Infer and visualize copy number from high-throughput DNA sequencing data.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

43 line
1.2KB

  1. task batch {
  2. String sample_id
  3. Array[File] tumor_bam
  4. Array[File] tumor_bai
  5. Array[File] normal_bam
  6. Array[File] normal_bai
  7. File bed
  8. File ref_dir
  9. String fasta
  10. File ref_flat
  11. File access_bed
  12. String docker
  13. String cluster_config
  14. String disk_size
  15. command <<<
  16. set -o pipefail
  17. set -e
  18. mkdir -p /cromwell_root/tmp/cnvkit
  19. cp ${sep=' ' normal_bai} /cromwell_root/tmp/cnvkit
  20. cp ${sep=' ' tumor_bai} /cromwell_root/tmp/cnvkit
  21. cd /cromwell_root/tmp/cnvkit
  22. mkdir results
  23. cnvkit.py batch faidx --no-rebuild${sep=' ' tumor_bam} --normal ${sep=' ' normal_bam} \
  24. --targets ${bed} --annotate ${ref_flat} \
  25. --fasta ${ref_dir}/${fasta} --access ${access_bed} \
  26. --output-reference ${sample_id}.reference.cnn --output-dir /cromwell_root/tmp/cnvkit/results/ \
  27. --diagram --scatter
  28. >>>
  29. runtime {
  30. docker: docker
  31. cluster: cluster_config
  32. systemDisk: "cloud_ssd 40"
  33. dataDisk: "cloud_ssd " + disk_size + " /cromwell_root/"
  34. }
  35. output {
  36. File reference_cnn = "${sample_id}.reference.cnn"
  37. Array[File] results = glob("/cromwell_root/tmp/cnvkit/results/*")
  38. }
  39. }