def inputs(self):
return [
*super(Gatk4CollectInsertSizeMetricsBase, self).inputs(),
ToolInput(
"bam",
BamBai(optional=False),
prefix="-I",
doc="Input SAM or BAM file. Required.",
position=10,
),
ToolInput(
"outputFilename",
Filename(
prefix=InputSelector("bam", remove_file_extension=True),
extension=".txt",
suffix=".metrics",
),
prefix="-O",
doc="File to write the output to. Required.",
),
ToolInput(
"outputHistogram",
Filename(
prefix=InputSelector("bam", remove_file_extension=True),
extension=".pdf",
suffix=".histogram",
),
prefix="-H",
doc="File to write insert size Histogram chart to. Required. ",
),
*Gatk4CollectInsertSizeMetricsBase.additional_args,
]
def inputs(self):
return [
ToolInput(
"bam",
BamBai(),
prefix="-I",
position=10,
secondaries_present_as={".bai": "^.bai"},
doc=
"One or more input SAM or BAM files to analyze. Must be coordinate sorted.",
),
ToolInput(
"outputFilename",
Filename(extension=".bam"),
position=10,
prefix="-O",
doc="File to write duplication metrics to",
),
ToolInput(
"metricsFilename",
Filename(extension=".metrics.txt"),
position=10,
prefix="-M",
doc="The output file to write marked records to.",
),
*super(Gatk4MarkDuplicatesBase, self).inputs(),
*self.additional_args,
]
def inputs(self):
return [
*super().inputs(),
*Gatk4CalculateContaminationBase.additional_args,
ToolInput(
"pileupTable",
File(),
prefix="-I",
doc="pileup table from summarize pileup",
),
ToolInput(
"segmentationFileOut",
Filename(
prefix=InputSelector("pileupTable",
remove_file_extension=True),
extension=".mutect2_segments",
),
prefix="--tumor-segmentation",
doc="Reference sequence file",
),
ToolInput(
"contaminationFileOut",
Filename(
prefix=InputSelector("pileupTable",
remove_file_extension=True),
extension=".mutect2_contamination",
),
position=2,
prefix="-O",
),
]
def inputs(self):
return [
ToolInput("bams", Array(Bam()), position=10),
ToolInput("reference",
FastaWithDict(),
position=1,
prefix="--reference"),
ToolInput(
"outputFilename",
Filename(suffix=".svs", extension=".vcf"),
position=2,
prefix="--output",
),
ToolInput(
"assemblyFilename",
Filename(suffix=".assembled", extension=".bam"),
position=3,
prefix="--assembly",
),
ToolInput("threads",
Int(optional=True),
default=CpuSelector(),
prefix="--threads"),
ToolInput("blacklist",
Bed(optional=True),
position=4,
prefix="--blacklist"),
ToolInput("tmpdir",
String(optional=True),
default="./TMP",
prefix="--workingdir"),
]
def inputs(self) -> List[ToolInput]:
import uuid
fastq_uuid = str(uuid.uuid1())
return [
ToolInput("fastq", FastqGzPair, position=5),
ToolInput(
"adapter",
input_type=Array(String(), optional=True),
prefix="-a",
prefix_applies_to_all_elements=True,
doc=
"Sequence of an adapter ligated to the 3' end (paired data: of the first read). "
"The adapter and subsequent bases are trimmed. If a '$' character is appended ('anchoring'), "
"the adapter is only found if it is a suffix of the read.",
),
ToolInput(
"outputFilename",
Filename(suffix="-R1", extension=".fastq.gz"),
prefix="-o",
doc=
"Write trimmed reads to FILE. FASTQ or FASTA format is chosen depending on input. "
"The summary report is sent to standard output. Use '{name}' in FILE to demultiplex "
"reads into multiple files. Default: write to standard output",
),
ToolInput(
"secondReadFile",
Filename(suffix="-R2", extension=".fastq.gz"),
prefix="-p",
doc="Write second read in a pair to FILE.",
),
*self.additional_args,
]
def inputs(self):
# Would be good to include this in the prefix:
# If(InputSelector("bam").length().equals(1), InputSelector("bam")[0].basename(), None)
prefix = FirstOperator([InputSelector("outputPrefix"), "generated"])
return [
ToolInput(
"bam",
Array(Bam),
prefix="-I",
position=10,
# secondaries_present_as={".bai": "^.bai"},
doc=
"One or more input SAM or BAM files to analyze. Must be coordinate sorted.",
),
ToolInput("outputPrefix", String(optional=True)),
ToolInput(
