flatten collection", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 866.5750427246094, + "top": 603.0000244140625 + }, + "post_job_actions": {}, + "tool_id": "__FLATTEN__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"join_identifier\": \"_\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.0", + "type": "tool", + "uuid": "390d4a87-df49-4921-af66-242f7bb67e06", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "Extract element identifiers from flattened collection to prepare for renaming", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", + "errors": null, + "id": 5, + "input_connections": { + "input_collection": { + "id": 4, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Extract element identifiers", + "outputs": [ + { + "name": "output", + "type": "txt" + } + ], + "position": { + "left": 1170.5999450683594, + "top": 602.8875366210938 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", + "tool_shed_repository": { + "changeset_revision": "3e27acfa4830", + "name": "collection_element_identifiers", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"input_collection\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.0.3", + "type": "tool", + "uuid": "2277359e-9fff-4a91-ac55-de361a90439c", + "when": null, + "workflow_outputs": [] + }, + "6": { + "annotation": "Clean element identifiers after flattening to restore compatible naming for downstream tools", + "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", + "errors": null, + "id": 6, + "input_connections": { + "input": { + "id": 5, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Regex Find And Replace", + "outputs": [ + { + "name": "out_file1", + "type": "input" + } + ], + "position": { + "left": 1456.9501085652712, + "top": 607.8749560421887 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", + "tool_shed_repository": { + "changeset_revision": "503bcd6ebe4b", + "name": "regex_find_replace", + "owner": "galaxyp", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"checks\": [{\"__index__\": 0, \"pattern\": \"^[^_]+_\", \"replacement\": \"\"}], \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.3", + "type": "tool", + "uuid": "52c68971-3407-49c2-bd29-9bfa40c06ad5", + "when": null, + "workflow_outputs": [] + }, + "7": { + "annotation": "Rename cleaned identifiers to match SameStr expected format", + "content_id": "__RELABEL_FROM_FILE__", + "errors": null, + "id": 7, + "input_connections": { + "how|labels": { + "id": 6, + "output_name": "out_file1" + }, + "input": { + "id": 4, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Relabel identifiers", + "name": "how" + } + ], + "label": null, + "name": "Relabel identifiers", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 1708.700108565271, + "top": 593.76246824922 + }, + "post_job_actions": {}, + "tool_id": "__RELABEL_FROM_FILE__", + "tool_state": "{\"how\": {\"how_select\": \"txt\", \"__current_case__\": 0, \"labels\": {\"__class__\": \"ConnectedValue\"}, \"strict\": false}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "10bb239a-98ea-42df-b481-fcb1311da260", + "when": null, + "workflow_outputs": [] + }, + "8": { + "annotation": "Merge SNV profiles from multiple samples for cross-sample strain comparison", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", + "errors": null, + "id": 8, + "input_connections": { + "input_files": { + "id": 7, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Merge", + "outputs": [ + { + "name": "npz_files", + "type": "input" + }, + { + "name": "sample_name", + "type": "input" + } + ], + "position": { + "left": 1483.7124938964844, + "top": 172.42501220703124 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"clade\": null, \"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "ce294c50-ae1d-4bd9-a514-ab503fb4c9b7", + "when": null, + "workflow_outputs": [] + }, + "9": { + "annotation": "Filter SNV profiles to retain high confidence variants for strain analysis", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", + "errors": null, + "id": 9, + "input_connections": { + "input_names": { + "id": 8, + "output_name": "sample_name" + }, + "input_snvs": { + "id": 8, + "output_name": "npz_files" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool SameStr Filter", + "name": "sample_filtering" + } + ], + "label": null, + "name": "SameStr Filter", + "outputs": [ + { + "name": "filtered_profile", + "type": "npz" + }, + { + "name": "sample_names", + "type": "tabular" + } + ], + "position": { + "left": 1823.2750597371457, + "top": 171.13749876679842 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "4a661ef3-3f7c-4c5d-866f-d2f034afda7e", + "when": null, + "workflow_outputs": [] + }, + "10": { + "annotation": "Compare SNV profiles across samples to identify shared strains", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", + "errors": null, + "id": 10, + "input_connections": { + "input_names": { + "id": 9, + "output_name": "sample_names" + }, + "input_snvs": { + "id": 9, + "output_name": "filtered_profile" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Compare", + "outputs": [ + { + "name": "overlap_file", + "type": "tabular" + }, + { + "name": "close_file", + "type": "tabular" + }, + { + "name": "fraction_file", + "type": "tabular" + } + ], + "position": { + "left": 2155.5249938964844, + "top": 157.26250610351562 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "0e149f56-196c-43ba-a8e1-2b37555efeb7", + "when": null, + "workflow_outputs": [] + }, + "11": { + "annotation": "empty datasets with insufficient coverage or no SNVs detected", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 11, + "input_connections": { + "input": { + "id": 9, + "output_name": "filtered_profile" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2192.550018310547, + "top": 441.3875366210938 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "4edb9ead-f835-4884-9ce9-8a401e1d371a", + "when": null, + "workflow_outputs": [] + }, + "12": { + "annotation": "empty datasets with insufficient coverage or no SNVs detected", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 12, + "input_connections": { + "input": { + "id": 9, + "output_name": "sample_names" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2197.612518310547, + "top": 618.900048828125 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "7c14bf4c-ae4d-42ea-bd53-3d00f172b9a9", + "when": null, + "workflow_outputs": [] + }, + "13": { + "annotation": "empty datasets with insufficient coverage or no SNVs detected", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 13, + "input_connections": { + "input": { + "id": 10, + "output_name": "overlap_file" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2460.0125427246094, + "top": 73.67498168945312 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "d098e445-5b12-4d54-8012-c547773689a2", + "when": null, + "workflow_outputs": [] + }, + "14": { + "annotation": "empty datasets with insufficient coverage or no SNVs detected", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 14, + "input_connections": { + "input": { + "id": 10, + "output_name": "fraction_file" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2461.962559737145, + "top": 263.36250487031396 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "790c8cb1-51e7-4714-8ade-30442337be24", + "when": null, + "workflow_outputs": [] + }, + "15": { + "annotation": "Generate summary statistics of SNV profiles per sample", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", + "errors": null, + "id": 15, + "input_connections": { + "input_names": { + "id": 12, + "output_name": "output" + }, + "input_snvs": { + "id": 11, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Stats", + "outputs": [ + { + "name": "stats_file", + "type": "tabular" + } + ], + "position": { + "left": 2467.4124450683594, + "top": 552.3750244140625 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "3dfdf54a-5c95-4b6b-bb03-5b8a6f7603c8", + "when": null, + "workflow_outputs": [ + { + "label": "stats_file_metaphlan", + "output_name": "stats_file", + "uuid": "010faa73-37a4-4609-b724-4de5cdbd8284" + } + ] + }, + "16": { + "annotation": "Summarize strain sharing results across all sample pairs", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", + "errors": null, + "id": 16, + "input_connections": { + "overlaps": { + "id": 13, + "output_name": "output" + }, + "similarities": { + "id": 14, + "output_name": "output" + }, + "tax_profiles": { + "id": 1, + "output_name": "output_file" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Summarize", + "outputs": [ + { + "name": "cooccurrences", + "type": "tabular" + }, + { + "name": "strain_events", + "type": "tabular" + }, + { + "name": "taxon_counts", + "type": "tabular" + } + ], + "position": { + "left": 2897.7834118519604, + "top": 129.03333497002757 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "c67ca84a-bd25-4161-9771-e8a4af61dda8", + "when": null, + "workflow_outputs": [ + { + "label": "cooccurrences_metaphlan", + "output_name": "cooccurrences", + "uuid": "bbed4322-9b5e-44ef-add5-80ebe52f3d8f" + }, + { + "label": "taxon_counts_metaphlan", + "output_name": "taxon_counts", + "uuid": "515aa694-9278-4949-8df6-8787dd7488f1" + }, + { + "label": "strain_events_metaphlan", + "output_name": "strain_events", + "uuid": "eba65d16-643b-43e8-8bd1-e4aedbaf4b86" + } + ] + } + }, + "tags": [], + "uuid": "c8e27718-529f-4b32-8a1e-23d54be0c03a" + }, + "tool_id": null, + "type": "subworkflow", + "uuid": "c08e32e9-daed-408b-9eb9-b8801fc2193d", + "when": "$(inputs.when)", + "workflow_outputs": [ + { + "label": "taxon_counts_metaphlan", + "output_name": "taxon_counts_metaphlan", + "uuid": "ffa8076e-da12-424c-b64a-d835716c4684" + }, + { + "label": "strain_events_metaphlan", + "output_name": "strain_events_metaphlan", + "uuid": "a64d8146-b48d-4df0-9467-9864bb4577f9" + }, + { + "label": "stats_file_metaphlan", + "output_name": "stats_file_metaphlan", + "uuid": "8561dee5-e0b2-446f-8837-b105c56ad848" + }, + { + "label": "cooccurrences_metaphlan", + "output_name": "cooccurrences_metaphlan", + "uuid": "2461dbeb-6783-466f-8ae9-eda0bef85de5" + } + ] + } + }, + "tags": [ + "Metagenomics", + "microbiome", + "shared-strains" + ], + "uuid": "e708b582-edad-4273-aa71-de991244b74c", + "version": 52 +} \ No newline at end of file diff --git a/workflows/microbiome/samestr-workflow/README.md b/workflows/microbiome/samestr-workflow/README.md new file mode 100644 index 0000000000..d1ee5c97df --- /dev/null +++ b/workflows/microbiome/samestr-workflow/README.md @@ -0,0 +1,21 @@ +# SameStr Workflow for Strain-Level Analysis of FMT Samples + +This workflow processes paired-end shotgun metagenomic sequencing reads from pre-FMT (recipient), donor, and post-FMT samples. It performs the following steps: + +- **Preprocessing**: Quality trimming and host read removal using KneadData +- **Taxonomic profiling**: MetaPhlAn4 or mOTUs for taxonomic classification +- **Marker-based alignment**: MetaPhlAn or mOTUs for alignment +- **Strain detection**: SameStr tools identify strains across samples and compute pairwise strain comparisons using Maximum Variant Profile Similarity (MVS) scores. + +## Inputs + +- **Raw Reads**: A collection of paired-end FASTQ files (`.fastq.gz`) representing pre-FMT, donor, and post-FMT samples +- **Run MetaPhlAn**: Boolean parameter (default: true) that enables MetaPhlAn-based strain detection +- **Run mOTUs**: Boolean parameter (default: false) that enables mOTUs-based strain detection + +## Outputs + +- **stats_file**: Summary statistics of SNV profiles per sample +- **taxon_counts**: Taxonomic abundance table +- **strain_events**: Strain-level events detected across samples +- **cooccurrences**: Strain co-occurrence patterns across samples From 3133db5cbf138a6a776bcd26890b6315182eea2e Mon Sep 17 00:00:00 2001 From: xens25 Date: Fri, 19 Jun 2026 14:15:27 +0200 Subject: [PATCH 02/12] Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --- workflows/microbiome/samestr-workflow/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/workflows/microbiome/samestr-workflow/README.md b/workflows/microbiome/samestr-workflow/README.md index d1ee5c97df..e06e7b6b9f 100644 --- a/workflows/microbiome/samestr-workflow/README.md +++ b/workflows/microbiome/samestr-workflow/README.md @@ -1,6 +1,6 @@ -# SameStr Workflow for Strain-Level Analysis of FMT Samples +# SameStr workflow for shared-strain detection in metagenomes -This workflow processes paired-end shotgun metagenomic sequencing reads from pre-FMT (recipient), donor, and post-FMT samples. It performs the following steps: +This workflow processes paired-end shotgun metagenomic sequencing reads from multiple samples. It performs the following steps: - **Preprocessing**: Quality trimming and host read removal using KneadData - **Taxonomic profiling**: MetaPhlAn4 or mOTUs for taxonomic classification From e781751a5bc4eefb1eb8845c570fe4978ece0f27 Mon Sep 17 00:00:00 2001 From: Xenia Date: Sat, 20 Jun 2026 18:40:28 +0200 Subject: [PATCH 03/12] Applied Copilot suggestions --- .../samestr-workflow/.dockstore.yml | 9 +- .../microbiome/samestr-workflow/README.md | 8 +- ...w-tests.yml => samestr-workflow-tests.yml} | 26 +- ...ameStr_Workflow.ga => samestr-workflow.ga} | 289 ++++++++---------- 4 files changed, 148 insertions(+), 184 deletions(-) rename workflows/microbiome/samestr-workflow/{Galaxy-Workflow-SameStr_Workflow-tests.yml => samestr-workflow-tests.yml} (65%) rename workflows/microbiome/samestr-workflow/{Galaxy-Workflow-SameStr_Workflow.ga => samestr-workflow.ga} (96%) diff --git a/workflows/microbiome/samestr-workflow/.dockstore.yml b/workflows/microbiome/samestr-workflow/.dockstore.yml index 6c74e2f764..0c2a730202 100644 --- a/workflows/microbiome/samestr-workflow/.dockstore.yml +++ b/workflows/microbiome/samestr-workflow/.dockstore.yml @@ -3,11 +3,8 @@ workflows: - name: main subclass: Galaxy publish: true - primaryDescriptorPath: /Galaxy-Workflow-SameStr_Workflow.ga + primaryDescriptorPath: /samestr-workflow.ga testParameterFiles: - - /Galaxy-Workflow-SameStr_Workflow-tests.yml + - /samestr-workflow-tests.yml authors: - - name: 'Xenia ' - familyName: "Morera Mart\xEDnez" - - name: 'Saim ' - familyName: Momin + - name: 'Xenia Morera Martinez' diff --git a/workflows/microbiome/samestr-workflow/README.md b/workflows/microbiome/samestr-workflow/README.md index e06e7b6b9f..570fbe359a 100644 --- a/workflows/microbiome/samestr-workflow/README.md +++ b/workflows/microbiome/samestr-workflow/README.md @@ -9,13 +9,11 @@ This workflow processes paired-end shotgun metagenomic sequencing reads from mul ## Inputs -- **Raw Reads**: A collection of paired-end FASTQ files (`.fastq.gz`) representing pre-FMT, donor, and post-FMT samples +- **Raw Reads**: A collection of paired-end FASTQ files from one or more samples to compare - **Run MetaPhlAn**: Boolean parameter (default: true) that enables MetaPhlAn-based strain detection - **Run mOTUs**: Boolean parameter (default: false) that enables mOTUs-based strain detection ## Outputs -- **stats_file**: Summary statistics of SNV profiles per sample -- **taxon_counts**: Taxonomic abundance table -- **strain_events**: Strain-level events detected across samples -- **cooccurrences**: Strain co-occurrence patterns across samples + - **MetaPhlAn results** (if enabled): SNV profile summary statistics, taxon counts, strain events, and co-occurrence tables + - **mOTUs results** (if enabled): SNV profile summary statistics, taxon counts, strain events, and co-occurrence tables diff --git a/workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow-tests.yml b/workflows/microbiome/samestr-workflow/samestr-workflow-tests.yml similarity index 65% rename from workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow-tests.yml rename to workflows/microbiome/samestr-workflow/samestr-workflow-tests.yml index af2ad9d45b..43455506b0 100644 --- a/workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow-tests.yml +++ b/workflows/microbiome/samestr-workflow/samestr-workflow-tests.yml @@ -10,34 +10,40 @@ elements: - class: File identifier: forward - galaxy_id: "26c75dcccb616ac82be854397f71b1c9" + location: https://zenodo.org/records/20745835/files/28C_R1.fastq.gz + filetype: fastqsanger.gz - class: File identifier: reverse - galaxy_id: "26c75dcccb616ac8e428a378a8fe9c34" + location: https://zenodo.org/records/20745835/files/28C_R2.fastq.gz + filetype: fastqsanger.gz - class: Collection type: paired identifier: 28B elements: - class: File identifier: forward - galaxy_id: "26c75dcccb616ac8fb1de12482e3da71" + location: https://zenodo.org/records/20745835/files/28B_R1.fastq.gz + filetype: fastqsanger.gz - class: File identifier: reverse - galaxy_id: "26c75dcccb616ac8bf67f112ed1e99a0" + location: https://zenodo.org/records/20745835/files/28B_R2.fastq.gz + filetype: fastqsanger.gz - class: Collection type: paired identifier: 28A elements: - class: File identifier: forward - galaxy_id: "26c75dcccb616ac83af14439b6619568" + location: https://zenodo.org/records/20745835/files/28A_R1.fastq.gz + filetype: fastqsanger.gz - class: File identifier: reverse - galaxy_id: "26c75dcccb616ac83b3c1acd5116120b" + location: https://zenodo.org/records/20745835/files/28A_R2.fastq.gz + filetype: fastqsanger.gz Run mOTUs: false Run MetaPhlAn: true outputs: - stats_file_metaphlan: + "Stats file (MetaPhlAn)": element_tests: t__SGB15299: asserts: @@ -51,7 +57,7 @@ asserts: has_text: text: "28B" - taxon_counts_metaphlan: + "Taxon counts (MetaPhlAn)": asserts: has_text: text: "28A" @@ -59,7 +65,7 @@ text: "28B" has_text: text: "28C" - strain_events_metaphlan: + "Strain events (MetaPhlAn)": asserts: has_text: text: "t__SGB15299" @@ -71,7 +77,7 @@ text: "28B" has_text: text: "28C" - cooccurrences_metaphlan: + "Co-occurrences (MetaPhlAn)": asserts: has_text: text: "28A" diff --git a/workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow.ga b/workflows/microbiome/samestr-workflow/samestr-workflow.ga similarity index 96% rename from workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow.ga rename to workflows/microbiome/samestr-workflow/samestr-workflow.ga index a8d30eef8c..295e92911e 100644 --- a/workflows/microbiome/samestr-workflow/Galaxy-Workflow-SameStr_Workflow.ga +++ b/workflows/microbiome/samestr-workflow/samestr-workflow.ga @@ -2,26 +2,6 @@ "a_galaxy_workflow": "true", "annotation": "This workflow performs strain-level metagenomic analysis of shotgun sequencing data, enabling taxonomic profiling, strain identification, and shared strain detection across samples.", "comments": [ - { - "child_steps": [ - 3, - 4 - ], - "color": "yellow", - "data": { - "title": "Preprocessing Steps" - }, - "id": 1, - "position": [ - 316.5, - 43.9 - ], - "size": [ - 516, - 356 - ], - "type": "frame" - }, { "child_steps": [ 0 @@ -33,7 +13,7 @@ "id": 0, "position": [ 0, - 101.4 + 106.63711806335814 ], "size": [ 240, @@ -50,13 +30,33 @@ "id": 2, "position": [ 259.2, - 646 + 651.2371180633581 ], "size": [ 0, 0 ], "type": "text" + }, + { + "child_steps": [ + 3, + 4 + ], + "color": "yellow", + "data": { + "title": "Preprocessing Steps" + }, + "id": 1, + "position": [ + 316.5, + 49.137118063358145 + ], + "size": [ + 516, + 356 + ], + "type": "frame" } ], "creator": [ @@ -77,40 +77,6 @@ "report": { "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" }, - "outputs": [ - { - "label": "stats_file_metaphlan", - "output_name": "stats_file_metaphlan" - }, - { - "label": "taxon_counts_metaphlan", - "output_name": "taxon_counts_metaphlan" - }, - { - "label": "strain_events_metaphlan", - "output_name": "strain_events_metaphlan" - }, - { - "label": "cooccurrences_metaphlan", - "output_name": "cooccurrences_metaphlan" - }, - { - "label": "stats_file_motus", - "output_name": "stats_file_motus" - }, - { - "label": "taxon_counts_motus", - "output_name": "taxon_counts_motus" - }, - { - "label": "strain_events_motus", - "output_name": "strain_events_motus" - }, - { - "label": "cooccurrences_motus", - "output_name": "cooccurrences_motus" - } - ], "steps": { "0": { "annotation": "Raw paired-end sequencing reads in FASTQ format. ", @@ -129,7 +95,7 @@ "outputs": [], "position": { "left": 19.99998512403619, - "top": 141.40169542817313 + "top": 146.63881349153127 }, "tool_id": null, "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", @@ -156,7 +122,7 @@ "outputs": [], "position": { "left": 987.6423524333857, - "top": 0.1667327880859375 + "top": 5.403850851444081 }, "tool_id": null, "tool_state": "{\"default\": false, \"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", @@ -183,7 +149,7 @@ "outputs": [], "position": { "left": 992.4084167480469, - "top": 440.3083190917969 + "top": 445.545437155155 }, "tool_id": null, "tool_state": "{\"default\": true, \"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", @@ -236,7 +202,7 @@ ], "position": { "left": 347.21852281613917, - "top": 79.24585125852026 + "top": 84.4829693218784 }, "post_job_actions": { "HideDatasetActiontrimmed_paired": { @@ -291,7 +257,7 @@ ], "position": { "left": 612.5937791206638, - "top": 101.86172339925348 + "top": 107.09884146261162 }, "post_job_actions": {}, "tool_id": "__MERGE_COLLECTION__", @@ -328,7 +294,7 @@ "outputs": [], "position": { "left": 1266.5750427246094, - "top": 0 + "top": 0.0 }, "subworkflow": { "a_galaxy_workflow": "true", @@ -336,8 +302,24 @@ "comments": [ { "child_steps": [ - 20 + 19 + ], + "color": "green", + "data": { + "title": "SameStr Output" + }, + "id": 2, + "position": [ + 2779.8, + 514.5 + ], + "size": [ + 241, + 216 ], + "type": "frame" + }, + { "color": "green", "data": { "title": "SameStr Output" @@ -355,20 +337,21 @@ }, { "child_steps": [ - 19 + 6, + 5 ], - "color": "green", + "color": "orange", "data": { - "title": "SameStr Output" + "title": "Taxonomic Profiling and Marker-Based AlignmentFrame" }, - "id": 2, + "id": 0, "position": [ - 2779.8, - 514.5 + 866.9, + 0 ], "size": [ - 241, - 216 + 241.1, + 367 ], "type": "frame" }, @@ -393,26 +376,6 @@ 311.9 ], "type": "frame" - }, - { - "child_steps": [ - 6, - 5 - ], - "color": "orange", - "data": { - "title": "Taxonomic Profiling and Marker-Based AlignmentFrame" - }, - "id": 0, - "position": [ - 866.9, - 0 - ], - "size": [ - 241.1, - 367 - ], - "type": "frame" } ], "creator": [ @@ -1251,9 +1214,9 @@ "when": null, "workflow_outputs": [ { - "label": "stats_file_motus", + "label": "Stats file (mOTUs)", "output_name": "stats_file", - "uuid": "5d7e7125-1ea5-46ad-9d3c-a1aefbb1e489" + "uuid": "02aae137-a5f5-4090-ba11-49923c09286d" } ] }, @@ -1313,25 +1276,25 @@ "when": null, "workflow_outputs": [ { - "label": "cooccurrences_motus", - "output_name": "cooccurrences", - "uuid": "a4ae9512-dee1-48e7-92c3-6be570af50dc" + "label": "Taxon counts (mOTUs)", + "output_name": "taxon_counts", + "uuid": "6ab5dc84-3c03-411c-8dcb-f2412d69c332" }, { - "label": "strain_events_motus", + "label": "Strain events (mOTUs)", "output_name": "strain_events", - "uuid": "85a78d13-bf76-4dad-b072-89a88ee5d01d" + "uuid": "20da34ba-86e5-4a28-ab4c-6158480747be" }, { - "label": "taxon_counts_motus", - "output_name": "taxon_counts", - "uuid": "9009bfe0-75d3-455d-b932-1ccef119da77" + "label": "Co-occurrences (mOTUs)", + "output_name": "cooccurrences", + "uuid": "69dabd78-7640-475a-94e3-05f9625f4e12" } ] } }, "tags": [], - "uuid": "2cb7814e-4e14-4697-b5c4-ab2d4c41e052" + "uuid": "0ef8afaf-7578-4279-a2a3-885fe5ae3c6b" }, "tool_id": null, "type": "subworkflow", @@ -1339,24 +1302,24 @@ "when": "$(inputs.when)", "workflow_outputs": [ { - "label": "strain_events_motus", - "output_name": "strain_events_motus", - "uuid": "8e255eab-cb55-472c-bb47-65eb3a6920cc" + "label": "Co-occurrences (mOTUs)", + "output_name": "Co-occurrences (mOTUs)", + "uuid": "c6c44065-1358-40fd-82d4-e5a42d336371" }, { - "label": "stats_file_motus", - "output_name": "stats_file_motus", - "uuid": "f88720e9-5001-4e0c-9df6-a2dd1c5a07bb" + "label": "Taxon counts (mOTUs)", + "output_name": "Taxon counts (mOTUs)", + "uuid": "c2ff3bad-5a37-4752-a050-f6a0c6e747e8" }, { - "label": "cooccurrences_motus", - "output_name": "cooccurrences_motus", - "uuid": "fb239d56-1750-4007-89ef-f40602df8307" + "label": "Strain events (mOTUs)", + "output_name": "Strain events (mOTUs)", + "uuid": "783f2882-bf8f-4b4f-9925-d60766e3450e" }, { - "label": "taxon_counts_motus", - "output_name": "taxon_counts_motus", - "uuid": "adf9d1e7-368f-4277-a701-d82d7d4ae0e7" + "label": "Stats file (mOTUs)", + "output_name": "Stats file (mOTUs)", + "uuid": "3b2b48ef-d311-4317-b888-50fd7f956297" } ] }, @@ -1384,8 +1347,8 @@ "name": "Metaphlan Subworkflow", "outputs": [], "position": { - "left": 1262.2417907714844, - "top": 321.0083923339844 + "left": 1268.6418151855469, + "top": 342.2455256561316 }, "subworkflow": { "a_galaxy_workflow": "true", @@ -1393,20 +1356,20 @@ "comments": [ { "child_steps": [ - 16 + 1 ], - "color": "green", + "color": "orange", "data": { - "title": "SameStr Output" + "title": "Taxonomic Profiling and Marker-Based Alignment" }, - "id": 3, + "id": 0, "position": [ - 2877.7875, - 89 + 358.3875, + 0 ], "size": [ - 245, - 479 + 240, + 284.4 ], "type": "frame" }, @@ -1434,39 +1397,39 @@ }, { "child_steps": [ - 15 + 16 ], "color": "green", "data": { "title": "SameStr Output" }, - "id": 2, + "id": 3, "position": [ - 2447.3875, - 512.4 + 2877.7875, + 89 ], "size": [ - 243, - 222 + 245, + 479 ], "type": "frame" }, { "child_steps": [ - 1 + 15 ], - "color": "orange", + "color": "green", "data": { - "title": "Taxonomic Profiling and Marker-Based Alignment" + "title": "SameStr Output" }, - "id": 0, + "id": 2, "position": [ - 358.3875, - 0 + 2447.3875, + 512.4 ], "size": [ - 240, - 284.4 + 243, + 222 ], "type": "frame" } @@ -2146,9 +2109,9 @@ "when": null, "workflow_outputs": [ { - "label": "stats_file_metaphlan", + "label": "Stats file (MetaPhlAn)", "output_name": "stats_file", - "uuid": "010faa73-37a4-4609-b724-4de5cdbd8284" + "uuid": "3e0b436a-485a-48eb-870c-c0928c1c54d8" } ] }, @@ -2208,25 +2171,25 @@ "when": null, "workflow_outputs": [ { - "label": "cooccurrences_metaphlan", + "label": "Co-occurrences (MetaPhlAn)", "output_name": "cooccurrences", - "uuid": "bbed4322-9b5e-44ef-add5-80ebe52f3d8f" + "uuid": "b9b9a2ea-45a5-4874-895d-8b334da3c289" }, { - "label": "taxon_counts_metaphlan", - "output_name": "taxon_counts", - "uuid": "515aa694-9278-4949-8df6-8787dd7488f1" + "label": "Strain events (MetaPhlAn)", + "output_name": "strain_events", + "uuid": "c3833465-80a0-486f-b54f-0eda31728915" }, { - "label": "strain_events_metaphlan", - "output_name": "strain_events", - "uuid": "eba65d16-643b-43e8-8bd1-e4aedbaf4b86" + "label": "Taxon counts (MetaPhlAn)", + "output_name": "taxon_counts", + "uuid": "376e6e79-0cc9-449b-bd6e-948da38a297c" } ] } }, "tags": [], - "uuid": "c8e27718-529f-4b32-8a1e-23d54be0c03a" + "uuid": "d860cdf4-5d79-4ac0-8301-b4716e0996c0" }, "tool_id": null, "type": "subworkflow", @@ -2234,24 +2197,24 @@ "when": "$(inputs.when)", "workflow_outputs": [ { - "label": "taxon_counts_metaphlan", - "output_name": "taxon_counts_metaphlan", - "uuid": "ffa8076e-da12-424c-b64a-d835716c4684" + "label": "Co-occurrences (MetaPhlAn)", + "output_name": "Co-occurrences (MetaPhlAn)", + "uuid": "70aa3d70-8961-481b-a143-9b364663cbdc" }, { - "label": "strain_events_metaphlan", - "output_name": "strain_events_metaphlan", - "uuid": "a64d8146-b48d-4df0-9467-9864bb4577f9" + "label": "Stats file (MetaPhlAn)", + "output_name": "Stats file (MetaPhlAn)", + "uuid": "72a9cdb9-4472-42d9-bc0e-090341889275" }, { - "label": "stats_file_metaphlan", - "output_name": "stats_file_metaphlan", - "uuid": "8561dee5-e0b2-446f-8837-b105c56ad848" + "label": "Taxon counts (MetaPhlAn)", + "output_name": "Taxon counts (MetaPhlAn)", + "uuid": "06652c72-c3f3-4f1e-bb5d-47c6b90e8e5e" }, { - "label": "cooccurrences_metaphlan", - "output_name": "cooccurrences_metaphlan", - "uuid": "2461dbeb-6783-466f-8ae9-eda0bef85de5" + "label": "Strain events (MetaPhlAn)", + "output_name": "Strain events (MetaPhlAn)", + "uuid": "56b78ea8-129b-4606-b557-304c03460562" } ] } @@ -2261,6 +2224,6 @@ "microbiome", "shared-strains" ], - "uuid": "e708b582-edad-4273-aa71-de991244b74c", - "version": 52 + "uuid": "7af358a3-fd2b-4fb1-a667-60f79c08402f", + "version": 57 } \ No newline at end of file From a824fc03ae357803d0c6e89f6faabb962983b82c Mon Sep 17 00:00:00 2001 From: Xenia Date: Mon, 22 Jun 2026 09:11:57 +0200 Subject: [PATCH 04/12] add fix --- workflows/microbiome/samestr-workflow/samestr-workflow.ga | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/workflows/microbiome/samestr-workflow/samestr-workflow.ga b/workflows/microbiome/samestr-workflow/samestr-workflow.ga index 295e92911e..5f21b9df7a 100644 --- a/workflows/microbiome/samestr-workflow/samestr-workflow.ga +++ b/workflows/microbiome/samestr-workflow/samestr-workflow.ga @@ -73,6 +73,7 @@ ], "format-version": "0.1", "license": "MIT", + "release": "0.1", "name": "SameStr Workflow", "report": { "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" @@ -2226,4 +2227,4 @@ ], "uuid": "7af358a3-fd2b-4fb1-a667-60f79c08402f", "version": 57 -} \ No newline at end of file +} From 41459b3b6ff54a9c2ef53454d8aa9fe48439141a Mon Sep 17 00:00:00 2001 From: xens25 Date: Tue, 23 Jun 2026 17:26:09 +0200 Subject: [PATCH 05/12] Apply suggestions from code review Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> --- workflows/microbiome/samestr-workflow/.dockstore.yml | 5 +++-- workflows/microbiome/samestr-workflow/samestr-workflow.ga | 4 ++-- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/workflows/microbiome/samestr-workflow/.dockstore.yml b/workflows/microbiome/samestr-workflow/.dockstore.yml index 0c2a730202..3d4a823dee 100644 --- a/workflows/microbiome/samestr-workflow/.dockstore.yml +++ b/workflows/microbiome/samestr-workflow/.dockstore.yml @@ -5,6 +5,7 @@ workflows: publish: true primaryDescriptorPath: /samestr-workflow.ga testParameterFiles: - - /samestr-workflow-tests.yml + - /samestr-workflow-tests.yml authors: - - name: 'Xenia Morera Martinez' + - name: 'Xenia Morera Martínez' + - name: 'Saim Momin' diff --git a/workflows/microbiome/samestr-workflow/samestr-workflow.ga b/workflows/microbiome/samestr-workflow/samestr-workflow.ga index 5f21b9df7a..ec37531785 100644 --- a/workflows/microbiome/samestr-workflow/samestr-workflow.ga +++ b/workflows/microbiome/samestr-workflow/samestr-workflow.ga @@ -63,12 +63,12 @@ { "class": "Person", "familyName": "Morera Mart\u00ednez", - "name": "Xenia " + "name": "Xenia" }, { "class": "Person", "familyName": "Momin", - "name": "Saim " + "name": "Saim" } ], "format-version": "0.1", From 59a7b984c621189ce5df9db29ec593c609913dde Mon Sep 17 00:00:00 2001 From: Xenia Date: Tue, 23 Jun 2026 18:36:33 +0200 Subject: [PATCH 06/12] fixed readme, fixed names, added orcid, made several parameters configurable --- workflows/microbiome/samestr-workflow/.dockstore.yml | 2 +- workflows/microbiome/samestr-workflow/README.md | 3 +-- workflows/microbiome/samestr-workflow/samestr-workflow.ga | 8 ++------ 3 files changed, 4 insertions(+), 9 deletions(-) diff --git a/workflows/microbiome/samestr-workflow/.dockstore.yml b/workflows/microbiome/samestr-workflow/.dockstore.yml index 3d4a823dee..695fdc2d29 100644 --- a/workflows/microbiome/samestr-workflow/.dockstore.yml +++ b/workflows/microbiome/samestr-workflow/.dockstore.yml @@ -8,4 +8,4 @@ workflows: - /samestr-workflow-tests.yml authors: - name: 'Xenia Morera Martínez' - - name: 'Saim Momin' + orcid: 0009-0000-2380-8385 diff --git a/workflows/microbiome/samestr-workflow/README.md b/workflows/microbiome/samestr-workflow/README.md index 570fbe359a..9b6d12cf75 100644 --- a/workflows/microbiome/samestr-workflow/README.md +++ b/workflows/microbiome/samestr-workflow/README.md @@ -3,8 +3,7 @@ This workflow processes paired-end shotgun metagenomic sequencing reads from multiple samples. It performs the following steps: - **Preprocessing**: Quality trimming and host read removal using KneadData -- **Taxonomic profiling**: MetaPhlAn4 or mOTUs for taxonomic classification -- **Marker-based alignment**: MetaPhlAn or mOTUs for alignment +- **Taxonomic profiling and marker-based alignment**: MetaPhlAn4 or mOTUs for taxonomic classification and marker based alignment - **Strain detection**: SameStr tools identify strains across samples and compute pairwise strain comparisons using Maximum Variant Profile Similarity (MVS) scores. ## Inputs diff --git a/workflows/microbiome/samestr-workflow/samestr-workflow.ga b/workflows/microbiome/samestr-workflow/samestr-workflow.ga index ec37531785..dd3a8bd3a5 100644 --- a/workflows/microbiome/samestr-workflow/samestr-workflow.ga +++ b/workflows/microbiome/samestr-workflow/samestr-workflow.ga @@ -62,13 +62,9 @@ "creator": [ { "class": "Person", - "familyName": "Morera Mart\u00ednez", + "familyName": "Morera Martínez", "name": "Xenia" - }, - { - "class": "Person", - "familyName": "Momin", - "name": "Saim" + "identifier": "https://orcid.org/0009-0000-2380-8385" } ], "format-version": "0.1", From 57545dd575386f34efb0e93548ea9aa99859f7f4 Mon Sep 17 00:00:00 2001 From: Xenia Date: Tue, 23 Jun 2026 18:37:26 +0200 Subject: [PATCH 07/12] fixed readme, fixed names, added orcid, made several parameters configurable --- .../samestr-workflow/samestr-workflow.ga | 32 +++++++++---------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/workflows/microbiome/samestr-workflow/samestr-workflow.ga b/workflows/microbiome/samestr-workflow/samestr-workflow.ga index dd3a8bd3a5..3dee8d2f92 100644 --- a/workflows/microbiome/samestr-workflow/samestr-workflow.ga +++ b/workflows/microbiome/samestr-workflow/samestr-workflow.ga @@ -220,7 +220,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"alignment\": {\"alignment_tool\": {\"tool_choice\": \"bowtie2\", \"__current_case__\": 0, \"bowtie2_db\": \"hg19\"}, \"save_contaminants\": false}, \"fastqc\": {\"fastqc_report\": {\"select_fastqc\": \"no_fastqc\", \"__current_case__\": 1}, \"run_trim_repetitive\": false}, \"log_level\": \"INFO\", \"read_type\": {\"select_read_type\": \"paired\", \"__current_case__\": 1, \"save_unmatched\": true, \"paired_collection\": {\"__class__\": \"ConnectedValue\"}}, \"tandem\": {\"trf_step\": {\"trf_bool\": \"skip\", \"__current_case__\": 1}}, \"trimmomatic\": {\"trimmomatic_step\": {\"decide_trimmomatic\": \"run_trimmomatic\", \"__current_case__\": 0, \"sequencer\": \"NexteraPE\"}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"alignment\": {\"alignment_tool\": {\"tool_choice\": \"bowtie2\", \"__current_case__\": 0, \"bowtie2_db\": {\"__class__\": \"RuntimeValue\"}}, \"save_contaminants\": false}, \"fastqc\": {\"fastqc_report\": {\"select_fastqc\": \"no_fastqc\", \"__current_case__\": 1}, \"run_trim_repetitive\": false}, \"log_level\": \"INFO\", \"read_type\": {\"select_read_type\": \"paired\", \"__current_case__\": 1, \"save_unmatched\": true, \"paired_collection\": {\"__class__\": \"ConnectedValue\"}}, \"tandem\": {\"trf_step\": {\"trf_bool\": \"skip\", \"__current_case__\": 1}}, \"trimmomatic\": {\"trimmomatic_step\": {\"decide_trimmomatic\": \"run_trimmomatic\", \"__current_case__\": 0, \"sequencer\": {\"__class__\": \"RuntimeValue\"}}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "0.12.1+galaxy1", "type": "tool", @@ -605,7 +605,7 @@ "owner": "bgruening", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"algorithm_advanced_options\": {\"advanced_options\": {\"customize_algorithm_options\": \"default_options\", \"__current_case__\": 1}}, \"all_taxonomic_level\": false, \"biom_format\": false, \"cami_format_option\": {\"cami_options\": \"no\", \"__current_case__\": 1}, \"full_rank_taxonomy\": false, \"full_species_name\": false, \"inputs\": {\"input_type\": {\"selector\": \"reads\", \"__current_case__\": 0, \"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}}, \"sample_name\": null, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": \"db_from_2026-04-27T094930Z\"}}, \"ncbi_taxonomy_ids\": false, \"ref_motus\": false, \"result_as_counts\": false, \"save_bam\": false, \"save_mgc\": false, \"taxonomic_level_option\": {\"taxonomic_option\": \"no\", \"__current_case__\": 1}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"algorithm_advanced_options\": {\"advanced_options\": {\"customize_algorithm_options\": \"default_options\", \"__current_case__\": 1}}, \"all_taxonomic_level\": false, \"biom_format\": false, \"cami_format_option\": {\"cami_options\": \"no\", \"__current_case__\": 1}, \"full_rank_taxonomy\": false, \"full_species_name\": false, \"inputs\": {\"input_type\": {\"selector\": \"reads\", \"__current_case__\": 0, \"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}}, \"sample_name\": null, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": {\"__class__\": \"RuntimeValue\"}}, \"ncbi_taxonomy_ids\": false, \"ref_motus\": false, \"result_as_counts\": false, \"save_bam\": false, \"save_mgc\": false, \"taxonomic_level_option\": {\"taxonomic_option\": \"no\", \"__current_case__\": 1}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "3.1.0+galaxy1", "type": "tool", @@ -649,7 +649,7 @@ "owner": "bgruening", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"algorithm_advanced_options\": {\"verbosity_level_selection\": \"3\", \"minimum_alignment_len\": \"75\"}, \"inputs\": {\"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": \"db_from_2026-04-27T094930Z\"}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"algorithm_advanced_options\": {\"verbosity_level_selection\": \"3\", \"minimum_alignment_len\": \"75\"}, \"inputs\": {\"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": {\"__class__\": \"RuntimeValue\"}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "3.1.0+galaxy0", "type": "tool", @@ -697,7 +697,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": \"db_from_2026-04-27T094930Z\", \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -898,7 +898,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"clade\": null, \"database\": \"db_from_2026-04-27T094930Z\", \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"clade\": null, \"database\": {\"__class__\": \"RuntimeValue\"}, \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -951,7 +951,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": \"db_from_2026-04-27T094930Z\", \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1003,7 +1003,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"database\": \"db_from_2026-04-27T094930Z\", \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"database\": {\"__class__\": \"RuntimeValue\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1203,7 +1203,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"database\": \"db_from_2026-04-27T094930Z\", \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"database\": {\"__class__\": \"RuntimeValue\"}, \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1265,7 +1265,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": \"db_from_2026-04-27T094930Z\", \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1504,7 +1504,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"analysis\": {\"analysis_type\": {\"t\": \"rel_ab\", \"__current_case__\": 0, \"tax_lev\": {\"tax_lev\": \"a\", \"__current_case__\": 0, \"split_levels\": false}}, \"min_alignment_len\": null, \"organism_profiling\": null, \"stat\": \"tavg_g\", \"stat_q\": \"0.2\", \"perc_nonzero\": \"0.33\", \"ignore_markers\": {\"__class__\": \"RuntimeValue\"}, \"avoid_disqm\": true}, \"inputs\": {\"in\": {\"selector\": \"raw\", \"__current_case__\": 0, \"raw_in\": {\"selector\": \"paired_collection\", \"__current_case__\": 2, \"in\": {\"__class__\": \"ConnectedValue\"}}, \"read_min_len\": \"70\", \"mapping\": {\"bt2_ps\": \"very-sensitive\", \"min_mapq_val\": \"5\"}}, \"db\": {\"db_selector\": \"cached\", \"__current_case__\": 0, \"cached_db\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"viral_analysis\": {\"profile_vsc\": \"\", \"__current_case__\": 1}}}, \"out\": {\"sample_id_key\": \"SampleID\", \"sample_id\": \"Metaphlan_Analysis\", \"use_group_representative\": false, \"CAMI_format_output\": false, \"skip_unclassified_estimation\": false, \"biom_format_output\": false, \"krona_output\": false}, \"subsample\": {\"selector\": \"no\", \"__current_case__\": 0}, \"test\": \"false\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"analysis\": {\"analysis_type\": {\"t\": \"rel_ab\", \"__current_case__\": 0, \"tax_lev\": {\"tax_lev\": \"a\", \"__current_case__\": 0, \"split_levels\": false}}, \"min_alignment_len\": null, \"organism_profiling\": null, \"stat\": \"tavg_g\", \"stat_q\": \"0.2\", \"perc_nonzero\": \"0.33\", \"ignore_markers\": {\"__class__\": \"RuntimeValue\"}, \"avoid_disqm\": true}, \"inputs\": {\"in\": {\"selector\": \"raw\", \"__current_case__\": 0, \"raw_in\": {\"selector\": \"paired_collection\", \"__current_case__\": 2, \"in\": {\"__class__\": \"ConnectedValue\"}}, \"read_min_len\": \"70\", \"mapping\": {\"bt2_ps\": \"very-sensitive\", \"min_mapq_val\": \"5\"}}, \"db\": {\"db_selector\": \"cached\", \"__current_case__\": 0, \"cached_db\": {\"__class__\": \"RuntimeValue\"}, \"viral_analysis\": {\"profile_vsc\": \"\", \"__current_case__\": 1}}}, \"out\": {\"sample_id_key\": \"SampleID\", \"sample_id\": \"Metaphlan_Analysis\", \"use_group_representative\": false, \"CAMI_format_output\": false, \"skip_unclassified_estimation\": false, \"biom_format_output\": false, \"krona_output\": false}, \"subsample\": {\"selector\": \"no\", \"__current_case__\": 0}, \"test\": \"false\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "4.2.4+galaxy0", "type": "tool", @@ -1592,7 +1592,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1793,7 +1793,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"clade\": null, \"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"clade\": null, \"database\": {\"__class__\": \"RuntimeValue\"}, \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1846,7 +1846,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1898,7 +1898,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"database\": {\"__class__\": \"RuntimeValue\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -2098,7 +2098,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"database\": {\"__class__\": \"RuntimeValue\"}, \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -2160,7 +2160,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", From 9bd8ec94e19633dd9a7b98e04a7279ca04aaac97 Mon Sep 17 00:00:00 2001 From: Xenia Date: Tue, 30 Jun 2026 11:05:46 +0200 Subject: [PATCH 08/12] Fix workflow parameter inputs --- .../samestr-workflow/.dockstore.yml | 4 +- .../microbiome/samestr-workflow/README.md | 2 +- ...orkflow-tests.yml => samestrgal-tests.yml} | 7 +- .../{samestr-workflow.ga => samestrgal.ga} | 1053 +++++++++++------ 4 files changed, 712 insertions(+), 354 deletions(-) rename workflows/microbiome/samestr-workflow/{samestr-workflow-tests.yml => samestrgal-tests.yml} (88%) rename workflows/microbiome/samestr-workflow/{samestr-workflow.ga => samestrgal.ga} (77%) diff --git a/workflows/microbiome/samestr-workflow/.dockstore.yml b/workflows/microbiome/samestr-workflow/.dockstore.yml index 695fdc2d29..6afbc0fd6e 100644 --- a/workflows/microbiome/samestr-workflow/.dockstore.yml +++ b/workflows/microbiome/samestr-workflow/.dockstore.yml @@ -3,9 +3,9 @@ workflows: - name: main subclass: Galaxy publish: true - primaryDescriptorPath: /samestr-workflow.ga + primaryDescriptorPath: /samestrgal.ga testParameterFiles: - - /samestr-workflow-tests.yml + - /samestrgal-tests.yml authors: - name: 'Xenia Morera Martínez' orcid: 0009-0000-2380-8385 diff --git a/workflows/microbiome/samestr-workflow/README.md b/workflows/microbiome/samestr-workflow/README.md index 9b6d12cf75..549ca0ac4a 100644 --- a/workflows/microbiome/samestr-workflow/README.md +++ b/workflows/microbiome/samestr-workflow/README.md @@ -1,4 +1,4 @@ -# SameStr workflow for shared-strain detection in metagenomes +# SamestrGal for shared-strain detection in metagenomes This workflow processes paired-end shotgun metagenomic sequencing reads from multiple samples. It performs the following steps: diff --git a/workflows/microbiome/samestr-workflow/samestr-workflow-tests.yml b/workflows/microbiome/samestr-workflow/samestrgal-tests.yml similarity index 88% rename from workflows/microbiome/samestr-workflow/samestr-workflow-tests.yml rename to workflows/microbiome/samestr-workflow/samestrgal-tests.yml index 43455506b0..350d2893e3 100644 --- a/workflows/microbiome/samestr-workflow/samestr-workflow-tests.yml +++ b/workflows/microbiome/samestr-workflow/samestrgal-tests.yml @@ -1,4 +1,4 @@ -- doc: Test outline for SameStr-Workflow +- doc: Test outline for samestrgal job: Raw Reads: class: Collection @@ -42,6 +42,11 @@ filetype: fastqsanger.gz Run mOTUs: false Run MetaPhlAn: true + Select SameStr database: mpa_vJan25_CHOCOPhlAnSGB_202503-11062025 + Select MetaPhlAn Database: mpa_vJan25_CHOCOPhlAnSGB_202503-11062025 + Select the mOTUs database: db_from_2026-04-27T094930Z + Host reference genome: hg19 + Sequencer type: NexteraPE outputs: "Stats file (MetaPhlAn)": element_tests: diff --git a/workflows/microbiome/samestr-workflow/samestr-workflow.ga b/workflows/microbiome/samestr-workflow/samestrgal.ga similarity index 77% rename from workflows/microbiome/samestr-workflow/samestr-workflow.ga rename to workflows/microbiome/samestr-workflow/samestrgal.ga index 3dee8d2f92..6c794d52be 100644 --- a/workflows/microbiome/samestr-workflow/samestr-workflow.ga +++ b/workflows/microbiome/samestr-workflow/samestrgal.ga @@ -2,18 +2,38 @@ "a_galaxy_workflow": "true", "annotation": "This workflow performs strain-level metagenomic analysis of shotgun sequencing data, enabling taxonomic profiling, strain identification, and shared strain detection across samples.", "comments": [ + { + "child_steps": [ + 8, + 9 + ], + "color": "yellow", + "data": { + "title": "Preprocessing Steps" + }, + "id": 1, + "position": [ + 317.7, + 159.53587672666492 + ], + "size": [ + 517, + 454 + ], + "type": "frame" + }, { "child_steps": [ 0 ], "color": "red", "data": { - "title": "Inputs" + "title": "Input Samples" }, "id": 0, "position": [ 0, - 106.63711806335814 + 180.39875866330678 ], "size": [ 240, @@ -22,55 +42,54 @@ "type": "frame" }, { - "color": "none", + "child_steps": [ + 2, + 1 + ], + "color": "red", "data": { - "size": 2, - "text": "
" + "title": "Input Parameters" }, "id": 2, "position": [ - 259.2, - 651.2371180633581 + 5.8, + 359.3987586633068 ], "size": [ - 0, - 0 + 244, + 239 ], - "type": "text" + "type": "frame" }, { - "child_steps": [ - 3, - 4 - ], - "color": "yellow", + "color": "none", "data": { - "title": "Preprocessing Steps" + "size": 2, + "text": "
" }, - "id": 1, + "id": 3, "position": [ - 316.5, - 49.137118063358145 + 260.4, + 761.635876726665 ], "size": [ - 516, - 356 + 0, + 0 ], - "type": "frame" + "type": "text" } ], "creator": [ { "class": "Person", "familyName": "Morera Martínez", - "name": "Xenia" - "identifier": "https://orcid.org/0009-0000-2380-8385" + "name": "Xenia", + "identifier": "https://orcid.org/0009-0000-2380-8385" } ], "format-version": "0.1", "license": "MIT", - "release": "0.1", - "name": "SameStr Workflow", + "name": "SamestrGal", "report": { "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" }, @@ -91,23 +110,77 @@ "name": "Input dataset collection", "outputs": [], "position": { - "left": 19.99998512403619, - "top": 146.63881349153127 + "left": 19.978197146864574, + "top": 220.4411929095941 }, "tool_id": null, "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", "tool_version": null, "type": "data_collection_input", - "uuid": "d5cfa62b-9d85-497b-8ad3-a5a3e48d21ad", + "uuid": "b2a5ebe6-be68-42ed-bd76-6b15b1bf9db9", "when": null, "workflow_outputs": [] }, "1": { - "annotation": "Run mOTUs subworkflow for shared strain detection.", + "annotation": "Select the host reference genome for removing contaminating reads. ", "content_id": null, "errors": null, "id": 1, "input_connections": {}, + "inputs": [ + { + "description": "Select the host reference genome for removing contaminating reads. ", + "name": "Select Host reference genome" + } + ], + "label": "Select Host reference genome", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 21.09338350273935, + "top": 392.84874141591763 + }, + "tool_id": null, + "tool_state": "{\"default\": \"hg19\", \"multiple\": false, \"validators\": [], \"suggestions\": [\"hg19\", \"hg38\", \"mm10\", \"mm39\", \"rn6\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "53e7f1d9-a567-41de-af46-45aa3c807e54", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "Select the sequencer for Trimmomatic", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "Select the sequencer for Trimmomatic", + "name": "Select Sequencer for Trimmomatic" + } + ], + "label": "Select Sequencer for Trimmomatic", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 21.258392333984375, + "top": 498.87510681152344 + }, + "tool_id": null, + "tool_state": "{\"default\": \"NexteraPE\", \"multiple\": false, \"validators\": [], \"restrictions\": [\"NexteraPE\", \"TruSeq2\", \"TruSeq3\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "2b87cb9d-9f7d-40f3-ae19-a67834afbe27", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "Run mOTUs subworkflow for shared strain detection.", + "content_id": null, + "errors": null, + "id": 3, + "input_connections": {}, "inputs": [ { "description": "Run mOTUs subworkflow for shared strain detection.", @@ -118,22 +191,76 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 987.6423524333857, - "top": 5.403850851444081 + "left": 982.7384201811337, + "top": 0 }, "tool_id": null, "tool_state": "{\"default\": false, \"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "9d41f03f-7ed3-4f25-a75d-72d900fc8a43", + "uuid": "94754676-a16b-447e-9d0f-4500c2e715ca", "when": null, "workflow_outputs": [] }, - "2": { + "4": { + "annotation": "Select the mOTUs database for taxonomic profiling and marker-based alignment.", + "content_id": null, + "errors": null, + "id": 4, + "input_connections": {}, + "inputs": [ + { + "description": "Select the mOTUs database for taxonomic profiling and marker-based alignment.", + "name": "Select the mOTUs database" + } + ], + "label": "Select the mOTUs database", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 985.0052059706488, + "top": 112.4623606340167 + }, + "tool_id": null, + "tool_state": "{\"default\": \"db_from_2026-04-27T094930Z\", \"multiple\": false, \"validators\": [], \"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "dd4a0b90-1b4f-4c38-b2e4-5a4b10e604ea", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "Select SameStr database. If running MetaPhlAn subworkflow, only select MetaPhlan databases. If running mOTUs, only select mOTUs databases.", + "content_id": null, + "errors": null, + "id": 5, + "input_connections": {}, + "inputs": [ + { + "description": "Select SameStr database. If running MetaPhlAn subworkflow, only select MetaPhlan databases. If running mOTUs, only select mOTUs databases.", + "name": "Select SameStr database" + } + ], + "label": "Select SameStr database", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 989.5775856818063, + "top": 299.61369370042223 + }, + "tool_id": null, + "tool_state": "{\"multiple\": false, \"validators\": [], \"suggestions\": [\"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"db_from_2026-04-27T094930Z\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "a0a6433f-8241-4bfb-9216-8ba9a6dddf6c", + "when": null, + "workflow_outputs": [] + }, + "6": { "annotation": "Run MetaPhlAn subworkflow for shared strain detection.", "content_id": null, "errors": null, - "id": 2, + "id": 6, "input_connections": {}, "inputs": [ { @@ -145,26 +272,61 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 992.4084167480469, - "top": 445.545437155155 + "left": 991.7033778977649, + "top": 452.73601839257384 }, "tool_id": null, "tool_state": "{\"default\": true, \"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "3750ea2c-d863-44f0-942f-6086a93f0162", + "uuid": "4b85acb6-5d5e-4703-bf84-421a2de2b209", "when": null, "workflow_outputs": [] }, - "3": { + "7": { + "annotation": "Choose the MetaPhlAn database version", + "content_id": null, + "errors": null, + "id": 7, + "input_connections": {}, + "inputs": [ + { + "description": "Choose the MetaPhlAn database version", + "name": "Select MetaPhlAn Database" + } + ], + "label": "Select MetaPhlAn Database", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 991.7314835474111, + "top": 558.9235833466704 + }, + "tool_id": null, + "tool_state": "{\"default\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"multiple\": false, \"validators\": [], \"suggestions\": [\"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"mpa_vOct22_CHOCOPhlAnSGB_202403-30092024\", \"mpa_vJun23_CHOCOPhlAnSGB_202403-30092024\", \"mpa_vJan21_TOY_CHOCOPhlAnSGB_202103-23012026\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "393f0af0-4748-4270-8342-8fdc28907c07", + "when": null, + "workflow_outputs": [] + }, + "8": { "annotation": "Quality trimming and host read removal", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/kneaddata/kneaddata/0.12.1+galaxy1", "errors": null, - "id": 3, + "id": 8, "input_connections": { + "alignment|alignment_tool|bowtie2_db": { + "id": 1, + "output_name": "output" + }, "read_type|paired_collection": { "id": 0, "output_name": "output" + }, + "trimmomatic|trimmomatic_step|sequencer": { + "id": 2, + "output_name": "output" } }, "inputs": [ @@ -198,8 +360,8 @@ } ], "position": { - "left": 347.21852281613917, - "top": 84.4829693218784 + "left": 348.41852281613916, + "top": 194.88172798518517 }, "post_job_actions": { "HideDatasetActiontrimmed_paired": { @@ -220,26 +382,26 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"alignment\": {\"alignment_tool\": {\"tool_choice\": \"bowtie2\", \"__current_case__\": 0, \"bowtie2_db\": {\"__class__\": \"RuntimeValue\"}}, \"save_contaminants\": false}, \"fastqc\": {\"fastqc_report\": {\"select_fastqc\": \"no_fastqc\", \"__current_case__\": 1}, \"run_trim_repetitive\": false}, \"log_level\": \"INFO\", \"read_type\": {\"select_read_type\": \"paired\", \"__current_case__\": 1, \"save_unmatched\": true, \"paired_collection\": {\"__class__\": \"ConnectedValue\"}}, \"tandem\": {\"trf_step\": {\"trf_bool\": \"skip\", \"__current_case__\": 1}}, \"trimmomatic\": {\"trimmomatic_step\": {\"decide_trimmomatic\": \"run_trimmomatic\", \"__current_case__\": 0, \"sequencer\": {\"__class__\": \"RuntimeValue\"}}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"alignment\": {\"alignment_tool\": {\"tool_choice\": \"bowtie2\", \"__current_case__\": 0, \"bowtie2_db\": {\"__class__\": \"ConnectedValue\"}}, \"save_contaminants\": false}, \"fastqc\": {\"fastqc_report\": {\"select_fastqc\": \"no_fastqc\", \"__current_case__\": 1}, \"run_trim_repetitive\": false}, \"log_level\": \"INFO\", \"read_type\": {\"select_read_type\": \"paired\", \"__current_case__\": 1, \"save_unmatched\": true, \"paired_collection\": {\"__class__\": \"ConnectedValue\"}}, \"tandem\": {\"trf_step\": {\"trf_bool\": \"skip\", \"__current_case__\": 1}}, \"trimmomatic\": {\"trimmomatic_step\": {\"decide_trimmomatic\": \"run_trimmomatic\", \"__current_case__\": 0, \"sequencer\": {\"__class__\": \"ConnectedValue\"}}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "0.12.1+galaxy1", "type": "tool", - "uuid": "82d77df5-b99a-4f75-b0f3-7fbb15801f2f", + "uuid": "9fe3494e-b20e-43fc-963c-818e81bc2d93", "when": null, "workflow_outputs": [] }, - "4": { + "9": { "annotation": "Merge paired-end and orphaned reads from KneadData output", "content_id": "__MERGE_COLLECTION__", "errors": null, - "id": 4, + "id": 9, "input_connections": { "inputs_0|input": { - "id": 3, + "id": 8, "output_name": "paired_output" }, "inputs_1|input": { - "id": 3, + "id": 8, "output_name": "unmatched_paired" } }, @@ -253,8 +415,8 @@ } ], "position": { - "left": 612.5937791206638, - "top": 107.09884146261162 + "left": 613.7937791206638, + "top": 217.4976001259184 }, "post_job_actions": {}, "tool_id": "__MERGE_COLLECTION__", @@ -262,21 +424,31 @@ "tool_uuid": null, "tool_version": "1.0.0", "type": "tool", - "uuid": "a5e4be2f-5314-4af7-a08e-7e9e2f416710", + "uuid": "9d6634d3-7b42-4b27-86d7-51b712fe5da4", "when": null, "workflow_outputs": [] }, - "5": { + "10": { "annotation": "Taxonomic profiling with mOTUs", - "id": 5, + "id": 10, "input_connections": { "Raw Inputs": { - "id": 4, + "id": 9, "input_subworkflow_step_id": 0, "output_name": "output" }, + "SameStr Database Selector": { + "id": 5, + "input_subworkflow_step_id": 2, + "output_name": "output" + }, + "Select the mOTUs database": { + "id": 4, + "input_subworkflow_step_id": 1, + "output_name": "output" + }, "when": { - "id": 1, + "id": 3, "output_name": "output" } }, @@ -290,8 +462,8 @@ "name": "mOTUs Subworkflow", "outputs": [], "position": { - "left": 1266.5750427246094, - "top": 0.0 + "left": 1269.9875956705075, + "top": 1.3683197666703406 }, "subworkflow": { "a_galaxy_workflow": "true", @@ -299,78 +471,81 @@ "comments": [ { "child_steps": [ - 19 + 9, + 14, + 15, + 16 ], - "color": "green", + "color": "turquoise", "data": { - "title": "SameStr Output" + "title": "SameStr Strain-level Analysis" }, - "id": 2, + "id": 1, "position": [ - 2779.8, - 514.5 + 1226.0999389648437, + 170.58949951252163 ], "size": [ - 241, - 216 + 1265.7, + 311.9 ], "type": "frame" }, { - "color": "green", + "child_steps": [ + 8, + 7 + ], + "color": "orange", "data": { - "title": "SameStr Output" + "title": "Taxonomic Profiling and Marker-Based AlignmentFrame" }, - "id": 3, + "id": 0, "position": [ - 2971.1, - 65.1 + 866.8999389648437, + 65.78949951252162 ], "size": [ - 247, - 417 + 241, + 464 ], "type": "frame" }, { "child_steps": [ - 6, - 5 + 21 ], - "color": "orange", + "color": "green", "data": { - "title": "Taxonomic Profiling and Marker-Based AlignmentFrame" + "title": "SameStr Output" }, - "id": 0, + "id": 2, "position": [ - 866.9, - 0 + 2790.4, + 612.6894995125216 ], "size": [ - 241.1, - 367 + 250, + 268 ], "type": "frame" }, { "child_steps": [ - 13, - 12, - 7, - 14 + 22 ], - "color": "turquoise", + "color": "green", "data": { - "title": "SameStr Strain-level Analysis" + "title": "SameStr Output" }, - "id": 1, + "id": 3, "position": [ - 1226.1, - 104.8 + 2971.0999389648437, + 130.8894995125216 ], "size": [ - 1265.7, - 311.9 + 251, + 459 ], "type": "frame" } @@ -411,7 +586,7 @@ "outputs": [], "position": { "left": 0, - "top": 128.73394695351277 + "top": 194.5228216560763 }, "tool_id": null, "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", @@ -422,10 +597,64 @@ "workflow_outputs": [] }, "1": { + "annotation": "Select the mOTUs database for taxonomic profiling and marker-based alignment.", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "Select the mOTUs database for taxonomic profiling and marker-based alignment.", + "name": "Select the mOTUs database" + } + ], + "label": "Select the mOTUs database", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 558.2191733009017, + "top": 433.79110876553693 + }, + "tool_id": null, + "tool_state": "{\"default\": \"db_from_2026-04-27T094930Z\", \"multiple\": false, \"validators\": [], \"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "70b234db-03d1-49d3-ba37-7fcd59203067", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "For the mOTUs subworklfow select only mOTUs databases", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "For the mOTUs subworklfow select only mOTUs databases", + "name": "SameStr Database Selector" + } + ], + "label": "SameStr Database Selector", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 1725.5252075195312, + "top": 0.0 + }, + "tool_id": null, + "tool_state": "{\"default\": \"db_from_2026-04-27T094930Z\", \"multiple\": false, \"validators\": [], \"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "ed26ff63-ff2e-4298-826a-d33d147f15a5", + "when": null, + "workflow_outputs": [] + }, + "3": { "annotation": "", "content_id": "__EXTRACT_DATASET__", "errors": null, - "id": 1, + "id": 3, "input_connections": { "input": { "id": 0, @@ -442,8 +671,8 @@ } ], "position": { - "left": 275.5362707054305, - "top": 45.50926482270616 + "left": 275.5362096702743, + "top": 111.29876433522777 }, "post_job_actions": {}, "tool_id": "__EXTRACT_DATASET__", @@ -455,11 +684,11 @@ "when": null, "workflow_outputs": [] }, - "2": { + "4": { "annotation": "", "content_id": "__EXTRACT_DATASET__", "errors": null, - "id": 2, + "id": 4, "input_connections": { "input": { "id": 0, @@ -476,8 +705,8 @@ } ], "position": { - "left": 273.55029717097636, - "top": 182.63944336940284 + "left": 273.5502361358201, + "top": 248.42894288192446 }, "post_job_actions": {}, "tool_id": "__EXTRACT_DATASET__", @@ -489,14 +718,14 @@ "when": null, "workflow_outputs": [] }, - "3": { + "5": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", "errors": null, - "id": 3, + "id": 5, "input_connections": { "input_list": { - "id": 1, + "id": 3, "output_name": "output" } }, @@ -510,8 +739,8 @@ } ], "position": { - "left": 552.0248259632644, - "top": 39.9230628562196 + "left": 552.0247649281082, + "top": 105.71256236874122 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", @@ -529,14 +758,14 @@ "when": null, "workflow_outputs": [] }, - "4": { + "6": { "annotation": "", "content_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", "errors": null, - "id": 4, + "id": 6, "input_connections": { "input_list": { - "id": 2, + "id": 4, "output_name": "output" } }, @@ -550,8 +779,8 @@ } ], "position": { - "left": 550.9437432540947, - "top": 196.2375242685519 + "left": 550.9436822189384, + "top": 262.0270237810735 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", @@ -569,18 +798,22 @@ "when": null, "workflow_outputs": [] }, - "5": { + "7": { "annotation": "Profile microbial community composition using universal marker genes", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_profiler/3.1.0+galaxy1", "errors": null, - "id": 5, + "id": 7, "input_connections": { + "inputs|db|db_cached": { + "id": 1, + "output_name": "output" + }, "inputs|input_type|reads_type|forward_reads": { - "id": 3, + "id": 5, "output_name": "output" }, "inputs|input_type|reads_type|reverse_reads": { - "id": 4, + "id": 6, "output_name": "output" } }, @@ -594,8 +827,8 @@ } ], "position": { - "left": 885.1262385199572, - "top": 65.75285272023278 + "left": 885.1261774848009, + "top": 131.5423522327544 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_profiler/3.1.0+galaxy1", @@ -605,7 +838,7 @@ "owner": "bgruening", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"algorithm_advanced_options\": {\"advanced_options\": {\"customize_algorithm_options\": \"default_options\", \"__current_case__\": 1}}, \"all_taxonomic_level\": false, \"biom_format\": false, \"cami_format_option\": {\"cami_options\": \"no\", \"__current_case__\": 1}, \"full_rank_taxonomy\": false, \"full_species_name\": false, \"inputs\": {\"input_type\": {\"selector\": \"reads\", \"__current_case__\": 0, \"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}}, \"sample_name\": null, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": {\"__class__\": \"RuntimeValue\"}}, \"ncbi_taxonomy_ids\": false, \"ref_motus\": false, \"result_as_counts\": false, \"save_bam\": false, \"save_mgc\": false, \"taxonomic_level_option\": {\"taxonomic_option\": \"no\", \"__current_case__\": 1}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"algorithm_advanced_options\": {\"advanced_options\": {\"customize_algorithm_options\": \"default_options\", \"__current_case__\": 1}}, \"all_taxonomic_level\": false, \"biom_format\": false, \"cami_format_option\": {\"cami_options\": \"no\", \"__current_case__\": 1}, \"full_rank_taxonomy\": false, \"full_species_name\": false, \"inputs\": {\"input_type\": {\"selector\": \"reads\", \"__current_case__\": 0, \"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}}, \"sample_name\": null, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": {\"__class__\": \"ConnectedValue\"}}}, \"ncbi_taxonomy_ids\": false, \"ref_motus\": false, \"result_as_counts\": false, \"save_bam\": false, \"save_mgc\": false, \"taxonomic_level_option\": {\"taxonomic_option\": \"no\", \"__current_case__\": 1}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "3.1.0+galaxy1", "type": "tool", @@ -613,18 +846,22 @@ "when": null, "workflow_outputs": [] }, - "6": { + "8": { "annotation": "Map reads to mOTUs marker gene database for SNV calling", "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_map_snv/3.1.0+galaxy0", "errors": null, - "id": 6, + "id": 8, "input_connections": { + "inputs|db|db_cached": { + "id": 1, + "output_name": "output" + }, "inputs|reads_type|forward_reads": { - "id": 3, + "id": 5, "output_name": "output" }, "inputs|reads_type|reverse_reads": { - "id": 4, + "id": 6, "output_name": "output" } }, @@ -638,8 +875,8 @@ } ], "position": { - "left": 886.8530294435432, - "top": 224.19755572219503 + "left": 886.8500965070327, + "top": 343.80892035616665 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_map_snv/3.1.0+galaxy0", @@ -649,7 +886,7 @@ "owner": "bgruening", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"algorithm_advanced_options\": {\"verbosity_level_selection\": \"3\", \"minimum_alignment_len\": \"75\"}, \"inputs\": {\"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": {\"__class__\": \"RuntimeValue\"}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"algorithm_advanced_options\": {\"verbosity_level_selection\": \"3\", \"minimum_alignment_len\": \"75\"}, \"inputs\": {\"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": {\"__class__\": \"ConnectedValue\"}}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "3.1.0+galaxy0", "type": "tool", @@ -657,18 +894,22 @@ "when": null, "workflow_outputs": [] }, - "7": { + "9": { "annotation": "Convert BAM to SNV profiles for SameStr analysis", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", "errors": null, - "id": 7, + "id": 9, "input_connections": { "alignment": { - "id": 6, + "id": 8, "output_name": "bam_output" }, + "database": { + "id": 2, + "output_name": "output" + }, "profile": { - "id": 5, + "id": 7, "output_name": "output_motus" } }, @@ -686,8 +927,8 @@ } ], "position": { - "left": 1261.8275092603064, - "top": 158.33909953778584 + "left": 1261.8274482251502, + "top": 224.12859905030746 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", @@ -697,7 +938,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -705,14 +946,14 @@ "when": null, "workflow_outputs": [] }, - "8": { + "10": { "annotation": "Flatten collection to allow cross-sample SNV profile comparison. Note: this modifies element identifiers by adding an underscore, which makes naming afterwards unstable for SameStr", "content_id": "__FLATTEN__", "errors": null, - "id": 8, + "id": 10, "input_connections": { "input": { - "id": 7, + "id": 9, "output_name": "npz_files" } }, @@ -726,8 +967,8 @@ } ], "position": { - "left": 1137.183961831004, - "top": 548.5279972044827 + "left": 1137.1839007958476, + "top": 614.3174967170044 }, "post_job_actions": {}, "tool_id": "__FLATTEN__", @@ -739,14 +980,14 @@ "when": null, "workflow_outputs": [] }, - "9": { + "11": { "annotation": "Extract element identifiers from flattened collection to prepare for renaming", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", "errors": null, - "id": 9, + "id": 11, "input_connections": { "input_collection": { - "id": 8, + "id": 10, "output_name": "output" } }, @@ -760,8 +1001,8 @@ } ], "position": { - "left": 1442.2054905379298, - "top": 561.7634317296073 + "left": 1442.2054295027735, + "top": 627.5529312421289 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", @@ -779,14 +1020,14 @@ "when": null, "workflow_outputs": [] }, - "10": { + "12": { "annotation": "Clean element identifiers after flattening to restore compatible naming for downstream tools", "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", "errors": null, - "id": 10, + "id": 12, "input_connections": { "input": { - "id": 9, + "id": 11, "output_name": "output" } }, @@ -800,8 +1041,8 @@ } ], "position": { - "left": 1720.0195463093285, - "top": 569.6499661192393 + "left": 1720.0194852741722, + "top": 635.4394656317609 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", @@ -819,18 +1060,18 @@ "when": null, "workflow_outputs": [] }, - "11": { + "13": { "annotation": "Rename cleaned identifiers to match SameStr expected format", "content_id": "__RELABEL_FROM_FILE__", "errors": null, - "id": 11, + "id": 13, "input_connections": { "how|labels": { - "id": 10, + "id": 12, "output_name": "out_file1" }, "input": { - "id": 8, + "id": 10, "output_name": "output" } }, @@ -849,8 +1090,8 @@ } ], "position": { - "left": 2016.8126786335886, - "top": 548.8749942290515 + "left": 2016.8126175984323, + "top": 614.6644937415731 }, "post_job_actions": {}, "tool_id": "__RELABEL_FROM_FILE__", @@ -862,14 +1103,18 @@ "when": null, "workflow_outputs": [] }, - "12": { + "14": { "annotation": "Merge SNV profiles from multiple samples for cross-sample strain comparison", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", "errors": null, - "id": 12, + "id": 14, "input_connections": { + "database": { + "id": 2, + "output_name": "output" + }, "input_files": { - "id": 11, + "id": 13, "output_name": "output" } }, @@ -887,8 +1132,8 @@ } ], "position": { - "left": 1627.4833264469337, - "top": 181.20514913656223 + "left": 1627.4832654117774, + "top": 246.99464864908384 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", @@ -898,7 +1143,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"clade\": null, \"database\": {\"__class__\": \"RuntimeValue\"}, \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"clade\": null, \"database\": {\"__class__\": \"ConnectedValue\"}, \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -906,18 +1151,22 @@ "when": null, "workflow_outputs": [] }, - "13": { + "15": { "annotation": "Filter SNV profiles to retain high confidence variants for strain analysis", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", "errors": null, - "id": 13, + "id": 15, "input_connections": { + "database": { + "id": 2, + "output_name": "output" + }, "input_names": { - "id": 12, + "id": 14, "output_name": "sample_name" }, "input_snvs": { - "id": 12, + "id": 14, "output_name": "npz_files" } }, @@ -940,8 +1189,8 @@ } ], "position": { - "left": 1993.7006647946978, - "top": 172.32397552702548 + "left": 1993.7002372536087, + "top": 225.2849040506854 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", @@ -951,7 +1200,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -959,18 +1208,22 @@ "when": null, "workflow_outputs": [] }, - "14": { + "16": { "annotation": "Compare SNV profiles across samples to identify shared strains", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", "errors": null, - "id": 14, + "id": 16, "input_connections": { + "database": { + "id": 2, + "output_name": "output" + }, "input_names": { - "id": 13, + "id": 15, "output_name": "sample_names" }, "input_snvs": { - "id": 13, + "id": 15, "output_name": "filtered_profile" } }, @@ -992,8 +1245,8 @@ } ], "position": { - "left": 2271.7786830381865, - "top": 144.78305330970247 + "left": 2271.7786220030303, + "top": 210.57255282222408 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", @@ -1003,7 +1256,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"database\": {\"__class__\": \"RuntimeValue\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1011,14 +1264,14 @@ "when": null, "workflow_outputs": [] }, - "15": { + "17": { "annotation": "empty datasets with insufficient coverage or no SNVs detected", "content_id": "__FILTER_EMPTY_DATASETS__", "errors": null, - "id": 15, + "id": 17, "input_connections": { "input": { - "id": 13, + "id": 15, "output_name": "filtered_profile" } }, @@ -1037,8 +1290,8 @@ } ], "position": { - "left": 2496.1663411369873, - "top": 435.7383376287588 + "left": 2496.166280101831, + "top": 501.52783714128043 }, "post_job_actions": {}, "tool_id": "__FILTER_EMPTY_DATASETS__", @@ -1050,14 +1303,14 @@ "when": null, "workflow_outputs": [] }, - "16": { + "18": { "annotation": "empty datasets with insufficient coverage or no SNVs detected", "content_id": "__FILTER_EMPTY_DATASETS__", "errors": null, - "id": 16, + "id": 18, "input_connections": { "input": { - "id": 13, + "id": 15, "output_name": "sample_names" } }, @@ -1076,8 +1329,8 @@ } ], "position": { - "left": 2499.049389896233, - "top": 609.799429971278 + "left": 2499.049328861077, + "top": 675.5889294837996 }, "post_job_actions": {}, "tool_id": "__FILTER_EMPTY_DATASETS__", @@ -1089,14 +1342,14 @@ "when": null, "workflow_outputs": [] }, - "17": { + "19": { "annotation": "empty datasets with insufficient coverage or no SNVs detected", "content_id": "__FILTER_EMPTY_DATASETS__", "errors": null, - "id": 17, + "id": 19, "input_connections": { "input": { - "id": 14, + "id": 16, "output_name": "fraction_file" } }, @@ -1115,8 +1368,8 @@ } ], "position": { - "left": 2674.136469674208, - "top": 32.28881158568977 + "left": 2674.1364086390518, + "top": 98.07831109821139 }, "post_job_actions": {}, "tool_id": "__FILTER_EMPTY_DATASETS__", @@ -1128,14 +1381,14 @@ "when": null, "workflow_outputs": [] }, - "18": { + "20": { "annotation": "empty datasets with insufficient coverage or no SNVs detected", "content_id": "__FILTER_EMPTY_DATASETS__", "errors": null, - "id": 18, + "id": 20, "input_connections": { "input": { - "id": 14, + "id": 16, "output_name": "overlap_file" } }, @@ -1154,8 +1407,8 @@ } ], "position": { - "left": 2684.140946034504, - "top": 214.49601656615144 + "left": 2684.1408849993477, + "top": 280.285516078673 }, "post_job_actions": {}, "tool_id": "__FILTER_EMPTY_DATASETS__", @@ -1167,18 +1420,22 @@ "when": null, "workflow_outputs": [] }, - "19": { + "21": { "annotation": "Generate summary statistics of SNV profiles per sample", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", "errors": null, - "id": 19, + "id": 21, "input_connections": { + "database": { + "id": 2, + "output_name": "output" + }, "input_names": { - "id": 16, + "id": 18, "output_name": "output" }, "input_snvs": { - "id": 15, + "id": 17, "output_name": "output" } }, @@ -1192,8 +1449,8 @@ } ], "position": { - "left": 2799.761534585506, - "top": 554.5036623080092 + "left": 2810.3335880500167, + "top": 652.654207770746 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", @@ -1203,7 +1460,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"database\": {\"__class__\": \"RuntimeValue\"}, \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1217,22 +1474,26 @@ } ] }, - "20": { + "22": { "annotation": "Summarize strain sharing results across all sample pairs", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", "errors": null, - "id": 20, + "id": 22, "input_connections": { + "database": { + "id": 2, + "output_name": "output" + }, "overlaps": { - "id": 18, + "id": 20, "output_name": "output" }, "similarities": { - "id": 17, + "id": 19, "output_name": "output" }, "tax_profiles": { - "id": 5, + "id": 7, "output_name": "output_motus" } }, @@ -1254,8 +1515,8 @@ } ], "position": { - "left": 2991.083575513044, - "top": 105.97949575129569 + "left": 2991.0835144778875, + "top": 171.76899526381732 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", @@ -1265,7 +1526,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1291,46 +1552,56 @@ } }, "tags": [], - "uuid": "0ef8afaf-7578-4279-a2a3-885fe5ae3c6b" + "uuid": "c5b75e4c-c4d6-47b2-9427-ad0edbf95fa6" }, "tool_id": null, "type": "subworkflow", - "uuid": "0841c539-6ebb-4406-b3b0-e3e9a6d6bf9f", + "uuid": "57baa291-5b4d-489b-a992-a356b9db514b", "when": "$(inputs.when)", "workflow_outputs": [ - { - "label": "Co-occurrences (mOTUs)", - "output_name": "Co-occurrences (mOTUs)", - "uuid": "c6c44065-1358-40fd-82d4-e5a42d336371" - }, { "label": "Taxon counts (mOTUs)", "output_name": "Taxon counts (mOTUs)", - "uuid": "c2ff3bad-5a37-4752-a050-f6a0c6e747e8" + "uuid": "4c69705d-4654-4101-9b35-2333c774bf08" + }, + { + "label": "Co-occurrences (mOTUs)", + "output_name": "Co-occurrences (mOTUs)", + "uuid": "e04d06ce-0174-4c67-87d6-084c93a2b718" }, { "label": "Strain events (mOTUs)", "output_name": "Strain events (mOTUs)", - "uuid": "783f2882-bf8f-4b4f-9925-d60766e3450e" + "uuid": "3258d895-4b57-4440-a18e-263d40b7c04e" }, { "label": "Stats file (mOTUs)", "output_name": "Stats file (mOTUs)", - "uuid": "3b2b48ef-d311-4317-b888-50fd7f956297" + "uuid": "d10a8c49-a905-45e5-a486-2ae8dcf573f8" } ] }, - "6": { + "11": { "annotation": "Taxonomic profiling with MetaPhlAn ", - "id": 6, + "id": 11, "input_connections": { "0:Input dataset collection": { - "id": 4, + "id": 9, "input_subworkflow_step_id": 0, "output_name": "output" }, + "Select MetaPhlAn Database": { + "id": 7, + "input_subworkflow_step_id": 1, + "output_name": "output" + }, + "Select SameStr database MetaPhlAn": { + "id": 5, + "input_subworkflow_step_id": 2, + "output_name": "output" + }, "when": { - "id": 2, + "id": 6, "output_name": "output" } }, @@ -1344,8 +1615,8 @@ "name": "Metaphlan Subworkflow", "outputs": [], "position": { - "left": 1268.6418151855469, - "top": 342.2455256561316 + "left": 1269.841815185547, + "top": 452.6442843194384 }, "subworkflow": { "a_galaxy_workflow": "true", @@ -1353,80 +1624,80 @@ "comments": [ { "child_steps": [ - 1 + 5, + 10, + 11, + 12 ], - "color": "orange", + "color": "turquoise", "data": { - "title": "Taxonomic Profiling and Marker-Based Alignment" + "title": "SameStr Strain-level Analysis" }, - "id": 0, + "id": 1, "position": [ - 358.3875, - 0 + 1092.0875, + 147.27748418122366 ], "size": [ - 240, - 284.4 + 1288, + 312 ], "type": "frame" }, { "child_steps": [ - 9, - 8, - 3, - 10 + 3 ], - "color": "turquoise", + "color": "orange", "data": { - "title": "SameStr Strain-level Analysis" + "title": "Taxonomic Profiling and Marker-Based Alignment" }, - "id": 1, + "id": 0, "position": [ - 1092.0875, - 117.30000000000001 + 358.3875, + 29.977484181223637 ], "size": [ - 1284, - 298 + 240, + 372 ], "type": "frame" }, { "child_steps": [ - 16 + 17 ], "color": "green", "data": { "title": "SameStr Output" }, - "id": 3, + "id": 2, "position": [ - 2877.7875, - 89 + 2447.3875, + 542.3774841812236 ], "size": [ 245, - 479 + 255 ], "type": "frame" }, { "child_steps": [ - 15 + 18 ], "color": "green", "data": { "title": "SameStr Output" }, - "id": 2, + "id": 3, "position": [ - 2447.3875, - 512.4 + 2877.7875, + 118.97748418122364 ], "size": [ - 243, - 222 + 244, + 504 ], "type": "frame" } @@ -1449,7 +1720,7 @@ "outputs": [], "position": { "left": 0, - "top": 23.475 + "top": 53.45248418122364 }, "tool_id": null, "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", @@ -1460,11 +1731,69 @@ "workflow_outputs": [] }, "1": { + "annotation": "Choose the MetaPhlAn database version", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "Choose the MetaPhlAn database version", + "name": "Select MetaPhlAn Database" + } + ], + "label": "Select MetaPhlAn Database", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 5.745321782154769, + "top": 165.94111900112858 + }, + "tool_id": null, + "tool_state": "{\"default\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"multiple\": false, \"validators\": [], \"suggestions\": [\"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"mpa_vOct22_CHOCOPhlAnSGB_202403-30092024\", \"mpa_vJun23_CHOCOPhlAnSGB_202403-30092024\", \"mpa_vJan21_TOY_CHOCOPhlAnSGB_202103-23012026\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "735532ca-b622-4445-b5e1-f34a1e4c26b0", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "Select SameStr database. Only select MetaPhlan databases", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "Select SameStr database. Only select MetaPhlan databases", + "name": "Select SameStr database MetaPhlAn" + } + ], + "label": "Select SameStr database MetaPhlAn", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 1521.8250122070312, + "top": 0 + }, + "tool_id": null, + "tool_state": "{\"default\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"multiple\": false, \"validators\": [], \"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "af0c000e-1004-405e-899b-e0b129671183", + "when": null, + "workflow_outputs": [] + }, + "3": { "annotation": "Generate taxonomic profiles and marker gene alignments for SameStr", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/metaphlan/metaphlan/4.2.4+galaxy0", "errors": null, - "id": 1, + "id": 3, "input_connections": { + "inputs|db|cached_db": { + "id": 1, + "output_name": "output" + }, "inputs|in|raw_in|in": { "id": 0, "output_name": "output" @@ -1493,8 +1822,8 @@ } ], "position": { - "left": 378.3625183105469, - "top": 54.387506103515626 + "left": 379.4250183105469, + "top": 100.35832214355469 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/metaphlan/metaphlan/4.2.4+galaxy0", @@ -1504,7 +1833,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"analysis\": {\"analysis_type\": {\"t\": \"rel_ab\", \"__current_case__\": 0, \"tax_lev\": {\"tax_lev\": \"a\", \"__current_case__\": 0, \"split_levels\": false}}, \"min_alignment_len\": null, \"organism_profiling\": null, \"stat\": \"tavg_g\", \"stat_q\": \"0.2\", \"perc_nonzero\": \"0.33\", \"ignore_markers\": {\"__class__\": \"RuntimeValue\"}, \"avoid_disqm\": true}, \"inputs\": {\"in\": {\"selector\": \"raw\", \"__current_case__\": 0, \"raw_in\": {\"selector\": \"paired_collection\", \"__current_case__\": 2, \"in\": {\"__class__\": \"ConnectedValue\"}}, \"read_min_len\": \"70\", \"mapping\": {\"bt2_ps\": \"very-sensitive\", \"min_mapq_val\": \"5\"}}, \"db\": {\"db_selector\": \"cached\", \"__current_case__\": 0, \"cached_db\": {\"__class__\": \"RuntimeValue\"}, \"viral_analysis\": {\"profile_vsc\": \"\", \"__current_case__\": 1}}}, \"out\": {\"sample_id_key\": \"SampleID\", \"sample_id\": \"Metaphlan_Analysis\", \"use_group_representative\": false, \"CAMI_format_output\": false, \"skip_unclassified_estimation\": false, \"biom_format_output\": false, \"krona_output\": false}, \"subsample\": {\"selector\": \"no\", \"__current_case__\": 0}, \"test\": \"false\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"analysis\": {\"analysis_type\": {\"t\": \"rel_ab\", \"__current_case__\": 0, \"tax_lev\": {\"tax_lev\": \"a\", \"__current_case__\": 0, \"split_levels\": false}}, \"min_alignment_len\": null, \"organism_profiling\": null, \"stat\": \"tavg_g\", \"stat_q\": \"0.2\", \"perc_nonzero\": \"0.33\", \"ignore_markers\": {\"__class__\": \"RuntimeValue\"}, \"avoid_disqm\": true}, \"inputs\": {\"in\": {\"selector\": \"raw\", \"__current_case__\": 0, \"raw_in\": {\"selector\": \"paired_collection\", \"__current_case__\": 2, \"in\": {\"__class__\": \"ConnectedValue\"}}, \"read_min_len\": \"70\", \"mapping\": {\"bt2_ps\": \"very-sensitive\", \"min_mapq_val\": \"5\"}}, \"db\": {\"db_selector\": \"cached\", \"__current_case__\": 0, \"cached_db\": {\"__class__\": \"ConnectedValue\"}, \"viral_analysis\": {\"profile_vsc\": \"\", \"__current_case__\": 1}}}, \"out\": {\"sample_id_key\": \"SampleID\", \"sample_id\": \"Metaphlan_Analysis\", \"use_group_representative\": false, \"CAMI_format_output\": false, \"skip_unclassified_estimation\": false, \"biom_format_output\": false, \"krona_output\": false}, \"subsample\": {\"selector\": \"no\", \"__current_case__\": 0}, \"test\": \"false\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "4.2.4+galaxy0", "type": "tool", @@ -1512,14 +1841,14 @@ "when": null, "workflow_outputs": [] }, - "2": { + "4": { "annotation": "Convert SAM to BAM format", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samtools_view/samtools_view/1.22+galaxy2", "errors": null, - "id": 2, + "id": 4, "input_connections": { "input": { - "id": 1, + "id": 3, "output_name": "sam_output_file" } }, @@ -1534,7 +1863,7 @@ ], "position": { "left": 754.0375671386719, - "top": 273.9250122070313 + "top": 303.9024963882549 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samtools_view/samtools_view/1.22+galaxy2", @@ -1552,18 +1881,22 @@ "when": null, "workflow_outputs": [] }, - "3": { + "5": { "annotation": "Convert BAM to SNV profiles for SameStr analysis", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", "errors": null, - "id": 3, + "id": 5, "input_connections": { "alignment": { - "id": 2, + "id": 4, "output_name": "outputsam" }, + "database": { + "id": 2, + "output_name": "output" + }, "profile": { - "id": 1, + "id": 3, "output_name": "output_file" } }, @@ -1582,7 +1915,7 @@ ], "position": { "left": 1112.0749816894531, - "top": 165.487451171875 + "top": 195.46493535309864 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", @@ -1592,7 +1925,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1600,14 +1933,14 @@ "when": null, "workflow_outputs": [] }, - "4": { + "6": { "annotation": "Flatten collection to allow cross-sample SNV profile comparison. Note: this modifies element identifiers by adding an underscore, which makes naming afterwards unstable for SameStr", "content_id": "__FLATTEN__", "errors": null, - "id": 4, + "id": 6, "input_connections": { "input": { - "id": 3, + "id": 5, "output_name": "npz_files" } }, @@ -1622,7 +1955,7 @@ ], "position": { "left": 866.5750427246094, - "top": 603.0000244140625 + "top": 632.9775085952862 }, "post_job_actions": {}, "tool_id": "__FLATTEN__", @@ -1634,14 +1967,14 @@ "when": null, "workflow_outputs": [] }, - "5": { + "7": { "annotation": "Extract element identifiers from flattened collection to prepare for renaming", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", "errors": null, - "id": 5, + "id": 7, "input_connections": { "input_collection": { - "id": 4, + "id": 6, "output_name": "output" } }, @@ -1656,7 +1989,7 @@ ], "position": { "left": 1170.5999450683594, - "top": 602.8875366210938 + "top": 632.8650208023174 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", @@ -1674,14 +2007,14 @@ "when": null, "workflow_outputs": [] }, - "6": { + "8": { "annotation": "Clean element identifiers after flattening to restore compatible naming for downstream tools", "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", "errors": null, - "id": 6, + "id": 8, "input_connections": { "input": { - "id": 5, + "id": 7, "output_name": "output" } }, @@ -1696,7 +2029,7 @@ ], "position": { "left": 1456.9501085652712, - "top": 607.8749560421887 + "top": 637.8524402234124 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", @@ -1714,18 +2047,18 @@ "when": null, "workflow_outputs": [] }, - "7": { + "9": { "annotation": "Rename cleaned identifiers to match SameStr expected format", "content_id": "__RELABEL_FROM_FILE__", "errors": null, - "id": 7, + "id": 9, "input_connections": { "how|labels": { - "id": 6, + "id": 8, "output_name": "out_file1" }, "input": { - "id": 4, + "id": 6, "output_name": "output" } }, @@ -1745,7 +2078,7 @@ ], "position": { "left": 1708.700108565271, - "top": 593.76246824922 + "top": 623.7399524304436 }, "post_job_actions": {}, "tool_id": "__RELABEL_FROM_FILE__", @@ -1757,14 +2090,18 @@ "when": null, "workflow_outputs": [] }, - "8": { + "10": { "annotation": "Merge SNV profiles from multiple samples for cross-sample strain comparison", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", "errors": null, - "id": 8, + "id": 10, "input_connections": { + "database": { + "id": 2, + "output_name": "output" + }, "input_files": { - "id": 7, + "id": 9, "output_name": "output" } }, @@ -1783,7 +2120,7 @@ ], "position": { "left": 1483.7124938964844, - "top": 172.42501220703124 + "top": 202.4024963882549 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", @@ -1793,7 +2130,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"clade\": null, \"database\": {\"__class__\": \"RuntimeValue\"}, \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"clade\": null, \"database\": {\"__class__\": \"ConnectedValue\"}, \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1801,18 +2138,22 @@ "when": null, "workflow_outputs": [] }, - "9": { + "11": { "annotation": "Filter SNV profiles to retain high confidence variants for strain analysis", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", "errors": null, - "id": 9, + "id": 11, "input_connections": { + "database": { + "id": 2, + "output_name": "output" + }, "input_names": { - "id": 8, + "id": 10, "output_name": "sample_name" }, "input_snvs": { - "id": 8, + "id": 10, "output_name": "npz_files" } }, @@ -1835,8 +2176,8 @@ } ], "position": { - "left": 1823.2750597371457, - "top": 171.13749876679842 + "left": 1823.275109572711, + "top": 190.86132373743087 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", @@ -1846,7 +2187,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1854,18 +2195,22 @@ "when": null, "workflow_outputs": [] }, - "10": { + "12": { "annotation": "Compare SNV profiles across samples to identify shared strains", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", "errors": null, - "id": 10, + "id": 12, "input_connections": { + "database": { + "id": 2, + "output_name": "output" + }, "input_names": { - "id": 9, + "id": 11, "output_name": "sample_names" }, "input_snvs": { - "id": 9, + "id": 11, "output_name": "filtered_profile" } }, @@ -1888,7 +2233,7 @@ ], "position": { "left": 2155.5249938964844, - "top": 157.26250610351562 + "top": 187.23999028473926 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", @@ -1898,7 +2243,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"database\": {\"__class__\": \"RuntimeValue\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -1906,14 +2251,14 @@ "when": null, "workflow_outputs": [] }, - "11": { + "13": { "annotation": "empty datasets with insufficient coverage or no SNVs detected", "content_id": "__FILTER_EMPTY_DATASETS__", "errors": null, - "id": 11, + "id": 13, "input_connections": { "input": { - "id": 9, + "id": 11, "output_name": "filtered_profile" } }, @@ -1933,7 +2278,7 @@ ], "position": { "left": 2192.550018310547, - "top": 441.3875366210938 + "top": 471.3650208023174 }, "post_job_actions": {}, "tool_id": "__FILTER_EMPTY_DATASETS__", @@ -1945,14 +2290,14 @@ "when": null, "workflow_outputs": [] }, - "12": { + "14": { "annotation": "empty datasets with insufficient coverage or no SNVs detected", "content_id": "__FILTER_EMPTY_DATASETS__", "errors": null, - "id": 12, + "id": 14, "input_connections": { "input": { - "id": 9, + "id": 11, "output_name": "sample_names" } }, @@ -1972,7 +2317,7 @@ ], "position": { "left": 2197.612518310547, - "top": 618.900048828125 + "top": 648.8775330093487 }, "post_job_actions": {}, "tool_id": "__FILTER_EMPTY_DATASETS__", @@ -1984,14 +2329,14 @@ "when": null, "workflow_outputs": [] }, - "13": { + "15": { "annotation": "empty datasets with insufficient coverage or no SNVs detected", "content_id": "__FILTER_EMPTY_DATASETS__", "errors": null, - "id": 13, + "id": 15, "input_connections": { "input": { - "id": 10, + "id": 12, "output_name": "overlap_file" } }, @@ -2011,7 +2356,7 @@ ], "position": { "left": 2460.0125427246094, - "top": 73.67498168945312 + "top": 103.65246587067676 }, "post_job_actions": {}, "tool_id": "__FILTER_EMPTY_DATASETS__", @@ -2023,14 +2368,14 @@ "when": null, "workflow_outputs": [] }, - "14": { + "16": { "annotation": "empty datasets with insufficient coverage or no SNVs detected", "content_id": "__FILTER_EMPTY_DATASETS__", "errors": null, - "id": 14, + "id": 16, "input_connections": { "input": { - "id": 10, + "id": 12, "output_name": "fraction_file" } }, @@ -2050,7 +2395,7 @@ ], "position": { "left": 2461.962559737145, - "top": 263.36250487031396 + "top": 293.3399890515376 }, "post_job_actions": {}, "tool_id": "__FILTER_EMPTY_DATASETS__", @@ -2062,18 +2407,22 @@ "when": null, "workflow_outputs": [] }, - "15": { + "17": { "annotation": "Generate summary statistics of SNV profiles per sample", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", "errors": null, - "id": 15, + "id": 17, "input_connections": { + "database": { + "id": 2, + "output_name": "output" + }, "input_names": { - "id": 12, + "id": 14, "output_name": "output" }, "input_snvs": { - "id": 11, + "id": 13, "output_name": "output" } }, @@ -2088,7 +2437,7 @@ ], "position": { "left": 2467.4124450683594, - "top": 552.3750244140625 + "top": 582.3525085952862 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", @@ -2098,7 +2447,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"database\": {\"__class__\": \"RuntimeValue\"}, \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -2112,22 +2461,26 @@ } ] }, - "16": { + "18": { "annotation": "Summarize strain sharing results across all sample pairs", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", "errors": null, - "id": 16, + "id": 18, "input_connections": { + "database": { + "id": 2, + "output_name": "output" + }, "overlaps": { - "id": 13, + "id": 15, "output_name": "output" }, "similarities": { - "id": 14, + "id": 16, "output_name": "output" }, "tax_profiles": { - "id": 1, + "id": 3, "output_name": "output_file" } }, @@ -2150,7 +2503,7 @@ ], "position": { "left": 2897.7834118519604, - "top": 129.03333497002757 + "top": 159.0108191512512 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", @@ -2160,7 +2513,7 @@ "owner": "iuc", "tool_shed": "toolshed.g2.bx.psu.edu" }, - "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": {\"__class__\": \"RuntimeValue\"}, \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, "tool_version": "1.2025.111+galaxy0", "type": "tool", @@ -2168,9 +2521,9 @@ "when": null, "workflow_outputs": [ { - "label": "Co-occurrences (MetaPhlAn)", - "output_name": "cooccurrences", - "uuid": "b9b9a2ea-45a5-4874-895d-8b334da3c289" + "label": "Taxon counts (MetaPhlAn)", + "output_name": "taxon_counts", + "uuid": "376e6e79-0cc9-449b-bd6e-948da38a297c" }, { "label": "Strain events (MetaPhlAn)", @@ -2178,40 +2531,40 @@ "uuid": "c3833465-80a0-486f-b54f-0eda31728915" }, { - "label": "Taxon counts (MetaPhlAn)", - "output_name": "taxon_counts", - "uuid": "376e6e79-0cc9-449b-bd6e-948da38a297c" + "label": "Co-occurrences (MetaPhlAn)", + "output_name": "cooccurrences", + "uuid": "b9b9a2ea-45a5-4874-895d-8b334da3c289" } ] } }, "tags": [], - "uuid": "d860cdf4-5d79-4ac0-8301-b4716e0996c0" + "uuid": "7d18be01-a7dc-41a5-932e-d557bacb3403" }, "tool_id": null, "type": "subworkflow", - "uuid": "c08e32e9-daed-408b-9eb9-b8801fc2193d", + "uuid": "976c1574-a7cd-4dd8-9d2d-6ea9821bc0ac", "when": "$(inputs.when)", "workflow_outputs": [ { "label": "Co-occurrences (MetaPhlAn)", "output_name": "Co-occurrences (MetaPhlAn)", - "uuid": "70aa3d70-8961-481b-a143-9b364663cbdc" + "uuid": "0a233933-71dc-497b-a4f7-f41b091e5ec8" }, { - "label": "Stats file (MetaPhlAn)", - "output_name": "Stats file (MetaPhlAn)", - "uuid": "72a9cdb9-4472-42d9-bc0e-090341889275" + "label": "Strain events (MetaPhlAn)", + "output_name": "Strain events (MetaPhlAn)", + "uuid": "85ab6172-3eb6-4a49-bef3-c81bf4c0c278" }, { "label": "Taxon counts (MetaPhlAn)", "output_name": "Taxon counts (MetaPhlAn)", - "uuid": "06652c72-c3f3-4f1e-bb5d-47c6b90e8e5e" + "uuid": "8cd1a75a-a3d5-41de-9d2a-5d29853d057e" }, { - "label": "Strain events (MetaPhlAn)", - "output_name": "Strain events (MetaPhlAn)", - "uuid": "56b78ea8-129b-4606-b557-304c03460562" + "label": "Stats file (MetaPhlAn)", + "output_name": "Stats file (MetaPhlAn)", + "uuid": "c4227302-b049-44e8-a05a-b648d884db44" } ] } @@ -2221,6 +2574,6 @@ "microbiome", "shared-strains" ], - "uuid": "7af358a3-fd2b-4fb1-a667-60f79c08402f", - "version": 57 + "uuid": "80532af2-4cc6-4654-87a9-d4d4cfe875d5", + "version": 91 } From ee8a574d687e138afaa3d3043a464775381838a9 Mon Sep 17 00:00:00 2001 From: Xenia Date: Thu, 2 Jul 2026 16:56:07 +0200 Subject: [PATCH 09/12] Add fix lint and test --- .../samestr-workflow/samestrgal-tests.yml | 3 +- .../microbiome/samestr-workflow/samestrgal.ga | 165 ++++++++++-------- 2 files changed, 98 insertions(+), 70 deletions(-) diff --git a/workflows/microbiome/samestr-workflow/samestrgal-tests.yml b/workflows/microbiome/samestr-workflow/samestrgal-tests.yml index 350d2893e3..9d7c197d65 100644 --- a/workflows/microbiome/samestr-workflow/samestrgal-tests.yml +++ b/workflows/microbiome/samestr-workflow/samestrgal-tests.yml @@ -42,7 +42,8 @@ filetype: fastqsanger.gz Run mOTUs: false Run MetaPhlAn: true - Select SameStr database: mpa_vJan25_CHOCOPhlAnSGB_202503-11062025 + Select SameStr database MetaPhlAn: mpa_vJan25_CHOCOPhlAnSGB_202503-11062025 + Select SameStr database mOTUs: db_from_2026-04-27T094930Z Select MetaPhlAn Database: mpa_vJan25_CHOCOPhlAnSGB_202503-11062025 Select the mOTUs database: db_from_2026-04-27T094930Z Host reference genome: hg19 diff --git a/workflows/microbiome/samestr-workflow/samestrgal.ga b/workflows/microbiome/samestr-workflow/samestrgal.ga index 6c794d52be..cb529358cf 100644 --- a/workflows/microbiome/samestr-workflow/samestrgal.ga +++ b/workflows/microbiome/samestr-workflow/samestrgal.ga @@ -4,47 +4,47 @@ "comments": [ { "child_steps": [ - 8, - 9 + 0 ], - "color": "yellow", + "color": "red", "data": { - "title": "Preprocessing Steps" + "title": "Input Samples" }, - "id": 1, + "id": 0, "position": [ - 317.7, - 159.53587672666492 + 0, + 180.39875866330678 ], "size": [ - 517, - 454 + 240, + 121.2 ], "type": "frame" }, { "child_steps": [ - 0 + 9, + 10 ], - "color": "red", + "color": "yellow", "data": { - "title": "Input Samples" + "title": "Preprocessing Steps" }, - "id": 0, + "id": 1, "position": [ - 0, - 180.39875866330678 + 317.7, + 159.53587672666492 ], "size": [ - 240, - 121.2 + 517, + 454 ], "type": "frame" }, { "child_steps": [ - 2, - 1 + 1, + 2 ], "color": "red", "data": { @@ -80,13 +80,13 @@ } ], "creator": [ - { - "class": "Person", - "familyName": "Morera Martínez", - "name": "Xenia", - "identifier": "https://orcid.org/0009-0000-2380-8385" - } - ], + { + "class": "Person", + "familyName": "Morera Martínez", + "name": "Xenia", + "identifier": "https://orcid.org/0009-0000-2380-8385" + } +], "format-version": "0.1", "license": "MIT", "name": "SamestrGal", @@ -238,30 +238,57 @@ "inputs": [ { "description": "Select SameStr database. If running MetaPhlAn subworkflow, only select MetaPhlan databases. If running mOTUs, only select mOTUs databases.", - "name": "Select SameStr database" + "name": "Select SameStr database mOTUs" } ], - "label": "Select SameStr database", + "label": "Select SameStr database mOTUs", "name": "Input parameter", "outputs": [], "position": { - "left": 989.5775856818063, - "top": 299.61369370042223 + "left": 987.8405871150695, + "top": 207.86714118402494 }, "tool_id": null, - "tool_state": "{\"multiple\": false, \"validators\": [], \"suggestions\": [\"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"db_from_2026-04-27T094930Z\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_state": "{\"multiple\": false, \"validators\": [], \"suggestions\": [\"db_from_2026-04-27T094930Z\"], \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "a0a6433f-8241-4bfb-9216-8ba9a6dddf6c", + "uuid": "837f823d-2d32-481b-a124-98f672a7a70a", "when": null, "workflow_outputs": [] }, "6": { - "annotation": "Run MetaPhlAn subworkflow for shared strain detection.", + "annotation": "Select SameStr database. If running MetaPhlAn subworkflow, only select MetaPhlan databases. If running mOTUs, only select mOTUs databases.", "content_id": null, "errors": null, "id": 6, "input_connections": {}, + "inputs": [ + { + "description": "Select SameStr database. If running MetaPhlAn subworkflow, only select MetaPhlan databases. If running mOTUs, only select mOTUs databases.", + "name": "Select SameStr database MetaPhlAn" + } + ], + "label": "Select SameStr database MetaPhlAn", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 994.7018992526371, + "top": 358.56714067651876 + }, + "tool_id": null, + "tool_state": "{\"multiple\": false, \"validators\": [], \"suggestions\": [\"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "a0a6433f-8241-4bfb-9216-8ba9a6dddf6c", + "when": null, + "workflow_outputs": [] + }, + "7": { + "annotation": "Run MetaPhlAn subworkflow for shared strain detection.", + "content_id": null, + "errors": null, + "id": 7, + "input_connections": {}, "inputs": [ { "description": "Run MetaPhlAn subworkflow for shared strain detection.", @@ -283,11 +310,11 @@ "when": null, "workflow_outputs": [] }, - "7": { + "8": { "annotation": "Choose the MetaPhlAn database version", "content_id": null, "errors": null, - "id": 7, + "id": 8, "input_connections": {}, "inputs": [ { @@ -310,11 +337,11 @@ "when": null, "workflow_outputs": [] }, - "8": { + "9": { "annotation": "Quality trimming and host read removal", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/kneaddata/kneaddata/0.12.1+galaxy1", "errors": null, - "id": 8, + "id": 9, "input_connections": { "alignment|alignment_tool|bowtie2_db": { "id": 1, @@ -390,18 +417,18 @@ "when": null, "workflow_outputs": [] }, - "9": { + "10": { "annotation": "Merge paired-end and orphaned reads from KneadData output", "content_id": "__MERGE_COLLECTION__", "errors": null, - "id": 9, + "id": 10, "input_connections": { "inputs_0|input": { - "id": 8, + "id": 9, "output_name": "paired_output" }, "inputs_1|input": { - "id": 8, + "id": 9, "output_name": "unmatched_paired" } }, @@ -428,12 +455,12 @@ "when": null, "workflow_outputs": [] }, - "10": { + "11": { "annotation": "Taxonomic profiling with mOTUs", - "id": 10, + "id": 11, "input_connections": { "Raw Inputs": { - "id": 9, + "id": 10, "input_subworkflow_step_id": 0, "output_name": "output" }, @@ -1560,14 +1587,9 @@ "when": "$(inputs.when)", "workflow_outputs": [ { - "label": "Taxon counts (mOTUs)", - "output_name": "Taxon counts (mOTUs)", - "uuid": "4c69705d-4654-4101-9b35-2333c774bf08" - }, - { - "label": "Co-occurrences (mOTUs)", - "output_name": "Co-occurrences (mOTUs)", - "uuid": "e04d06ce-0174-4c67-87d6-084c93a2b718" + "label": "Stats file (mOTUs)", + "output_name": "Stats file (mOTUs)", + "uuid": "d10a8c49-a905-45e5-a486-2ae8dcf573f8" }, { "label": "Strain events (mOTUs)", @@ -1575,33 +1597,38 @@ "uuid": "3258d895-4b57-4440-a18e-263d40b7c04e" }, { - "label": "Stats file (mOTUs)", - "output_name": "Stats file (mOTUs)", - "uuid": "d10a8c49-a905-45e5-a486-2ae8dcf573f8" + "label": "Co-occurrences (mOTUs)", + "output_name": "Co-occurrences (mOTUs)", + "uuid": "e04d06ce-0174-4c67-87d6-084c93a2b718" + }, + { + "label": "Taxon counts (mOTUs)", + "output_name": "Taxon counts (mOTUs)", + "uuid": "4c69705d-4654-4101-9b35-2333c774bf08" } ] }, - "11": { + "12": { "annotation": "Taxonomic profiling with MetaPhlAn ", - "id": 11, + "id": 12, "input_connections": { "0:Input dataset collection": { - "id": 9, + "id": 10, "input_subworkflow_step_id": 0, "output_name": "output" }, "Select MetaPhlAn Database": { - "id": 7, + "id": 8, "input_subworkflow_step_id": 1, "output_name": "output" }, "Select SameStr database MetaPhlAn": { - "id": 5, + "id": 6, "input_subworkflow_step_id": 2, "output_name": "output" }, "when": { - "id": 6, + "id": 7, "output_name": "output" } }, @@ -2546,6 +2573,11 @@ "uuid": "976c1574-a7cd-4dd8-9d2d-6ea9821bc0ac", "when": "$(inputs.when)", "workflow_outputs": [ + { + "label": "Stats file (MetaPhlAn)", + "output_name": "Stats file (MetaPhlAn)", + "uuid": "c4227302-b049-44e8-a05a-b648d884db44" + }, { "label": "Co-occurrences (MetaPhlAn)", "output_name": "Co-occurrences (MetaPhlAn)", @@ -2560,11 +2592,6 @@ "label": "Taxon counts (MetaPhlAn)", "output_name": "Taxon counts (MetaPhlAn)", "uuid": "8cd1a75a-a3d5-41de-9d2a-5d29853d057e" - }, - { - "label": "Stats file (MetaPhlAn)", - "output_name": "Stats file (MetaPhlAn)", - "uuid": "c4227302-b049-44e8-a05a-b648d884db44" } ] } @@ -2574,6 +2601,6 @@ "microbiome", "shared-strains" ], - "uuid": "80532af2-4cc6-4654-87a9-d4d4cfe875d5", - "version": 91 -} + "uuid": "f39609c0-8971-44e9-a93e-b79a8493abb7", + "version": 92 +} \ No newline at end of file From 382b644ffb8072fae99b5fec11f17c8bf6236576 Mon Sep 17 00:00:00 2001 From: Xenia Date: Thu, 2 Jul 2026 18:46:08 +0200 Subject: [PATCH 10/12] fix lint --- workflows/microbiome/samestr-workflow/samestrgal.ga | 1 + 1 file changed, 1 insertion(+) diff --git a/workflows/microbiome/samestr-workflow/samestrgal.ga b/workflows/microbiome/samestr-workflow/samestrgal.ga index cb529358cf..6e66e0a887 100644 --- a/workflows/microbiome/samestr-workflow/samestrgal.ga +++ b/workflows/microbiome/samestr-workflow/samestrgal.ga @@ -90,6 +90,7 @@ "format-version": "0.1", "license": "MIT", "name": "SamestrGal", + "release": "0.1", "report": { "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" }, From facb60e08e0cfdf345f28fb1d73aafc471463d49 Mon Sep 17 00:00:00 2001 From: Xenia Date: Tue, 7 Jul 2026 15:48:26 +0200 Subject: [PATCH 11/12] removed subworkflow motus, added database fix --- .../samestr-workflow/samestrgal-tests.yml | 3 - .../microbiome/samestr-workflow/samestrgal.ga | 1730 ++--------------- 2 files changed, 211 insertions(+), 1522 deletions(-) diff --git a/workflows/microbiome/samestr-workflow/samestrgal-tests.yml b/workflows/microbiome/samestr-workflow/samestrgal-tests.yml index 9d7c197d65..3821e45990 100644 --- a/workflows/microbiome/samestr-workflow/samestrgal-tests.yml +++ b/workflows/microbiome/samestr-workflow/samestrgal-tests.yml @@ -40,12 +40,9 @@ identifier: reverse location: https://zenodo.org/records/20745835/files/28A_R2.fastq.gz filetype: fastqsanger.gz - Run mOTUs: false Run MetaPhlAn: true Select SameStr database MetaPhlAn: mpa_vJan25_CHOCOPhlAnSGB_202503-11062025 - Select SameStr database mOTUs: db_from_2026-04-27T094930Z Select MetaPhlAn Database: mpa_vJan25_CHOCOPhlAnSGB_202503-11062025 - Select the mOTUs database: db_from_2026-04-27T094930Z Host reference genome: hg19 Sequencer type: NexteraPE outputs: diff --git a/workflows/microbiome/samestr-workflow/samestrgal.ga b/workflows/microbiome/samestr-workflow/samestrgal.ga index 6e66e0a887..111e86f7af 100644 --- a/workflows/microbiome/samestr-workflow/samestrgal.ga +++ b/workflows/microbiome/samestr-workflow/samestrgal.ga @@ -2,6 +2,28 @@ "a_galaxy_workflow": "true", "annotation": "This workflow performs strain-level metagenomic analysis of shotgun sequencing data, enabling taxonomic profiling, strain identification, and shared strain detection across samples.", "comments": [ + { + "child_steps": [ + 8, + 5, + 3, + 4 + ], + "color": "blue", + "data": { + "title": "MetaPhlAn Subworkflow" + }, + "id": 3, + "position": [ + 893.4, + 0 + ], + "size": [ + 512, + 469 + ], + "type": "frame" + }, { "child_steps": [ 0 @@ -13,7 +35,7 @@ "id": 0, "position": [ 0, - 180.39875866330678 + 25.19875866330679 ], "size": [ 240, @@ -23,8 +45,8 @@ }, { "child_steps": [ - 9, - 10 + 6, + 7 ], "color": "yellow", "data": { @@ -33,7 +55,7 @@ "id": 1, "position": [ 317.7, - 159.53587672666492 + 4.335876726664907 ], "size": [ 517, @@ -41,36 +63,16 @@ ], "type": "frame" }, - { - "child_steps": [ - 1, - 2 - ], - "color": "red", - "data": { - "title": "Input Parameters" - }, - "id": 2, - "position": [ - 5.8, - 359.3987586633068 - ], - "size": [ - 244, - 239 - ], - "type": "frame" - }, { "color": "none", "data": { "size": 2, "text": "
" }, - "id": 3, + "id": 2, "position": [ 260.4, - 761.635876726665 + 606.435876726665 ], "size": [ 0, @@ -80,13 +82,13 @@ } ], "creator": [ - { - "class": "Person", - "familyName": "Morera Martínez", - "name": "Xenia", - "identifier": "https://orcid.org/0009-0000-2380-8385" - } -], + { + "class": "Person", + "familyName": "Morera Martínez", + "name": "Xenia", + "identifier": "https://orcid.org/0009-0000-2380-8385" + } + ], "format-version": "0.1", "license": "MIT", "name": "SamestrGal", @@ -112,7 +114,7 @@ "outputs": [], "position": { "left": 19.978197146864574, - "top": 220.4411929095941 + "top": 65.2411929095941 }, "tool_id": null, "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", @@ -138,11 +140,11 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 21.09338350273935, - "top": 392.84874141591763 + "left": 21.089008554360447, + "top": 237.64203478760095 }, "tool_id": null, - "tool_state": "{\"default\": \"hg19\", \"multiple\": false, \"validators\": [], \"suggestions\": [\"hg19\", \"hg38\", \"mm10\", \"mm39\", \"rn6\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_state": "{\"default\": \"hg19\", \"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", "uuid": "53e7f1d9-a567-41de-af46-45aa3c807e54", @@ -165,11 +167,11 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 21.258392333984375, - "top": 498.87510681152344 + "left": 21.258349362270508, + "top": 343.6750153034452 }, "tool_id": null, - "tool_state": "{\"default\": \"NexteraPE\", \"multiple\": false, \"validators\": [], \"restrictions\": [\"NexteraPE\", \"TruSeq2\", \"TruSeq3\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_state": "{\"default\": \"NexteraPE\", \"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", "uuid": "2b87cb9d-9f7d-40f3-ae19-a67834afbe27", @@ -177,91 +179,10 @@ "workflow_outputs": [] }, "3": { - "annotation": "Run mOTUs subworkflow for shared strain detection.", - "content_id": null, - "errors": null, - "id": 3, - "input_connections": {}, - "inputs": [ - { - "description": "Run mOTUs subworkflow for shared strain detection.", - "name": "Run mOTUs" - } - ], - "label": "Run mOTUs", - "name": "Input parameter", - "outputs": [], - "position": { - "left": 982.7384201811337, - "top": 0 - }, - "tool_id": null, - "tool_state": "{\"default\": false, \"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", - "tool_version": null, - "type": "parameter_input", - "uuid": "94754676-a16b-447e-9d0f-4500c2e715ca", - "when": null, - "workflow_outputs": [] - }, - "4": { - "annotation": "Select the mOTUs database for taxonomic profiling and marker-based alignment.", - "content_id": null, - "errors": null, - "id": 4, - "input_connections": {}, - "inputs": [ - { - "description": "Select the mOTUs database for taxonomic profiling and marker-based alignment.", - "name": "Select the mOTUs database" - } - ], - "label": "Select the mOTUs database", - "name": "Input parameter", - "outputs": [], - "position": { - "left": 985.0052059706488, - "top": 112.4623606340167 - }, - "tool_id": null, - "tool_state": "{\"default\": \"db_from_2026-04-27T094930Z\", \"multiple\": false, \"validators\": [], \"parameter_type\": \"text\", \"optional\": false}", - "tool_version": null, - "type": "parameter_input", - "uuid": "dd4a0b90-1b4f-4c38-b2e4-5a4b10e604ea", - "when": null, - "workflow_outputs": [] - }, - "5": { - "annotation": "Select SameStr database. If running MetaPhlAn subworkflow, only select MetaPhlan databases. If running mOTUs, only select mOTUs databases.", - "content_id": null, - "errors": null, - "id": 5, - "input_connections": {}, - "inputs": [ - { - "description": "Select SameStr database. If running MetaPhlAn subworkflow, only select MetaPhlan databases. If running mOTUs, only select mOTUs databases.", - "name": "Select SameStr database mOTUs" - } - ], - "label": "Select SameStr database mOTUs", - "name": "Input parameter", - "outputs": [], - "position": { - "left": 987.8405871150695, - "top": 207.86714118402494 - }, - "tool_id": null, - "tool_state": "{\"multiple\": false, \"validators\": [], \"suggestions\": [\"db_from_2026-04-27T094930Z\"], \"parameter_type\": \"text\", \"optional\": false}", - "tool_version": null, - "type": "parameter_input", - "uuid": "837f823d-2d32-481b-a124-98f672a7a70a", - "when": null, - "workflow_outputs": [] - }, - "6": { "annotation": "Select SameStr database. If running MetaPhlAn subworkflow, only select MetaPhlan databases. If running mOTUs, only select mOTUs databases.", "content_id": null, "errors": null, - "id": 6, + "id": 3, "input_connections": {}, "inputs": [ { @@ -273,22 +194,22 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 994.7018992526371, - "top": 358.56714067651876 + "left": 912.5013902808578, + "top": 52.935621088787016 }, "tool_id": null, - "tool_state": "{\"multiple\": false, \"validators\": [], \"suggestions\": [\"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", "uuid": "a0a6433f-8241-4bfb-9216-8ba9a6dddf6c", "when": null, "workflow_outputs": [] }, - "7": { + "4": { "annotation": "Run MetaPhlAn subworkflow for shared strain detection.", "content_id": null, "errors": null, - "id": 7, + "id": 4, "input_connections": {}, "inputs": [ { @@ -300,8 +221,8 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 991.7033778977649, - "top": 452.73601839257384 + "left": 916.5509815398043, + "top": 153.37585094505036 }, "tool_id": null, "tool_state": "{\"default\": true, \"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", @@ -311,11 +232,11 @@ "when": null, "workflow_outputs": [] }, - "8": { + "5": { "annotation": "Choose the MetaPhlAn database version", "content_id": null, "errors": null, - "id": 8, + "id": 5, "input_connections": {}, "inputs": [ { @@ -327,22 +248,22 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 991.7314835474111, - "top": 558.9235833466704 + "left": 917.6385491266412, + "top": 262.74546966067135 }, "tool_id": null, - "tool_state": "{\"default\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"multiple\": false, \"validators\": [], \"suggestions\": [\"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"mpa_vOct22_CHOCOPhlAnSGB_202403-30092024\", \"mpa_vJun23_CHOCOPhlAnSGB_202403-30092024\", \"mpa_vJan21_TOY_CHOCOPhlAnSGB_202103-23012026\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", "uuid": "393f0af0-4748-4270-8342-8fdc28907c07", "when": null, "workflow_outputs": [] }, - "9": { - "annotation": "Quality trimming and host read removal", + "6": { + "annotation": "Quality trimming and host read removal. Boolean parameter 'Save all unmatched reads' must remain set to True. \n", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/kneaddata/kneaddata/0.12.1+galaxy1", "errors": null, - "id": 9, + "id": 6, "input_connections": { "alignment|alignment_tool|bowtie2_db": { "id": 1, @@ -388,8 +309,8 @@ } ], "position": { - "left": 348.41852281613916, - "top": 194.88172798518517 + "left": 348.40905086852905, + "top": 39.66743258872239 }, "post_job_actions": { "HideDatasetActiontrimmed_paired": { @@ -418,1218 +339,65 @@ "when": null, "workflow_outputs": [] }, - "10": { - "annotation": "Merge paired-end and orphaned reads from KneadData output", - "content_id": "__MERGE_COLLECTION__", - "errors": null, - "id": 10, - "input_connections": { - "inputs_0|input": { - "id": 9, - "output_name": "paired_output" - }, - "inputs_1|input": { - "id": 9, - "output_name": "unmatched_paired" - } - }, - "inputs": [], - "label": "Merge Collections", - "name": "Merge collections", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 613.7937791206638, - "top": 217.4976001259184 - }, - "post_job_actions": {}, - "tool_id": "__MERGE_COLLECTION__", - "tool_state": "{\"advanced\": {\"conflict\": {\"duplicate_options\": \"keep_first\", \"__current_case__\": 3}}, \"inputs\": [{\"__index__\": 0, \"input\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"input\": {\"__class__\": \"ConnectedValue\"}}], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.0.0", - "type": "tool", - "uuid": "9d6634d3-7b42-4b27-86d7-51b712fe5da4", - "when": null, - "workflow_outputs": [] - }, - "11": { - "annotation": "Taxonomic profiling with mOTUs", - "id": 11, - "input_connections": { - "Raw Inputs": { - "id": 10, - "input_subworkflow_step_id": 0, - "output_name": "output" - }, - "SameStr Database Selector": { - "id": 5, - "input_subworkflow_step_id": 2, - "output_name": "output" - }, - "Select the mOTUs database": { - "id": 4, - "input_subworkflow_step_id": 1, - "output_name": "output" - }, - "when": { - "id": 3, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "Taxonomic profiling with mOTUs", - "name": "mOTUs Subworkflow" - } - ], - "label": "mOTUs Subworkflow", - "name": "mOTUs Subworkflow", - "outputs": [], - "position": { - "left": 1269.9875956705075, - "top": 1.3683197666703406 - }, - "subworkflow": { - "a_galaxy_workflow": "true", - "annotation": "", - "comments": [ - { - "child_steps": [ - 9, - 14, - 15, - 16 - ], - "color": "turquoise", - "data": { - "title": "SameStr Strain-level Analysis" - }, - "id": 1, - "position": [ - 1226.0999389648437, - 170.58949951252163 - ], - "size": [ - 1265.7, - 311.9 - ], - "type": "frame" - }, - { - "child_steps": [ - 8, - 7 - ], - "color": "orange", - "data": { - "title": "Taxonomic Profiling and Marker-Based AlignmentFrame" - }, - "id": 0, - "position": [ - 866.8999389648437, - 65.78949951252162 - ], - "size": [ - 241, - 464 - ], - "type": "frame" - }, - { - "child_steps": [ - 21 - ], - "color": "green", - "data": { - "title": "SameStr Output" - }, - "id": 2, - "position": [ - 2790.4, - 612.6894995125216 - ], - "size": [ - 250, - 268 - ], - "type": "frame" - }, - { - "child_steps": [ - 22 - ], - "color": "green", - "data": { - "title": "SameStr Output" - }, - "id": 3, - "position": [ - 2971.0999389648437, - 130.8894995125216 - ], - "size": [ - 251, - 459 - ], - "type": "frame" - } - ], - "creator": [ - { - "class": "Person", - "familyName": "Morera Mart\u00ednez", - "name": "Xenia" - }, - { - "class": "Person", - "familyName": "Momin", - "name": "Saim" - } - ], - "format-version": "0.1", - "license": "MIT", - "name": "mOTUs Subworkflow", - "report": { - "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" - }, - "steps": { - "0": { - "annotation": "Merged paired-end and orphaned reads", - "content_id": null, - "errors": null, - "id": 0, - "input_connections": {}, - "inputs": [ - { - "description": "Merged paired-end and orphaned reads", - "name": "Raw Inputs" - } - ], - "label": "Raw Inputs", - "name": "Input dataset collection", - "outputs": [], - "position": { - "left": 0, - "top": 194.5228216560763 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", - "tool_version": null, - "type": "data_collection_input", - "uuid": "15ed0dc8-e3e6-46a7-93c5-9fb6494fb49b", - "when": null, - "workflow_outputs": [] - }, - "1": { - "annotation": "Select the mOTUs database for taxonomic profiling and marker-based alignment.", - "content_id": null, - "errors": null, - "id": 1, - "input_connections": {}, - "inputs": [ - { - "description": "Select the mOTUs database for taxonomic profiling and marker-based alignment.", - "name": "Select the mOTUs database" - } - ], - "label": "Select the mOTUs database", - "name": "Input parameter", - "outputs": [], - "position": { - "left": 558.2191733009017, - "top": 433.79110876553693 - }, - "tool_id": null, - "tool_state": "{\"default\": \"db_from_2026-04-27T094930Z\", \"multiple\": false, \"validators\": [], \"parameter_type\": \"text\", \"optional\": false}", - "tool_version": null, - "type": "parameter_input", - "uuid": "70b234db-03d1-49d3-ba37-7fcd59203067", - "when": null, - "workflow_outputs": [] - }, - "2": { - "annotation": "For the mOTUs subworklfow select only mOTUs databases", - "content_id": null, - "errors": null, - "id": 2, - "input_connections": {}, - "inputs": [ - { - "description": "For the mOTUs subworklfow select only mOTUs databases", - "name": "SameStr Database Selector" - } - ], - "label": "SameStr Database Selector", - "name": "Input parameter", - "outputs": [], - "position": { - "left": 1725.5252075195312, - "top": 0.0 - }, - "tool_id": null, - "tool_state": "{\"default\": \"db_from_2026-04-27T094930Z\", \"multiple\": false, \"validators\": [], \"parameter_type\": \"text\", \"optional\": false}", - "tool_version": null, - "type": "parameter_input", - "uuid": "ed26ff63-ff2e-4298-826a-d33d147f15a5", - "when": null, - "workflow_outputs": [] - }, - "3": { - "annotation": "", - "content_id": "__EXTRACT_DATASET__", - "errors": null, - "id": 3, - "input_connections": { - "input": { - "id": 0, - "output_name": "output" - } - }, - "inputs": [], - "label": "Extract Forward Reads 2", - "name": "Extract dataset", - "outputs": [ - { - "name": "output", - "type": "data" - } - ], - "position": { - "left": 275.5362096702743, - "top": 111.29876433522777 - }, - "post_job_actions": {}, - "tool_id": "__EXTRACT_DATASET__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"which\": {\"which_dataset\": \"by_index\", \"__current_case__\": 2, \"index\": \"0\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.0.2", - "type": "tool", - "uuid": "5ac92002-0fb0-4d49-a457-80139e51f8bc", - "when": null, - "workflow_outputs": [] - }, - "4": { - "annotation": "", - "content_id": "__EXTRACT_DATASET__", - "errors": null, - "id": 4, - "input_connections": { - "input": { - "id": 0, - "output_name": "output" - } - }, - "inputs": [], - "label": "Extract Reverse Reads 2", - "name": "Extract dataset", - "outputs": [ - { - "name": "output", - "type": "data" - } - ], - "position": { - "left": 273.5502361358201, - "top": 248.42894288192446 - }, - "post_job_actions": {}, - "tool_id": "__EXTRACT_DATASET__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"which\": {\"which_dataset\": \"by_index\", \"__current_case__\": 2, \"index\": \"1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.0.2", - "type": "tool", - "uuid": "7996854f-77ba-4f82-995d-653abd62a079", - "when": null, - "workflow_outputs": [] - }, - "5": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", - "errors": null, - "id": 5, - "input_connections": { - "input_list": { - "id": 3, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "Collapse Collection", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 552.0247649281082, - "top": 105.71256236874122 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", - "tool_shed_repository": { - "changeset_revision": "90981f86000f", - "name": "collapse_collections", - "owner": "nml", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"filename\": {\"add_name\": false, \"__current_case__\": 1}, \"input_list\": {\"__class__\": \"ConnectedValue\"}, \"one_header\": false, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "5.1.0", - "type": "tool", - "uuid": "7a97b520-d68d-4d9a-a34d-6475f40d8a56", - "when": null, - "workflow_outputs": [] - }, - "6": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", - "errors": null, - "id": 6, - "input_connections": { - "input_list": { - "id": 4, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "Collapse Collection", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 550.9436822189384, - "top": 262.0270237810735 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/nml/collapse_collections/collapse_dataset/5.1.0", - "tool_shed_repository": { - "changeset_revision": "90981f86000f", - "name": "collapse_collections", - "owner": "nml", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"filename\": {\"add_name\": false, \"__current_case__\": 1}, \"input_list\": {\"__class__\": \"ConnectedValue\"}, \"one_header\": false, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "5.1.0", - "type": "tool", - "uuid": "c3305f5a-681c-4449-a38e-4d1b9d2447f9", - "when": null, - "workflow_outputs": [] - }, - "7": { - "annotation": "Profile microbial community composition using universal marker genes", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_profiler/3.1.0+galaxy1", - "errors": null, - "id": 7, - "input_connections": { - "inputs|db|db_cached": { - "id": 1, - "output_name": "output" - }, - "inputs|input_type|reads_type|forward_reads": { - "id": 5, - "output_name": "output" - }, - "inputs|input_type|reads_type|reverse_reads": { - "id": 6, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "mOTUs_profiler", - "outputs": [ - { - "name": "output_motus", - "type": "txt" - } - ], - "position": { - "left": 885.1261774848009, - "top": 131.5423522327544 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_profiler/3.1.0+galaxy1", - "tool_shed_repository": { - "changeset_revision": "b2b7a3897ef6", - "name": "motus", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"algorithm_advanced_options\": {\"advanced_options\": {\"customize_algorithm_options\": \"default_options\", \"__current_case__\": 1}}, \"all_taxonomic_level\": false, \"biom_format\": false, \"cami_format_option\": {\"cami_options\": \"no\", \"__current_case__\": 1}, \"full_rank_taxonomy\": false, \"full_species_name\": false, \"inputs\": {\"input_type\": {\"selector\": \"reads\", \"__current_case__\": 0, \"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}}, \"sample_name\": null, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": {\"__class__\": \"ConnectedValue\"}}}, \"ncbi_taxonomy_ids\": false, \"ref_motus\": false, \"result_as_counts\": false, \"save_bam\": false, \"save_mgc\": false, \"taxonomic_level_option\": {\"taxonomic_option\": \"no\", \"__current_case__\": 1}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "3.1.0+galaxy1", - "type": "tool", - "uuid": "696af434-1636-458f-ba0d-5abda5f7a622", - "when": null, - "workflow_outputs": [] - }, - "8": { - "annotation": "Map reads to mOTUs marker gene database for SNV calling", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_map_snv/3.1.0+galaxy0", - "errors": null, - "id": 8, - "input_connections": { - "inputs|db|db_cached": { - "id": 1, - "output_name": "output" - }, - "inputs|reads_type|forward_reads": { - "id": 5, - "output_name": "output" - }, - "inputs|reads_type|reverse_reads": { - "id": 6, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "Map SNV", - "outputs": [ - { - "name": "bam_output", - "type": "bam" - } - ], - "position": { - "left": 886.8500965070327, - "top": 343.80892035616665 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/motus/motus_map_snv/3.1.0+galaxy0", - "tool_shed_repository": { - "changeset_revision": "b2b7a3897ef6", - "name": "motus", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"algorithm_advanced_options\": {\"verbosity_level_selection\": \"3\", \"minimum_alignment_len\": \"75\"}, \"inputs\": {\"reads_type\": {\"selector\": \"paired\", \"__current_case__\": 0, \"forward_reads\": {\"__class__\": \"ConnectedValue\"}, \"reverse_reads\": {\"__class__\": \"ConnectedValue\"}}, \"db\": {\"db_source\": \"cached\", \"__current_case__\": 0, \"db_cached\": {\"__class__\": \"ConnectedValue\"}}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "3.1.0+galaxy0", - "type": "tool", - "uuid": "c88518b5-264a-4743-9945-4a06e116d669", - "when": null, - "workflow_outputs": [] - }, - "9": { - "annotation": "Convert BAM to SNV profiles for SameStr analysis", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", - "errors": null, - "id": 9, - "input_connections": { - "alignment": { - "id": 8, - "output_name": "bam_output" - }, - "database": { - "id": 2, - "output_name": "output" - }, - "profile": { - "id": 7, - "output_name": "output_motus" - } - }, - "inputs": [], - "label": null, - "name": "SameStr Convert", - "outputs": [ - { - "name": "npz_files", - "type": "input" - }, - { - "name": "stats_file", - "type": "tabular" - } - ], - "position": { - "left": 1261.8274482251502, - "top": 224.12859905030746 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "56abb72c-8e85-40ff-b4e2-1e392e80f6ce", - "when": null, - "workflow_outputs": [] - }, - "10": { - "annotation": "Flatten collection to allow cross-sample SNV profile comparison. Note: this modifies element identifiers by adding an underscore, which makes naming afterwards unstable for SameStr", - "content_id": "__FLATTEN__", - "errors": null, - "id": 10, - "input_connections": { - "input": { - "id": 9, - "output_name": "npz_files" - } - }, - "inputs": [], - "label": null, - "name": "Flatten collection", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 1137.1839007958476, - "top": 614.3174967170044 - }, - "post_job_actions": {}, - "tool_id": "__FLATTEN__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"join_identifier\": \"_\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.0.0", - "type": "tool", - "uuid": "c3e62419-c72d-41e8-8efc-d4f124b982d7", - "when": null, - "workflow_outputs": [] - }, - "11": { - "annotation": "Extract element identifiers from flattened collection to prepare for renaming", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", - "errors": null, - "id": 11, - "input_connections": { - "input_collection": { - "id": 10, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "Extract element identifiers", - "outputs": [ - { - "name": "output", - "type": "txt" - } - ], - "position": { - "left": 1442.2054295027735, - "top": 627.5529312421289 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", - "tool_shed_repository": { - "changeset_revision": "3e27acfa4830", - "name": "collection_element_identifiers", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"input_collection\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "0.0.3", - "type": "tool", - "uuid": "1dcc573e-640d-4d59-a571-cdbd85f5dc46", - "when": null, - "workflow_outputs": [] - }, - "12": { - "annotation": "Clean element identifiers after flattening to restore compatible naming for downstream tools", - "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", - "errors": null, - "id": 12, - "input_connections": { - "input": { - "id": 11, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "Regex Find And Replace", - "outputs": [ - { - "name": "out_file1", - "type": "input" - } - ], - "position": { - "left": 1720.0194852741722, - "top": 635.4394656317609 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", - "tool_shed_repository": { - "changeset_revision": "503bcd6ebe4b", - "name": "regex_find_replace", - "owner": "galaxyp", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"checks\": [{\"__index__\": 0, \"pattern\": \"^[^_]+_\", \"replacement\": \"\"}], \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.0.3", - "type": "tool", - "uuid": "cff1e2ca-8a4a-4440-b31f-e13fdbff9200", - "when": null, - "workflow_outputs": [] - }, - "13": { - "annotation": "Rename cleaned identifiers to match SameStr expected format", - "content_id": "__RELABEL_FROM_FILE__", - "errors": null, - "id": 13, - "input_connections": { - "how|labels": { - "id": 12, - "output_name": "out_file1" - }, - "input": { - "id": 10, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Relabel identifiers", - "name": "how" - } - ], - "label": null, - "name": "Relabel identifiers", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 2016.8126175984323, - "top": 614.6644937415731 - }, - "post_job_actions": {}, - "tool_id": "__RELABEL_FROM_FILE__", - "tool_state": "{\"how\": {\"how_select\": \"txt\", \"__current_case__\": 0, \"labels\": {\"__class__\": \"ConnectedValue\"}, \"strict\": false}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.1.0", - "type": "tool", - "uuid": "63710c7f-f0c1-4110-b701-83d3e1920c6d", - "when": null, - "workflow_outputs": [] - }, - "14": { - "annotation": "Merge SNV profiles from multiple samples for cross-sample strain comparison", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", - "errors": null, - "id": 14, - "input_connections": { - "database": { - "id": 2, - "output_name": "output" - }, - "input_files": { - "id": 13, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "SameStr Merge", - "outputs": [ - { - "name": "npz_files", - "type": "input" - }, - { - "name": "sample_name", - "type": "input" - } - ], - "position": { - "left": 1627.4832654117774, - "top": 246.99464864908384 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"clade\": null, \"database\": {\"__class__\": \"ConnectedValue\"}, \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "71266426-6068-484c-891c-934ebbc7c3e7", - "when": null, - "workflow_outputs": [] - }, - "15": { - "annotation": "Filter SNV profiles to retain high confidence variants for strain analysis", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", - "errors": null, - "id": 15, - "input_connections": { - "database": { - "id": 2, - "output_name": "output" - }, - "input_names": { - "id": 14, - "output_name": "sample_name" - }, - "input_snvs": { - "id": 14, - "output_name": "npz_files" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool SameStr Filter", - "name": "sample_filtering" - } - ], - "label": null, - "name": "SameStr Filter", - "outputs": [ - { - "name": "filtered_profile", - "type": "npz" - }, - { - "name": "sample_names", - "type": "tabular" - } - ], - "position": { - "left": 1993.7002372536087, - "top": 225.2849040506854 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "63048b47-0099-4866-b51f-897324b1a499", - "when": null, - "workflow_outputs": [] - }, - "16": { - "annotation": "Compare SNV profiles across samples to identify shared strains", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", - "errors": null, - "id": 16, - "input_connections": { - "database": { - "id": 2, - "output_name": "output" - }, - "input_names": { - "id": 15, - "output_name": "sample_names" - }, - "input_snvs": { - "id": 15, - "output_name": "filtered_profile" - } - }, - "inputs": [], - "label": null, - "name": "SameStr Compare", - "outputs": [ - { - "name": "overlap_file", - "type": "tabular" - }, - { - "name": "close_file", - "type": "tabular" - }, - { - "name": "fraction_file", - "type": "tabular" - } - ], - "position": { - "left": 2271.7786220030303, - "top": 210.57255282222408 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "b44c7357-4903-485d-8c5c-fc9b0563aa04", - "when": null, - "workflow_outputs": [] - }, - "17": { - "annotation": "empty datasets with insufficient coverage or no SNVs detected", - "content_id": "__FILTER_EMPTY_DATASETS__", - "errors": null, - "id": 17, - "input_connections": { - "input": { - "id": 15, - "output_name": "filtered_profile" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Filter empty datasets", - "name": "replacement" - } - ], - "label": null, - "name": "Filter empty datasets", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 2496.166280101831, - "top": 501.52783714128043 - }, - "post_job_actions": {}, - "tool_id": "__FILTER_EMPTY_DATASETS__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.1.0", - "type": "tool", - "uuid": "6d907258-064b-4399-b470-a1a1255702a1", - "when": null, - "workflow_outputs": [] - }, - "18": { - "annotation": "empty datasets with insufficient coverage or no SNVs detected", - "content_id": "__FILTER_EMPTY_DATASETS__", - "errors": null, - "id": 18, - "input_connections": { - "input": { - "id": 15, - "output_name": "sample_names" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Filter empty datasets", - "name": "replacement" - } - ], - "label": null, - "name": "Filter empty datasets", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 2499.049328861077, - "top": 675.5889294837996 - }, - "post_job_actions": {}, - "tool_id": "__FILTER_EMPTY_DATASETS__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.1.0", - "type": "tool", - "uuid": "850e77e8-2159-4029-90e0-c99668f52d7b", - "when": null, - "workflow_outputs": [] - }, - "19": { - "annotation": "empty datasets with insufficient coverage or no SNVs detected", - "content_id": "__FILTER_EMPTY_DATASETS__", - "errors": null, - "id": 19, - "input_connections": { - "input": { - "id": 16, - "output_name": "fraction_file" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Filter empty datasets", - "name": "replacement" - } - ], - "label": null, - "name": "Filter empty datasets", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 2674.1364086390518, - "top": 98.07831109821139 - }, - "post_job_actions": {}, - "tool_id": "__FILTER_EMPTY_DATASETS__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.1.0", - "type": "tool", - "uuid": "c6084e15-55eb-4a8e-ad31-1cfdbeab0df5", - "when": null, - "workflow_outputs": [] - }, - "20": { - "annotation": "empty datasets with insufficient coverage or no SNVs detected", - "content_id": "__FILTER_EMPTY_DATASETS__", - "errors": null, - "id": 20, - "input_connections": { - "input": { - "id": 16, - "output_name": "overlap_file" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Filter empty datasets", - "name": "replacement" - } - ], - "label": null, - "name": "Filter empty datasets", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 2684.1408849993477, - "top": 280.285516078673 - }, - "post_job_actions": {}, - "tool_id": "__FILTER_EMPTY_DATASETS__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.1.0", - "type": "tool", - "uuid": "c2aa3a79-6f1d-43ba-a3db-5b1ede2b003b", - "when": null, - "workflow_outputs": [] - }, - "21": { - "annotation": "Generate summary statistics of SNV profiles per sample", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", - "errors": null, - "id": 21, - "input_connections": { - "database": { - "id": 2, - "output_name": "output" - }, - "input_names": { - "id": 18, - "output_name": "output" - }, - "input_snvs": { - "id": 17, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "SameStr Stats", - "outputs": [ - { - "name": "stats_file", - "type": "tabular" - } - ], - "position": { - "left": 2810.3335880500167, - "top": 652.654207770746 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "e0f8fb96-7c7b-46b6-b609-5d5e7e3618c9", - "when": null, - "workflow_outputs": [ - { - "label": "Stats file (mOTUs)", - "output_name": "stats_file", - "uuid": "02aae137-a5f5-4090-ba11-49923c09286d" - } - ] - }, - "22": { - "annotation": "Summarize strain sharing results across all sample pairs", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", - "errors": null, - "id": 22, - "input_connections": { - "database": { - "id": 2, - "output_name": "output" - }, - "overlaps": { - "id": 20, - "output_name": "output" - }, - "similarities": { - "id": 19, - "output_name": "output" - }, - "tax_profiles": { - "id": 7, - "output_name": "output_motus" - } - }, - "inputs": [], - "label": null, - "name": "SameStr Summarize", - "outputs": [ - { - "name": "cooccurrences", - "type": "tabular" - }, - { - "name": "strain_events", - "type": "tabular" - }, - { - "name": "taxon_counts", - "type": "tabular" - } - ], - "position": { - "left": 2991.0835144778875, - "top": 171.76899526381732 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "7fe1a149-9d24-48b7-a81c-f9548eddfea7", - "when": null, - "workflow_outputs": [ - { - "label": "Taxon counts (mOTUs)", - "output_name": "taxon_counts", - "uuid": "6ab5dc84-3c03-411c-8dcb-f2412d69c332" - }, - { - "label": "Strain events (mOTUs)", - "output_name": "strain_events", - "uuid": "20da34ba-86e5-4a28-ab4c-6158480747be" - }, - { - "label": "Co-occurrences (mOTUs)", - "output_name": "cooccurrences", - "uuid": "69dabd78-7640-475a-94e3-05f9625f4e12" - } - ] - } + "7": { + "annotation": "Merge paired-end and orphaned reads from KneadData output", + "content_id": "__MERGE_COLLECTION__", + "errors": null, + "id": 7, + "input_connections": { + "inputs_0|input": { + "id": 6, + "output_name": "paired_output" }, - "tags": [], - "uuid": "c5b75e4c-c4d6-47b2-9427-ad0edbf95fa6" + "inputs_1|input": { + "id": 6, + "output_name": "unmatched_paired" + } }, - "tool_id": null, - "type": "subworkflow", - "uuid": "57baa291-5b4d-489b-a992-a356b9db514b", - "when": "$(inputs.when)", - "workflow_outputs": [ - { - "label": "Stats file (mOTUs)", - "output_name": "Stats file (mOTUs)", - "uuid": "d10a8c49-a905-45e5-a486-2ae8dcf573f8" - }, - { - "label": "Strain events (mOTUs)", - "output_name": "Strain events (mOTUs)", - "uuid": "3258d895-4b57-4440-a18e-263d40b7c04e" - }, - { - "label": "Co-occurrences (mOTUs)", - "output_name": "Co-occurrences (mOTUs)", - "uuid": "e04d06ce-0174-4c67-87d6-084c93a2b718" - }, + "inputs": [], + "label": "Merge Collections", + "name": "Merge collections", + "outputs": [ { - "label": "Taxon counts (mOTUs)", - "output_name": "Taxon counts (mOTUs)", - "uuid": "4c69705d-4654-4101-9b35-2333c774bf08" + "name": "output", + "type": "input" } - ] + ], + "position": { + "left": 613.7878702851508, + "top": 62.29048218334535 + }, + "post_job_actions": {}, + "tool_id": "__MERGE_COLLECTION__", + "tool_state": "{\"advanced\": {\"conflict\": {\"duplicate_options\": \"keep_first\", \"__current_case__\": 3}}, \"inputs\": [{\"__index__\": 0, \"input\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"input\": {\"__class__\": \"ConnectedValue\"}}], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.0", + "type": "tool", + "uuid": "9d6634d3-7b42-4b27-86d7-51b712fe5da4", + "when": null, + "workflow_outputs": [] }, - "12": { + "8": { "annotation": "Taxonomic profiling with MetaPhlAn ", - "id": 12, + "id": 8, "input_connections": { "0:Input dataset collection": { - "id": 10, + "id": 7, "input_subworkflow_step_id": 0, "output_name": "output" }, "Select MetaPhlAn Database": { - "id": 