first commit

defaults

@@ -0,0 +1,7 @@
+{   
+    "reference":"oss://pgx-reference-data/reference/pindel/GRCh38.d1.vd1.fa",
+    "reference_fai":"oss://pgx-reference-data/reference/pindel/GRCh38.d1.vd1.fa.fai"
+    "pindel_docker":"registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/pindel:0.2.5b9_3",
+    "pindel_cluster":"OnDemand bcs.a2.3xlarge img-ubuntu-vpc",
+    "disk_size":"200"
+}

inputs

@@ -0,0 +1,9 @@
+{
+    "{{ project_name }}.sample_id": "{{ sample_id }}",
+    "{{ project_name }}.bam": "{{ bam }}",
+    "{{ project_name }}.reference": "{{ reference }}",
+    "{{ project_name }}.reference_fai": "{{ reference_fai }}",
+    "{{ project_name }}.pindel_docker": "{{ pindel_docker }}",
+    "{{ project_name }}.pindel_cluster": "{{ pindel_cluster }}",
+    "{{ project_name }}.disk_size": "{{ disk_size }
+}

tasks/pindel.wdl

@@ -0,0 +1,80 @@
+task pindel{
+    String sample_id
+    File bam
+    File reference
+    File reference_fai
+
+    String docker
+    String cluster
+    String disk_size
+
+
+    command <<<
+	
+        set -o pipefail
+        set -e
+
+        mkdir ./pindel_result/
+        mkdir ./input
+
+        cp ${bam} ./input
+
+        bam_file_name=`echo ${bam}|awk -F "/" '{print $NF}'`
+        
+        samtools index -@ 4 ./input/$bam_file_name
+        
+        java "-Xmx16G" -jar /software/picard/picard.jar  CollectInsertSizeMetrics \
+            -H ./pindel_result/${sample_id}_picard.pdf \
+            -I ./input/$bam_file_name \
+            -O ./pindel_result/${sample_id}_picard.txt
+
+        mean_insert_size=`cat pindel_result/${sample_id}_picard.txt|sed -n '8p'|cut -f 6|cut -d . -f 1`
+        bam_file_name=`echo ${bam}|awk -F "/" '{print $NF}'`
+
+        echo -e "./input/$bam_file_name\t$mean_insert_size\t${sample_id}" > ${sample_id}_config.txt
+
+        pindel -i ${sample_id}_config.txt \
+            -f ${reference} \
+            -o ./pindel_result/${sample_id} \
+            -c all \
+            -T 4 \
+            -x 4 \
+            -l \
+            -B 0 \
+            -M 3 \
+            -J /software/picard/hg38_ucsc_centromere.bed
+
+        grep "ChrID" pindel_result/${sample_id}_SI > pindel_result/${sample_id}_all_indel
+        grep "ChrID" pindel_result/${sample_id}_D >> pindel_result/${sample_id}_all_indel
+
+        awk -v chrID="chr1" '$8==chrID {print}' pindel_result/${sample_id}_all_indel > pindel_result/${sample_id}_indel
+        
+        for i in `seq 2 22`  X Y M
+            do
+                awk -v chrID=chr$i '$8==chrID {print}' pindel_result/${sample_id}_all_indel >> pindel_result/${sample_id}_indel
+            done
+
+        pindel2vcf  -r ${reference} \
+            -R GRCh38.d1.vd1 \
+            -d GDC \
+            -p pindel_result/${sample_id}_indel \
+            -v pindel_result/${sample_id}.pindel.indel.vcf
+        
+
+
+    >>>
+	
+    runtime {
+        docker : docker
+        cluster : cluster
+        systemDisk: "cloud_ssd 40"
+        dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/
+    }
+
+    output {
+        Array[File] pindel_result=glob("./pindel_result/${sample_id}*")
+    }
+
+}
+
+

workflow.wdl

@@ -0,0 +1,22 @@
+import "./tasks/pindel.wdl" as pindel
+
+workflow run_pindel {
+    String sample_id
+    File bam
+    File reference
+    File reference_fai
+
+    String pindel_docker
+
+        call pindel.pindel as pindel {
+                input:	
+                sample_id=sample_id,
+                bam=bam,
+                reference=reference,
+                reference_fai=reference_fai,
+                docker=pindel_docker
+        }
+
+
+}	
+