"outputFilename",
Filename(prefix=prefix, suffix=".markduped", extension=".bam"),
position=10,
prefix="-O",
doc="File to write duplication metrics to",
),
ToolInput(
"metricsFilename",
Filename(prefix=prefix, suffix=".metrics", extension=".txt"),
position=10,
prefix="-M",
doc="The output file to write marked records to.",
),
*super().inputs(),
*self.additional_args,
]
def test_input_value_filename_nostringenv(self):
fn = Filename()
self.assertEqual(
'"%s"' % fn.generated_filename(),
wdl.get_input_value_from_potential_selector_or_generator(
fn, None, string_environment=False),
)
def test_input_value_filename_stringenv(self):
import uuid
fn = Filename(guid=str(uuid.uuid4()))
self.assertEqual(
fn.generated_filename(),
wdl.get_input_value_from_potential_selector_or_generator(
fn, None, string_environment=True
),
)
def inputs(self):
return [
*super(Gatk4HaplotypeCallerBase, self).inputs(),
*Gatk4HaplotypeCallerBase.optional_args,
ToolInput(
"inputRead",
BamBai(),
doc="BAM/SAM/CRAM file containing reads",
prefix="--input",
secondaries_present_as={".bai": "^.bai"},
),
ToolInput(
"reference",
FastaWithDict(),
position=5,
prefix="--reference",
doc="Reference sequence file",
),
ToolInput(
"outputFilename",
Filename(
prefix=InputSelector("inputRead",
remove_file_extension=True),
extension=".vcf.gz",
),
position=8,
prefix="--output",
doc="File to which variants should be written",
),
ToolInput(
"dbsnp",
VcfTabix(optional=True),
position=7,
prefix="--dbsnp",
doc="(Also: -D) A dbSNP VCF file.",
),
ToolInput(
"intervals",
Bed(optional=True),
prefix="--intervals",
doc=
"-L (BASE) One or more genomic intervals over which to operate",
),
ToolInput(
"outputBamName",
Filename(
prefix=InputSelector("inputRead",
remove_file_extension=True),
extension=".bam",
),
position=8,
prefix="-bamout",
doc="File to which assembled haplotypes should be written",
),
]
def inputs(self) -> List[ToolInput]:
return [
ToolInput(
"outputFilename",
Filename(extension=".vcf", suffix=".combined"),
prefix="-o",
),
ToolInput(
"regions",
Filename(extension=".tsv"),
prefix="--regions",
doc=
"Region file containing all the variants, used as samtools mpileup",
),
ToolInput(
"vcfs",
Array(Vcf()),
prefix="-i",
prefix_applies_to_all_elements=True,
doc=
"input vcfs, the priority of the vcfs will be based on the order of the input",
),
ToolInput("type",
String(),
prefix="--type",
doc="germline | somatic"),
ToolInput(
"columns",
Array(String(), optional=True),
prefix="--columns",
prefix_applies_to_all_elements=True,
doc="Columns to keep, seperated by space output vcf (unsorted)",
),
ToolInput(
"normal",
String(optional=True),
prefix="--normal",
doc=
"Sample id of germline vcf, or normal sample id of somatic vcf",
),
ToolInput(
"tumor",
String(optional=True),
prefix="--tumor",
doc="tumor sample ID, required if inputs are somatic vcfs",
),
ToolInput(
"priority",
Int(optional=True),
prefix="--priority",
doc=
"The priority of the callers, must match with the callers in the source header",
),
]
def inputs(self):
return [
*super().inputs(),
ToolInput(
"callVCF",
VcfTabix(),
prefix="--CALL_VCF",
doc="The VCF containing the call sample",
),
ToolInput(
"truthVCF",
VcfIdx(),
prefix="--TRUTH_VCF",
doc="The VCF containing the truth sample",
),
ToolInput(
"outputBasename",
Filename(),
prefix="--OUTPUT",
doc="Basename for the three metrics files that are to be written. Resulting files will be:"
"(1) .genotype_concordance_summary_metrics, "
"(2) .genotype_concordance_detail_metrics, "
"(3) .genotype_concordance_contingency_metrics.",
),
# *super(Gatk4GenotypeConcordanceBase, self).inputs(),
*self.additional_args,
]
def inputs(self) -> List[ToolInput]:
return [
ToolInput("intervals", Bed(), position=2, shell_quote=False),
ToolInput(
"outputFilename",
Filename(extension=".vcf", suffix=".vardict"),
prefix=">",
position=6,
shell_quote=False,
),
ToolInput(
"bam",
BamBai(),
prefix="-b",
