first commit

defaults

@@ -0,0 +1,17 @@
+{
+    "adapter_seq": "not_available",
+    "randomBase_in_adapter": "0",
+    "QFILTER_MIN_QUAL": "20",
+    "QFILTER_MIN_READ_FRAC": "80",
+    "MIN_READ_LENGTH": "18",
+    "KEEP_RANDOM_BARCODE_STATS": "false",
+    "MAIN_ORGANISM_GENOME_ID": "hg38",
+    "STAR_alignEndsType": "Local",
+    "outFilterMatchNmin": "18",
+    "outFilterMatchNminOverLread": "0.9",
+    "STAR_outFilterMismatchNmax": "1",
+    "ENDOGENOUS_LIB_PRIORITY": "miRNA,tRNA,gencode,piRNA,circRNA",
+    "JAVA_RAM": "10G",
+    "cluster_config": "cls-grhjsd45els3f5kg62u002",
+    "disk_size": "200"
+}

inputs

@@ -0,0 +1,21 @@
+{
+    "{{ project_name }}.sample_id": "{{ sample_id }}",
+    "{{ project_name }}.INPUT_FILE_PATH": "{{ raw_fastq }}",
+    "{{ project_name }}.ADAPTER_SEQ": "{{ adapter_seq }}",
+    "{{ project_name }}.RANDOM_BARCODE_LENGTH": "{{ randomBase_in_adapter }}",
+    "{{ project_name }}.QFILTER_MIN_QUAL": "{{ QFILTER_MIN_QUAL }}",
+    "{{ project_name }}.QFILTER_MIN_READ_FRAC": "{{ QFILTER_MIN_READ_FRAC }}",
+    "{{ project_name }}.MIN_READ_LENGTH": "{{ MIN_READ_LENGTH }}",
+    "{{ project_name }}.KEEP_RANDOM_BARCODE_STATS": "{{ KEEP_RANDOM_BARCODE_STATS }}",
+    "{{ project_name }}.MAIN_ORGANISM_GENOME_ID": "{{ MAIN_ORGANISM_GENOME_ID }}",
+    "{{ project_name }}.STAR_alignEndsType": "{{ STAR_alignEndsType }}",
+    "{{ project_name }}.STAR_outFilterMatchNmin": "{{ outFilterMatchNmin }}",
+    "{{ project_name }}.STAR_outFilterMatchNminOverLread": "{{ outFilterMatchNminOverLread }}",
+    "{{ project_name }}.STAR_outFilterMismatchNmax": "{{ STAR_outFilterMismatchNmax }}",
+    "{{ project_name }}.ENDOGENOUS_LIB_PRIORITY": "{{ ENDOGENOUS_LIB_PRIORITY }}",
+    "{{ project_name }}.JAVA_RAM": "{{ JAVA_RAM }}",
+    "{{ project_name }}.DATABASE_PATH": "oss://pgx-reference-data/exceRpt_reference/",
+    "{{ project_name }}.docker": "registry.cn-shanghai.aliyuncs.com/pgx-docker-registry/excerpt:latest",
+    "{{ project_name }}.cluster_config": "{{ cluster_config }}",
+    "{{ project_name }}.disk_size": "{{ disk_size }}"
+}

