From fee626de4cdef6fa469a0dc294093e4d4e3af51c Mon Sep 17 00:00:00 2001 From: EC2 Default User Date: Wed, 22 Jan 2025 19:08:13 +0000 Subject: [PATCH 1/2] In cases where the READID has 'YT' in it, this code will fail since it indexes the first element. To fix this, we can grep for all columns with 'YT:Z:' which should only capture the column that we're interested in. --- modules/local/extractUnconcReadIDs/main.nf | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modules/local/extractUnconcReadIDs/main.nf b/modules/local/extractUnconcReadIDs/main.nf index 0b826228..93e1604f 100644 --- a/modules/local/extractUnconcReadIDs/main.nf +++ b/modules/local/extractUnconcReadIDs/main.nf @@ -22,7 +22,7 @@ process EXTRACT_UNCONC_READ_IDS { continue id = line_split[0] try: - status_field = [f for f in line_split if "YT" in f][0] + status_field = [f for f in line_split if "YT:Z:" in f][0] status = re.findall("YT:Z:(.*)", status_field)[0] except: print(line_split) From 127eefdf1b9220a33939c4bb1bf574122b47344e Mon Sep 17 00:00:00 2001 From: Harmon Bhasin Date: Wed, 22 Jan 2025 14:12:25 -0500 Subject: [PATCH 2/2] Update CHANGELOG.md Adding changelog --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 74336d58..8b85ee27 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -9,6 +9,7 @@ - Added Fastp adapter trimming after running BBDuk in the EXTRACT_VIRAL_READS subworkflow. - Implement masking of viral genome reference in index workflow with MASK_GENOME_FASTA to remove adapter, low-entropy and repeat sequences. - Remove TRIMMOMATIC and BBMAP from the pipeline. +- Fixed bug in extractUnconcReadID that would cause the pipeline to fail if it contained the string 'YT' in the read id. # v2.6.0.0 - Updated version to reflect the new versioning scheme, which is described in `docs/version_schema.md`.