position=1,
shell_quote=False,
doc="The indexed BAM file",
),
ToolInput(
"reference",
FastaFai(),
prefix="-G",
position=1,
shell_quote=False,
doc="The reference fasta. Should be indexed (.fai). "
"Defaults to: /ngs/reference_data/genomes/Hsapiens/hg19/seq/hg19.fa",
),
*VarDictGermlineBase.vardict_inputs,
*VarDictGermlineBase.var2vcf_inputs,
]
def inputs(self):
return [
*super(Gatk4ApplyBqsrBase, self).inputs(),
ToolInput(
"bam",
BamBai(),
prefix="-I",
doc="The SAM/BAM/CRAM file containing reads.",
secondaries_present_as={".bai": "^.bai"},
position=10,
),
ToolInput(
"reference", FastaWithDict(), prefix="-R", doc="Reference sequence"
),
ToolInput(
"outputFilename",
Filename(extension=".bam"),
prefix="-O",
doc="Write output to this file",
),
ToolInput(
"recalFile",
Tsv(optional=True),
prefix="--bqsr-recal-file",
doc="Input recalibration table for BQSR",
),
ToolInput(
"intervals",
Bed(optional=True),
prefix="--intervals",
doc="-L (BASE) One or more genomic intervals over which to operate",
),
*self.additional_args,
]
def inputs(self):
return [
ToolInput(
"kmer_size",
Int(optional=True),
prefix="-k",
position=1,
doc="k-mer (odd) length (default: 31, max value: 31)",
),
ToolInput(
"index",
Filename(extension=".kidx"),
prefix="-i",
position=2,
doc="Filename for the kallisto index to be constructed",
),
ToolInput(
"reference",
Fasta,
position=3,
localise_file=True,
doc="Filename for a reference transcriptome",
),
# --make-unique Replace repeated target names with unique names
]
def inputs(self):
return [
ToolInput(
"flagstat",
File(),
prefix="--flagstat",
doc="output of samtools flagstat on bam",
),
ToolInput(
"collectInsertSizeMetrics",
File,
prefix="--collect_insert_metrics",
doc="output of CollectInsertMetrics (GATK or Picard) on bam",
),
ToolInput(
"coverage",
File(),
prefix="--coverage",
doc="output of bedtools coverageBed for targeted bam; bedtools genomeCoverageBed for whole genome bam",
),
ToolInput(
"outputPrefix",
Filename(extension=".csv"),
prefix="-o",
doc="prefix of output summary csv",
),
*self.additional_args,
]
def inputs(self):
return [
*super(Gatk4SortSamBase, self).inputs(),
ToolInput(
"bam",
Bam(),
prefix="-I",
doc="The SAM/BAM/CRAM file to sort.",
position=10,
),
ToolInput(
"outputFilename",
Filename(
prefix=InputSelector("bam", remove_file_extension=True),
suffix=".sorted",
extension=".bam",
),
position=10,
prefix="-O",
doc="The sorted SAM/BAM/CRAM output file.",
),
ToolInput(
"sortOrder",
String(),
prefix="-SO",
position=10,
doc=
"The --SORT_ORDER argument is an enumerated type (SortOrder), which can have one of "
"the following values: [unsorted, queryname, coordinate, duplicate, unknown]",
),
*Gatk4SortSamBase.additional_args,
]
def inputs(self):
return [
*super().inputs(),
*Gatk4GetPileUpSummariesBase.additional_args,
ToolInput(
"bam",
Array(BamBai()),
prefix="-I",
prefix_applies_to_all_elements=True,
doc="The SAM/BAM/CRAM file containing reads.",
position=0,
),
ToolInput(
"sites",
VcfTabix(),
prefix="-V",
doc="sites of common biallelic variants",
),
ToolInput(
"intervals",
VcfTabix(optional=True),
prefix="--intervals",
doc=
"-L (BASE) One or more genomic intervals over which to operate",
),
ToolInput("pileupTableOut",
Filename(extension=".txt"),
position=1,
prefix="-O"),
]
def test_resolve_filename_in_inpselect(self):
fn = Filename(extension=".ext")
ti = {"ti": ToolInput("ti", fn)}
b = StringFormatter("fn: {place}", place=InputSelector("ti"))
res = wdl.get_input_value_from_potential_selector_or_generator(b, ti)
self.assertEqual(
f'fn: ~{{select_first([ti, "{fn.generated_filename()}"])}}', res)
def inputs(self):
return [
*super(Gatk4LearnReadOrientationModelBase, self).inputs(),
*Gatk4LearnReadOrientationModelBase.additional_args,
ToolInput(
"f1r2CountsFiles",
Array(TarFileGz),
position=0,
prefix="-I",
prefix_applies_to_all_elements=True,
doc="Counts for the read orientation of fragments",
),