8, + "id": 5, "input_subworkflow_step_id": 1, "output_name": "output" }, "Select SameStr database MetaPhlAn": { - "id": 6, + "id": 3, "input_subworkflow_step_id": 2, "output_name": "output" }, "when": { - "id": 7, + "id": 4, "output_name": "output" } }, @@ -1643,8 +411,8 @@ "name": "Metaphlan Subworkflow", "outputs": [], "position": { - "left": 1269.841815185547, - "top": 452.6442843194384 + "left": 1187.3670214501526, + "top": 39.95931732854578 }, "subworkflow": { "a_galaxy_workflow": "true", @@ -1652,23 +420,20 @@ "comments": [ { "child_steps": [ - 5, - 10, - 11, - 12 + 15 ], - "color": "turquoise", + "color": "green", "data": { - "title": "SameStr Strain-level Analysis" + "title": "SameStr Output" }, - "id": 1, + "id": 2, "position": [ - 1092.0875, - 147.27748418122366 + 2433.9, + 553.5482875065583 ], "size": [ - 1288, - 312 + 245, + 255 ], "type": "frame" }, @@ -1683,7 +448,7 @@ "id": 0, "position": [ 358.3875, - 29.977484181223637 + 29.12577168778195 ], "size": [ 240, @@ -1693,26 +458,31 @@ }, { "child_steps": [ - 17 + 5, + 10, + 11, + 12, + 14, + 13 ], - "color": "green", + "color": "turquoise", "data": { - "title": "SameStr Output" + "title": "SameStr Strain-level Analysis" }, - "id": 2, + "id": 1, "position": [ - 2447.3875, - 542.3774841812236 + 1092.0875, + 146.42577168778197 ], "size": [ - 245, - 255 + 1587, + 388 ], "type": "frame" }, { "child_steps": [ - 18 + 16 ], "color": "green", "data": { @@ -1720,8 +490,8 @@ }, "id": 3, "position": [ - 2877.7875, - 118.97748418122364 + 2735.7, + 112.24828750655831 ], "size": [ 244, @@ -1748,7 +518,7 @@ "outputs": [], "position": { "left": 0, - "top": 53.45248418122364 + "top": 52.60077168778195 }, "tool_id": null, "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", @@ -1775,10 +545,10 @@ "outputs": [], "position": { "left": 5.745321782154769, - "top": 165.94111900112858 + "top": 165.0894065076869 }, "tool_id": null, - "tool_state": "{\"default\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"multiple\": false, \"validators\": [], \"suggestions\": [\"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"mpa_vOct22_CHOCOPhlAnSGB_202403-30092024\", \"mpa_vJun23_CHOCOPhlAnSGB_202403-30092024\", \"mpa_vJan21_TOY_CHOCOPhlAnSGB_202103-23012026\"], \"parameter_type\": \"text\", \"optional\": false}", + "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", "uuid": "735532ca-b622-4445-b5e1-f34a1e4c26b0", @@ -1801,11 +571,11 @@ "name": "Input parameter", "outputs": [], "position": { - "left": 1521.8250122070312, + "left": 1503.9321967283095, "top": 0 }, "tool_id": null, - "tool_state": "{\"default\": \"mpa_vJan25_CHOCOPhlAnSGB_202503-11062025\", \"multiple\": false, \"validators\": [], \"parameter_type\": \"text\", \"optional\": false}", + "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", "uuid": "af0c000e-1004-405e-899b-e0b129671183", @@ -1851,7 +621,7 @@ ], "position": { "left": 379.4250183105469, - "top": 100.35832214355469 + "top": 99.506609650113 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/metaphlan/metaphlan/4.2.4+galaxy0", @@ -1891,7 +661,7 @@ ], "position": { "left": 754.0375671386719, - "top": 303.9024963882549 + "top": 303.0507838948132 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samtools_view/samtools_view/1.22+galaxy2", @@ -1943,7 +713,7 @@ ], "position": { "left": 1112.0749816894531, - "top": 195.46493535309864 + "top": 194.61322285965696 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", @@ -1983,7 +753,7 @@ ], "position": { "left": 866.5750427246094, - "top": 632.9775085952862 + "top": 632.1257961018445 }, "post_job_actions": {}, "tool_id": "__FLATTEN__", @@ -2017,7 +787,7 @@ ], "position": { "left": 1170.5999450683594, - "top": 632.8650208023174 + "top": 632.0133083088757 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", @@ -2057,7 +827,7 @@ ], "position": { "left": 1456.9501085652712, - "top": 637.8524402234124 + "top": 637.0007277299707 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", @@ -2106,7 +876,7 @@ ], "position": { "left": 1708.700108565271, - "top": 623.7399524304436 + "top": 622.8882399370019 }, "post_job_actions": {}, "tool_id": "__RELABEL_FROM_FILE__", @@ -2148,7 +918,7 @@ ], "position": { "left": 1483.7124938964844, - "top": 202.4024963882549 + "top": 201.5507838948132 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", @@ -2205,7 +975,7 @@ ], "position": { "left": 1823.275109572711, - "top": 190.86132373743087 + "top": 190.00961124398918 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", @@ -2224,66 +994,10 @@ "workflow_outputs": [] }, "12": { - "annotation": "Compare SNV profiles across samples to identify shared strains", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", - "errors": null, - "id": 12, - "input_connections": { - "database": { - "id": 2, - "output_name": "output" - }, - "input_names": { - "id": 11, - "output_name": "sample_names" - }, - "input_snvs": { - "id": 11, - "output_name": "filtered_profile" - } - }, - "inputs": [], - "label": null, - "name": "SameStr Compare", - "outputs": [ - { - "name": "overlap_file", - "type": "tabular" - }, - { - "name": "close_file", - "type": "tabular" - }, - { - "name": "fraction_file", - "type": "tabular" - } - ], - "position": { - "left": 2155.5249938964844, - "top": 187.23999028473926 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "0e149f56-196c-43ba-a8e1-2b37555efeb7", - "when": null, - "workflow_outputs": [] - }, - "13": { "annotation": "empty datasets with insufficient coverage or no SNVs detected", "content_id": "__FILTER_EMPTY_DATASETS__", "errors": null, - "id": 13, + "id": 12, "input_connections": { "input": { "id": 11, @@ -2305,8 +1019,8 @@ } ], "position": { - "left": 2192.550018310547, - "top": 471.3650208023174 + "left": 2096.202567546577, + "top": 192.1534902400213 }, "post_job_actions": {}, "tool_id": "__FILTER_EMPTY_DATASETS__", @@ -2318,11 +1032,11 @@ "when": null, "workflow_outputs": [] }, - "14": { + "13": { "annotation": "empty datasets with insufficient coverage or no SNVs detected", "content_id": "__FILTER_EMPTY_DATASETS__", "errors": null, - "id": 14, + "id": 13, "input_connections": { "input": { "id": 11, @@ -2344,8 +1058,8 @@ } ], "position": { - "left": 2197.612518310547, - "top": 648.8775330093487 + "left": 2096.278478020317, + "top": 362.1451321080018 }, "post_job_actions": {}, "tool_id": "__FILTER_EMPTY_DATASETS__", @@ -2357,100 +1071,78 @@ "when": null, "workflow_outputs": [] }, - "15": { - "annotation": "empty datasets with insufficient coverage or no SNVs detected", - "content_id": "__FILTER_EMPTY_DATASETS__", + "14": { + "annotation": "Compare SNV profiles across samples to identify shared strains", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", "errors": null, - "id": 15, + "id": 14, "input_connections": { - "input": { + "database": { + "id": 2, + "output_name": "output" + }, + "input_names": { + "id": 13, + "output_name": "output" + }, + "input_snvs": { "id": 12, - "output_name": "overlap_file" + "output_name": "output" } }, - "inputs": [ - { - "description": "runtime parameter for tool Filter empty datasets", - "name": "replacement" - } - ], + "inputs": [], "label": null, - "name": "Filter empty datasets", + "name": "SameStr Compare", "outputs": [ { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 2460.0125427246094, - "top": 103.65246587067676 - }, - "post_job_actions": {}, - "tool_id": "__FILTER_EMPTY_DATASETS__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.1.0", - "type": "tool", - "uuid": "d098e445-5b12-4d54-8012-c547773689a2", - "when": null, - "workflow_outputs": [] - }, - "16": { - "annotation": "empty datasets with insufficient coverage or no SNVs detected", - "content_id": "__FILTER_EMPTY_DATASETS__", - "errors": null, - "id": 16, - "input_connections": { - "input": { - "id": 12, - "output_name": "fraction_file" - } - }, - "inputs": [ + "name": "overlap_file", + "type": "tabular" + }, { - "description": "runtime parameter for tool Filter empty datasets", - "name": "replacement" - } - ], - "label": null, - "name": "Filter empty datasets", - "outputs": [ + "name": "close_file", + "type": "tabular" + }, { - "name": "output", - "type": "input" + "name": "fraction_file", + "type": "tabular" } ], "position": { - "left": 2461.962559737145, - "top": 293.3399890515376 + "left": 2378.0972762621154, + "top": 203.82359708661107 }, "post_job_actions": {}, - "tool_id": "__FILTER_EMPTY_DATASETS__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", "tool_uuid": null, - "tool_version": "1.1.0", + "tool_version": "1.2025.111+galaxy0", "type": "tool", - "uuid": "790c8cb1-51e7-4714-8ade-30442337be24", + "uuid": "0e149f56-196c-43ba-a8e1-2b37555efeb7", "when": null, "workflow_outputs": [] }, - "17": { + "15": { "annotation": "Generate summary statistics of SNV profiles per sample", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", "errors": null, - "id": 17, + "id": 15, "input_connections": { "database": { "id": 2, "output_name": "output" }, "input_names": { - "id": 14, + "id": 13, "output_name": "output" }, "input_snvs": { - "id": 13, + "id": 12, "output_name": "output" } }, @@ -2464,8 +1156,8 @@ } ], "position": { - "left": 2467.4124450683594, - "top": 582.3525085952862 + "left": 2453.862400870168, + "top": 593.6517663631948 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", @@ -2489,23 +1181,23 @@ } ] }, - "18": { + "16": { "annotation": "Summarize strain sharing results across all sample pairs", "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", "errors": null, - "id": 18, + "id": 16, "input_connections": { "database": { "id": 2, "output_name": "output" }, "overlaps": { - "id": 15, - "output_name": "output" + "id": 14, + "output_name": "overlap_file" }, "similarities": { - "id": 16, - "output_name": "output" + "id": 14, + "output_name": "fraction_file" }, "tax_profiles": { "id": 3, @@ -2530,8 +1222,8 @@ } ], "position": { - "left": 2897.7834118519604, - "top": 159.0108191512512 + "left": 2755.692519986277, + "top": 152.29339375080397 }, "post_job_actions": {}, "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", @@ -2548,6 +1240,11 @@ "uuid": "c67ca84a-bd25-4161-9771-e8a4af61dda8", "when": null, "workflow_outputs": [ + { + "label": "Co-occurrences (MetaPhlAn)", + "output_name": "cooccurrences", + "uuid": "b9b9a2ea-45a5-4874-895d-8b334da3c289" + }, { "label": "Taxon counts (MetaPhlAn)", "output_name": "taxon_counts", @@ -2557,17 +1254,12 @@ "label": "Strain events (MetaPhlAn)", "output_name": "strain_events", "uuid": "c3833465-80a0-486f-b54f-0eda31728915" - }, - { - "label": "Co-occurrences (MetaPhlAn)", - "output_name": "cooccurrences", - "uuid": "b9b9a2ea-45a5-4874-895d-8b334da3c289" } ] } }, "tags": [], - "uuid": "7d18be01-a7dc-41a5-932e-d557bacb3403" + "uuid": "6687f903-e65d-4e41-b3ee-7f758979fa9a" }, "tool_id": null, "type": "subworkflow", @@ -2579,6 +1271,11 @@ "output_name": "Stats file (MetaPhlAn)", "uuid": "c4227302-b049-44e8-a05a-b648d884db44" }, + { + "label": "Taxon counts (MetaPhlAn)", + "output_name": "Taxon counts (MetaPhlAn)", + "uuid": "8cd1a75a-a3d5-41de-9d2a-5d29853d057e" + }, { "label": "Co-occurrences (MetaPhlAn)", "output_name": "Co-occurrences (MetaPhlAn)", @@ -2588,11 +1285,6 @@ "label": "Strain events (MetaPhlAn)", "output_name": "Strain events (MetaPhlAn)", "uuid": "85ab6172-3eb6-4a49-bef3-c81bf4c0c278" - }, - { - "label": "Taxon counts (MetaPhlAn)", - "output_name": "Taxon counts (MetaPhlAn)", - "uuid": "8cd1a75a-a3d5-41de-9d2a-5d29853d057e" } ] } @@ -2602,6 +1294,6 @@ "microbiome", "shared-strains" ], - "uuid": "f39609c0-8971-44e9-a93e-b79a8493abb7", - "version": 92 -} \ No newline at end of file + "uuid": "7498be57-b555-411c-ac2c-080c74705344", + "version": 106 +} From 0dc448e2bd6f53450502258ac43f16bd0849f3ea Mon Sep 17 00:00:00 2001 From: Xenia Date: Sun, 19 Jul 2026 15:27:32 +0200 Subject: [PATCH 12/12] modified structure --- .../microbiome/samestr-workflow/README.md | 2 - .../samestr-workflow/samestrgal-tests.yml | 65 +- .../microbiome/samestr-workflow/samestrgal.ga | 2423 ++++++++++------- 3 files changed, 1412 insertions(+), 1078 deletions(-) diff --git a/workflows/microbiome/samestr-workflow/README.md b/workflows/microbiome/samestr-workflow/README.md index 549ca0ac4a..3a4415f236 100644 --- a/workflows/microbiome/samestr-workflow/README.md +++ b/workflows/microbiome/samestr-workflow/README.md @@ -10,9 +10,7 @@ This workflow processes paired-end shotgun metagenomic sequencing reads from mul - **Raw Reads**: A collection of paired-end FASTQ files from one or more samples to compare - **Run MetaPhlAn**: Boolean parameter (default: true) that enables MetaPhlAn-based strain detection -- **Run mOTUs**: Boolean parameter (default: false) that enables mOTUs-based strain detection ## Outputs - **MetaPhlAn results** (if enabled): SNV profile summary statistics, taxon counts, strain events, and co-occurrence tables - - **mOTUs results** (if enabled): SNV profile summary statistics, taxon counts, strain events, and co-occurrence tables diff --git a/workflows/microbiome/samestr-workflow/samestrgal-tests.yml b/workflows/microbiome/samestr-workflow/samestrgal-tests.yml index 3821e45990..2091391057 100644 --- a/workflows/microbiome/samestr-workflow/samestrgal-tests.yml +++ b/workflows/microbiome/samestr-workflow/samestrgal-tests.yml @@ -5,7 +5,7 @@ collection_type: list:paired elements: - class: Collection - type: paired + collection_type: paired identifier: 28C elements: - class: File @@ -17,7 +17,7 @@ location: https://zenodo.org/records/20745835/files/28C_R2.fastq.gz filetype: fastqsanger.gz - class: Collection - type: paired + collection_type: paired identifier: 28B elements: - class: File @@ -29,7 +29,7 @@ location: https://zenodo.org/records/20745835/files/28B_R2.fastq.gz filetype: fastqsanger.gz - class: Collection - type: paired + collection_type: paired identifier: 28A elements: - class: File @@ -40,51 +40,66 @@ identifier: reverse location: https://zenodo.org/records/20745835/files/28A_R2.fastq.gz filetype: fastqsanger.gz - Run MetaPhlAn: true - Select SameStr database MetaPhlAn: mpa_vJan25_CHOCOPhlAnSGB_202503-11062025 + Select Host reference genome: hg19 + Select Sequencer for Trimmomatic: NexteraPE Select MetaPhlAn Database: mpa_vJan25_CHOCOPhlAnSGB_202503-11062025 - Host reference genome: hg19 - Sequencer type: NexteraPE + Select SameStr database: mpa_vJan25_CHOCOPhlAnSGB_202503-11062025 + Run MetaPhlAn: true + "Percent identity": 0.9 + "Minimum alignment length": 40 + "Minimum base quality": 20 + "Minimum alignment quality": 0 + "Minimum vertical coverage": 3 + "SameStr Filter: Minimum samples per clade": 2 + "SameStr Filter: Marker truncation length": 50 + "SameStr Filter: Nucleotides minimum variant coverage": 2 + "SameStr Filter: Minimum variant coverage fraction": 0.05 + "SameStr Filter: Minimum position coverage": 1 + "SameStr Filter: Position coverage standard deviation cutoff": 3.0 + "SameStr Filter: Minimum horizontal coverage": 5000 + "SameStr Filter: Minimum sample coverage per position": 2 + "SameStr Summarize: Minimum overlap for comparison": 5000 + "SameStr Summarize: Minimum similarity for shared strains": 0.999 outputs: - "Stats file (MetaPhlAn)": + "stats file": element_tests: t__SGB15299: asserts: - has_text: + - that: has_text text: "28B" t__SGB4285: asserts: - has_text: + - that: has_text text: "28B" t__SGB6362: asserts: - has_text: + - that: has_text text: "28B" - "Taxon counts (MetaPhlAn)": + "taxon counts": asserts: - has_text: + - that: has_text text: "28A" - has_text: + - that: has_text text: "28B" - has_text: + - that: has_text text: "28C" - "Strain events (MetaPhlAn)": + "strain events": asserts: - has_text: + - that: has_text text: "t__SGB15299" - has_text: + - that: has_text text: "t__SGB4285" - has_text: + - that: has_text text: "t__SGB6362" - has_text: + - that: has_text text: "28B" - has_text: + - that: has_text text: "28C" - "Co-occurrences (MetaPhlAn)": + "cooccurrences": asserts: - has_text: + - that: has_text text: "28A" - has_text: + - that: has_text text: "28B" - has_text: + - that: has_text text: "28C" diff --git a/workflows/microbiome/samestr-workflow/samestrgal.ga b/workflows/microbiome/samestr-workflow/samestrgal.ga index 111e86f7af..7b3a621dc4 100644 --- a/workflows/microbiome/samestr-workflow/samestrgal.ga +++ b/workflows/microbiome/samestr-workflow/samestrgal.ga @@ -4,62 +4,77 @@ "comments": [ { "child_steps": [ - 8, - 5, - 3, - 4 + 0 ], - "color": "blue", + "color": "red", "data": { - "title": "MetaPhlAn Subworkflow" + "title": "Input Samples" }, - "id": 3, + "id": 0, "position": [ - 893.4, - 0 + 0, + 372.55833722393095 ], "size": [ - 512, - 469 + 240, + 121.2 ], "type": "frame" }, { "child_steps": [ - 0 + 36 ], - "color": "red", + "color": "green", "data": { - "title": "Input Samples" + "title": "SameStr Output" }, - "id": 0, + "id": 5, "position": [ - 0, - 25.19875866330679 + 3608.2, + 365.1689085188362 ], "size": [ - 240, - 121.2 + 322.8, + 487.8 ], "type": "frame" }, { "child_steps": [ - 6, - 7 + 34 ], - "color": "yellow", + "color": "green", "data": { - "title": "Preprocessing Steps" + "title": "SameStr Output" }, - "id": 1, + "id": 4, "position": [ - 317.7, - 4.335876726664907 + 3061.4, + 718.9689085188362 + ], + "size": [ + 279.6, + 246.8 + ], + "type": "frame" + }, + { + "child_steps": [ + 23 + ], + "color": "orange", + "data": { + "title": "Taxonomic Profiling and Marker-Based AlignmentFrame" + }, + "id": 3, + "position": [ + 919.2, + 419.8689085188362 ], "size": [ - 517, - 454 + 283.6, + 397 ], "type": "frame" }, @@ -72,13 +87,33 @@ "id": 2, "position": [ 260.4, - 606.435876726665 + 953.7954552872891 ], "size": [ 0, 0 ], "type": "text" + }, + { + "child_steps": [ + 21, + 22 + ], + "color": "yellow", + "data": { + "title": "Preprocessing SClade and marker setting steps" + }, + "id": 1, + "position": [ + 317.7, + 351.69545528728906 + ], + "size": [ + 528, + 468 + ], + "type": "frame" } ], "creator": [ @@ -92,7 +127,7 @@ "format-version": "0.1", "license": "MIT", "name": "SamestrGal", - "release": "0.1", + "readme": "# SamestrGal for shared-strain detection in metagenomes\n\nThis workflow processes paired-end shotgun metagenomic sequencing reads from multiple samples. It performs the following steps:\n\n- **Preprocessing**: Quality trimming and host read removal using KneadData\n- **Taxonomic profiling and marker-based alignment**: MetaPhlAn4 or mOTUs for taxonomic classification and marker based alignment\n- **Strain detection**: SameStr tools identify strains across samples and compute pairwise strain comparisons using Maximum Variant Profile Similarity (MVS) scores.\n\n## Inputs\n\n- **Raw Reads**: A collection of paired-end FASTQ files from one or more samples to compare\n- **Run MetaPhlAn**: Boolean parameter (default: true) that enables MetaPhlAn-based strain detection\n- **Run mOTUs**: Boolean parameter (default: false) that enables mOTUs-based strain detection\n\n## Outputs\n\n - **MetaPhlAn results** (if enabled): SNV profile summary statistics, taxon counts, strain events, and co-occurrence tables\n - **mOTUs results** (if enabled): SNV profile summary statistics, taxon counts, strain events, and co-occurrence tables\n", "report": { "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" }, @@ -114,7 +149,7 @@ "outputs": [], "position": { "left": 19.978197146864574, - "top": 65.2411929095941 + "top": 412.6007714702182 }, "tool_id": null, "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", @@ -141,7 +176,7 @@ "outputs": [], "position": { "left": 21.089008554360447, - "top": 237.64203478760095 + "top": 585.0016133482251 }, "tool_id": null, "tool_state": "{\"default\": \"hg19\", \"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", @@ -152,1139 +187,1425 @@ "workflow_outputs": [] }, "2": { - "annotation": "Select the sequencer for Trimmomatic", + "annotation": "Run MetaPhlAn ", "content_id": null, "errors": null, "id": 2, "input_connections": {}, "inputs": [ { - "description": "Select the sequencer for Trimmomatic", - "name": "Select Sequencer for Trimmomatic" + "description": "Run MetaPhlAn ", + "name": "Run MetaPhlAn" } ], - "label": "Select Sequencer for Trimmomatic", + "label": "Run MetaPhlAn", "name": "Input parameter", "outputs": [], "position": { - "left": 21.258349362270508, - "top": 343.6750153034452 + "left": 673.1477845186159, + "top": 102.91109784322902 }, "tool_id": null, - "tool_state": "{\"default\": \"NexteraPE\", \"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", + "tool_state": "{\"default\": true, \"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "2b87cb9d-9f7d-40f3-ae19-a67834afbe27", + "uuid": "4b85acb6-5d5e-4703-bf84-421a2de2b209", "when": null, "workflow_outputs": [] }, "3": { - "annotation": "Select SameStr database. If running MetaPhlAn subworkflow, only select MetaPhlan databases. If running mOTUs, only select mOTUs databases.", + "annotation": "Select the sequencer for Trimmomatic", "content_id": null, "errors": null, "id": 3, "input_connections": {}, "inputs": [ { - "description": "Select SameStr database. If running MetaPhlAn subworkflow, only select MetaPhlan databases. If running mOTUs, only select mOTUs databases.", - "name": "Select SameStr database MetaPhlAn" + "description": "Select the sequencer for Trimmomatic", + "name": "Select Sequencer for Trimmomatic" } ], - "label": "Select SameStr database MetaPhlAn", + "label": "Select Sequencer for Trimmomatic", "name": "Input parameter", "outputs": [], "position": { - "left": 912.5013902808578, - "top": 52.935621088787016 + "left": 21.258349362270508, + "top": 691.0345938640694 }, "tool_id": null, - "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", + "tool_state": "{\"default\": \"NexteraPE\", \"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "a0a6433f-8241-4bfb-9216-8ba9a6dddf6c", + "uuid": "2b87cb9d-9f7d-40f3-ae19-a67834afbe27", "when": null, "workflow_outputs": [] }, "4": { - "annotation": "Run MetaPhlAn subworkflow for shared strain detection.", + "annotation": "Choose the MetaPhlAn database version", "content_id": null, "errors": null, "id": 4, "input_connections": {}, "inputs": [ { - "description": "Run MetaPhlAn subworkflow for shared strain detection.", - "name": "Run MetaPhlAn" + "description": "Choose the MetaPhlAn database version", + "name": "Select MetaPhlAn Database" } ], - "label": "Run MetaPhlAn", + "label": "Select MetaPhlAn Database", "name": "Input parameter", "outputs": [], "position": { - "left": 916.5509815398043, - "top": 153.37585094505036 + "left": 672.2023205322555, + "top": 202.4333030061197 }, "tool_id": null, - "tool_state": "{\"default\": true, \"validators\": [], \"parameter_type\": \"boolean\", \"optional\": false}", + "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "4b85acb6-5d5e-4703-bf84-421a2de2b209", + "uuid": "393f0af0-4748-4270-8342-8fdc28907c07", "when": null, "workflow_outputs": [] }, "5": { - "annotation": "Choose the MetaPhlAn database version", + "annotation": "Select SameStr database. Only select databases that match the selected profiler", "content_id": null, "errors": null, "id": 5, "input_connections": {}, "inputs": [ { - "description": "Choose the MetaPhlAn database version", - "name": "Select MetaPhlAn Database" + "description": "Select SameStr database. Only select databases that match the selected profiler", + "name": "Select SameStr database" } ], - "label": "Select MetaPhlAn Database", + "label": "Select SameStr database", "name": "Input parameter", "outputs": [], "position": { - "left": 917.6385491266412, - "top": 262.74546966067135 + "left": 1157.102350586718, + "top": 0 }, "tool_id": null, "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", "tool_version": null, "type": "parameter_input", - "uuid": "393f0af0-4748-4270-8342-8fdc28907c07", + "uuid": "05f0a84c-c654-475a-b712-361a446a21de", "when": null, "workflow_outputs": [] }, "6": { - "annotation": "Quality trimming and host read removal. Boolean parameter 'Save all unmatched reads' must remain set to True. \n", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/kneaddata/kneaddata/0.12.1+galaxy1", + "annotation": "Alignment Filtering: Minimum percent identity required to retain an alignment (default: 0,9)", + "content_id": null, "errors": null, "id": 6, - "input_connections": { - "alignment|alignment_tool|bowtie2_db": { - "id": 1, - "output_name": "output" - }, - "read_type|paired_collection": { - "id": 0, - "output_name": "output" - }, - "trimmomatic|trimmomatic_step|sequencer": { - "id": 2, - "output_name": "output" - } - }, + "input_connections": {}, "inputs": [ { - "description": "runtime parameter for tool KneadData", - "name": "read_type" - } - ], - "label": "Trimming and Host Removal", - "name": "KneadData", - "outputs": [ - { - "name": "paired_output", - "type": "input" - }, - { - "name": "unmatched_paired", - "type": "input" - }, - { - "name": "trimmed_paired", - "type": "input" - }, - { - "name": "unmatched_trimmed_paired", - "type": "input" - }, - { - "name": "log_file", - "type": "txt" + "description": "Alignment Filtering: Minimum percent identity required to retain an alignment (default: 0,9)", + "name": "Percent identity" } ], + "label": "Percent identity", + "name": "Input parameter", + "outputs": [], "position": { - "left": 348.40905086852905, - "top": 39.66743258872239 + "left": 1412.9526594119561, + "top": 106.80560438229855 }, - "post_job_actions": { - "HideDatasetActiontrimmed_paired": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "trimmed_paired" - }, - "HideDatasetActionunmatched_trimmed_paired": { - "action_arguments": {}, - "action_type": "HideDatasetAction", - "output_name": "unmatched_trimmed_paired" - } - }, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/kneaddata/kneaddata/0.12.1+galaxy1", - "tool_shed_repository": { - "changeset_revision": "10f8abc1fbdf", - "name": "kneaddata", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"alignment\": {\"alignment_tool\": {\"tool_choice\": \"bowtie2\", \"__current_case__\": 0, \"bowtie2_db\": {\"__class__\": \"ConnectedValue\"}}, \"save_contaminants\": false}, \"fastqc\": {\"fastqc_report\": {\"select_fastqc\": \"no_fastqc\", \"__current_case__\": 1}, \"run_trim_repetitive\": false}, \"log_level\": \"INFO\", \"read_type\": {\"select_read_type\": \"paired\", \"__current_case__\": 1, \"save_unmatched\": true, \"paired_collection\": {\"__class__\": \"ConnectedValue\"}}, \"tandem\": {\"trf_step\": {\"trf_bool\": \"skip\", \"__current_case__\": 1}}, \"trimmomatic\": {\"trimmomatic_step\": {\"decide_trimmomatic\": \"run_trimmomatic\", \"__current_case__\": 0, \"sequencer\": {\"__class__\": \"ConnectedValue\"}}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "0.12.1+galaxy1", - "type": "tool", - "uuid": "9fe3494e-b20e-43fc-963c-818e81bc2d93", + "tool_id": null, + "tool_state": "{\"default\": 0.9, \"validators\": [{\"min\": 0.0, \"max\": 1.0, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"float\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "9a86d4c4-3580-42aa-bd44-145106454577", "when": null, "workflow_outputs": [] }, "7": { - "annotation": "Merge paired-end and orphaned reads from KneadData output", - "content_id": "__MERGE_COLLECTION__", + "annotation": "Alignment Filtering: Minimum alignment length, in base pairs, required to retain an alignment (default: 40)", + "content_id": null, "errors": null, "id": 7, - "input_connections": { - "inputs_0|input": { - "id": 6, - "output_name": "paired_output" - }, - "inputs_1|input": { - "id": 6, - "output_name": "unmatched_paired" - } - }, - "inputs": [], - "label": "Merge Collections", - "name": "Merge collections", - "outputs": [ + "input_connections": {}, + "inputs": [ { - "name": "output", - "type": "input" + "description": "Alignment Filtering: Minimum alignment length, in base pairs, required to retain an alignment (default: 40)", + "name": "Minimum alignment length" } ], + "label": "Minimum alignment length", + "name": "Input parameter", + "outputs": [], "position": { - "left": 613.7878702851508, - "top": 