dxapp.json

{
  "name": "vcf_trimmer",
  "title": "VCF Trimmer",
  "summary": "Trims VCFs by removing unwanted INFO and FORMAT fields, splits multi-allelic sites, and applies filters to VCFs.",
  "dxapi": "1.0.0",
  "version": "0.0.1",
  "inputSpec": [
    {
      "name": "vcf_file_list",
      "label": "VCF file list",
      "class": "file",
      "optional": false,
      "patterns": [
        "*"
      ],
      "help": "File containing list of full VCF paths to process. One file per line."
    },
    {
      "name": "file_label",
      "label": "Label to add to file",
      "class": "string",
      "optional": true,
      "default": "trimmed",
      "help": "Label to insert into filename prior to .vcf.gz"
    },
    {
      "name": "output_dir",
      "label": "Output directory",
      "class": "string",
      "optional": true,
      "default": "/",
      "help": "Output directory for newly created VCFs"
    },
    {
      "name": "qc_thresholds",
      "label": "Comma separated list of metric thresholds to apply.",
      "class": "string",
      "optional": true,
      "default": "INFO/AAScore>0.5",
      "help": "Comma separated list of quality control thresholds to apply. Format: Field/MetricComparisonThreshold. e.g. INFO/AAScore>0.5"
    },
    {
      "name": "fields_to_remove",
      "label": "Comma separated list of fields to remove. Should not include fields used for QC thresholding",
      "class": "string",
      "optional": true,
      "default": "FORMAT/FT,FORMAT/AD,FORMAT/MD,FORMAT/DP,FORMAT/RA,FORMAT/PP,FORMAT/GQ,FORMAT/PL",
      "help": "Format: FIELD/METRIC. e.g. INFO/ABHet"
    },
    {
      "name": "threads",
      "label": "Number of threads",
      "class": "string",
      "optional": true,
      "default": "4",
      "help": "Threads x concurrent processes should <= N cores"
    },
    {
      "name": "concurrent_processes",
      "label": "Number of concurrent processes",
      "class": "string",
      "optional": true,
      "default": "20",
      "help": "Maximum number of VCFs to process on worker concurrently. On mem2_ssd1_v2_x32, 20 is the limit to avoid resource issues."
    }
  ],
  "outputSpec": [],
  "runSpec": {
    "timeoutPolicy": {
      "*": {
        "hours": 48
      }
    },
    "interpreter": "bash",
    "file": "src/vcf_trimmer.sh",
    "distribution": "Ubuntu",
    "release": "20.04",
    "version": "0"
  },
  "access": {
    "project": "CONTRIBUTE"
  },
  "regionalOptions": {
    "aws:eu-west-2": {
      "systemRequirements": {
        "*": {
          "instanceType": "mem2_ssd1_v2_x32"
        }
      }
    }
  }
}