Add batch processing to InterProScan

main.nf

@@ -59,6 +59,7 @@ workflow NFCORE_PROTEINANNOTATOR {
         params.skip_interproscan,
         params.interproscan_db_url,
         params.interproscan_db,
+        params.interproscan_batch_size,
         params.skip_s4pred
     )
     emit:

nextflow.config

@@ -39,6 +39,7 @@ params {
     interproscan_db            = null
     interproscan_applications  = 'Hamap,PANTHER,PIRSF,TIGRFAM,sfld'
     interproscan_enableprecalc = false
+    interproscan_batch_size    = 1000
 
     // Secondary structure prediction (s4pred)
     skip_s4pred   = false

nextflow_schema.json

@@ -346,6 +346,14 @@
                     "help_text": "This increases the speed of functional annotation with InterProScan by pre-calculating matches found in the UniProtKB, thereby identifying unique matches in the query sequences for faster annotation. By default this is turned off.\n\nFor more information about this flag see the tool [documentation](https://interproscan-docs.readthedocs.io/en/latest/HowToRun.html).\n\n> Modifies tool parameter(s):\n> - InterProScan: `--disable-precalc`",
                     "description": "Pre-calculates residue mutual matches.",
                     "fa_icon": "fas fa-clock"
+                },
+                "interproscan_batch_size": {
+                    "type": "integer",
+                    "default": 1000,
+                    "minimum": 1,
+                    "description": "Number of sequences per InterProScan batch.",
+                    "help_text": "Split input FASTA files into batches of this many sequences before running InterProScan. This enables parallel processing of large proteomes and reduces memory usage per job. Results are automatically concatenated after all batches complete. Default: 1000 sequences per batch.",
+                    "fa_icon": "fas fa-layer-group"
                 }
             },
             "help_text": "This subworkflow adds additional protein annotations to all input sequences. Currently, only annotation with InterProScan is integrated in the subworkflow.",

