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 outputs(self):
return [
ToolOutput(
"configPickle",
File(),
glob=InputSelector("rundir") + "/runWorkflow.py.config.pickle",
),
ToolOutput("script",
File(),
glob=InputSelector("rundir") + "/runWorkflow.py"),
ToolOutput(
"stats",
Tsv(),
glob=InputSelector("rundir") + "/results/stats/runStats.tsv",
doc=
"A tab-delimited report of various internal statistics from the variant calling process: "
"Runtime information accumulated for each genome segment, excluding auxiliary steps such "
"as BAM indexing and vcf merging. Indel candidacy statistics",
),
ToolOutput(
"indels",
VcfTabix(),
glob=InputSelector("rundir") +
"/results/variants/somatic.indels.vcf.gz",
doc="",
),
ToolOutput(
"snvs",
VcfTabix(),
glob=InputSelector("rundir") +
"/results/variants/somatic.snvs.vcf.gz",
doc="",
),
]
def inputs(self):
return [
*self.additional_inputs,
ToolInput(
"inputBam",
Bam(optional=True),
prefix="-ibam",
doc=
"Input bam file. Note: BAM _must_ be sorted by position. A 'samtools sort <BAM>' should suffice.",
),
ToolInput(
"inputBed",
File(optional=True),
prefix="-iBed",
doc=
"Input bed file. Must be grouped by chromosome. A simple 'sort -k 1,1 <BED> > <BED>.sorted' will suffice.",
),
ToolInput(
"inputFile",
File(optional=True),
prefix="-i",
doc="Input file, can be gff/vcf.",
),
ToolInput(
"genome",
File(optional=True),
prefix="-g",
doc=
"Genome file. The genome file should tab delimited and structured as follows: <chromName><TAB><chromSize>.",
),
]
def inputs(self):
return [
ToolInput(
"bam",
BamBai(),
prefix="-I",
doc="Input file containing sequence data (BAM or CRAM)",
secondaries_present_as={".bai": "^.bai"},
position=10,
),
ToolInput("reference",
FastaWithDict(),
prefix="-R",
doc="Reference sequence file"),
ToolInput(
"outputPrefix",
String(),
prefix="-o",
doc=
"An output file created by the walker. Will overwrite contents if file exists",
),
ToolInput(
"intervals",
File(optional=True),
prefix="-L",
doc="One or more genomic intervals over which to operate",
),
ToolInput(
"excludeIntervals",
File(optional=True),
prefix="--excludeIntervals",
doc="One or more genomic intervals to exclude from processing",
),
*self.additional_args,
]
def outputs(self):
return [
ToolOutput(
"summaryMetrics",
File(),
glob=WildcardSelector(
"*.genotype_concordance_summary_metrics", select_first=True
),
),
ToolOutput(
"detailMetrics",
File(),
glob=WildcardSelector(
"*.genotype_concordance_detail_metrics", select_first=True
),
),
ToolOutput(
"contingencyMetrics",
File(),
glob=WildcardSelector(
"*.genotype_concordance_contingency_metrics", select_first=True
),
),
# ToolOutput("vcf", VcfIdx(optional=True), glob=WildcardSelector("*.vcf"))
]
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 outputs(self) -> List[ToolOutput]:
return [
ToolOutput(
"python", File(), glob=InputSelector("runDir") + "/runWorkflow.py"
),
ToolOutput(
"pickle",
File(),
glob=InputSelector("runDir") + "/runWorkflow.py.config.pickle",
),
ToolOutput(
"candidateSV",
VcfTabix(),
glob=InputSelector("runDir") + "/results/variants/candidateSV.vcf.gz",
),
ToolOutput(
"candidateSmallIndels",
VcfTabix(),
glob=InputSelector("runDir")
+ "/results/variants/candidateSmallIndels.vcf.gz",
),
ToolOutput(
"diploidSV",
VcfTabix(),
glob=InputSelector("runDir") + "/results/variants/diploidSV.vcf.gz",
),
ToolOutput(
"alignmentStatsSummary",
File(),
glob=InputSelector("runDir")
+ "/results/stats/alignmentStatsSummary.txt",
),
ToolOutput(
"svCandidateGenerationStats",
Tsv(),
glob=InputSelector("runDir")
+ "/results/stats/svCandidateGenerationStats.tsv",
),
ToolOutput(
"svLocusGraphStats",
Tsv(),
glob=InputSelector("runDir") + "/results/stats/svLocusGraphStats.tsv",
),
# optional outputs
ToolOutput(
"somaticSV",
VcfTabix(optional=True),
glob=InputSelector("runDir") + "/results/variants/somaticSV.vcf.gz",
),
ToolOutput(
"tumorSV",
VcfTabix(optional=True),
glob=InputSelector("runDir") + "/results/variants/tumorSV.vcf.gz",
),
]
def constructor(self):
self.input("bam", BamBai)
