From 4226f0ca641cfd0a1d6854716f7ef91237133c14 Mon Sep 17 00:00:00 2001 From: Jover Lee Date: Thu, 11 Apr 2024 15:43:23 -0700 Subject: [PATCH 1/3] phylogenetic: Use latest ingest data I missed this in review of https://github.com/nextstrain/dengue/pull/38. The phylogenetic workflow was still pulling from old S3 URLs and not the ingest workflow output data. This commit corrects the S3 URL to the ingest output files and updates the `strain_id_field` config param to use the appropriate ID column from the ingest output. --- phylogenetic/config/config_dengue.yaml | 2 +- phylogenetic/rules/prepare_sequences.smk | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/phylogenetic/config/config_dengue.yaml b/phylogenetic/config/config_dengue.yaml index 3824415b..d6f3f6d8 100644 --- a/phylogenetic/config/config_dengue.yaml +++ b/phylogenetic/config/config_dengue.yaml @@ -1,4 +1,4 @@ -strain_id_field: "accession" +strain_id_field: "genbank_accession" display_strain_field: "strain" filter: diff --git a/phylogenetic/rules/prepare_sequences.smk b/phylogenetic/rules/prepare_sequences.smk index 9c163a61..5cb14c75 100644 --- a/phylogenetic/rules/prepare_sequences.smk +++ b/phylogenetic/rules/prepare_sequences.smk @@ -21,8 +21,8 @@ rule download: metadata = "data/metadata_{serotype}.tsv.zst" params: - sequences_url = "https://data.nextstrain.org/files/dengue/sequences_{serotype}.fasta.zst", - metadata_url = "https://data.nextstrain.org/files/dengue/metadata_{serotype}.tsv.zst" + sequences_url = "https://data.nextstrain.org/files/workflows/dengue/sequences_{serotype}.fasta.zst", + metadata_url = "https://data.nextstrain.org/files/workflows/dengue/metadata_{serotype}.tsv.zst" shell: """ curl -fsSL --compressed {params.sequences_url:q} --output {output.sequences} From c6a0f3a0cd8698a9f82ab1faa6e5ef6e270e5dc9 Mon Sep 17 00:00:00 2001 From: Jover Lee Date: Thu, 11 Apr 2024 16:28:23 -0700 Subject: [PATCH 2/3] phylogenetic: Update example data Match the ingest outputs to use `genbnak_accession` column. --- phylogenetic/example_data/metadata_all.tsv | 2 +- phylogenetic/example_data/metadata_denv1.tsv | 2 +- phylogenetic/example_data/metadata_denv2.tsv | 2 +- phylogenetic/example_data/metadata_denv3.tsv | 2 +- phylogenetic/example_data/metadata_denv4.tsv | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) diff --git a/phylogenetic/example_data/metadata_all.tsv b/phylogenetic/example_data/metadata_all.tsv index ba8c0c35..01a411da 100644 --- a/phylogenetic/example_data/metadata_all.tsv +++ b/phylogenetic/example_data/metadata_all.tsv @@ -1,4 +1,4 @@ -strain virus accession date region country division city db segment authors url title journal paper_url +strain virus genbank_accession date region country division city db segment authors url title journal paper_url DENV1/VIETNAM/BIDV1862/2008 dengue FJ410220 2008-XX-XX Southeast Asia Vietnam Vietnam Vietnam ? genome Alvarado et al. ? ? ? ? DENV3/WALLIS_AND_FUTUNA/1404838/1989 dengue JQ920487 1989-08-14 ? Wallis And Futuna French Overseas Collectivity Wallis And Futuna ? genome Aubry et al. ? ? ? ? DENV/BRAZIL/SJRP778/2013 dengue KT438585 2013-02-04 South America Brazil Brazil Brazil ? genome Araujo et al. ? ? ? ? diff --git a/phylogenetic/example_data/metadata_denv1.tsv b/phylogenetic/example_data/metadata_denv1.tsv index b697eb54..0574a0c7 100644 --- a/phylogenetic/example_data/metadata_denv1.tsv +++ b/phylogenetic/example_data/metadata_denv1.tsv @@ -1,4 +1,4 @@ -strain virus accession date region country division city db segment authors url title journal paper_url +strain virus genbank_accession date region country division city db segment authors url title journal paper_url DENV1/INDIA/237/1962 dengue JF297572 1962-XX-XX South Asia India India India ? genome Cecilia et al. ? ? ? ? DENV1/CHINA/RL6/2013 dengue KJ470727 2013-09-XX China China China China ? genome Guo et al. ? ? ? ? DENV1/THAILAND/AILANDKPPKDV08491NC04528V0L/2007 dengue JQ993108 2007-XX-XX Southeast Asia Thailand Thailand Thailand ? genome Aldstadt et al. ? ? ? ? diff --git a/phylogenetic/example_data/metadata_denv2.tsv b/phylogenetic/example_data/metadata_denv2.tsv index 31f88305..5c694c00 100644 --- a/phylogenetic/example_data/metadata_denv2.tsv +++ b/phylogenetic/example_data/metadata_denv2.tsv @@ -1,4 +1,4 @@ -strain virus accession date region country division city db segment authors url title journal paper_url +strain virus genbank_accession date region country division city db segment authors url title journal paper_url DENV2/INDONESIA/MKS0084/2007 dengue KC762660 2007-11-21 Southeast Asia Indonesia Makassar Makassar ? genome Bifani et al. ? ? ? ? DENV2/TAIWAN/71/2002 