tasks/Core.wdl

@@ -0,0 +1,79 @@
+task Core {
+    String  sample_id
+
+    File    INPUT_FILE_PATH
+    File    DATABASE_PATH
+
+    String  ADAPTER_SEQ
+    String  RANDOM_BARCODE_LENGTH
+    Int     QFILTER_MIN_QUAL
+    Int     QFILTER_MIN_READ_FRAC
+    Int     MIN_READ_LENGTH
+
+    String  KEEP_RANDOM_BARCODE_STATS
+
+    String  MAIN_ORGANISM_GENOME_ID
+    
+    String  STAR_alignEndsType
+    Int     STAR_outFilterMatchNmin
+    Float   STAR_outFilterMatchNminOverLread
+    Int     STAR_outFilterMismatchNmax
+
+    String  ENDOGENOUS_LIB_PRIORITY
+
+    String  JAVA_RAM
+
+    String docker
+    String cluster_config
+    String disk_size
+    String INPUT_FILE_ID = if basename("${INPUT_FILE_PATH}", ".gz") != basename("${INPUT_FILE_PATH}") then basename("${INPUT_FILE_PATH}", ".gz") else basename(basename("${INPUT_FILE_PATH}", ".fastq"), ".sra")
+
+    command <<<
+
+        #set -o pipefail
+        #set -e
+        nt=$(nproc)
+
+        mkdir ${sample_id}
+
+        
+        if [ "${ADAPTER_SEQ}" = "not_available" ]
+        then
+            PARAMETERS_ADAPTER=""
+        else
+            PARAMETERS_ADAPTER=$(echo '-A ${ADAPTER_SEQ}')
+        fi
+
+        exceRpt \
+            -d ${DATABASE_PATH} \
+            -N $nt \
+            $PARAMETERS_ADAPTER -l ${RANDOM_BARCODE_LENGTH} -m ${MIN_READ_LENGTH} \
+            -Q ${QFILTER_MIN_QUAL} -F ${QFILTER_MIN_READ_FRAC} \
+            -M ${MAIN_ORGANISM_GENOME_ID} \
+            -S ${STAR_alignEndsType} -O ${STAR_outFilterMatchNmin} -f ${STAR_outFilterMatchNminOverLread} -T ${STAR_outFilterMismatchNmax} \
+            -E ${ENDOGENOUS_LIB_PRIORITY} \
+            -K ${KEEP_RANDOM_BARCODE_STATS} \
+            -J ${JAVA_RAM} \
+            -i ${INPUT_FILE_PATH} \
+            -o ${sample_id} \
+            -s ${sample_id}
+        
+        find . -depth > fileList.txt
+
+    >>>
+
+    runtime {
+        docker:docker
+	cluster:cluster_config
+	systemDisk:"cloud_ssd 40"
+	dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+
+    output {      
+        File fileList = "fileList.txt"
+	Array[File] files_stat = glob("${sample_id}/*")
+	Array[File] files_core = glob("${sample_id}/${INPUT_FILE_ID}_${sample_id}/*")
+    }
+	
+
+}

workflow.wdl

@@ -0,0 +1,47 @@
+import "./tasks/Core.wdl" as Core
+
+workflow {{ project_name }} {
+
+    String  sample_id
+
+    File    INPUT_FILE_PATH
+    File    DATABASE_PATH
+
+    String  ADAPTER_SEQ
+    Int     RANDOM_BARCODE_LENGTH
+    Int     QFILTER_MIN_QUAL
+    Int     QFILTER_MIN_READ_FRAC
+    Int     MIN_READ_LENGTH
+
+    String  KEEP_RANDOM_BARCODE_STATS
+    
+    String  MAIN_ORGANISM_GENOME_ID
+    
+    String  STAR_alignEndsType
+    Int     STAR_outFilterMatchNmin
+    Float   STAR_outFilterMatchNminOverLread
+    Int     STAR_outFilterMismatchNmax
+
+    String  ENDOGENOUS_LIB_PRIORITY
+    
+    String  JAVA_RAM
+    
+    String docker
+	String cluster_config
+	String disk_size
+
+    call Core.Core as Core {
+        input:
+            sample_id=sample_id,
+            INPUT_FILE_PATH=INPUT_FILE_PATH, DATABASE_PATH=DATABASE_PATH,
+            ADAPTER_SEQ=ADAPTER_SEQ, RANDOM_BARCODE_LENGTH=RANDOM_BARCODE_LENGTH, QFILTER_MIN_QUAL=QFILTER_MIN_QUAL, QFILTER_MIN_READ_FRAC=QFILTER_MIN_READ_FRAC, MIN_READ_LENGTH=MIN_READ_LENGTH,
+            KEEP_RANDOM_BARCODE_STATS=KEEP_RANDOM_BARCODE_STATS, MAIN_ORGANISM_GENOME_ID=MAIN_ORGANISM_GENOME_ID,
+            STAR_alignEndsType=STAR_alignEndsType, STAR_outFilterMatchNmin=STAR_outFilterMatchNmin, STAR_outFilterMatchNminOverLread=STAR_outFilterMatchNminOverLread, STAR_outFilterMismatchNmax=STAR_outFilterMismatchNmax,
+            ENDOGENOUS_LIB_PRIORITY=ENDOGENOUS_LIB_PRIORITY,
+            JAVA_RAM=JAVA_RAM,
+            docker=docker, cluster_config=cluster_config, disk_size=disk_size
+ 
+    }
+
+
+}