ToolInput(
"numEmIterations",
Int(optional=True),
position=1,
prefix="--num-em-iterations",
default=30, # Sebastian thinks this is best
doc="Amount of iterations for the em process before it bails",
),
ToolInput("modelFileOut",
Filename(extension=".tar.gz"),
position=3,
prefix="-O"),
]
def inputs(self) -> List[ToolInput]:
return [
ToolInput("vcf", Vcf(optional=True), position=1,
shell_quote=False),
ToolInput(
"compressedTabixVcf",
VcfTabix(optional=True),
position=1,
shell_quote=False,
),
ToolInput(
"compressedVcf",
CompressedVcf(optional=True),
position=1,
shell_quote=False,
),
ToolInput(
"reference",
FastaWithDict(),
prefix="-r",
position=4,
shell_quote=False,
),
ToolInput(
"outputFilename",
Filename(extension=".vcf", suffix=".norm"),
position=6,
prefix="-o",
shell_quote=False,
),
]
def inputs(self):
return [
*super().inputs(),
ToolInput(
"bams",
Array(BamBai()),
prefix="-I",
prefix_applies_to_all_elements=True,
doc="The SAM/BAM file to sort.",
position=10,
),
ToolInput(
"sampleName",
String(optional=True),
doc="Used for naming purposes only",
),
ToolInput(
"outputFilename",
Filename(
prefix=InputSelector("sampleName"),
suffix=".merged",
extension=".bam",
),
position=10,
prefix="-O",
doc="SAM/BAM file to write merged result to",
),
*self.additional_args,
]
def inputs(self):
return [
ToolInput(
"ubam",
BamBai(),
prefix="--UNMAPPED_BAM",
prefix_applies_to_all_elements=True,
doc=
"Original SAM or BAM file of unmapped reads, which must be in queryname order.",
position=10,
),
ToolInput(
"bam",
Array(BamBai()),
prefix="--ALIGNED_BAM",
prefix_applies_to_all_elements=True,
doc="SAM or BAM file(s) with alignment data.",
position=10,
),
ToolInput(
"reference",
FastaWithDict(optional=True),
prefix="--REFERENCE_SEQUENCE",
position=10,
doc="Reference sequence file.",
),
ToolInput(
"outputFilename",
Filename(extension=".bam"),
position=10,
prefix="--OUTPUT",
doc="Merged SAM or BAM file to write to.",
),
*self.additional_args,
]
def inputs(self):
return [
ToolInput(
"vcf",
UnionType(Vcf, CompressedVcf),
position=1,
doc="The VCF file to sort",
),
ToolInput(
"outputFilename",
Filename(suffix=".sorted", extension=".vcf.gz"),
prefix="--output-file",
doc="(-o) output file name [stdout]",
),
ToolInput(
"outputType",
String(optional=True),
prefix="--output-type",
default="z",
doc="(-O) b: compressed BCF, u: uncompressed BCF, z: compressed VCF, v: uncompressed VCF [v]",
),
ToolInput(
"tempDir",
String(optional=True),
prefix="--temp-dir",
doc="(-T) temporary files [/tmp/bcftools-sort.XXXXXX/]",
),
]
def inputs(self):
return [
*self.additional_inputs,
ToolInput(
"bam",
Array(Bam),
position=10,
doc=
"A list of SAM or BAM format files. They can be either name or location sorted. If no files provided, <stdin> input is expected. Location-sorted paired-end reads are automatically sorted by read names.",
),
ToolInput(
"outputFilename",
Filename(extension=".txt"),
prefix="-o",
doc=
"Name of output file including read counts. A separate file including summary statistics of counting results is also included in the output ('<string>.summary'). Both files are in tab delimited format.",
),
ToolInput(
"annotationFile",
File,
prefix="-a",
doc=
"Name of an annotation file. GTF/GFF format by default. See -F option for more format information. Inbuilt annotations (SAF format) is available in 'annotation' directory of the package. Gzipped file is also accepted.",
),
]
def inputs(self):
return [
*super(SamToolsViewBase, self).inputs(),
*SamToolsViewBase.additional_inputs,
ToolInput("sam", UnionType(Sam(), Bam(), Cram()), position=10),
ToolInput(
"reference",
FastaWithDict(optional=True),
position=6,
prefix="-T",
doc=
"A FASTA format reference FILE, optionally compressed by bgzip and ideally indexed "
"by samtools faidx. If an index is not present, one will be generated for you.",
),
ToolInput(
"outputFilename",
Filename(
prefix=InputSelector("sam", remove_file_extension=True),
