From e37f8221defd6056a67c810c602ee5bacdb2ca3d Mon Sep 17 00:00:00 2001 From: Curtis Kapsak Date: Wed, 17 Jan 2024 09:05:05 -0500 Subject: [PATCH] theiacov_fasta wf logic change for flu (#305) * theiacov_fasta wf logic change. only run abricate if user sets organism to "flu" AND flu_subtype is not set or unknown * allow for empty string to be passed into organism_parameters subwf for flu_subtype input string * instead of empty string, pass "N/A" for when flu_subtype is unknown or undefined by user * force theiacov_fasta CI to skip pangolin due to errors with really long pathnames when scorpio is running * update the CI correctly this time. booleans are special * update hashes for pangolin command and output CSV (expected changes) --- tests/inputs/theiacov/wf_theiacov_fasta.json | 3 ++- tests/workflows/theiacov/test_wf_theiacov_fasta.yml | 4 ++-- workflows/theiacov/wf_theiacov_fasta.wdl | 5 +++-- 3 files changed, 7 insertions(+), 5 deletions(-) diff --git a/tests/inputs/theiacov/wf_theiacov_fasta.json b/tests/inputs/theiacov/wf_theiacov_fasta.json index 586e25b68..881c6cd84 100644 --- a/tests/inputs/theiacov/wf_theiacov_fasta.json +++ b/tests/inputs/theiacov/wf_theiacov_fasta.json @@ -3,5 +3,6 @@ "theiacov_fasta.assembly_fasta": "tests/data/theiacov/fasta/clearlabs.fasta.gz", "theiacov_fasta.seq_method": "clearlabs", "theiacov_fasta.input_assembly_method": "clearlabs", - "theiacov_fasta.reference_genome": "tests/inputs/completely-empty-for-test.txt" + "theiacov_fasta.reference_genome": "tests/inputs/completely-empty-for-test.txt", + "theiacov_fasta.pangolin4.skip_scorpio": true } diff --git a/tests/workflows/theiacov/test_wf_theiacov_fasta.yml b/tests/workflows/theiacov/test_wf_theiacov_fasta.yml index 5eef42a15..337e4ab79 100644 --- a/tests/workflows/theiacov/test_wf_theiacov_fasta.yml +++ b/tests/workflows/theiacov/test_wf_theiacov_fasta.yml @@ -122,7 +122,7 @@ - path: miniwdl_run/call-nextclade_output_parser/work/input.tsv md5sum: 9b459df2831ab1974c9c8cef5bc5340e - path: miniwdl_run/call-pangolin4/command - md5sum: 85d3001929bde4169a11947fb38fb693 + md5sum: 558f8f3b23b7562e7dca67dc0a647522 - path: miniwdl_run/call-pangolin4/inputs.json - path: miniwdl_run/call-pangolin4/outputs.json - path: miniwdl_run/call-pangolin4/stderr.txt @@ -144,7 +144,7 @@ md5sum: 9f9c4c00a1ceb5526bed7dc4cdb3dcfd - path: miniwdl_run/call-pangolin4/work/_miniwdl_inputs/0/clearlabs.fasta.gz - path: miniwdl_run/call-pangolin4/work/fasta.pangolin_report.csv - md5sum: 81679363ffed582650f8512794035806 + md5sum: c8ddc2706b30b5bfcaf32636ed5a63ec - path: miniwdl_run/call-vadr/command md5sum: f4ad614b7ad39f28a8145cec280a93c0 - path: miniwdl_run/call-vadr/inputs.json diff --git a/workflows/theiacov/wf_theiacov_fasta.wdl b/workflows/theiacov/wf_theiacov_fasta.wdl index a232ab0b4..cba3e8269 100644 --- a/workflows/theiacov/wf_theiacov_fasta.wdl +++ b/workflows/theiacov/wf_theiacov_fasta.wdl @@ -37,7 +37,8 @@ workflow theiacov_fasta { Int? maxlen String? vadr_opts } - if (!defined(flu_subtype)) { + # only run abricate if user sets organism = "flu" AND if flu_subtype is unknown/not set by user + if (!defined(flu_subtype) && organism == "flu") { call abricate.abricate_flu { input: assembly = assembly_fasta, @@ -49,7 +50,7 @@ workflow theiacov_fasta { input: organism = organism, flu_segment = flu_segment, - flu_subtype = select_first([flu_subtype, abricate_subtype]), + flu_subtype = select_first([flu_subtype, abricate_subtype, "N/A"]), reference_genome = reference_genome, genome_length = genome_length, nextclade_ds_reference = nextclade_dataset_reference,