上传文件至 'tasks'

tasks/BQSR.wdl

@@ -0,0 +1,67 @@
+task Sentieon_BQSR{
+    File ref_dir
+    File dbsnp_dir
+    File dbmills_dir
+
+    String sample_id
+    String ref_fasta
+    String dbsnp
+    String db_mills
+
+    File deduped_bam
+    File deduped_bam_index
+
+    # excute env
+    String docker
+    String cluster_config
+    String disk_size
+    
+    String SENTIEON_LICENSE
+
+    command<<<
+        set -o pipefail
+        set -exo
+        export SENTIEON_LICENSE=${SENTIEON_LICENSE}
+        
+        nt=$(nproc)
+
+
+        sentieon driver -t $nt \
+        -r ${ref_dir}/${ref_fasta} -i ${deduped_bam} \
+        --algo QualCal \
+        -k ${dbsnp_dir}/${dbsnp} -k ${dbmills_dir}/${db_mills} \
+        ${sample_id}_recal_data.table
+
+        sentieon driver -t $nt \
+        -r ${ref_dir}/${ref_fasta} -i ${deduped_bam} \
+        -q ${sample_id}_recal_data.table \
+        --algo QualCal \
+        -k ${dbsnp_dir}/${dbsnp} -k ${dbmills_dir}/${db_mills} \
+        ${sample_id}_recal_data.table.post \
+        --algo ReadWriter ${sample_id}.sorted.deduped.recaled.bam
+
+        sentieon driver -t $nt --algo QualCal \
+        --plot --before ${sample_id}_recal_data.table --after ${sample_id}_recal_data.table.post ${sample_id}_recal_data.csv
+
+        sentieon plot bqsr -o ${sample_id}_bqsrreport.pdf ${sample_id}_recal_data.csv
+    >>>
+
+    runtime{
+        docker:docker
+        cluster:cluster_config
+        systemDisk:"cloud_ssd 250"
+        dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+
+
+    }
+
+    output{
+        File recal_table = "${sample_id}_recal_data.table"
+        File recal_post = "${sample_id}_recal_data.table.post"
+        File recaled_bam = "${sample_id}.sorted.deduped.recaled.bam"
+        File recaled_bam_index = "${sample_id}.sorted.deduped.recaled.bam.bai"
+        File recal_csv = "${sample_id}_recal_data.csv"
+        File bqsrreport_pdf = "${sample_id}_bqsrreport.pdf"
+
+    }
+}

tasks/annovar.wdl

@@ -0,0 +1,35 @@
+task ANNOVAR {
+
+  File vcf
+  String basename = basename(vcf,".vcf")
+  File annovar_database
+  String docker
+  String cluster_config
+  String disk_size
+
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+    
+    /installations/annovar/table_annovar.pl ${vcf} \
+    ${annovar_database} -buildver hg38 \
+    -out ${basename} -remove \
+    -protocol refGene,cytoBand,genomicSuperDups,clinvar_20220320,intervar_20180118,cosmic95_coding,cosmic95_noncoding,gnomad211_exome,dbnsfp42c,avsnp150 \
+    -operation g,r,r,f,f,f,f,f,f,f \
+    -nastring . -vcfinput -polish -thread $nt
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    File avinput = "${basename}.avinput"
+    File multianno_txt = "${basename}.hg38_multianno.txt"
+    File multianno_vcf = "${basename}.hg38_multianno.vcf"
+  }
+}

tasks/bcftools.wdl

@@ -0,0 +1,31 @@
+task bcftools {
+  
+  File ref_dir
+  String fasta
+  File vcf
+  String basename = basename(vcf,".vcf")
+  String docker
+  String cluster_config
+  String disk_size
+
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+    
+    # bcftools norm -m -both ${vcf} | bcftools norm -f ${ref_dir}/${fasta} -Ov -o ${basename}.norm.vcf
+    # Split multiallelic sites
+    bcftools norm -m -both ${vcf} -o ${basename}.norm.vcf
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    File norm_vcf = "${basename}.norm.vcf"
+  }
+}

tasks/bcftools_concat.wdl

@@ -0,0 +1,33 @@
+task bcftools {
+  
+  File ref_dir
+  String fasta
+  File vcf_indels
+  File vcf_snvs
+  String sample_id
+  String docker
+  String cluster_config
+  String disk_size
+
+  command <<<
+    set -o pipefail
+    set -e
+    nt=$(nproc)
+    
+    bcftools concat -a ${vcf_indels} ${vcf_snvs} -Oz -o ${sample_id}_stralka.vcf.gz
+    bcftools index -t ${sample_id}_stralka.vcf.gz
+
+  >>>
+  
+  runtime {
+    docker: docker
+    cluster: cluster_config
+    systemDisk: "cloud_ssd 40"
+    dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
+  }
+  
+  output {
+    File concat_vcf = "${sample_id}_stralka.vcf.gz"
+    File concat_vcf_index = "${sample_id}_stralka.vcf.gz.tbi"
+  }
+}

tasks/fastp.wdl

@@ -0,0 +1,65 @@
+
+task fastp {
+    
+    # I/O options
+    File in1
+    File in2
+    String sample_id
+
+    Boolean? phred64 = false 
+    Boolean? fix_mgi_id = false
+
+    String? adapter_sequence
+    String? adapter_sequence_r2
+
+    Int? reads_to_process # specify how many reads/pairs to be processed. Default 0 means process all reads.
+
+    # reporting options
+    String json = sample_id+"fastp.json"
+    String html = sample_id+"fastp.html"
+    String report_title = "\'fastp report\'"
+
+    # excute env
+    String docker
+    String cluster_config
+    String disk_size
+
+    String out1_name = sample_id+'_clean_1.fastq'
+    String out2_name = sample_id+'_clean_2.fastq'
+
+    command <<<
+
+        # basic command
+        /opt/conda/bin/fastp \
+        --in1 ${in1} \
+        --in2 ${in2} \
+        --out1 ${out1_name} \
+        --out2 ${out2_name} \
+        --json ${json} \
+        --html ${html} \
+        --report_title ${report_title} \
+        
+        # options 
+        ${ true="--phred64 " false="" phred64 } \
+        ${ "--reads_to_process " + reads_to_process } \
+        ${ true="--fix_mgi_id " false="" fix_mgi_id } \
+        ${ "--adapter_sequence " + adapter_sequence } \
+        ${ "--adapter_sequence_r2 " + adapter_sequence_r2 }
+
+    >>>
+
+    runtime {
+		docker:docker
+		cluster:cluster_config
+		systemDisk:"cloud_ssd 40"
+		dataDisk:"cloud_ssd " + disk_size + " /cromwell_root/"
+    }
+
+    output {
+        File out1 = out1_name
+        File out2 = out2_name
+        File json_report = json
+        File html_report = html
+    }
+
+}