ro-crate-metadata.json

@@ -22,8 +22,8 @@
             "@id": "./",
             "@type": "Dataset",
             "creativeWorkStatus": "InProgress",
-            "datePublished": "2026-07-24T12:36:11+00:00",
-            "description": "<h1>\n  <picture>\n    <source media=\"(prefers-color-scheme: dark)\" srcset=\"docs/images/nf-core-proteinannotator_logo_dark.png\">\n    <img alt=\"nf-core/proteinannotator\" src=\"docs/images/nf-core-proteinannotator_logo_light.png\">\n  </picture>\n</h1>\n\n[![Open in GitHub Codespaces](https://img.shields.io/badge/Open_In_GitHub_Codespaces-black?labelColor=grey&logo=github)](https://github.com/codespaces/new/nf-core/proteinannotator)\n[![GitHub Actions CI Status](https://github.com/nf-core/proteinannotator/actions/workflows/nf-test.yml/badge.svg)](https://github.com/nf-core/proteinannotator/actions/workflows/nf-test.yml)\n[![GitHub Actions Linting Status](https://github.com/nf-core/proteinannotator/actions/workflows/linting.yml/badge.svg)](https://github.com/nf-core/proteinannotator/actions/workflows/linting.yml)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/proteinannotator/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX)\n[![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)\n\n[![Nextflow](https://img.shields.io/badge/version-%E2%89%A525.10.4-green?style=flat&logo=nextflow&logoColor=white&color=%230DC09D&link=https%3A%2F%2Fnextflow.io)](https://www.nextflow.io/)\n[![nf-core template version](https://img.shields.io/badge/nf--core_template-4.0.3-green?style=flat&logo=nfcore&logoColor=white&color=%2324B064&link=https%3A%2F%2Fnf-co.re)](https://github.com/nf-core/tools/releases/tag/4.0.3)\n[![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)\n[![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/)\n[![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)\n[![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://cloud.seqera.io/launch?pipeline=https://github.com/nf-core/proteinannotator)\n\n[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23proteinannotator-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/proteinannotator)[![Follow on Bluesky](https://img.shields.io/badge/bluesky-%40nf__core-1185fe?labelColor=000000&logo=bluesky)](https://bsky.app/profile/nf-co.re)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core)\n\n## Introduction\n\n**nf-core/proteinannotator** is a bioinformatics pipeline that ...\n\n<!-- TODO nf-core:\n   Complete this sentence with a 2-3 sentence summary of what types of data the pipeline ingests, a brief overview of the\n   major pipeline sections and the types of output it produces. You're giving an overview to someone new\n   to nf-core here, in 15-20 seconds. For an example, see https://github.com/nf-core/rnaseq/blob/master/README.md#introduction\n-->\n\n<!-- TODO nf-core: Include a figure that guides the user through the major workflow steps. Many nf-core\n     workflows use the \"tube map\" design for that. See https://nf-co.re/docs/community/brand/workflow-schematics#examples for examples.   -->\n<!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->2. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))\n\n## Usage\n\n> [!NOTE]\n> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/get_started/environment_setup/overview) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/get_started/run-your-first-pipeline) with `-profile test` before running the workflow on actual data.\n\n<!-- TODO nf-core: Describe the minimum required steps to execute the pipeline, e.g. how to prepare samplesheets.\n     Explain what rows and columns represent. For instance (please edit as appropriate):\n\nFirst, prepare a samplesheet with your input data that looks as follows:\n\n`samplesheet.csv`:\n\n```csv\nsample,fastq_1,fastq_2\nCONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz\n```\n\nEach row represents a fastq file (single-end) or a pair of fastq files (paired end).\n\n-->\n\nNow, you can run the pipeline using:\n\n<!-- TODO nf-core: update the following command to include all required parameters for a minimal example -->\n\n```bash\nnextflow run nf-core/proteinannotator \\\n   -profile <docker/singularity/.../institute> \\\n   --input samplesheet.csv \\\n   --outdir <OUTDIR>\n```\n\n> [!WARNING]\n> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; see [docs](https://nf-co.re/docs/running/run-pipelines#using-parameter-files).\n\nFor more details and further functionality, please refer to the [usage documentation](https://nf-co.re/proteinannotator/usage) and the [parameter documentation](https://nf-co.re/proteinannotator/parameters).\n\n## Pipeline output\n\nTo see the results of an example test run with a full size dataset refer to the [results](https://nf-co.re/proteinannotator/results) tab on the nf-core website pipeline page.\nFor more details about the output files and reports, please refer to the\n[output documentation](https://nf-co.re/proteinannotator/output).\n\n## Credits\n\nnf-core/proteinannotator was originally written by Olga Botvinnik, Evangelos Karatzas.\n\nWe thank the following people for their extensive assistance in the development of this pipeline:\n\n<!-- TODO nf-core: If applicable, make list of people who have also contributed -->\n\n## Contributions and Support\n\nIf you would like to contribute to this pipeline, please see the [contributing guidelines](docs/CONTRIBUTING.md).\n\nFor further information or help, don't hesitate to get in touch on the [Slack `#proteinannotator` channel](https://nfcore.slack.com/channels/proteinannotator) (you can join with [this invite](https://nf-co.re/join/slack)).\n\n## Citations\n\n<!-- TODO nf-core: Add citation for pipeline after first release. Uncomment lines below and update Zenodo doi and badge at the top of this file. -->\n<!-- If you use nf-core/proteinannotator for your analysis, please cite it using the following doi: [10.5281/zenodo.XXXXXX](https://doi.org/10.5281/zenodo.XXXXXX) -->\n\n<!-- TODO nf-core: Add bibliography of tools and data used in your pipeline -->\n\nAn extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.\n\nYou can cite the `nf-core` publication as follows:\n\n> **The nf-core framework for community-curated bioinformatics pipelines.**\n>\n> Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen.\n>\n> _Nat Biotechnol._ 2020 Feb 13. doi: [10.1038/s41587-020-0439-x](https://dx.doi.org/10.1038/s41587-020-0439-x).\n",
+            "datePublished": "2026-02-09T13:54:13+00:00",
+            "description": "<h1>\n  <picture>\n    <source media=\"(prefers-color-scheme: dark)\" srcset=\"docs/images/nf-core-proteinannotator_logo_dark.png\">\n    <img alt=\"nf-core/proteinannotator\" src=\"docs/images/nf-core-proteinannotator_logo_light.png\">\n  </picture>\n</h1>\n\n[![Open in GitHub Codespaces](https://img.shields.io/badge/Open_In_GitHub_Codespaces-black?labelColor=grey&logo=github)](https://github.com/codespaces/new/nf-core/proteinannotator)\n[![GitHub Actions CI Status](https://github.com/nf-core/proteinannotator/actions/workflows/nf-test.yml/badge.svg)](https://github.com/nf-core/proteinannotator/actions/workflows/nf-test.yml)\n[![GitHub Actions Linting Status](https://github.com/nf-core/proteinannotator/actions/workflows/linting.yml/badge.svg)](https://github.com/nf-core/proteinannotator/actions/workflows/linting.yml)[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/proteinannotator/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.18547735-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.18547735)\n[![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)\n\n[![Nextflow](https://img.shields.io/badge/version-%E2%89%A525.10.0-green?style=flat&logo=nextflow&logoColor=white&color=%230DC09D&link=https%3A%2F%2Fnextflow.io)](https://www.nextflow.io/)\n[![nf-core template version](https://img.shields.io/badge/nf--core_template-3.5.1-green?style=flat&logo=nfcore&logoColor=white&color=%2324B064&link=https%3A%2F%2Fnf-co.re)](https://github.com/nf-core/tools/releases/tag/3.5.1)\n[![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)\n[![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/)\n[![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)\n[![Launch on Seqera Platform](https://img.shields.io/badge/Launch%20%F0%9F%9A%80-Seqera%20Platform-%234256e7)](https://cloud.seqera.io/launch?pipeline=https://github.com/nf-core/proteinannotator)\n\n[![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23proteinannotator-4A154B?labelColor=000000&logo=slack)](https://nfcore.slack.com/channels/proteinannotator)[![Follow on Bluesky](https://img.shields.io/badge/bluesky-%40nf__core-1185fe?labelColor=000000&logo=bluesky)](https://bsky.app/profile/nf-co.re)[![Follow on Mastodon](https://img.shields.io/badge/mastodon-nf__core-6364ff?labelColor=FFFFFF&logo=mastodon)](https://mstdn.science/@nf_core)[![Watch on YouTube](http://img.shields.io/badge/youtube-nf--core-FF0000?labelColor=000000&logo=youtube)](https://www.youtube.com/c/nf-core)\n\n## Introduction\n\n**nf-core/proteinannotator** is a bioinformatics pipeline that computes statistics for protein FASTA inputs and produces protein annotations based on predicted sequence features, including conserved domains, functions, and secondary structure.\n\n<p>\n  <picture>\n    <source media=\"(prefers-color-scheme: dark)\" srcset=\"docs/images/proteinannotator_metromap_dark.png\">\n    <img alt=\"nf-core/proteinannotator\" src=\"docs/images/proteinannotator_metromap_light.png\">\n  </picture>\n</p>\n\n### Check quality and pre-process\n\nGenerate input amino acid sequence statistics with ([`SeqFu`](https://github.com/telatin/seqfu2/)) and pre-process them (i.e., gap removal, convert to upper case, validate, filter by length, replace special characters such as `/`, and remove duplicate sequences) with ([`SeqKit`](https://github.com/shenwei356/seqkit/))\n\n### Annotate sequences\n\n1. Conserved domain annotation with ([`hmmer`](https://github.com/EddyRivasLab/hmmer/)) against databases\n   such as [Pfam](https://ftp.ebi.ac.uk/pub/databases/Pfam/) and [FunFam](https://download.cathdb.info/cath/releases/all-releases/)\n2. Functional annotation:\n   - ([`InterProScan`](https://interproscan-docs.readthedocs.io/en/v5/)) a software tool used to analyze protein sequences by scanning them against the signatures of protein families, domains, and sites in the [InterPro](https://www.ebi.ac.uk/interpro/) database, helping to identify their functional characteristics.\n3. Predict secondary structure compositional features such as \u03b1-helices, \u03b2-strands and coils with ([`s4pred`](https://github.com/psipred/s4pred))\n4. Present QC stats for input sequences before and after initial pre-processing with ([`MultiQC`](http://multiqc.info/))\n\n## Usage\n\n> [!NOTE]\n> If you are new to Nextflow and nf-core, please refer to [this page](https://nf-co.re/docs/usage/installation) on how to set-up Nextflow. Make sure to [test your setup](https://nf-co.re/docs/usage/introduction#how-to-run-a-pipeline) with `-profile test` before running the workflow on actual data.\n\nFirst, prepare a samplesheet with your input data that looks as follows:\n\n`samplesheet.csv`:\n\n```csv\nid,fasta\nspecies1,species1_proteins.fasta\nspecies2,species2_proteins.fasta\n```\n\nEach row represents a FASTA file of proteins from a single species.\n\nNow, you can run the pipeline using:\n\n```bash\nnextflow run nf-core/proteinannotator \\\n   -profile <docker/singularity/.../institute> \\\n   --input samplesheet.csv \\\n   --outdir <OUTDIR>\n```\n\n> [!WARNING]\n> Please provide pipeline parameters via the CLI or Nextflow `-params-file` option. Custom config files including those provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; see [docs](https://nf-co.re/docs/usage/getting_started/configuration#custom-configuration-files).\n\nFor more details and further functionality, please refer to the [usage documentation](https://nf-co.re/proteinannotator/usage) and the [parameter documentation](https://nf-co.re/proteinannotator/parameters).\n\n## Pipeline output\n\nTo see the results of an example test run with a full size dataset refer to the [results](https://nf-co.re/proteinannotator/results) tab on the nf-core website pipeline page.\nFor more details about the output files and reports, please refer to the\n[output documentation](https://nf-co.re/proteinannotator/output).\n\n## Credits\n\nnf-core/proteinannotator was originally written by Olga Botvinnik and Evangelos Karatzas.\n\nWe thank the following people for their extensive assistance in the development of this pipeline:\n\n- [Michael L Heuer](https://github.com/heuermh)\n- [Edmund Miller](https://github.com/edmundmiller)\n- [Eric Wei](https://github.com/eweizy)\n- [Martin Beracochea](https://github.com/mberacochea)\n\n## Contributions and Support\n\nIf you would like to contribute to this pipeline, please see the [contributing guidelines](.github/CONTRIBUTING.md).\n\nFor further information or help, don't hesitate to get in touch on the [Slack `#proteinannotator` channel](https://nfcore.slack.com/channels/proteinannotator) (you can join with [this invite](https://nf-co.re/join/slack)).\n\n## Citations\n\nIf you use nf-core/proteinannotator for your analysis, please cite it using the following doi: [10.5281/zenodo.18547735](https://doi.org/10.5281/zenodo.18547735)\n\nAn extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.\n\nYou can cite the `nf-core` publication as follows:\n\n> **The nf-core framework for community-curated bioinformatics pipelines.**\n>\n> Philip Ewels, Alexander Peltzer, Sven Fillinger, Harshil Patel, Johannes Alneberg, Andreas Wilm, Maxime Ulysse Garcia, Paolo Di Tommaso & Sven Nahnsen.\n>\n> _Nat Biotechnol._ 2020 Feb 13. doi: [10.1038/s41587-020-0439-x](https://dx.doi.org/10.1038/s41587-020-0439-x).\n",
             "hasPart": [
                 {
                     "@id": "main.nf"

subworkflows/local/functional_annotation/main.nf

@@ -4,10 +4,11 @@ include { INTERPROSCAN } from '../../../modules/nf-core/interproscan/main'
 
 workflow FUNCTIONAL_ANNOTATION {
     take:
-    ch_fasta            // channel: [ val(meta), [ fasta ] ]
-    skip_interproscan   // boolean
-    interproscan_db_url // string, url to download db
-    interproscan_db     // string, existing db
+    ch_fasta                // channel: [ val(meta), [ fasta ] ]
+    skip_interproscan       // boolean
+    interproscan_db_url     // string, url to download db
+    interproscan_db         // string, existing db
+    interproscan_batch_size // integer, number of sequences per batch
 
     main:
     ch_interproscan_tsv = channel.empty()
@@ -23,8 +24,24 @@ workflow FUNCTIONAL_ANNOTATION {
             ch_interproscan_db = UNTAR.out.untar.map{ f -> f[1] }
         }
 
-        INTERPROSCAN( ch_fasta, ch_interproscan_db )
-        ch_interproscan_tsv = ch_interproscan_tsv.mix(INTERPROSCAN.out.tsv)
+        // Split FASTA into batches for parallel InterProScan processing
+        ch_fasta_batched = ch_fasta
+            .flatMap { meta, fasta ->
+                def chunks = fasta.splitFasta(by: interproscan_batch_size, file: true)
+                if (chunks instanceof Path) {
+                    // Single chunk (fewer sequences than batch size)
+                    return [[ meta, chunks ]]
+                }
+                chunks.withIndex().collect { chunk, idx ->
+                    def new_meta = meta.clone()
+                    new_meta.original_id = meta.id
+                    new_meta.id = "${meta.id}_batch${idx}"
+                    [ new_meta, chunk ]
+                }
+            }
+
+        INTERPROSCAN( ch_fasta_batched, ch_interproscan_db )
+        ch_interproscan_tsv = INTERPROSCAN.out.tsv
     }
 
     emit:

subworkflows/local/functional_annotation/tests/main.nf.test

@@ -21,6 +21,7 @@ nextflow_workflow {
                 input[1] = false
                 input[2] = params.pipelines_testdata_base_path + '/testdata/interproscan/interproscan_test.tar.gz'
                 input[3] = []
+                input[4] = 1000
                 """
             }
         }
@@ -49,6 +50,7 @@ nextflow_workflow {
                 input[1] = true
                 input[2] = []
                 input[3] = []
+                input[4] = 1000
                 """
             }
         }