org_broadinstitute_hellbender_tools_copynumber_CollectReadCounts.json

{
  "summary": "Collects read counts at specified intervals",
  "arguments": [
    {
      "summary": "If true, adds a PG tag to created SAM/BAM/CRAM files.",
      "name": "--add-output-sam-program-record",
      "synonyms": "-add-output-sam-program-record",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "true",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "If true, adds a command line header line to created VCF files.",
      "name": "--add-output-vcf-command-line",
      "synonyms": "-add-output-vcf-command-line",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "true",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "read one or more arguments files and add them to the command line",
      "name": "--arguments_file",
      "synonyms": "NA",
      "type": "List[File]",
      "required": "no",
      "fulltext": "",
      "defaultValue": "[]",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": []
    },
    {
      "summary": "Size of the cloud-only prefetch buffer (in MB; 0 to disable). Defaults to cloudPrefetchBuffer if unset.",
      "name": "--cloud-index-prefetch-buffer",
      "synonyms": "-CIPB",
      "type": "int",
      "required": "no",
      "fulltext": "",
      "defaultValue": "-1",
      "minValue": "-Infinity",
      "maxValue": "Infinity",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": []
    },
    {
      "summary": "Size of the cloud-only prefetch buffer (in MB; 0 to disable).",
      "name": "--cloud-prefetch-buffer",
      "synonyms": "-CPB",
      "type": "int",
      "required": "no",
      "fulltext": "",
      "defaultValue": "40",
      "minValue": "-Infinity",
      "maxValue": "Infinity",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": []
    },
    {
      "summary": "If true, create a BAM/CRAM index when writing a coordinate-sorted BAM/CRAM file.",
      "name": "--create-output-bam-index",
      "synonyms": "-OBI",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "true",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "If true, create a MD5 digest for any BAM/SAM/CRAM file created",
      "name": "--create-output-bam-md5",
      "synonyms": "-OBM",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "If true, create a VCF index when writing a coordinate-sorted VCF file.",
      "name": "--create-output-variant-index",
      "synonyms": "-OVI",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "true",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "If true, create a a MD5 digest any VCF file created.",
      "name": "--create-output-variant-md5",
      "synonyms": "-OVM",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "If true, don\u0027t cache bam indexes, this will reduce memory requirements but may harm performance if many intervals are specified.  Caching is automatically disabled if there are no intervals specified.",
      "name": "--disable-bam-index-caching",
      "synonyms": "-DBIC",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": []
    },
    {
      "summary": "Read filters to be disabled before analysis",
      "name": "--disable-read-filter",
      "synonyms": "-DF",
      "type": "List[String]",
      "required": "no",
      "fulltext": "",
      "defaultValue": "[]",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "If specified, do not check the sequence dictionaries from our inputs for compatibility. Use at your own risk!",
      "name": "--disable-sequence-dictionary-validation",
      "synonyms": "-disable-sequence-dictionary-validation",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": []
    },
    {
      "summary": "Disable all tool default read filters (WARNING: many tools will not function correctly without their default read filters on)",
      "name": "--disable-tool-default-read-filters",
      "synonyms": "-disable-tool-default-read-filters",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "One or more genomic intervals to exclude from processing",
      "name": "--exclude-intervals",
      "synonyms": "-XL",
      "type": "List[String]",
      "required": "no",
      "fulltext": "Use this argument to exclude certain parts of the genome from the analysis (like -L, but the opposite).\n This argument can be specified multiple times. You can use samtools-style intervals either explicitly on the\n command line (e.g. -XL 1 or -XL 1:100-200) or by loading in a file containing a list of intervals\n (e.g. -XL myFile.intervals).",
      "defaultValue": "[]",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "Output file format.",
      "name": "--format",
      "synonyms": "NA",
      "type": "Format",
      "required": "no",
      "fulltext": "",
      "defaultValue": "HDF5",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": [
        {
          "summary": "",
          "name": "TSV"
        },
        {
          "summary": "",
          "name": "HDF5"
        }
      ]
    },
    {
      "summary": "A configuration file to use with the GATK.",
      "name": "--gatk-config-file",
      "synonyms": "NA",
      "type": "String",
      "required": "no",
      "fulltext": "",
      "defaultValue": "null",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "If the GCS bucket channel errors out, how many times it will attempt to re-initiate the connection",
      "name": "--gcs-max-retries",
      "synonyms": "-gcs-retries",
      "type": "int",
      "required": "no",
      "fulltext": "",
      "defaultValue": "20",
      "minValue": "-Infinity",
      "maxValue": "Infinity",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": []
