quartet_dna_quality_control_wgs_big_pipeline/tasks/Dedup.wdl

task Dedup {
	File sorted_bam
	File sorted_bam_index
	String sample = basename(sorted_bam,".sorted.bam")
	String docker
	String cluster_config
	String disk_size


	command <<<
		set -o pipefail
		set -e

		nt=$(nproc)
		# ${SENTIEON_INSTALL_DIR}/bin/sentieon driver -t $nt -i ${sorted_bam} --algo LocusCollector --fun score_info ${sample}_score.txt
		# ${SENTIEON_INSTALL_DIR}/bin/sentieon driver -t $nt -i ${sorted_bam} --algo Dedup --rmdup --score_info ${sample}_score.txt --metrics ${sample}_dedup_metrics.txt ${sample}.sorted.deduped.bam	
		java -jar picard.jar  MarkDuplicates \
					-I ${sorted_bam}  \
					-O ${sample}.sorted.deduped.bam 
					-M ${sample}_dedup_metrics.txt \
					--REMOVE_DUPLICATES
					
		samtools index -@ $(nproc) -o  ${sample}.sorted.deduped.bam.bai  ${sample}.sorted.deduped.bam
	>>>
	runtime {
		docker:docker
    	cluster: cluster_config
    	systemDisk: "cloud_ssd 40"
    	dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
	}

	output {
		# File score = "${sample}_score.txt"
		# File dedup_metrics = "${sample}_dedup_metrics.txt"
		File Dedup_bam = "${sample}.sorted.deduped.bam"
		File Dedup_bam_index = "${sample}.sorted.deduped.bam.bai"
	}
}