62.29048218334535 + "left": 1413.3523128783154, + "top": 199.8708753214608 }, - "post_job_actions": {}, - "tool_id": "__MERGE_COLLECTION__", - "tool_state": "{\"advanced\": {\"conflict\": {\"duplicate_options\": \"keep_first\", \"__current_case__\": 3}}, \"inputs\": [{\"__index__\": 0, \"input\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"input\": {\"__class__\": \"ConnectedValue\"}}], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.0.0", - "type": "tool", - "uuid": "9d6634d3-7b42-4b27-86d7-51b712fe5da4", + "tool_id": null, + "tool_state": "{\"default\": 40, \"validators\": [{\"min\": 0, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "9ec544ab-7778-4890-bac1-757cf575401d", "when": null, "workflow_outputs": [] }, "8": { - "annotation": "Taxonomic profiling with MetaPhlAn ", + "annotation": "Alignment Filtering: Minimum quality score required for a base call to be retained (default: 20)", + "content_id": null, + "errors": null, "id": 8, - "input_connections": { - "0:Input dataset collection": { - "id": 7, - "input_subworkflow_step_id": 0, - "output_name": "output" - }, - "Select MetaPhlAn Database": { - "id": 5, - "input_subworkflow_step_id": 1, - "output_name": "output" - }, - "Select SameStr database MetaPhlAn": { - "id": 3, - "input_subworkflow_step_id": 2, - "output_name": "output" - }, - "when": { - "id": 4, - "output_name": "output" + "input_connections": {}, + "inputs": [ + { + "description": "Alignment Filtering: Minimum quality score required for a base call to be retained (default: 20)", + "name": "Minimum base quality" } + ], + "label": "Minimum base quality", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 1417.1388429839783, + "top": 288.01004747237084 }, + "tool_id": null, + "tool_state": "{\"default\": 20, \"validators\": [{\"min\": 0, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "1f74002d-fa4e-4e1c-b02e-c5afcdfd5124", + "when": null, + "workflow_outputs": [] + }, + "9": { + "annotation": "Alignment Filtering: Minimum mapping quality required to retain an alignment. Increasing this threshold can drastically reduce the number of considered variants (default: 0)", + "content_id": null, + "errors": null, + "id": 9, + "input_connections": {}, "inputs": [ { - "description": "Taxonomic profiling with MetaPhlAn ", - "name": "Metaphlan Subworkflow" + "description": "Alignment Filtering: Minimum mapping quality required to retain an alignment. Increasing this threshold can drastically reduce the number of considered variants (default: 0)", + "name": "Minimum alignment quality" } ], - "label": "Metaphlan Subworkflow", - "name": "Metaphlan Subworkflow", + "label": "Minimum alignment quality", + "name": "Input parameter", "outputs": [], "position": { - "left": 1187.3670214501526, - "top": 39.95931732854578 - }, - "subworkflow": { - "a_galaxy_workflow": "true", - "annotation": "", - "comments": [ - { - "child_steps": [ - 15 - ], - "color": "green", - "data": { - "title": "SameStr Output" - }, - "id": 2, - "position": [ - 2433.9, - 553.5482875065583 - ], - "size": [ - 245, - 255 - ], - "type": "frame" - }, - { - "child_steps": [ - 3 - ], - "color": "orange", - "data": { - "title": "Taxonomic Profiling and Marker-Based Alignment" - }, - "id": 0, - "position": [ - 358.3875, - 29.12577168778195 - ], - "size": [ - 240, - 372 - ], - "type": "frame" - }, - { - "child_steps": [ - 5, - 10, - 11, - 12, - 14, - 13 - ], - "color": "turquoise", - "data": { - "title": "SameStr Strain-level Analysis" - }, - "id": 1, - "position": [ - 1092.0875, - 146.42577168778197 - ], - "size": [ - 1587, - 388 - ], - "type": "frame" - }, - { - "child_steps": [ - 16 - ], - "color": "green", - "data": { - "title": "SameStr Output" - }, - "id": 3, - "position": [ - 2735.7, - 112.24828750655831 - ], - "size": [ - 244, - 504 - ], - "type": "frame" - } - ], - "format-version": "0.1", - "name": "Metaphlan Subworkflow", - "report": { - "markdown": "\n# Workflow Execution Report\n\n## Workflow Inputs\n```galaxy\ninvocation_inputs()\n```\n\n## Workflow Outputs\n```galaxy\ninvocation_outputs()\n```\n\n## Workflow\n```galaxy\nworkflow_display()\n```\n" - }, - "steps": { - "0": { - "annotation": "Merged paired-end and orphaned reads", - "content_id": null, - "errors": null, - "id": 0, - "input_connections": {}, - "inputs": [], - "label": null, - "name": "Input dataset collection", - "outputs": [], - "position": { - "left": 0, - "top": 52.60077168778195 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null, \"collection_type\": \"list:paired\", \"fields\": null, \"column_definitions\": null}", - "tool_version": null, - "type": "data_collection_input", - "uuid": "3517c677-41a8-4963-b760-60c3e79dd9d1", - "when": null, - "workflow_outputs": [] - }, - "1": { - "annotation": "Choose the MetaPhlAn database version", - "content_id": null, - "errors": null, - "id": 1, - "input_connections": {}, - "inputs": [ - { - "description": "Choose the MetaPhlAn database version", - "name": "Select MetaPhlAn Database" - } - ], - "label": "Select MetaPhlAn Database", - "name": "Input parameter", - "outputs": [], - "position": { - "left": 5.745321782154769, - "top": 165.0894065076869 - }, - "tool_id": null, - "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", - "tool_version": null, - "type": "parameter_input", - "uuid": "735532ca-b622-4445-b5e1-f34a1e4c26b0", - "when": null, - "workflow_outputs": [] - }, - "2": { - "annotation": "Select SameStr database. Only select MetaPhlan databases", - "content_id": null, - "errors": null, - "id": 2, - "input_connections": {}, - "inputs": [ - { - "description": "Select SameStr database. Only select MetaPhlan databases", - "name": "Select SameStr database MetaPhlAn" - } - ], - "label": "Select SameStr database MetaPhlAn", - "name": "Input parameter", - "outputs": [], - "position": { - "left": 1503.9321967283095, - "top": 0 - }, - "tool_id": null, - "tool_state": "{\"multiple\": false, \"validators\": [], \"restrictOnConnections\": true, \"parameter_type\": \"text\", \"optional\": false}", - "tool_version": null, - "type": "parameter_input", - "uuid": "af0c000e-1004-405e-899b-e0b129671183", - "when": null, - "workflow_outputs": [] - }, - "3": { - "annotation": "Generate taxonomic profiles and marker gene alignments for SameStr", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/metaphlan/metaphlan/4.2.4+galaxy0", - "errors": null, - "id": 3, - "input_connections": { - "inputs|db|cached_db": { - "id": 1, - "output_name": "output" - }, - "inputs|in|raw_in|in": { - "id": 0, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool MetaPhlAn", - "name": "analysis" - } - ], - "label": null, - "name": "MetaPhlAn", - "outputs": [ - { - "name": "output_file", - "type": "tabular" - }, - { - "name": "mapout", - "type": "tabular" - }, - { - "name": "sam_output_file", - "type": "sam" - } - ], - "position": { - "left": 379.4250183105469, - "top": 99.506609650113 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/metaphlan/metaphlan/4.2.4+galaxy0", - "tool_shed_repository": { - "changeset_revision": "56ff60ec416d", - "name": "metaphlan", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"analysis\": {\"analysis_type\": {\"t\": \"rel_ab\", \"__current_case__\": 0, \"tax_lev\": {\"tax_lev\": \"a\", \"__current_case__\": 0, \"split_levels\": false}}, \"min_alignment_len\": null, \"organism_profiling\": null, \"stat\": \"tavg_g\", \"stat_q\": \"0.2\", \"perc_nonzero\": \"0.33\", \"ignore_markers\": {\"__class__\": \"RuntimeValue\"}, \"avoid_disqm\": true}, \"inputs\": {\"in\": {\"selector\": \"raw\", \"__current_case__\": 0, \"raw_in\": {\"selector\": \"paired_collection\", \"__current_case__\": 2, \"in\": {\"__class__\": \"ConnectedValue\"}}, \"read_min_len\": \"70\", \"mapping\": {\"bt2_ps\": \"very-sensitive\", \"min_mapq_val\": \"5\"}}, \"db\": {\"db_selector\": \"cached\", \"__current_case__\": 0, \"cached_db\": {\"__class__\": \"ConnectedValue\"}, \"viral_analysis\": {\"profile_vsc\": \"\", \"__current_case__\": 1}}}, \"out\": {\"sample_id_key\": \"SampleID\", \"sample_id\": \"Metaphlan_Analysis\", \"use_group_representative\": false, \"CAMI_format_output\": false, \"skip_unclassified_estimation\": false, \"biom_format_output\": false, \"krona_output\": false}, \"subsample\": {\"selector\": \"no\", \"__current_case__\": 0}, \"test\": \"false\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "4.2.4+galaxy0", - "type": "tool", - "uuid": "2024124c-b74b-4851-843e-2119d8824dec", - "when": null, - "workflow_outputs": [] - }, - "4": { - "annotation": "Convert SAM to BAM format", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samtools_view/samtools_view/1.22+galaxy2", - "errors": null, - "id": 4, - "input_connections": { - "input": { - "id": 3, - "output_name": "sam_output_file" - } - }, - "inputs": [], - "label": null, - "name": "Samtools view", - "outputs": [ - { - "name": "outputsam", - "type": "input" - } - ], - "position": { - "left": 754.0375671386719, - "top": 303.0507838948132 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samtools_view/samtools_view/1.22+galaxy2", - "tool_shed_repository": { - "changeset_revision": "5cf9fcc93508", - "name": "samtools_view", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"addref_cond\": {\"addref_select\": \"no\", \"__current_case__\": 0}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"mode\": {\"outtype\": \"all_reads\", \"__current_case__\": 0, \"output_options\": {\"reads_report_type\": \"retained\", \"__current_case__\": 0, \"adv_output\": {\"readtags\": [], \"collapsecigar\": false}, \"output_format\": {\"oformat\": \"bam\", \"__current_case__\": 2}}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.22+galaxy2", - "type": "tool", - "uuid": "4166154d-3177-470a-af56-aaadc1a39165", - "when": null, - "workflow_outputs": [] - }, - "5": { - "annotation": "Convert BAM to SNV profiles for SameStr analysis", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", - "errors": null, - "id": 5, - "input_connections": { - "alignment": { - "id": 4, - "output_name": "outputsam" - }, - "database": { - "id": 2, - "output_name": "output" - }, - "profile": { - "id": 3, - "output_name": "output_file" - } - }, - "inputs": [], - "label": null, - "name": "SameStr Convert", - "outputs": [ - { - "name": "npz_files", - "type": "input" - }, - { - "name": "stats_file", - "type": "tabular" - } - ], - "position": { - "left": 1112.0749816894531, - "top": 194.61322285965696 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": \"0.9\", \"min_aln_len\": \"40\", \"min_base_qual\": \"20\", \"min_aln_qual\": \"0\", \"min_vcov\": \"3\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "f63a91e2-40b5-4d61-b398-21016209f9af", - "when": null, - "workflow_outputs": [] - }, - "6": { - "annotation": "Flatten collection to allow cross-sample SNV profile comparison. Note: this modifies element identifiers by adding an underscore, which makes naming afterwards unstable for SameStr", - "content_id": "__FLATTEN__", - "errors": null, - "id": 6, - "input_connections": { - "input": { - "id": 5, - "output_name": "npz_files" - } - }, - "inputs": [], - "label": null, - "name": "Flatten collection", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 866.5750427246094, - "top": 632.1257961018445 - }, - "post_job_actions": {}, - "tool_id": "__FLATTEN__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"join_identifier\": \"_\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.0.0", - "type": "tool", - "uuid": "390d4a87-df49-4921-af66-242f7bb67e06", - "when": null, - "workflow_outputs": [] - }, - "7": { - "annotation": "Extract element identifiers from flattened collection to prepare for renaming", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", - "errors": null, - "id": 7, - "input_connections": { - "input_collection": { - "id": 6, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "Extract element identifiers", - "outputs": [ - { - "name": "output", - "type": "txt" - } - ], - "position": { - "left": 1170.5999450683594, - "top": 632.0133083088757 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/collection_element_identifiers/collection_element_identifiers/0.0.3", - "tool_shed_repository": { - "changeset_revision": "3e27acfa4830", - "name": "collection_element_identifiers", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"input_collection\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "0.0.3", - "type": "tool", - "uuid": "2277359e-9fff-4a91-ac55-de361a90439c", - "when": null, - "workflow_outputs": [] - }, - "8": { - "annotation": "Clean element identifiers after flattening to restore compatible naming for downstream tools", - "content_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", - "errors": null, - "id": 8, - "input_connections": { - "input": { - "id": 7, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "Regex Find And Replace", - "outputs": [ - { - "name": "out_file1", - "type": "input" - } - ], - "position": { - "left": 1456.9501085652712, - "top": 637.0007277299707 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/galaxyp/regex_find_replace/regex1/1.0.3", - "tool_shed_repository": { - "changeset_revision": "503bcd6ebe4b", - "name": "regex_find_replace", - "owner": "galaxyp", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"checks\": [{\"__index__\": 0, \"pattern\": \"^[^_]+_\", \"replacement\": \"\"}], \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.0.3", - "type": "tool", - "uuid": "52c68971-3407-49c2-bd29-9bfa40c06ad5", - "when": null, - "workflow_outputs": [] - }, - "9": { - "annotation": "Rename cleaned identifiers to match SameStr expected format", - "content_id": "__RELABEL_FROM_FILE__", - "errors": null, - "id": 9, - "input_connections": { - "how|labels": { - "id": 8, - "output_name": "out_file1" - }, - "input": { - "id": 6, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Relabel identifiers", - "name": "how" - } - ], - "label": null, - "name": "Relabel identifiers", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 1708.700108565271, - "top": 622.8882399370019 - }, - "post_job_actions": {}, - "tool_id": "__RELABEL_FROM_FILE__", - "tool_state": "{\"how\": {\"how_select\": \"txt\", \"__current_case__\": 0, \"labels\": {\"__class__\": \"ConnectedValue\"}, \"strict\": false}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.1.0", - "type": "tool", - "uuid": "10bb239a-98ea-42df-b481-fcb1311da260", - "when": null, - "workflow_outputs": [] - }, - "10": { - "annotation": "Merge SNV profiles from multiple samples for cross-sample strain comparison", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", - "errors": null, - "id": 10, - "input_connections": { - "database": { - "id": 2, - "output_name": "output" - }, - "input_files": { - "id": 9, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "SameStr Merge", - "outputs": [ - { - "name": "npz_files", - "type": "input" - }, - { - "name": "sample_name", - "type": "input" - } - ], - "position": { - "left": 1483.7124938964844, - "top": 201.5507838948132 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"clade\": null, \"database\": {\"__class__\": \"ConnectedValue\"}, \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "ce294c50-ae1d-4bd9-a514-ab503fb4c9b7", - "when": null, - "workflow_outputs": [] - }, - "11": { - "annotation": "Filter SNV profiles to retain high confidence variants for strain analysis", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", - "errors": null, - "id": 11, - "input_connections": { - "database": { - "id": 2, - "output_name": "output" - }, - "input_names": { - "id": 10, - "output_name": "sample_name" - }, - "input_snvs": { - "id": 10, - "output_name": "npz_files" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool SameStr Filter", - "name": "sample_filtering" - } - ], - "label": null, - "name": "SameStr Filter", - "outputs": [ - { - "name": "filtered_profile", - "type": "npz" - }, - { - "name": "sample_names", - "type": "tabular" - } - ], - "position": { - "left": 1823.275109572711, - "top": 190.00961124398918 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"clade_settings\": {\"clade_min_samples\": \"2\", \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": \"20\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"global_position_filtering\": {\"global_pos_min_n_vcov\": \"2\", \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": \"5000\", \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": \"1\", \"sample_pos_min_sd_vcov\": \"3.0\"}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": \"2\", \"sample_var_min_f_vcov\": \"0.1\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "4a661ef3-3f7c-4c5d-866f-d2f034afda7e", - "when": null, - "workflow_outputs": [] - }, - "12": { - "annotation": "empty datasets with insufficient coverage or no SNVs detected", - "content_id": "__FILTER_EMPTY_DATASETS__", - "errors": null, - "id": 12, - "input_connections": { - "input": { - "id": 11, - "output_name": "filtered_profile" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Filter empty datasets", - "name": "replacement" - } - ], - "label": null, - "name": "Filter empty datasets", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 2096.202567546577, - "top": 192.1534902400213 - }, - "post_job_actions": {}, - "tool_id": "__FILTER_EMPTY_DATASETS__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.1.0", - "type": "tool", - "uuid": "4edb9ead-f835-4884-9ce9-8a401e1d371a", - "when": null, - "workflow_outputs": [] - }, - "13": { - "annotation": "empty datasets with insufficient coverage or no SNVs detected", - "content_id": "__FILTER_EMPTY_DATASETS__", - "errors": null, - "id": 13, - "input_connections": { - "input": { - "id": 11, - "output_name": "sample_names" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Filter empty datasets", - "name": "replacement" - } - ], - "label": null, - "name": "Filter empty datasets", - "outputs": [ - { - "name": "output", - "type": "input" - } - ], - "position": { - "left": 2096.278478020317, - "top": 362.1451321080018 - }, - "post_job_actions": {}, - "tool_id": "__FILTER_EMPTY_DATASETS__", - "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.1.0", - "type": "tool", - "uuid": "7c14bf4c-ae4d-42ea-bd53-3d00f172b9a9", - "when": null, - "workflow_outputs": [] - }, - "14": { - "annotation": "Compare SNV profiles across samples to identify shared strains", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", - "errors": null, - "id": 14, - "input_connections": { - "database": { - "id": 2, - "output_name": "output" - }, - "input_names": { - "id": 13, - "output_name": "output" - }, - "input_snvs": { - "id": 12, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "SameStr Compare", - "outputs": [ - { - "name": "overlap_file", - "type": "tabular" - }, - { - "name": "close_file", - "type": "tabular" - }, - { - "name": "fraction_file", - "type": "tabular" - } - ], - "position": { - "left": 2378.0972762621154, - "top": 203.82359708661107 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "0e149f56-196c-43ba-a8e1-2b37555efeb7", - "when": null, - "workflow_outputs": [] - }, - "15": { - "annotation": "Generate summary statistics of SNV profiles per sample", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", - "errors": null, - "id": 15, - "input_connections": { - "database": { - "id": 2, - "output_name": "output" - }, - "input_names": { - "id": 13, - "output_name": "output" - }, - "input_snvs": { - "id": 12, - "output_name": "output" - } - }, - "inputs": [], - "label": null, - "name": "SameStr Stats", - "outputs": [ - { - "name": "stats_file", - "type": "tabular" - } - ], - "position": { - "left": 2453.862400870168, - "top": 593.6517663631948 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "3dfdf54a-5c95-4b6b-bb03-5b8a6f7603c8", - "when": null, - "workflow_outputs": [ - { - "label": "Stats file (MetaPhlAn)", - "output_name": "stats_file", - "uuid": "3e0b436a-485a-48eb-870c-c0928c1c54d8" - } - ] - }, - "16": { - "annotation": "Summarize strain sharing results across all sample pairs", - "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", - "errors": null, - "id": 16, - "input_connections": { - "database": { - "id": 2, - "output_name": "output" - }, - "overlaps": { - "id": 14, - "output_name": "overlap_file" - }, - "similarities": { - "id": 14, - "output_name": "fraction_file" - }, - "tax_profiles": { - "id": 3, - "output_name": "output_file" - } - }, - "inputs": [], - "label": null, - "name": "SameStr Summarize", - "outputs": [ - { - "name": "cooccurrences", - "type": "tabular" - }, - { - "name": "strain_events", - "type": "tabular" - }, - { - "name": "taxon_counts", - "type": "tabular" - } - ], - "position": { - "left": 2755.692519986277, - "top": 152.29339375080397 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", - "tool_shed_repository": { - "changeset_revision": "303e095c89c6", - "name": "samestr", - "owner": "iuc", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": \"5000\", \"aln_pair_min_similarity\": \"0.999\"}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", - "tool_uuid": null, - "tool_version": "1.2025.111+galaxy0", - "type": "tool", - "uuid": "c67ca84a-bd25-4161-9771-e8a4af61dda8", - "when": null, - "workflow_outputs": [ - { - "label": "Co-occurrences (MetaPhlAn)", - "output_name": "cooccurrences", - "uuid": "b9b9a2ea-45a5-4874-895d-8b334da3c289" - }, - { - "label": "Taxon counts (MetaPhlAn)", - "output_name": "taxon_counts", - "uuid": "376e6e79-0cc9-449b-bd6e-948da38a297c" - }, - { - "label": "Strain events (MetaPhlAn)", - "output_name": "strain_events", - "uuid": "c3833465-80a0-486f-b54f-0eda31728915" - } - ] - } - }, - "tags": [], - "uuid": "6687f903-e65d-4e41-b3ee-7f758979fa9a" + "left": 1420.251740166907, + "top": 374.7308038290005 }, "tool_id": null, - "type": "subworkflow", - "uuid": "976c1574-a7cd-4dd8-9d2d-6ea9821bc0ac", - "when": "$(inputs.when)", - "workflow_outputs": [ + "tool_state": "{\"default\": 0, \"validators\": [{\"min\": 0, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "9e36416a-fb90-4c1d-ae45-a0e1ba34a533", + "when": null, + "workflow_outputs": [] + }, + "10": { + "annotation": "Alignment Filtering: Minimum coverage depth required at a position for it to be considered covered (default: 3)", + "content_id": null, + "errors": null, + "id": 10, + "input_connections": {}, + "inputs": [ { - "label": "Stats file (MetaPhlAn)", - "output_name": "Stats file (MetaPhlAn)", - "uuid": "c4227302-b049-44e8-a05a-b648d884db44" - }, + "description": "Alignment Filtering: Minimum coverage depth required at a position for it to be considered covered (default: 3)", + "name": "Minimum vertical coverage" + } + ], + "label": "Minimum vertical coverage", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 1421.8468771356904, + "top": 464.57820691441964 + }, + "tool_id": null, + "tool_state": "{\"default\": 3, \"validators\": [{\"min\": null, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "8c9a04ba-9008-49b7-a241-b4c3f4a07d1b", + "when": null, + "workflow_outputs": [] + }, + "11": { + "annotation": "Clade and marker settings: Skip clades with fewer than this number of samples (default: 2)", + "content_id": null, + "errors": null, + "id": 11, + "input_connections": {}, + "inputs": [ + { + "description": "Clade and marker settings: Skip clades with fewer than this number of samples (default: 2)", + "name": "SameStr Filter: Minimum samples per clade" + } + ], + "label": "SameStr Filter: Minimum samples per clade", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 2101.7240312991016, + "top": 934.7096615706103 + }, + "tool_id": null, + "tool_state": "{\"default\": 2, \"validators\": [{\"min\": 0, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "b282c3db-e809-40c3-8151-88408716514c", + "when": null, + "workflow_outputs": [] + }, + "12": { + "annotation": "Clade and marker settings: Number of nucleotides to trim from each end of a marker sequence. (default: 50)", + "content_id": null, + "errors": null, + "id": 12, + "input_connections": {}, + "inputs": [ + { + "description": "Clade and marker settings: Number of nucleotides to trim from each end of a marker sequence. (default: 50)", + "name": "SameStr Filter: Marker truncation length" + } + ], + "label": "SameStr Filter: Marker truncation length", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 2101.136203363549, + "top": 1034.2339577054222 + }, + "tool_id": null, + "tool_state": "{\"default\": 50, \"validators\": [{\"min\": 0, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "6be8f7e7-8654-41ff-9f82-cda46c81ece5", + "when": null, + "workflow_outputs": [] + }, + "13": { + "annotation": "Sample Variant Filtering: Remove variants with nucleotide coverage below this threshold (default: 2)", + "content_id": null, + "errors": null, + "id": 13, + "input_connections": {}, + "inputs": [ + { + "description": "Sample Variant Filtering: Remove variants with nucleotide coverage below this threshold (default: 2)", + "name": "SameStr Filter: Nucleotides minimum variant coverage" + } + ], + "label": "SameStr Filter: Nucleotides minimum variant coverage", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 2101.5766761438904, + "top": 1141.550259482889 + }, + "tool_id": null, + "tool_state": "{\"default\": 2, \"validators\": [{\"min\": 0, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "c39ae696-2388-4955-85ba-051129f0979b", + "when": null, + "workflow_outputs": [] + }, + "14": { + "annotation": "Sample Variant Filtering: Remove variants with coverage below this fraction (default: 0.05)", + "content_id": null, + "errors": null, + "id": 14, + "input_connections": {}, + "inputs": [ + { + "description": "Sample Variant Filtering: Remove variants with coverage below this fraction (default: 0.05)", + "name": "SameStr Filter: Minimum variant coverage fraction" + } + ], + "label": "SameStr Filter: Minimum variant coverage fraction", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 2101.536212482662, + "top": 1250.7503814460079 + }, + "tool_id": null, + "tool_state": "{\"default\": 0.05, \"validators\": [{\"min\": 0.0, \"max\": 1.0, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"float\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "e8a74bf6-2167-437c-8fce-ffb868c1ed9f", + "when": null, + "workflow_outputs": [] + }, + "15": { + "annotation": "Sample Position Filtering: Remove positions with nucleotide coverage below this threshold (default: 1).", + "content_id": null, + "errors": null, + "id": 15, + "input_connections": {}, + "inputs": [ + { + "description": "Sample Position Filtering: Remove positions with nucleotide coverage below this threshold (default: 1).", + "name": "SameStr Filter: Minimum position coverage" + } + ], + "label": "SameStr Filter: Minimum position coverage", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 2100.568205480666, + "top": 1354.9615276886677 + }, + "tool_id": null, + "tool_state": "{\"default\": 1, \"validators\": [{\"min\": 0, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "e74a0082-bb23-470e-8015-97b279b9f4da", + "when": null, + "workflow_outputs": [] + }, + "16": { + "annotation": "Sample Position Filtering: Remove positions with coverage outside mean \u00b1 this standard deviation (default: 3.0).", + "content_id": null, + "errors": null, + "id": 16, + "input_connections": {}, + "inputs": [ + { + "description": "Sample Position Filtering: Remove positions with coverage outside mean \u00b1 this standard deviation (default: 3.0).", + "name": "SameStr Filter: Position coverage standard deviation cutoff" + } + ], + "label": "SameStr Filter: Position coverage standard deviation cutoff", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 2097.1611867284496, + "top": 1460.6660090245125 + }, + "tool_id": null, + "tool_state": "{\"default\": 3.0, \"validators\": [{\"min\": 0.0, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"float\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "6a4ec733-f6a4-4e84-bed8-e87b5b958108", + "when": null, + "workflow_outputs": [] + }, + "17": { + "annotation": "Sample