    },
    {
      "summary": "display the help message",
      "name": "--help",
      "synonyms": "-h",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": []
    },
    {
      "summary": "BAM/SAM/CRAM file containing reads",
      "name": "--input",
      "synonyms": "-I",
      "type": "List[String]",
      "required": "yes",
      "fulltext": "",
      "defaultValue": "[]",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "required",
      "options": []
    },
    {
      "summary": "Amount of padding (in bp) to add to each interval you are excluding.",
      "name": "--interval-exclusion-padding",
      "synonyms": "-ixp",
      "type": "int",
      "required": "no",
      "fulltext": "Use this to add padding to the intervals specified using -XL. For example, \u0027-XL 1:100\u0027 with a\n padding value of 20 would turn into \u0027-XL 1:80-120\u0027. This is typically used to add padding around targets when\n analyzing exomes.",
      "defaultValue": "0",
      "minValue": "-Infinity",
      "maxValue": "Infinity",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "Interval merging rule for abutting intervals",
      "name": "--interval-merging-rule",
      "synonyms": "-imr",
      "type": "IntervalMergingRule",
      "required": "no",
      "fulltext": "By default, the program merges abutting intervals (i.e. intervals that are directly side-by-side but do not\n actually overlap) into a single continuous interval. However you can change this behavior if you want them to be\n treated as separate intervals instead.",
      "defaultValue": "ALL",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": [
        {
          "summary": "",
          "name": "ALL"
        },
        {
          "summary": "",
          "name": "OVERLAPPING_ONLY"
        }
      ]
    },
    {
      "summary": "Amount of padding (in bp) to add to each interval you are including.",
      "name": "--interval-padding",
      "synonyms": "-ip",
      "type": "int",
      "required": "no",
      "fulltext": "Use this to add padding to the intervals specified using -L. For example, \u0027-L 1:100\u0027 with a\n padding value of 20 would turn into \u0027-L 1:80-120\u0027. This is typically used to add padding around targets when\n analyzing exomes.",
      "defaultValue": "0",
      "minValue": "-Infinity",
      "maxValue": "Infinity",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "Set merging approach to use for combining interval inputs",
      "name": "--interval-set-rule",
      "synonyms": "-isr",
      "type": "IntervalSetRule",
      "required": "no",
      "fulltext": "By default, the program will take the UNION of all intervals specified using -L and/or -XL. However, you can\n change this setting for -L, for example if you want to take the INTERSECTION of the sets instead. E.g. to\n perform the analysis only on chromosome 1 exomes, you could specify -L exomes.intervals -L 1 --interval-set-rule\n INTERSECTION. However, it is not possible to modify the merging approach for intervals passed using -XL (they will\n always be merged using UNION).\n\n Note that if you specify both -L and -XL, the -XL interval set will be subtracted from the -L interval set.",
      "defaultValue": "UNION",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": [
        {
          "summary": "Take the union of all intervals",
          "name": "UNION"
        },
        {
          "summary": "Take the intersection of intervals (the subset that overlaps all intervals specified)",
          "name": "INTERSECTION"
        }
      ]
    },
    {
      "summary": "One or more genomic intervals over which to operate",
      "name": "--intervals",
      "synonyms": "-L",
      "type": "List[String]",
      "required": "yes",
      "fulltext": "",
      "defaultValue": "[]",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "required",
      "options": []
    },
    {
      "summary": "Lenient processing of VCF files",
      "name": "--lenient",
      "synonyms": "-LE",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "Output file for read counts.",
      "name": "--output",
      "synonyms": "-O",
      "type": "File",
      "required": "yes",
      "fulltext": "",
      "defaultValue": "null",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "required",
      "options": []
    },
    {
      "summary": "Whether to suppress job-summary info on System.err.",
      "name": "--QUIET",
      "synonyms": "NA",
      "type": "Boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "Read filters to be applied before analysis",
      "name": "--read-filter",
      "synonyms": "-RF",
      "type": "List[String]",
      "required": "no",
      "fulltext": "",
      "defaultValue": "[]",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "Indices to use for the read inputs. If specified, an index must be provided for every read input and in the same order as the read inputs. If this argument is not specified, the path to the index for each input will be inferred automatically.",
      "name": "--read-index",
      "synonyms": "-read-index",
      "type": "List[String]",
      "required": "no",
      "fulltext": "",
      "defaultValue": "[]",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "Validation stringency for all SAM/BAM/CRAM/SRA files read by this program.  The default stringency value SILENT can improve performance when processing a BAM file in which variable-length data (read, qualities, tags) do not otherwise need to be decoded.",
      "name": "--read-validation-stringency",
      "synonyms": "-VS",
      "type": "ValidationStringency",
