From e7d917ee29fb472e5b93c176de739dc41c597640 Mon Sep 17 00:00:00 2001 From: "Gervaise H. Henry" <gervaise.henry@utsouthwestern.edu> Date: Sun, 3 Jan 2021 22:43:45 -0600 Subject: [PATCH] Update changelog --- CHANGELOG.md | 7 +++++++ workflow/rna-seq.nf | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 6b3749c..6ce68e8 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -8,6 +8,11 @@ * Upload mRNA QC * Create and upload output bag * Add optional to not upload +* Update references to use bags +* Update to newer references (GRCh38.p13.v36 and GRCm38.p6.vM25) +* Use production server for data-hub reference call +* Stop pipeline if submitted does not match infered +* Update execution run with "Success" or "Error" **Background** * Remove (comment out) option to pull references from S3 @@ -17,10 +22,12 @@ * Changed order of steps so that fastqc is done after the trim step * Change docker images to production * Add automated version badges +* Only calculate/report tin values on regular chromosomes (from gtf) *Known Bugs* * Datahub reference pull uses dev.gudmap.org as source until referencencs are placed on production * Override params (inputBag, fastq, species) aren't checked for integrity +* <hr> diff --git a/workflow/rna-seq.nf b/workflow/rna-seq.nf index 5c548b2..567c720 100644 --- a/workflow/rna-seq.nf +++ b/workflow/rna-seq.nf @@ -1248,7 +1248,7 @@ process dedupData { samtools index -@ `nproc` -b ${repRID}_sorted.deduped.bam ${repRID}_sorted.deduped.bam.bai # split the deduped BAM file for multi-threaded tin calculation - for i in `samtools view ${repRID}_sorted.deduped.bam | cut -f3 | sort | uniq`; + for i in `samtools view ${repRID}_sorted.deduped.bam | grep -o chr.* | cut -f3 | sort | uniq`; do echo "echo \"LOG: splitting each chromosome into its own BAM and BAI files with Samtools\"; samtools view -b ${repRID}_sorted.deduped.bam \${i} 1>> ${repRID}_sorted.deduped.\${i}.bam; samtools index -@ `nproc` -b ${repRID}_sorted.deduped.\${i}.bam ${repRID}_sorted.deduped.\${i}.bam.bai" done | parallel -j `nproc` -k -- GitLab