From e638db2050f431c4776245a21357fc5e4bfb27f1 Mon Sep 17 00:00:00 2001 From: Jennifer Chang Date: Wed, 6 Dec 2023 14:15:56 -0500 Subject: [PATCH] Set final targets Set final targets to be the pair of metadata_denvX.tsv and sequences_denvX.fasta files. --- ingest/Snakefile | 3 ++- ingest/config/optional.yaml | 12 ++++++++++-- ingest/workflow/snakemake_rules/nextclade.smk | 3 +++ 3 files changed, 15 insertions(+), 3 deletions(-) diff --git a/ingest/Snakefile b/ingest/Snakefile index 0ed057b4..b1cedb71 100644 --- a/ingest/Snakefile +++ b/ingest/Snakefile @@ -11,10 +11,11 @@ if not config: send_slack_notifications = config.get("send_slack_notifications", False) +serotypes = ['all', 'denv1', 'denv2', 'denv3', 'denv4'] def _get_all_targets(wildcards): # Default targets are the metadata TSV and sequences FASTA files - all_targets = ["results/sequences.fasta", "results/metadata.tsv"] + all_targets = expand(["results/sequences_{serotype}.fasta", "results/metadata_{serotype}.tsv"], serotype=serotypes) # Add additional targets based on upload config upload_config = config.get("upload", {}) diff --git a/ingest/config/optional.yaml b/ingest/config/optional.yaml index 727206ef..a23e26fc 100644 --- a/ingest/config/optional.yaml +++ b/ingest/config/optional.yaml @@ -10,8 +10,16 @@ upload: files_to_upload: genbank.ndjson.xz: data/genbank.ndjson all_sequences.ndjson.xz: data/sequences.ndjson - metadata.tsv.gz: results/metadata.tsv - sequences.fasta.xz: results/sequences.fasta + metadata_all.tsv.zst: results/metadata_all.tsv + sequences_all.fasta.zst: results/sequences_all.fasta + metadata_denv1.tsv.zst: results/metadata_denv1.tsv + sequences_denv1.fasta.zst: results/sequences_denv1.fasta + metadata_denv2.tsv.zst: results/metadata_denv2.tsv + sequences_denv2.fasta.zst: results/sequences_denv2.fasta + metadata_denv3.tsv.zst: results/metadata_denv3.tsv + sequences_denv3.fasta.zst: results/sequences_denv3.fasta + metadata_denv4.tsv.zst: results/metadata_denv4.tsv + sequences_denv4.fasta.zst: results/sequences_denv4.fasta alignment.fasta.xz: data/alignment.fasta insertions.csv.gz: data/insertions.csv translations.zip: data/translations.zip diff --git a/ingest/workflow/snakemake_rules/nextclade.smk b/ingest/workflow/snakemake_rules/nextclade.smk index b9657f1d..f8d92c91 100644 --- a/ingest/workflow/snakemake_rules/nextclade.smk +++ b/ingest/workflow/snakemake_rules/nextclade.smk @@ -29,12 +29,15 @@ rule split_dengue_sequences: metadata="results/metadata.tsv", nextclade_all_results="results/nextclade_results/nextclade_all.tsv", output: + sequences_all="results/sequences_all.fasta", sequences_denv1="results/sequences_denv1.fasta", sequences_denv2="results/sequences_denv2.fasta", sequences_denv3="results/sequences_denv3.fasta", sequences_denv4="results/sequences_denv4.fasta", shell: """ + cp {input.sequences} {output.sequences_all} + augur filter \ --sequences {input.sequences} \ --metadata {input.nextclade_all_results} \