From 56cb48fd4d38754c51cf9b40d2fc5afcd281afe3 Mon Sep 17 00:00:00 2001 From: John Huddleston Date: Mon, 28 Oct 2024 11:02:58 -0700 Subject: [PATCH 1/2] Force include 6B.1A.4 strain for H1 HA trees Adds a 6B.1A.4 strain to list of strains to be force included in the Nextclade datasets for H1 HA trees. --- nextclade/dataset_config/h1n1pdm/includes.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/nextclade/dataset_config/h1n1pdm/includes.txt b/nextclade/dataset_config/h1n1pdm/includes.txt index 42047c0..4f7d96b 100644 --- a/nextclade/dataset_config/h1n1pdm/includes.txt +++ b/nextclade/dataset_config/h1n1pdm/includes.txt @@ -59,3 +59,4 @@ A/Helsinki/2430/2012 A/Gansu-Ganzhou/SWL34/2012 A/Brisbane/96/2012 A/Minnesota/23/2014 +A/Nagano/2649/2018 From 9d9b97c514d3f4e1c918848851c5039fe7aa55f8 Mon Sep 17 00:00:00 2001 From: John Huddleston Date: Mon, 28 Oct 2024 11:14:56 -0700 Subject: [PATCH 2/2] Rename proposed subclade field Renames proposed subclade field to refer to subclades instead of clades and avoid potential confusion between the older "clade" names and the newer "subclade" names. Uses the underscore delimiter to remain consistent with other annotations in flu builds like `num_date`, `ne_star`, `submitting_lab`, etc.). --- nextclade/config/auspice_config.json | 2 +- nextclade/config/config_dict.yaml | 24 ++++++++++++------------ nextclade/scripts/merge_jsons.py | 6 ++---- 3 files changed, 15 insertions(+), 17 deletions(-) diff --git a/nextclade/config/auspice_config.json b/nextclade/config/auspice_config.json index 8d0e215..28d1af3 100644 --- a/nextclade/config/auspice_config.json +++ b/nextclade/config/auspice_config.json @@ -25,7 +25,7 @@ "type": "categorical" }, { - "key": "proposed_clade", + "key": "proposed_subclade", "title": "Subclade proposals", "type": "categorical" }, diff --git a/nextclade/config/config_dict.yaml b/nextclade/config/config_dict.yaml index d0a8e0c..ccf9451 100644 --- a/nextclade/config/config_dict.yaml +++ b/nextclade/config/config_dict.yaml @@ -14,9 +14,9 @@ builds: subclade: url: "seasonal_A-H1N1pdm_HA/main/.auto-generated/subclades.tsv" key: "subclade" - proposed_clade: + proposed_subclade: url: "seasonal_A-H1N1pdm_HA/main/.auto-generated/subclade_proposals.tsv" - key: "proposed_clade" + key: "proposed_subclade" refs: CY121680: # exclude South Korean genomes because of sequencing artifacts close to the start of HA filter: "--min-date 2009 --probabilistic-sampling --exclude-where country='south_korea' qc.overallStatus='bad' --group-by year --min-length 1500 --subsample-max-sequences 1500" @@ -35,9 +35,9 @@ builds: clade_systems: clade: url: "seasonal_A-H1N1pdm_NA/main/.auto-generated/subclades.tsv" - proposed_clade: + proposed_subclade: url: "seasonal_A-H1N1pdm_NA/main/.auto-generated/subclade_proposals.tsv" - key: "proposed_clade" + key: "proposed_subclade" refs: MW626056: filter: "--min-date 2019 --probabilistic-sampling --group-by year region --min-length 1400 --subsample-max-sequences 2000" @@ -57,9 +57,9 @@ builds: short-clade: url: "seasonal_A-H3N2_HA/main/.auto-generated/clades.tsv" key: "short-clade" - proposed_clade: + proposed_subclade: url: "seasonal_A-H3N2_HA/main/.auto-generated/subclade_proposals.tsv" - key: "proposed_clade" + key: "proposed_subclade" refs: EPI1857216: filter: "--min-date 2019 --probabilistic-sampling --group-by year region --min-length 1500 --subsample-max-sequences 2000" @@ -78,9 +78,9 @@ builds: clade_systems: clade: url: "seasonal_A-H3N2_NA/main/.auto-generated/subclades.tsv" - proposed_clade: + proposed_subclade: url: "seasonal_A-H3N2_NA/main/.auto-generated/subclade_proposals.tsv" - key: "proposed_clade" + key: "proposed_subclade" refs: EPI1857215: filter: "--min-date 2019 --probabilistic-sampling --group-by year region --min-length 1400 --subsample-max-sequences 1500" @@ -97,9 +97,9 @@ builds: subclade: url: "seasonal_B-Vic_HA/main/.auto-generated/subclades.tsv" key: "subclade" - proposed_clade: + proposed_subclade: url: "seasonal_B-Vic_HA/main/.auto-generated/subclade_proposals.tsv" - key: "proposed_clade" + key: "proposed_subclade" refs: KX058884: filter: "--min-date 2014 --probabilistic-sampling --group-by year --min-length 1500 --subsample-max-sequences 2000" @@ -112,9 +112,9 @@ builds: clade_systems: clade: url: "seasonal_B-Vic_NA/main/.auto-generated/subclades.tsv" - proposed_clade: + proposed_subclade: url: "seasonal_B-Vic_NA/main/.auto-generated/subclade_proposals.tsv" - key: "proposed_clade" + key: "proposed_subclade" refs: CY073894: filter: "--min-date 2014 --probabilistic-sampling --group-by year region --min-length 1400 --subsample-max-sequences 2000" diff --git a/nextclade/scripts/merge_jsons.py b/nextclade/scripts/merge_jsons.py index cf8da62..d1bf586 100644 --- a/nextclade/scripts/merge_jsons.py +++ b/nextclade/scripts/merge_jsons.py @@ -18,13 +18,12 @@ def get_clade_configs(name): "displayName": "Subclade", "description": "Experimental fine-grained subclade annotation." }, - "proposed_clade": { + "proposed_subclade": { "name": "Subclade proposal", "displayName": "Subclade proposal", "description": "Includes proposals of new subclades. These can change anytime.", "hideInWeb": True - } - }.get(name, {'name':name, "displayName":name, "description":""}) + }}.get(name, {'name':name, "displayName":name, "description":""}) if __name__=="__main__": @@ -73,4 +72,3 @@ def get_clade_configs(name): with open(args.output_auspice, 'w') as fh: json.dump(auspice_json, fh, indent=2) -