dengue EF016253 2002-XX-XX China Taiwan Taiwan Taiwan ? genome Ke et al. ? ? ? ? DENV2/PAKISTAN/8D/2011 dengue JX042512 2011-XX-XX West Asia Pakistan Pakistan Pakistan ? genome Alvi et al. ? ? ? ? diff --git a/phylogenetic/example_data/metadata_denv3.tsv b/phylogenetic/example_data/metadata_denv3.tsv index 911e8cef..18c5b0aa 100644 --- a/phylogenetic/example_data/metadata_denv3.tsv +++ b/phylogenetic/example_data/metadata_denv3.tsv @@ -1,4 +1,4 @@ -strain virus accession date region country division city db segment authors url title journal paper_url +strain virus genbank_accession date region country division city db segment authors url title journal paper_url DENV3/PUERTO_RICO/BIDV1615/2004 dengue FJ373302 2004-XX-XX North America Puerto Rico Puerto Rico Puerto Rico ? genome Alvarado et al. ? ? ? ? DENV3/THAILAND/BIDV2323/2001 dengue FJ744734 2001-XX-XX Southeast Asia Thailand Kamphaeng Phet Kamphaeng Phet ? genome Alvarado et al. ? ? ? ? DENV3/BANGLADESH/JACOB/NA dengue AY656673 ? South Asia Bangladesh Bangladesh Bangladesh ? genome Aaskov et al. ? ? ? ? diff --git a/phylogenetic/example_data/metadata_denv4.tsv b/phylogenetic/example_data/metadata_denv4.tsv index d3175b21..9d9ce386 100644 --- a/phylogenetic/example_data/metadata_denv4.tsv +++ b/phylogenetic/example_data/metadata_denv4.tsv @@ -1,4 +1,4 @@ -strain virus accession date region country division city db segment authors url title journal paper_url +strain virus genbank_accession date region country division city db segment authors url title journal paper_url DENV4/ECUADOR/FSE2098/2006 dengue GQ139572 2006-XX-XX South America Ecuador Ecuador Ecuador ? genome Alava et al. ? ? ? ? DENV4/BRAZIL/SJRP580/2012 dengue KP188562 2012-12-10 South America Brazil Brazil Brazil ? genome Araujo et al. ? ? ? ? DENV4/BRAZIL/GUSP0670/2013 dengue KP704043 2013-03-17 South America Brazil Brazil Brazil ? genome Balarini et al. ? ? ? ? From 9b9d1b2dc210a670a2b1588a830286ac3c9ea8b5 Mon Sep 17 00:00:00 2001 From: Jover Lee Date: Fri, 12 Apr 2024 10:37:43 -0700 Subject: [PATCH 3/3] phylogenetic: Update Auspice configs to include `genbank_accession` Include the `genbank_accession` as a separate field in the exported metadata so that it can be searched in the Auspice filter input and so Auspice automatically generates a URL for the GenBank accession. --- phylogenetic/config/auspice_config_all.json | 5 ++++- phylogenetic/config/auspice_config_denv1.json | 3 +++ phylogenetic/config/auspice_config_denv2.json | 3 +++ phylogenetic/config/auspice_config_denv3.json | 3 +++ phylogenetic/config/auspice_config_denv4.json | 3 +++ 5 files changed, 16 insertions(+), 1 deletion(-) diff --git a/phylogenetic/config/auspice_config_all.json b/phylogenetic/config/auspice_config_all.json index fa5fd966..d55a202f 100644 --- a/phylogenetic/config/auspice_config_all.json +++ b/phylogenetic/config/auspice_config_all.json @@ -3,7 +3,7 @@ "maintainers": [ {"name": "Trevor Bedford", "url": "http://bedford.io/team/trevor-bedford/"} ], - "build_url": "https://github.com/nextstrain/dengue", + "build_url": "https://github.com/nextstrain/dengue", "colorings": [ { "key": "gt", @@ -44,5 +44,8 @@ "country", "region", "author" + ], + "metadata_columns": [ + "genbank_accession" ] } diff --git a/phylogenetic/config/auspice_config_denv1.json b/phylogenetic/config/auspice_config_denv1.json index 19182bca..ae608416 100644 --- a/phylogenetic/config/auspice_config_denv1.json +++ b/phylogenetic/config/auspice_config_denv1.json @@ -43,5 +43,8 @@ "country", "region", "author" + ], + "metadata_columns": [ + "genbank_accession" ] } diff --git a/phylogenetic/config/auspice_config_denv2.json b/phylogenetic/config/auspice_config_denv2.json index a50dced9..6244d130 100644 --- a/phylogenetic/config/auspice_config_denv2.json +++ b/phylogenetic/config/auspice_config_denv2.json @@ -43,5 +43,8 @@ "country", "region", "author" + ], + "metadata_columns": [ + "genbank_accession" ] } diff --git a/phylogenetic/config/auspice_config_denv3.json b/phylogenetic/config/auspice_config_denv3.json index 42849eec..27d648ee 100644 --- a/phylogenetic/config/auspice_config_denv3.json +++ b/phylogenetic/config/auspice_config_denv3.json @@ -43,5 +43,8 @@ "country", "region", "author" + ], + "metadata_columns": [ + "genbank_accession" ] } diff --git a/phylogenetic/config/auspice_config_denv4.json b/phylogenetic/config/auspice_config_denv4.json index ee89e5e8..be3a933d 100644 --- a/phylogenetic/config/auspice_config_denv4.json +++ b/phylogenetic/config/auspice_config_denv4.json @@ -43,5 +43,8 @@ "country", "region", "author" + ], + "metadata_columns": [ + "genbank_accession" ] }