Filtering: Remove samples with horizontal coverage below this nucleotide count (default: 5000).", + "content_id": null, + "errors": null, + "id": 17, + "input_connections": {}, + "inputs": [ + { + "description": "Sample Filtering: Remove samples with horizontal coverage below this nucleotide count (default: 5000).", + "name": "SameStr Filter: Minimum horizontal coverage" + } + ], + "label": "SameStr Filter: Minimum horizontal coverage", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 2094.8689633663025, + "top": 1558.1500715879326 + }, + "tool_id": null, + "tool_state": "{\"default\": 5000, \"validators\": [{\"min\": 0, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "b6444560-57f3-42f3-b9b7-a4e83aed9893", + "when": null, + "workflow_outputs": [] + }, + "18": { + "annotation": "Global Position Filtering: Remove positions covered by fewer than this number of samples (default: 2). Overrides fraction-based filtering.", + "content_id": null, + "errors": null, + "id": 18, + "input_connections": {}, + "inputs": [ + { + "description": "Global Position Filtering: Remove positions covered by fewer than this number of samples (default: 2). Overrides fraction-based filtering.", + "name": "SameStr Filter: Minimum sample coverage per position" + } + ], + "label": "SameStr Filter: Minimum sample coverage per position", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 2096.533892363287, + "top": 1669.6248754855912 + }, + "tool_id": null, + "tool_state": "{\"default\": 2, \"validators\": [{\"min\": null, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "fa4861b2-8d9b-4f0b-bbd6-77923534c0d2", + "when": null, + "workflow_outputs": [] + }, + "19": { + "annotation": "Minimum number of positions that must be covered in both samples to consider their similarity reliable. Higher values are more stringent. (default: 5000).", + "content_id": null, + "errors": null, + "id": 19, + "input_connections": {}, + "inputs": [ + { + "description": "Minimum number of positions that must be covered in both samples to consider their similarity reliable. Higher values are more stringent. (default: 5000).", + "name": "SameStr Summarize: Minimum overlap for comparison" + } + ], + "label": "SameStr Summarize: Minimum overlap for comparison", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 3400.857412481063, + "top": 742.4188097862362 + }, + "tool_id": null, + "tool_state": "{\"default\": 5000, \"validators\": [{\"min\": 0, \"max\": null, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"integer\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "e9030e60-78ce-436b-8d9a-2937765c0975", + "when": null, + "workflow_outputs": [] + }, + "20": { + "annotation": "Samples with similarity scores above this threshold are considered the same strain. Higher values are more strict. (default: 0.999).", + "content_id": null, + "errors": null, + "id": 20, + "input_connections": {}, + "inputs": [ + { + "description": "Samples with similarity scores above this threshold are considered the same strain. Higher values are more strict. (default: 0.999).", + "name": "SameStr Summarize: Minimum similarity for shared strains" + } + ], + "label": "SameStr Summarize: Minimum similarity for shared strains", + "name": "Input parameter", + "outputs": [], + "position": { + "left": 3400.971047985045, + "top": 849.8269782059348 + }, + "tool_id": null, + "tool_state": "{\"default\": 0.999, \"validators\": [{\"min\": 0.0, \"max\": 1.0, \"negate\": false, \"type\": \"in_range\"}], \"parameter_type\": \"float\", \"optional\": false}", + "tool_version": null, + "type": "parameter_input", + "uuid": "f51b0488-4062-46e1-b49b-acb1d1670a5a", + "when": null, + "workflow_outputs": [] + }, + "21": { + "annotation": "Quality trimming and host read removal. Boolean parameter 'Save all unmatched reads' must remain set to True. \n", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/kneaddata/kneaddata/0.12.1+galaxy1", + "errors": null, + "id": 21, + "input_connections": { + "alignment|alignment_tool|bowtie2_db": { + "id": 1, + "output_name": "output" + }, + "read_type|paired_collection": { + "id": 0, + "output_name": "output" + }, + "trimmomatic|trimmomatic_step|sequencer": { + "id": 3, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool KneadData", + "name": "read_type" + } + ], + "label": "Trimming and Host Removal", + "name": "KneadData", + "outputs": [ + { + "name": "paired_output", + "type": "input" + }, + { + "name": "unmatched_paired", + "type": "input" + }, + { + "name": "trimmed_paired", + "type": "input" + }, + { + "name": "unmatched_trimmed_paired", + "type": "input" + }, + { + "name": "log_file", + "type": "txt" + } + ], + "position": { + "left": 348.40905086852905, + "top": 387.02701114934655 + }, + "post_job_actions": { + "HideDatasetActiontrimmed_paired": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "trimmed_paired" + }, + "HideDatasetActionunmatched_trimmed_paired": { + "action_arguments": {}, + "action_type": "HideDatasetAction", + "output_name": "unmatched_trimmed_paired" + } + }, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/kneaddata/kneaddata/0.12.1+galaxy1", + "tool_shed_repository": { + "changeset_revision": "10f8abc1fbdf", + "name": "kneaddata", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"alignment\": {\"alignment_tool\": {\"tool_choice\": \"bowtie2\", \"__current_case__\": 0, \"bowtie2_db\": {\"__class__\": \"ConnectedValue\"}}, \"save_contaminants\": false}, \"fastqc\": {\"fastqc_report\": {\"select_fastqc\": \"no_fastqc\", \"__current_case__\": 1}, \"run_trim_repetitive\": false}, \"log_level\": \"INFO\", \"read_type\": {\"select_read_type\": \"paired\", \"__current_case__\": 1, \"save_unmatched\": true, \"paired_collection\": {\"__class__\": \"ConnectedValue\"}}, \"tandem\": {\"trf_step\": {\"trf_bool\": \"skip\", \"__current_case__\": 1}}, \"trimmomatic\": {\"trimmomatic_step\": {\"decide_trimmomatic\": \"run_trimmomatic\", \"__current_case__\": 0, \"sequencer\": {\"__class__\": \"ConnectedValue\"}}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.12.1+galaxy1", + "type": "tool", + "uuid": "9fe3494e-b20e-43fc-963c-818e81bc2d93", + "when": null, + "workflow_outputs": [] + }, + "22": { + "annotation": "Merge paired-end and orphaned reads from KneadData output", + "content_id": "__MERGE_COLLECTION__", + "errors": null, + "id": 22, + "input_connections": { + "inputs_0|input": { + "id": 21, + "output_name": "paired_output" + }, + "inputs_1|input": { + "id": 21, + "output_name": "unmatched_paired" + } + }, + "inputs": [], + "label": "Merge Collections", + "name": "Merge collections", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 613.7878702851508, + "top": 409.65006074396945 + }, + "post_job_actions": {}, + "tool_id": "__MERGE_COLLECTION__", + "tool_state": "{\"advanced\": {\"conflict\": {\"duplicate_options\": \"keep_first\", \"__current_case__\": 3}}, \"inputs\": [{\"__index__\": 0, \"input\": {\"__class__\": \"ConnectedValue\"}}, {\"__index__\": 1, \"input\": {\"__class__\": \"ConnectedValue\"}}], \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.0", + "type": "tool", + "uuid": "9d6634d3-7b42-4b27-86d7-51b712fe5da4", + "when": null, + "workflow_outputs": [] + }, + "23": { + "annotation": "Generate taxonomic profiles and marker gene alignments for SameStr", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/metaphlan/metaphlan/4.2.4+galaxy0", + "errors": null, + "id": 23, + "input_connections": { + "inputs|db|cached_db": { + "id": 4, + "output_name": "output" + }, + "inputs|in|raw_in|in": { + "id": 22, + "output_name": "output" + }, + "when": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool MetaPhlAn", + "name": "analysis" + } + ], + "label": null, + "name": "MetaPhlAn", + "outputs": [ + { + "name": "output_file", + "type": "tabular" + }, + { + "name": "mapout", + "type": "tabular" + }, + { + "name": "sam_output_file", + "type": "sam" + } + ], + "position": { + "left": 960.6441209683094, + "top": 475.98016953472796 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/metaphlan/metaphlan/4.2.4+galaxy0", + "tool_shed_repository": { + "changeset_revision": "56ff60ec416d", + "name": "metaphlan", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"analysis\": {\"analysis_type\": {\"t\": \"rel_ab\", \"__current_case__\": 0, \"tax_lev\": {\"tax_lev\": \"a\", \"__current_case__\": 0, \"split_levels\": false}}, \"min_alignment_len\": null, \"organism_profiling\": null, \"stat\": \"tavg_g\", \"stat_q\": \"0.2\", \"perc_nonzero\": \"0.33\", \"ignore_markers\": {\"__class__\": \"RuntimeValue\"}, \"avoid_disqm\": true}, \"inputs\": {\"in\": {\"selector\": \"raw\", \"__current_case__\": 0, \"raw_in\": {\"selector\": \"paired_collection\", \"__current_case__\": 2, \"in\": {\"__class__\": \"ConnectedValue\"}}, \"read_min_len\": \"70\", \"mapping\": {\"bt2_ps\": \"very-sensitive\", \"min_mapq_val\": \"5\"}}, \"db\": {\"db_selector\": \"cached\", \"__current_case__\": 0, \"cached_db\": {\"__class__\": \"ConnectedValue\"}, \"viral_analysis\": {\"profile_vsc\": \"\", \"__current_case__\": 1}}}, \"out\": {\"sample_id_key\": \"SampleID\", \"sample_id\": \"Metaphlan_Analysis\", \"use_group_representative\": false, \"CAMI_format_output\": false, \"skip_unclassified_estimation\": false, \"biom_format_output\": false, \"krona_output\": false}, \"subsample\": {\"selector\": \"no\", \"__current_case__\": 0}, \"test\": \"false\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "4.2.4+galaxy0", + "type": "tool", + "uuid": "d6238a32-2682-429c-af06-3ae34c0c6e52", + "when": "$(inputs.when)", + "workflow_outputs": [] + }, + "24": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", + "errors": null, + "id": 24, + "input_connections": { + "style_cond|type_cond|pick_from_0|value": { + "id": 23, + "output_name": "output_file" + } + }, + "inputs": [], + "label": null, + "name": "Pick parameter value", + "outputs": [ + { + "name": "data_param", + "type": "input" + } + ], + "position": { + "left": 1386.4080393714219, + "top": 671.0640639046684 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", + "tool_shed_repository": { + "changeset_revision": "b19e21af9c52", + "name": "pick_value", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"style_cond\": {\"pick_style\": \"first\", \"__current_case__\": 0, \"type_cond\": {\"param_type\": \"data\", \"__current_case__\": 4, \"pick_from\": [{\"__index__\": 0, \"value\": {\"__class__\": \"ConnectedValue\"}}]}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.2.0", + "type": "tool", + "uuid": "077318bf-6476-43d0-bbc0-9560950fbffb", + "when": null, + "workflow_outputs": [] + }, + "25": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", + "errors": null, + "id": 25, + "input_connections": { + "style_cond|type_cond|pick_from_0|value": { + "id": 23, + "output_name": "sam_output_file" + } + }, + "inputs": [], + "label": null, + "name": "Pick parameter value", + "outputs": [ + { + "name": "data_param", + "type": "input" + } + ], + "position": { + "left": 1376.7759745774144, + "top": 797.8706817417145 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/pick_value/pick_value/0.2.0", + "tool_shed_repository": { + "changeset_revision": "b19e21af9c52", + "name": "pick_value", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"style_cond\": {\"pick_style\": \"first\", \"__current_case__\": 0, \"type_cond\": {\"param_type\": \"data\", \"__current_case__\": 4, \"pick_from\": [{\"__index__\": 0, \"value\": {\"__class__\": \"ConnectedValue\"}}]}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "0.2.0", + "type": "tool", + "uuid": "d0ea0951-7d33-434f-999d-ed8e54186c1a", + "when": null, + "workflow_outputs": [] + }, + "26": { + "annotation": "Convert SAM to BAM format", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samtools_view/samtools_view/1.22+galaxy2", + "errors": null, + "id": 26, + "input_connections": { + "input": { + "id": 25, + "output_name": "data_param" + } + }, + "inputs": [], + "label": null, + "name": "Samtools view", + "outputs": [ + { + "name": "outputsam", + "type": "input" + } + ], + "position": { + "left": 1660.5467458734454, + "top": 910.4293983209503 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samtools_view/samtools_view/1.22+galaxy2", + "tool_shed_repository": { + "changeset_revision": "5cf9fcc93508", + "name": "samtools_view", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"addref_cond\": {\"addref_select\": \"no\", \"__current_case__\": 0}, \"input\": {\"__class__\": \"ConnectedValue\"}, \"mode\": {\"outtype\": \"all_reads\", \"__current_case__\": 0, \"output_options\": {\"reads_report_type\": \"retained\", \"__current_case__\": 0, \"adv_output\": {\"readtags\": [], \"collapsecigar\": false}, \"output_format\": {\"oformat\": \"bam\", \"__current_case__\": 2}}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.22+galaxy2", + "type": "tool", + "uuid": "6558e684-0681-46e6-9b8c-009056062e27", + "when": null, + "workflow_outputs": [] + }, + "27": { + "annotation": "Convert BAM to SNV profiles for SameStr analysis", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", + "errors": null, + "id": 27, + "input_connections": { + "alignment": { + "id": 26, + "output_name": "outputsam" + }, + "alignment_param|min_aln_identity": { + "id": 6, + "output_name": "output" + }, + "alignment_param|min_aln_len": { + "id": 7, + "output_name": "output" + }, + "alignment_param|min_aln_qual": { + "id": 9, + "output_name": "output" + }, + "alignment_param|min_base_qual": { + "id": 8, + "output_name": "output" + }, + "alignment_param|min_vcov": { + "id": 10, + "output_name": "output" + }, + "database": { + "id": 5, + "output_name": "output" + }, + "profile": { + "id": 24, + "output_name": "data_param" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool SameStr Convert", + "name": "alignment_param" + }, + { + "description": "runtime parameter for tool SameStr Convert", + "name": "alignment_param" + }, + { + "description": "runtime parameter for tool SameStr Convert", + "name": "alignment_param" + }, + { + "description": "runtime parameter for tool SameStr Convert", + "name": "alignment_param" + }, + { + "description": "runtime parameter for tool SameStr Convert", + "name": "alignment_param" + } + ], + "label": null, + "name": "SameStr Convert", + "outputs": [ + { + "name": "npz_files", + "type": "input" + }, + { + "name": "stats_file", + "type": "tabular" + } + ], + "position": { + "left": 1700.0545954341565, + "top": 361.5827321424908 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_convert/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"alignment\": {\"__class__\": \"ConnectedValue\"}, \"alignment_param\": {\"min_aln_identity\": {\"__class__\": \"ConnectedValue\"}, \"min_aln_len\": {\"__class__\": \"ConnectedValue\"}, \"min_base_qual\": {\"__class__\": \"ConnectedValue\"}, \"min_aln_qual\": {\"__class__\": \"ConnectedValue\"}, \"min_vcov\": {\"__class__\": \"ConnectedValue\"}}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"profile\": {\"__class__\": \"ConnectedValue\"}, \"sample_name\": null, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "6c6eb3a2-3334-4d74-831c-95389ced99c5", + "when": null, + "workflow_outputs": [] + }, + "28": { + "annotation": "Flatten collection to allow cross-sample SNV profile comparison. Note: this modifies element identifiers by adding an underscore, which makes naming afterwards unstable for SameStr", + "content_id": "__FLATTEN__", + "errors": null, + "id": 28, + "input_connections": { + "input": { + "id": 27, + "output_name": "npz_files" + } + }, + "inputs": [], + "label": null, + "name": "Flatten collection", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 1865.6452355710771, + "top": 752.2782175982525 + }, + "post_job_actions": {}, + "tool_id": "__FLATTEN__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"join_identifier\": \"_\", \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.0.0", + "type": "tool", + "uuid": "ef7779f0-2c31-48ac-b88b-e2bed04b24fa", + "when": null, + "workflow_outputs": [] + }, + "29": { + "annotation": "Apply rules", + "content_id": "__APPLY_RULES__", + "errors": null, + "id": 29, + "input_connections": { + "input": { + "id": 28, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Apply rules", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2117.6438540968743, + "top": 758.0833639842949 + }, + "post_job_actions": {}, + "tool_id": "__APPLY_RULES__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"rules\": {\"mapping\": [{\"columns\": [1], \"type\": \"list_identifiers\"}], \"rules\": [{\"error\": null, \"type\": \"add_column_metadata\", \"value\": \"identifier0\", \"warn\": null}, {\"allow_unmatched\": false, \"error\": null, \"expression\": \"^[^_]+_(.*)$\", \"group_count\": null, \"replacement\": \"\\\\1\", \"target_column\": 0, \"type\": \"add_column_regex\", \"warn\": null}]}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "1171cd8a-b48f-42c9-bd21-338b048b7838", + "when": null, + "workflow_outputs": [] + }, + "30": { + "annotation": "Merge SNV profiles from multiple samples for cross-sample strain comparison", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", + "errors": null, + "id": 30, + "input_connections": { + "database": { + "id": 5, + "output_name": "output" + }, + "input_files": { + "id": 29, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Merge", + "outputs": [ + { + "name": "npz_files", + "type": "input" + }, + { + "name": "sample_name", + "type": "input" + } + ], + "position": { + "left": 2027.5045374912547, + "top": 388.7737881729979 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_merge/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"clade\": null, \"database\": {\"__class__\": \"ConnectedValue\"}, \"input_files\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "28436645-e153-4724-a8fb-2f19a91385ef", + "when": null, + "workflow_outputs": [] + }, + "31": { + "annotation": "Filter SNV profiles to retain high confidence variants for strain analysis", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", + "errors": null, + "id": 31, + "input_connections": { + "clade_settings|clade_min_samples": { + "id": 11, + "output_name": "output" + }, + "clade_settings|marker_trunc_len": { + "id": 12, + "output_name": "output" + }, + "database": { + "id": 5, + "output_name": "output" + }, + "global_position_filtering|global_pos_min_n_vcov": { + "id": 18, + "output_name": "output" + }, + "input_names": { + "id": 30, + "output_name": "sample_name" + }, + "input_snvs": { + "id": 30, + "output_name": "npz_files" + }, + "sample_filtering|samples_min_n_hcov": { + "id": 17, + "output_name": "output" + }, + "sample_position_filtering|sample_pos_min_n_vcov": { + "id": 15, + "output_name": "output" + }, + "sample_position_filtering|sample_pos_min_sd_vcov": { + "id": 16, + "output_name": "output" + }, + "sample_variant_filtering|sample_var_min_f_vcov": { + "id": 14, + "output_name": "output" + }, + "sample_variant_filtering|sample_var_min_n_vcov": { + "id": 13, + "output_name": "output" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool SameStr Filter", + "name": "clade_settings" + }, + { + "description": "runtime parameter for tool SameStr Filter", + "name": "clade_settings" + }, + { + "description": "runtime parameter for tool SameStr Filter", + "name": "global_position_filtering" + }, + { + "description": "runtime parameter for tool SameStr Filter", + "name": "sample_filtering" + }, + { + "description": "runtime parameter for tool SameStr Filter", + "name": "sample_filtering" + }, + { + "description": "runtime parameter for tool SameStr Filter", + "name": "sample_position_filtering" + }, + { + "description": "runtime parameter for tool SameStr Filter", + "name": "sample_position_filtering" + }, + { + "description": "runtime parameter for tool SameStr Filter", + "name": "sample_variant_filtering" + }, + { + "description": "runtime parameter for tool SameStr Filter", + "name": "sample_variant_filtering" + } + ], + "label": null, + "name": "SameStr Filter", + "outputs": [ + { + "name": "filtered_profile", + "type": "npz" + }, + { + "name": "sample_names", + "type": "tabular" + } + ], + "position": { + "left": 2431.63047499224, + "top": 363.3577918435363 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_filter/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"clade_settings\": {\"clade_min_samples\": {\"__class__\": \"ConnectedValue\"}, \"marker_selection\": {\"retain_or_drop\": \"\", \"__current_case__\": 0}, \"marker_trunc_len\": {\"__class__\": \"ConnectedValue\"}}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"global_position_filtering\": {\"global_pos_min_n_vcov\": {\"__class__\": \"ConnectedValue\"}, \"global_pos_min_f_vcov\": \"0.0\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"output_settings\": {\"keep_poly\": false, \"keep_mono\": false, \"delete_pos\": false}, \"sample_filtering\": {\"samples_select\": {\"__class__\": \"RuntimeValue\"}, \"samples_min_n_hcov\": {\"__class__\": \"ConnectedValue\"}, \"samples_min_f_hcov\": \"0.0\", \"samples_min_m_vcov\": \"0.0\"}, \"sample_position_filtering\": {\"sample_pos_min_n_vcov\": {\"__class__\": \"ConnectedValue\"}, \"sample_pos_min_sd_vcov\": {\"__class__\": \"ConnectedValue\"}}, \"sample_variant_filtering\": {\"sample_var_min_n_vcov\": {\"__class__\": \"ConnectedValue\"}, \"sample_var_min_f_vcov\": {\"__class__\": \"ConnectedValue\"}}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "b7496f15-b103-4bee-af77-6bf64704b1d0", + "when": null, + "workflow_outputs": [] + }, + "32": { + "annotation": "empty datasets with insufficient coverage or no SNVs detected", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 32, + "input_connections": { + "input": { + "id": 31, + "output_name": "filtered_profile" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2779.2610016371927, + "top": 378.54180130525464 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "bd809949-d68f-4a19-a66f-2cf75a446425", + "when": null, + "workflow_outputs": [] + }, + "33": { + "annotation": "empty datasets with insufficient coverage or no SNVs detected", + "content_id": "__FILTER_EMPTY_DATASETS__", + "errors": null, + "id": 33, + "input_connections": { + "input": { + "id": 31, + "output_name": "sample_names" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool Filter empty datasets", + "name": "replacement" + } + ], + "label": null, + "name": "Filter empty datasets", + "outputs": [ + { + "name": "output", + "type": "input" + } + ], + "position": { + "left": 2781.4707907181896, + "top": 578.5154965849554 + }, + "post_job_actions": {}, + "tool_id": "__FILTER_EMPTY_DATASETS__", + "tool_state": "{\"input\": {\"__class__\": \"ConnectedValue\"}, \"replacement\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.1.0", + "type": "tool", + "uuid": "4ba5aea1-0e93-4d6f-ac58-5d7a8b0baab8", + "when": null, + "workflow_outputs": [] + }, + "34": { + "annotation": "Generate summary statistics of SNV profiles per sample", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", + "errors": null, + "id": 34, + "input_connections": { + "database": { + "id": 5, + "output_name": "output" + }, + "input_names": { + "id": 33, + "output_name": "output" + }, + "input_snvs": { + "id": 32, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Stats", + "outputs": [ + { + "name": "stats_file", + "type": "tabular" + } + ], + "position": { + "left": 3093.5459375849655, + "top": 771.7928415136683 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_stats/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"dominant_variants\": false, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "c540753e-1676-458e-81eb-a870fa252b5b", + "when": null, + "workflow_outputs": [ + { + "label": "stats file", + "output_name": "stats_file", + "uuid": "677751a2-4e20-482e-a6d3-331c193c424f" + } + ] + }, + "35": { + "annotation": "Compare SNV profiles across samples to identify shared strains", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", + "errors": null, + "id": 35, + "input_connections": { + "database": { + "id": 5, + "output_name": "output" + }, + "input_names": { + "id": 33, + "output_name": "output" + }, + "input_snvs": { + "id": 32, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "SameStr Compare", + "outputs": [ + { + "name": "overlap_file", + "type": "tabular" + }, + { + "name": "close_file", + "type": "tabular" + }, + { + "name": "fraction_file", + "type": "tabular" + } + ], + "position": { + "left": 3183.9285837002303, + "top": 355.3042161418655 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_compare/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"database\": {\"__class__\": \"ConnectedValue\"}, \"input_names\": {\"__class__\": \"ConnectedValue\"}, \"input_snvs\": {\"__class__\": \"ConnectedValue\"}, \"variant_comparison_settings\": {\"minority_dominant\": \"\", \"dominant_variants_msa\": false}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "aa5695b6-ec87-4a3c-865a-c0f4e7e2d813", + "when": null, + "workflow_outputs": [] + }, + "36": { + "annotation": "Summarize strain sharing results across all sample pairs", + "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", + "errors": null, + "id": 36, + "input_connections": { + "arguments|aln_pair_min_overlap": { + "id": 19, + "output_name": "output" + }, + "arguments|aln_pair_min_similarity": { + "id": 20, + "output_name": "output" + }, + "database": { + "id": 5, + "output_name": "output" + }, + "overlaps": { + "id": 35, + "output_name": "overlap_file" + }, + "similarities": { + "id": 35, + "output_name": "fraction_file" + }, + "tax_profiles": { + "id": 23, + "output_name": "output_file" + } + }, + "inputs": [ + { + "description": "runtime parameter for tool SameStr Summarize", + "name": "arguments" + }, + { + "description": "runtime parameter for tool SameStr Summarize", + "name": "arguments" + } + ], + "label": null, + "name": "SameStr Summarize", + "outputs": [ + { + "name": "cooccurrences", + "type": "tabular" + }, + { + "name": "strain_events", + "type": "tabular" + }, + { + "name": "taxon_counts", + "type": "tabular" + } + ], + "position": { + "left": 3659.090890352673, + "top": 399.3186070278562 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/samestr/samestr_summarize/1.2025.111+galaxy0", + "tool_shed_repository": { + "changeset_revision": "303e095c89c6", + "name": "samestr", + "owner": "iuc", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"arguments\": {\"aln_pair_min_overlap\": {\"__class__\": \"ConnectedValue\"}, \"aln_pair_min_similarity\": {\"__class__\": \"ConnectedValue\"}}, \"database\": {\"__class__\": \"ConnectedValue\"}, \"overlaps\": {\"__class__\": \"ConnectedValue\"}, \"similarities\": {\"__class__\": \"ConnectedValue\"}, \"tax_profiles\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": 0, \"__rerun_remap_job_id__\": null}", + "tool_uuid": null, + "tool_version": "1.2025.111+galaxy0", + "type": "tool", + "uuid": "78947654-d993-42c5-86b9-e078df265523", + "when": null, + "workflow_outputs": [ { - "label": "Taxon counts (MetaPhlAn)", - "output_name": "Taxon counts (MetaPhlAn)", - "uuid": "8cd1a75a-a3d5-41de-9d2a-5d29853d057e" + "label": "cooccurrences", + "output_name": "cooccurrences", + "uuid": "c85d67a8-ade1-4330-8339-224e6b70541c" }, { - "label": "Co-occurrences (MetaPhlAn)", - "output_name": "Co-occurrences (MetaPhlAn)", - "uuid": "0a233933-71dc-497b-a4f7-f41b091e5ec8" + "label": "strain events", + "output_name": "strain_events", + "uuid": "1ce03cd6-d170-49c1-a3f9-2700ea61fc63" }, { - "label": "Strain events (MetaPhlAn)", - "output_name": "Strain events (MetaPhlAn)", - "uuid": "85ab6172-3eb6-4a49-bef3-c81bf4c0c278" + "label": "taxon counts", + "output_name": "taxon_counts", + "uuid": "e6a7aa1e-8eb6-410a-ae2d-f4a69883d891" } ] } @@ -1294,6 +1615,6 @@ "microbiome", "shared-strains" ], - "uuid": "7498be57-b555-411c-ac2c-080c74705344", - "version": 106 -} + "uuid": "cd0fb833-7f5e-4e2c-9355-5dd3e50ab427", + "version": 127 +} \ No newline at end of file