      "required": "no",
      "fulltext": "",
      "defaultValue": "SILENT",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": [
        {
          "summary": "",
          "name": "STRICT"
        },
        {
          "summary": "",
          "name": "LENIENT"
        },
        {
          "summary": "",
          "name": "SILENT"
        }
      ]
    },
    {
      "summary": "Reference sequence",
      "name": "--reference",
      "synonyms": "-R",
      "type": "String",
      "required": "no",
      "fulltext": "",
      "defaultValue": "null",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": []
    },
    {
      "summary": "Output traversal statistics every time this many seconds elapse",
      "name": "--seconds-between-progress-updates",
      "synonyms": "-seconds-between-progress-updates",
      "type": "double",
      "required": "no",
      "fulltext": "",
      "defaultValue": "10.0",
      "minValue": "-Infinity",
      "maxValue": "Infinity",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "Use the given sequence dictionary as the master/canonical sequence dictionary.  Must be a .dict file.",
      "name": "--sequence-dictionary",
      "synonyms": "-sequence-dictionary",
      "type": "String",
      "required": "no",
      "fulltext": "",
      "defaultValue": "null",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "display hidden arguments",
      "name": "--showHidden",
      "synonyms": "-showHidden",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "advanced",
      "options": []
    },
    {
      "summary": "If true, don\u0027t emit genotype fields when writing vcf file output.",
      "name": "--sites-only-vcf-output",
      "synonyms": "NA",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": []
    },
    {
      "summary": "Undocumented option",
      "name": "--TMP_DIR",
      "synonyms": "NA",
      "type": "List[File]",
      "required": "no",
      "fulltext": "",
      "defaultValue": "[]",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "Whether to use the JdkDeflater (as opposed to IntelDeflater)",
      "name": "--use-jdk-deflater",
      "synonyms": "-jdk-deflater",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "Whether to use the JdkInflater (as opposed to IntelInflater)",
      "name": "--use-jdk-inflater",
      "synonyms": "-jdk-inflater",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": []
    },
    {
      "summary": "Control verbosity of logging.",
      "name": "--verbosity",
      "synonyms": "-verbosity",
      "type": "LogLevel",
      "required": "no",
      "fulltext": "",
      "defaultValue": "INFO",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "common",
      "options": [
        {
          "summary": "",
          "name": "ERROR"
        },
        {
          "summary": "",
          "name": "WARNING"
        },
        {
          "summary": "",
          "name": "INFO"
        },
        {
          "summary": "",
          "name": "DEBUG"
        }
      ]
    },
    {
      "summary": "display the version number for this tool",
      "name": "--version",
      "synonyms": "NA",
      "type": "boolean",
      "required": "no",
      "fulltext": "",
      "defaultValue": "false",
      "minValue": "NA",
      "maxValue": "NA",
      "minRecValue": "NA",
      "maxRecValue": "NA",
      "kind": "optional",
      "options": []
    }
  ],
  "description": "Collects read counts at specified intervals.  The count for each interval is calculated by counting\n the number of read starts that lie in the interval.\n\n \u003ch3\u003eInputs\u003c/h3\u003e\n\n \u003cul\u003e\n     \u003cli\u003e\n         SAM format read data\n     \u003c/li\u003e\n     \u003cli\u003e\n         Intervals at which counts will be collected.\n         The argument interval-merging-rule must be set to IntervalMergingRule#OVERLAPPING_ONLY\n         and all other common arguments for interval padding or merging must be set to their defaults.\n     \u003c/li\u003e\n     \u003cli\u003e\n         Output file format.  This can be used to select TSV or HDF5 output.\n     \u003c/li\u003e\n \u003c/ul\u003e\n\n \u003ch3\u003eOutput\u003c/h3\u003e\n\n \u003cul\u003e\n     \u003cli\u003e\n         Counts file.\n         By default, the tool produces HDF5 format results. This can be changed with the format option\n         to TSV format. Using HDF5 files with CreateReadCountPanelOfNormals\n         can decrease runtime, by reducing time spent on IO, so this is the default output format.\n         The HDF5 format contains information in the paths defined in HDF5SimpleCountCollection. HDF5 files may be viewed using\n         \u003ca href\u003d\"https://support.hdfgroup.org/products/java/hdfview/\"\u003ehdfview\u003c/a\u003e or loaded in python using\n         \u003ca href\u003d\"http://www.pytables.org/\"\u003ePyTables\u003c/a\u003e or \u003ca href\u003d\"http://www.h5py.org/\"\u003eh5py\u003c/a\u003e.\n         The TSV format has a SAM-style header containing a read group sample name, a sequence dictionary, a row specifying the column headers contained in\n         SimpleCountCollection.SimpleCountTableColumn, and the corresponding entry rows.\n     \u003c/li\u003e\n \u003c/ul\u003e\n\n \u003ch3\u003eUsage example\u003c/h3\u003e\n\n \u003cpre\u003e\n     gatk CollectReadCounts \\\n          -I sample.bam \\\n          -L intervals.interval_list \\\n          --interval-merging-rule OVERLAPPING_ONLY \\\n          -O sample.counts.hdf5\n \u003c/pre\u003e",
  "name": "CollectReadCounts",
  "group": "Coverage Analysis",
  "beta": true,
  "experimental": false
}