extension=".bam",
),
position=5,
prefix="-o",
doc="Output to FILE [stdout].",
),
ToolInput(
"regions",
Array(String, optional=True),
position=11,
doc=
"Region specifications after the input filename to restrict output to only those alignments which "
"overlap the specified region(s). Use of region specifications requires a coordinate-sorted and "
"indexed input file (in BAM or CRAM format)",
),
]
def inputs(self) -> List[ToolInput]:
return [
ToolInput(
"vcf",
UnionType(Vcf, CompressedVcf),
position=1,
doc="Input vcf",
),
ToolInput(
"outputFilename",
Filename(
InputSelector("vcf", remove_file_extension=True),
suffix=".fill",
extension=".vcf",
),
position=6,
doc="Output vcf",
),
ToolInput(
"column",
String(),
prefix="--column",
position=3,
doc="REF or INFO tag, e.g. AA for ancestral allele",
),
ToolInput("fasta",
Fasta(),
prefix="--fasta",
position=3,
doc="fasta file"),
ToolInput(
"header_lines",
File(optional=True),
prefix="--header-lines",
position=3,
doc="optional file containing header lines to append",
),
ToolInput(
"include",
String(optional=True),
prefix="--include",
position=3,
doc="annotate only records passing filter expression",
),
ToolInput(
"exclude",
String(optional=True),
prefix="--exclude",
position=3,
doc="annotate only records failing filter expression",
),
ToolInput(
"replace_non_ACGTN",
Boolean(optional=True),
prefix="--replace-non-ACGTN",
position=3,
doc="replace non-ACGTN characters with N",
),
]
def inputs(self):
return [
*super().inputs(),
*Gatk4GetPileUpSummariesBase.additional_args,
ToolInput(
"bam",
Array(BamBai()),
prefix="-I",
prefix_applies_to_all_elements=True,
doc="The SAM/BAM/CRAM file containing reads.",
position=0,
),
ToolInput(
"sampleName", String(optional=True), doc="Used for naming purposes"
),
ToolInput(
"sites",
VcfTabix(),
prefix="-V",
doc="sites of common biallelic variants",
),
ToolInput(
"intervals",
Bed(optional=True),
prefix="--intervals",
doc="-L (BASE) One or more genomic intervals over which to operate",
),
ToolInput(
"pileupTableOut",
Filename(
prefix=JoinOperator(
FilterNullOperator(
[
FirstOperator(
[InputSelector("sampleName"), "generated"]
),
# If(
# IsDefined(InputSelector("intervals")),
# InputSelector(
# "intervals", remove_file_extension=True
# ),
# "",
# ),
]
),
".",
),
extension=".txt",
),
position=1,
prefix="-O",
),
ToolInput(
"reference",
FastaWithDict(optional=True),
prefix="-R",
doc="reference to use when decoding CRAMS",
),
]
def inputs(self):
return [
ToolInput("files", Array(File()), position=2, localise_file=True),
ToolInput(
"files2", Array(File(), optional=True), position=3, localise_file=True
),
ToolInput("outputFilename", Filename(extension=".tar"), position=1),
]
def inputs(self):
return [
ToolInput(
"listFile",
File(optional=True),
prefix="--list",
doc=
"List file: A tsv file contains SampleName\tPathToBedtoolsOutput on each line",
),
ToolInput(
"sampleName",
String(optional=True),
prefix="--name",
doc="Sample name if list not used",
),
ToolInput(
"bedtoolsOutputPath",
File(optional=True),
prefix="--path",
doc="Path to bedtools output if list not used",
),
ToolInput(
"outputGeneFile",
Filename(extension=".txt", suffix=".gene"),
prefix="--gene",
doc="Output gene file",
),
ToolInput(
"outputRegionFile",
Filename(extension=".txt", suffix=".region"),
prefix="--region",
doc="Output region file",
),
ToolInput(
"fold",
String(optional=True),
prefix="--fold",
doc="Folds, quoted and commna sepparated, default 1,10,20,100",
),
ToolInput(
"threads",
Int(optional=True),
prefix="--threads",
doc="number of threads, default:32",
),
]
def inputs(self):
return [
ToolInput("reference", FastaBwa(), position=9),
ToolInput("reads", Array(FastqGz()), position=10, doc=None),
ToolInput("mates", FastqGzPair(optional=True), position=11, doc=None),
ToolInput("outputFilename", Filename(extension=".sam")),
*BwaMemBase.additional_inputs,
]
