|
- task Jaccard_Index {
- File merged_gvcf
- String chromo
- String docker
- String cluster_config
- String disk_size
-
- command <<<
-
- cat ${merged_gvcf} | grep -v '##' | awk '
- BEGIN { OFS = "\t" }
- NF > 2 && FNR > 1 {
- for ( i=9; i<=NF; i++ ) {
- split($i,a,":") ;$i = a[1];
- }
- }
- { print }
- '| cut -f1,2,4,5,10- > ${chromo}.gt
-
- cat ${chromo}.gt | awk '{ if ((length($3) == 1) && (length($4) == 1)) { print } }' > ${chromo}.gt.snv
- cat ${chromo}.gt | awk '{ if ((length($3) != 1) || (length($4) != 1)) { print } }' > ${chromo}.gt.indel
-
- cat ${chromo}.gt | head -n1 | cat - ${chromo}.gt.snv > ${chromo}.gt.snv.txt
- python /opt/library_concordance.py -i ${chromo}.gt.snv.txt -prefix ${chromo}.snv
- python /opt/filter_indel_over_50.py -i ${chromo}.gt.indel -prefix ${chromo}
- cat ${chromo}.gt | head -n1 | cat - ${chromo}.indel.lessthan50bp.txt > ${chromo}.gt.indel.txt
- python /opt/library_concordance.py -i ${chromo}.gt.indel.txt -prefix ${chromo}.indel
-
- >>>
-
- runtime {
- docker:docker
- cluster: cluster_config
- systemDisk: "cloud_ssd 40"
- dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
- }
- output {
- File genotype = "${chromo}.gt"
- File snv = "${chromo}.gt.snv.txt"
- File indel = "${chromo}.indel.txt"
- File snv_inter = "${chromo}.snv.inter.txt"
- File snv_union = "${chromo}.snv.union.txt"
- File indel_inter = "${chromo}.indel.inter.txt"
- File indel_union = "${chromo}.indel.union.txt"
- }
- }
|
