Changed quantification in Stringtie

Changed Stringtie module to use native quantification from Stringtie instead of subread featureCounts
IGDRion · Nov 20, 2024 · d8f2fcb · d8f2fcb
1 parent c5f0724
commit d8f2fcb
Show file tree

Hide file tree

Showing 3 changed files with 16 additions and 12 deletions.
diff --git a/bin/qc.R b/bin/qc.R
@@ -409,8 +409,10 @@ sub_cover <- textGrob(sub_cover_text,
 grid.arrange(cover, sub_cover)
 
 # Command line
+formatted_command <- gsub("(^|\\s)(-{1,2}\\w+)", "\n\\1\\2", command)
+
 grid.arrange(textGrob(
-  paste(command)
+  paste(formatted_command)
 ))
 
 # Gene

diff --git a/modules/stringtie/stringtie_quant.nf b/modules/stringtie/stringtie_quant.nf
@@ -11,16 +11,22 @@ process STRINGTIE_QUANTIFY {
   path merged_gtf
 
   output:
-  path 'stringtie_quant.gtf', emit: stringtie_quant_qtf
+  path "${bam.simpleName}.counts_transcript.txt", emit: counts_transcript
+  path "${bam.simpleName}.counts_gene.txt", emit: counts_gene
 
   script:
   """
   stringtie \
     -L \
     -eB \
-    -p ${params.maxCpu} \
     -G ${merged_gtf} \
     -o stringtie_quant.gtf \
+    -A gene_abundance.tab \
+    -p ${params.maxCpu} \
     ${bam}
+
+    # Extract tx and gene counts
+    awk -v bam="${bam.simpleName}" 'BEGIN {OFS="\t"; print "transcript_id", "gene_id", bam}  NR>1 {print \$6, \$9, \$11}' t_data.ctab > ${bam.simpleName}.counts_transcript.txt
+    awk -v bam="${bam.simpleName}" 'BEGIN {OFS="\t"; print "gene_id", bam}  NR>1 {print \$1, \$7}' gene_abundance.tab > ${bam.simpleName}.counts_gene.txt
   """
 }
diff --git a/modules/stringtie/stringtie_workflow.nf b/modules/stringtie/stringtie_workflow.nf
@@ -21,10 +21,6 @@ workflow STRINGTIE {
         STRINGTIE_ASSEMBLE.out.stringtie_assemble_gtf.collect(), 
         input_gtf)
 
-    STRINGTIE_QUANTIFY(
-        samples, 
-        STRINGTIE_MERGE.out.stringtie_merged_gtf)
-
     GFFCOMPARE(
         input_gtf, 
         ref_fa, 
@@ -34,13 +30,13 @@ workflow STRINGTIE {
         STRINGTIE_MERGE.out.stringtie_merged_gtf,
         GFFCOMPARE.out.tracking_file)
 
-    SUBREAD_FEATURECOUNTS(
-        samples, 
-        FORMAT_GFFCOMPARE.out.stringtie_gtf)
+    STRINGTIE_QUANTIFY(
+    samples, 
+    STRINGTIE_MERGE.out.stringtie_merged_gtf)
 
     MERGE_COUNTS(
-        SUBREAD_FEATURECOUNTS.out.gene_counts.collect(), 
-        SUBREAD_FEATURECOUNTS.out.tx_counts.collect())
+        STRINGTIE_QUANTIFY.out.counts_gene.collect(), 
+        STRINGTIE_QUANTIFY.out.counts_transcript.collect())
 
     emit:
     stringtie_gtf = FORMAT_GFFCOMPARE.out.stringtie_gtf