From 4226f0ca641cfd0a1d6854716f7ef91237133c14 Mon Sep 17 00:00:00 2001 From: Jover Lee Date: Thu, 11 Apr 2024 15:43:23 -0700 Subject: [PATCH] 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}