high_confidence_calls_manuscript/tasks/bed_annotation.wdl

task bed_annotation {
	File merged_vcf
	File merged_vcf_idx
	File repeat_bed
	String sample
	String docker
	String cluster_config
	String disk_size
	
	command <<<

		rtg vcfannotate --bed-info=${repeat_bed} -i ${merged_vcf} -o ${sample}.normed.repeatAnno.vcf.gz	
		
		## DP
		zcat ${sample}.normed.repeatAnno.vcf.gz | grep -v '##' | awk '
		    BEGIN { OFS = "\t" }
		    NF > 2 && FNR > 1 { 
		        for ( i=9; i<=NF; i++ ) { 
		            split($i,a,":") ;$i = a[3];
		        } 
		    } 
		    { print }
		' > ${sample}.depth.txt
		
		## GQ
		zcat ${sample}.normed.repeatAnno.vcf.gz | grep -v '##' | awk '
		    BEGIN { OFS = "\t" }
		    NF > 2 && FNR > 1 { 
		        for ( i=9; i<=NF; i++ ) { 
		            split($i,a,":") ;$i = a[4];
		        } 
		    } 
		    { print }
		' > ${sample}.genotypeQuality.txt

		## MQ
		zcat ${sample}.normed.repeatAnno.vcf.gz | grep -v '##' | awk '
		    BEGIN { OFS = "\t" }
		    NF > 2 && FNR > 1 { 
		        for ( i=9; i<=NF; i++ ) { 
		            split($i,a,":") ;$i = a[6];
		        } 
		    } 
		    { print }
		' > ${sample}.mappinyQuality.txt

		## Allele frequency


	>>>

	runtime {
		docker:docker
		cluster: cluster_config
		systemDisk: "cloud_ssd 40"
		dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
	}
	output {
		File repeat_annotated_vcf = "${sample}.normed.repeatAnno.vcf.gz"
		File repeat_annotated_vcf_idx = "${sample}.normed.repeatAnno.vcf.gz.tbi"
	}
}