revised-bedtools-task

input_samples.csv

@@ -1,2 +0,0 @@
-oss://choppy-cromwell-result/test-choppy/iseq_150pe_rnaseq_20200221_wangshangzi/43061775-40e6-47e7-8f07-b961b44c596f/call-samtools/GCCACATA_S9_L001_R1_001.sorted.bam   oss://choppy-cromwell-result/test-choppy/iseq_150pe_rnaseq_20200221_wangshangzi/43061775-40e6-47e7-8f07-b961b44c596f/call-samtools/GCCACATA_S9_L001_R1_001.sorted.bam.bai  
-oss://choppy-cromwell-result/test-choppy/iseq_150pe_rnaseq_20200221_wangshangzi/49bd025e-5275-4fbd-9e67-b279b08ce8b5/call-samtools/F1_S6_L001_R1_001.sorted.bam oss://choppy-cromwell-result/test-choppy/iseq_150pe_rnaseq_20200221_wangshangzi/49bd025e-5275-4fbd-9e67-b279b08ce8b5/call-samtools/F1_S6_L001_R1_001.sorted.bam.bai

tasks/bedtools.wdl

@@ -1,7 +1,6 @@
 task bedtools {
 
-	Array[File] bam
-	Array[File] bai
+	Array[File] tmp_bam
 	File bed_file
 
 	String docker
@@ -10,7 +9,7 @@ task bedtools {
 
 	command <<<
 	    set -e -o pipefail
-		cat ~{sep=" " bam}|bedtools multicov -bed ${bed_file} > revread_count.txt 
+		bedtools multicov ${tmp_bam} -bed ${bed_file} > revread_count.txt 
 	
 	>>>
 

tasks/cp_bam.wdl

@@ -0,0 +1,26 @@
+task cp_bam {
+
+	File bam
+	File bai
+    String bamname = basename(bam,".bam")
+
+	String docker
+	String cluster_config
+	String disk_size
+
+	command <<<
+	    set -e -o pipefail
+		cp ${bam} ${bamname}_tmp.bam
+	>>>
+
+	runtime {
+		docker:docker
+		cluster:cluster_config
+		systemDisk:"cloud_ssd 40"
+		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+	}
+
+	output {
+		File tmp_bam = "${bamname}_tmp.bam"
+	}
+}

workflow.wdl

@@ -1,3 +1,4 @@
+import "./tasks/cp_bam.wdl" as cp_bam
 import "./tasks/bedtools.wdl" as bedtools
 
 workflow {{ project_name }} {
@@ -7,6 +8,12 @@ workflow {{ project_name }} {
 	Array[Array[File]] input_samples = read_tsv(input_samples_file)
     
 	scatter (sample in input_samples) {
+		call cp_bam.cp_bam as cp_bam {
+			input:
+			bam=sample[0],
+			bai=sample[1],
+
+		}
 
 		call bedtools.bedtools as bedtools {
 			input: