unified output file prefix

tasks/count.wdl

@@ -1,15 +1,15 @@
 task count {
   Array[File] ballgown
-  String sample_id
+  String base=basename(gene_abundance, ".gene.abundance.txt")
   String docker
   String cluster
   String disk_size
   Int count_length
 
   command <<<
-    mkdir -p /cromwell_root/tmp/ballgown/${sample_id}
-    cp -r ${sep=" " ballgown} /cromwell_root/tmp/ballgown/${sample_id}
-    count -i /cromwell_root/tmp/ballgown -l ${count_length} -g ${sample_id}_gene_count_matrix.csv -t ${sample_id}_transcript_count_matrix.csv
+    mkdir -p /cromwell_root/tmp/ballgown/${base}
+    cp -r ${sep=" " ballgown} /cromwell_root/tmp/ballgown/${base}
+    count -i /cromwell_root/tmp/ballgown -l ${count_length} -g ${base}_gene_count_matrix.csv -t ${base}_transcript_count_matrix.csv
   >>>
   
   runtime {
@@ -20,7 +20,7 @@ task count {
   }
   
   output {
-    File mat_expression_genecount="${sample_id}_gene_count_matrix.csv"
-    File mat_expression_transcriptcount="${sample_id}_transcript_count_matrix.csv"
+    File mat_expression_genecount="${base}_gene_count_matrix.csv"
+    File mat_expression_transcriptcount="${base}_transcript_count_matrix.csv"
   }
 }

tasks/fastp.wdl

@@ -1,7 +1,9 @@
 task fastp {
   File read1
   File read2
-  String sample_id
+  String read1name=sub(basename(read1),"\\.\\S+$", "")
+  String read2name=sub(basename(read2),"\\.\\S+$", "")
+  String sample_name=sub(basename(read1),"\\_*1.\\S+$", "")
   String adapter_sequence
   String adapter_sequence_r2
   String docker
@@ -14,10 +16,10 @@ command <<<
     
     ## Trim
     if [ "${trim_adapter}" != 'true' ]; then
-    cp ${read1} ${sample_id}_R1.fq.gz
-    cp ${read2} ${sample_id}_R2.fq.gz
+    cp ${read1} ${read1name}.fq.gz
+    cp ${read2} ${read2name}.fq.gz
     else
-    fastp --thread $nt --adapter_sequence ${adapter_sequence} --adapter_sequence_r2 ${adapter_sequence_r2} --detect_adapter_for_pe -i ${read1} -I ${read2} -o ${sample_id}_R1.fq.gz -O ${sample_id}_R2.fq.gz -j ${sample_id}.json -h ${sample_id}.html
+    fastp --thread $nt --adapter_sequence ${adapter_sequence} --adapter_sequence_r2 ${adapter_sequence_r2} --detect_adapter_for_pe -i ${read1} -I ${read2} -o ${read1name}.fq.gz -O ${read2name}.fq.gz -j ${sample_name}.json -h ${sample_name}.html
     fi
   >>>
   
@@ -29,9 +31,9 @@ command <<<
   }
 
   output {
-    File json = "${sample_id}.json"
-    File report = "${sample_id}.html"
-    File trim_R1 = "${sample_id}_R1.fq.gz"
-    File trim_R2 = "${sample_id}_R2.fq.gz"
+    File json = "${sample_name}.json"
+    File report = "${sample_name}.html"
+    File trim_R1 = "${read1name}.fq.gz"
+    File trim_R2 = "${read2name}.fq.gz"
   }
 }

tasks/hisat2.wdl

@@ -2,8 +2,8 @@ task hisat2 {
   File idx
   File read_1P
   File read_2P
+  String sample_name=sub(basename(read_1P),"\\_*1.\\S+$", "")
   String idx_prefix
-  String sample_id
   String docker
   String cluster
   String disk_size
@@ -11,7 +11,7 @@ task hisat2 {
 
   command {
     nt=$(nproc)
-    hisat2 -t -p $nt -x ${idx}/${idx_prefix} -1 ${read_1P} -2 ${read_2P} -S ${sample_id}.sam  --un-conc-gz ${sample_id}_un.fq.gz
+    hisat2 -t -p $nt -x ${idx}/${idx_prefix} -1 ${read_1P} -2 ${read_2P} -S ${sample_name}.sam  --un-conc-gz ${sample_name}_un.fq.gz
   }
    
   runtime { 
@@ -22,8 +22,8 @@ task hisat2 {
   }
 
   output {
-    File sam=sample_id + ".sam"
-    File unmapread_1p=sample_id + "_un.fq.1.gz"
-    File unmapread_2p=sample_id + "_un.fq.2.gz"
+    File sam=sample_name + ".sam"
+    File unmapread_1p=sample_name + "_un.fq.1.gz"
+    File unmapread_2p=sample_name + "_un.fq.2.gz"
   }
 }

workflow.wdl

@@ -71,7 +71,6 @@ workflow {{ project_name }} {
 
   call fastp.fastp as fastp {
     input:
-    sample_id=sample_id,
     read1=read1,
     read2=read2,
     docker=fastp_docker,
@@ -84,7 +83,6 @@ workflow {{ project_name }} {
       
   call hisat2.hisat2 as hisat2 {
     input:
-    sample_id=sample_id,
     docker=hisat2_docker,
     cluster=hisat2_cluster,
     idx=idx,
@@ -138,6 +136,7 @@ workflow {{ project_name }} {
     docker=count_docker,
     cluster=count_cluster,
     ballgown=stringtie.ballgown,
+    gene_abundance=stringtie.gene_abundance,
     disk_size=disk_size,
     count_length=count_length
   }