From 3fb3e9e6d13bc9a7f2ecef567a674fdafd4166b7 Mon Sep 17 00:00:00 2001 From: Kim Andrews <17375001+kimandrews@users.noreply.github.com> Date: Wed, 7 Feb 2024 17:05:58 -0800 Subject: [PATCH] Remove nextclade from Snakefile Remove nextclade-related if-else statements from Snakefile. This also requires editing final rule in curate.smk to output results/metadata.tsv instead of results/subset_metadata.tsv --- ingest/Snakefile | 25 ------------------------- ingest/rules/curate.smk | 2 +- 2 files changed, 1 insertion(+), 26 deletions(-) diff --git a/ingest/Snakefile b/ingest/Snakefile index 65e8fca..41c316f 100644 --- a/ingest/Snakefile +++ b/ingest/Snakefile @@ -28,31 +28,6 @@ include: "rules/fetch_from_ncbi.smk" include: "rules/curate.smk" -# We are pushing to standardize ingest workflows with Nextclade runs to include -# Nextclade outputs in our publicly hosted data. However, if a Nextclade dataset -# does not already exist, it requires curated data as input, so we are making -# Nextclade steps optional here. -# -# If Nextclade config values are included, the nextclade rules will create the -# final metadata TSV by joining the Nextclade output with the metadata. -# If Nextclade configs are not included, we rename the subset metadata TSV -# to the final metadata TSV. -if "nextclade" in config: - - include: "rules/nextclade.smk" - -else: - - rule create_final_metadata: - input: - metadata="results/subset_metadata.tsv" - output: - metadata="results/metadata.tsv" - shell: - """ - mv {input.metadata} {output.metadata} - """ - # Allow users to import custom rules provided via the config. # This allows users to run custom rules that can extend or override the workflow. # A concrete example of using custom rules is the extension of the workflow with diff --git a/ingest/rules/curate.smk b/ingest/rules/curate.smk index 9b0e37e..42b9b56 100644 --- a/ingest/rules/curate.smk +++ b/ingest/rules/curate.smk @@ -120,7 +120,7 @@ rule subset_metadata: input: metadata="results/all_metadata.tsv", output: - subset_metadata="results/subset_metadata.tsv", + subset_metadata="results/metadata.tsv", params: metadata_fields=",".join(config["curate"]["metadata_columns"]), shell: