sort vcf

tasks/benchmark.wdl

@@ -25,31 +25,35 @@ task benchmark {
 		echo -e "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tLCL7" > LCL7_name
 		echo -e "#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\tFORMAT\tLCL8" > LCL8_name
 
+		cat ${vcf} | grep '#' > header_original
+		cat ${vcf} | grep -v '#' | sort -k1,1 -k2,2n > body_sorted
+		cat header_original body_sorted > sorted.vcf 
+
 		if [[ ${sample} =~ "LCL5" ]];then
-			/opt/hap.py/bin/hap.py /cromwell_root/tmp/reference_datasets_v202103/LCL5.high.confidence.calls.vcf ${vcf} -f ${filtered_bed} --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
-			cat ${vcf} | grep '##' > header
-			cat ${vcf} | grep -v '#' > body
+			/opt/hap.py/bin/hap.py /cromwell_root/tmp/reference_datasets_v202103/LCL5.high.confidence.calls.vcf sorted.vcf -f ${filtered_bed} --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+			cat sorted.vcf | grep '##' > header
+			cat sorted.vcf | grep -v '#' > body
 			cat header LCL5_name body > LCL5.vcf
 			/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg bgzip LCL5.vcf -c > ${sample}.reformed.vcf.gz
 			/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg index -f vcf ${sample}.reformed.vcf.gz
 	    elif [[ ${sample} =~ "LCL6" ]]; then
-	    	/opt/hap.py/bin/hap.py /cromwell_root/tmp/reference_datasets_v202103/LCL6.high.confidence.calls.vcf ${vcf} -f ${filtered_bed} --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
-			cat ${vcf} | grep '##' > header
-			cat ${vcf} | grep -v '#' > body
+	    	/opt/hap.py/bin/hap.py /cromwell_root/tmp/reference_datasets_v202103/LCL6.high.confidence.calls.vcf sorted.vcf -f ${filtered_bed} --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+			cat sorted.vcf | grep '##' > header
+			cat sorted.vcf | grep -v '#' > body
 			cat header LCL6_name body > LCL6.vcf
 			/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg bgzip LCL6.vcf -c > ${sample}.reformed.vcf.gz
 			/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg index -f vcf ${sample}.reformed.vcf.gz
         elif [[ ${sample} =~ "LCL7" ]]; then
-        	/opt/hap.py/bin/hap.py /cromwell_root/tmp/reference_datasets_v202103/LCL7.high.confidence.calls.vcf ${vcf} -f ${filtered_bed} --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
-			cat ${vcf} | grep '##' > header
-			cat ${vcf} | grep -v '#' > body
+        	/opt/hap.py/bin/hap.py /cromwell_root/tmp/reference_datasets_v202103/LCL7.high.confidence.calls.vcf sorted.vcf -f ${filtered_bed} --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+			cat sorted.vcf | grep '##' > header
+			cat sorted.vcf | grep -v '#' > body
 			cat header LCL7_name body > LCL7.vcf
 			/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg bgzip LCL7.vcf -c > ${sample}.reformed.vcf.gz
 			/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg index -f vcf ${sample}.reformed.vcf.gz
 	    elif [[ ${sample} =~ "LCL8" ]]; then
-			/opt/hap.py/bin/hap.py /cromwell_root/tmp/reference_datasets_v202103/LCL8.high.confidence.calls.vcf ${vcf} -f ${filtered_bed} --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
-			cat ${vcf} | grep '##' > header
-			cat ${vcf} | grep -v '#' > body
+			/opt/hap.py/bin/hap.py /cromwell_root/tmp/reference_datasets_v202103/LCL8.high.confidence.calls.vcf sorted.vcf -f ${filtered_bed} --threads $nt -o ${sample} -r ${ref_dir}/${fasta}
+			cat sorted.vcf | grep '##' > header
+			cat sorted.vcf | grep -v '#' > body
 			cat header LCL8_name body > LCL8.vcf
 			/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg bgzip LCL8.vcf -c > ${sample}.reformed.vcf.gz
 			/opt/rtg-tools/dist/rtg-tools-3.10.1-4d58ead/rtg index -f vcf ${sample}.reformed.vcf.gz