Merge branch 'CW-3516' into 'dev'

Remove need to retry based on GTF/GFF

Closes CW-3516

See merge request epi2melabs/workflows/wf-transcriptomes!162

CHANGELOG.md

@@ -6,6 +6,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [unreleased]
 ### Changed
+- Improved handling of different annotation file types (eg. `.gtf/.gff/.gff3`) in `de_analysis` mode.
 - Improved handling of annotation files that do not contain version numbers in transcript_id (such as gtf's from Ensembl).
 ### Fixed
 - Differential expression failing with 10 or more samples.

bin/de_analysis.R

@@ -9,7 +9,6 @@ min_samps_gene_expr <- as.numeric(args[2])
 min_samps_feature_expr <- as.numeric(args[3])
 min_gene_expr <- as.numeric(args[4]) 
 min_feature_expr <- as.numeric(args[5])
-annotation_type <- args[6]
 
 cat("Loading counts, conditions and parameters.\n")
 cts <- as.matrix(read.csv("all_counts.tsv", sep="\t", row.names="Reference", stringsAsFactors=FALSE))
@@ -25,6 +24,23 @@ if(!"control" %in% coldata$condition)
        condition - unable to set reference.")
 coldata$condition <- relevel(coldata$condition, ref = "control")
 
+# a .gff annotation file extension may be gff2(gtf) or gff3 so check in files for use of = in the attribute field
+# if '=' present it is gff3 if not it is gtf.
+# see https://www.ensembl.org/info/website/upload/gff.html
+# and http://gmod.org/wiki/GFF2#Converting_GFF2_to_GFF3
+cat("Checking annotation file type.\n")
+lines <- readLines(file(ref_annotation), n=10000)
+# If transcript_id containing '=' (format eg. transcript_id=xxx)
+# annotation type is gff3
+check_file_type <- sum(grepl("transcript_id=", lines))
+if (check_file_type != 0){
+    cat("Annotation file type is gff3.\n")
+    annotation_type <- "gff3"
+} else {
+    # otherwise gtf
+    cat("Annotation file type is gtf.\n")
+    annotation_type <- "gtf"
+}
 
 # Transcript_id versions (eg. ENTXXX.1, eg. ENTXXX.2) represent how many times that transcript reference has been changed 
 # during its time in the database.

subworkflows/differential_expression.nf

@@ -60,10 +60,6 @@ process mergeTPM {
 
 process deAnalysis {
     label "isoforms"
-    errorStrategy "retry"
-    // Retry if it fails to make makeTxDbFromGFF 
-    // Because a file with .gff extension may be gff2(gtf) or gff3
-    maxRetries 1
     cpus 4
     memory "16 GB"
     input:
@@ -79,17 +75,10 @@ process deAnalysis {
         path "de_analysis/results_dexseq.tsv", emit: dexseq
         path "de_analysis", emit: de_analysis
         path "de_analysis/cpm_gene_counts.tsv", emit: cpm
-    script:
-    // Just try both annotation file type because a .gff extension may be gff2(gtf) or gff3
-    String annotation_type = "gtf"
-    if (task.attempt == 2){
-        annotation_type = "gff3"
-        log.info("Retry deAnalysis with gff format setting.")
-    }
     """
     mkdir merged
     mkdir de_analysis
-    de_analysis.R annotation.gtf $params.min_samps_gene_expr $params.min_samps_feature_expr $params.min_gene_expr $params.min_feature_expr $annotation_type
+    de_analysis.R annotation.gtf $params.min_samps_gene_expr $params.min_samps_feature_expr $params.min_gene_expr $params.min_feature_expr
     """
 }