self.input("reference", FastaWithDict)
# optional
self.input("intervals", BedTabix(optional=True))
self.input("is_exome", Boolean(optional=True))
self.input("manta_config", File(optional=True))
self.input("strelka_config", File(optional=True))
self.step(
"manta",
Manta_1_5_0(
bam=self.bam,
reference=self.reference,
callRegions=self.intervals,
exome=self.is_exome,
config=self.manta_config,
),
)
self.step(
"strelka",
StrelkaGermline_2_9_10(
bam=self.bam,
reference=self.reference,
callRegions=self.intervals,
exome=self.is_exome,
config=self.strelka_config,
),
)
# normalise and filter "PASS" variants
self.step(
"splitnormalisevcf",
SplitMultiAllele(
vcf=self.strelka.variants.as_type(CompressedVcf),
reference=self.reference,
),
)
self.step(
"filterpass",
VcfToolsvcftoolsLatest(
vcf=self.splitnormalisevcf.out,
removeFileteredAll=True,
recode=True,
recodeINFOAll=True,
),
)
self.output("sv", source=self.manta.diploidSV)
self.output("variants", source=self.strelka.variants)
self.output("out", source=self.filterpass.out)
def inputs(self):
return [
ToolInput("file", File(optional=True)),
ToolInput("files", Array(File(), optional=True), position=1),
ToolInput(
"number_output",
Boolean(optional=True),
prefix="-n",
doc="Number the output lines, starting at 1.",
),
ToolInput(
"number_non_blank",
Boolean(optional=True),
prefix="-b",
doc="Number the non-blank output lines, starting at 1.",
),
ToolInput(
"disable_output_buffer",
Boolean(optional=True),
prefix="-u",
doc="Disable output buffering.",
),
ToolInput(
"squeeze",
Boolean(optional=True),
prefix="-s",
doc=
"Squeeze multiple adjacent empty lines, causing the output to be single spaced.",
),
ToolInput(
"display_nonprint_and_eol_chars",
Boolean(optional=True),
prefix="-e",
doc=
"Display non-printing characters (see the -v option), and display "
"a dollar sign (`$') at the end of each line.",
),
ToolInput(
"display_nonprint_and_tab_chars",
Boolean(optional=True),
prefix="-t",
doc=
"Display non-printing characters (see the -v option), and display tab characters as `^I'.",
),
ToolInput(
"display_nonprint_chars",
Boolean(optional=True),
prefix="-v",
doc=
"Display non-printing characters so they are visible. Control characters print as `^X' for "
"control-X; the delete character (octal 0177) prints as `^?'. Non-ASCII characters (with the"
" high bit set) are printed as `M-' (for meta) followed by the character for the low 7 bits.",
),
]
def outputs(self):
return [
ToolOutput(
"out_summary",
File(),
glob=InputSelector("outputPrefix") + ".txt",
),
ToolOutput(
"out_purity_png",
File(),
glob=InputSelector("outputPrefix") + "_purity.png",
),
ToolOutput(
"out_purity_seg",
File(),
glob=InputSelector("outputPrefix") + "_purity.seg",
),
ToolOutput(
"out_purity_rds",
File(),
glob=InputSelector("outputPrefix") + "_purity.rds",
),
ToolOutput(
"out_hisens_png",
File(),
glob=InputSelector("outputPrefix") + "_hisens.png",
),
ToolOutput(
"out_hisens_seg",
File(),
glob=InputSelector("outputPrefix") + "_hisens.seg",
),
ToolOutput(
"out_hisens_rds",
File(),
glob=InputSelector("outputPrefix") + "_hisens.rds",
),
ToolOutput(
"out_arm_level",
File(optional=True),
glob=InputSelector("outputPrefix") + ".arm_level.txt",
),
ToolOutput(
"out_gene_level",
File(optional=True),
glob=InputSelector("outputPrefix") + ".gene_level.txt",
),
ToolOutput(
"out_qc",
File(optional=True),
glob=InputSelector("outputPrefix") + ".qc.txt",
),
]
def outputs(self) -> List[ToolOutput]:
return [
ToolOutput("out",
VcfTabix(optional=True),
selector=InputSelector("outputFilename")),
ToolOutput("out_stdout", Stdout),
ToolOutput("out_stats",
File(optional=True, extension=".html"),
selector=InputSelector("statsFile")),
ToolOutput("out_warnings",
File(optional=True, extension=".txt"),
selector=InputSelector("warningFile")),
]
def outputs(self):
return [
ToolOutput(
"unalignedReads",
output_type=Array(FastqGz()),
glob=WildcardSelector("*/*.fastq.gz"),
),
ToolOutput("stats",
output_type=Array(File()),
glob=WildcardSelector("Stats/*")),
ToolOutput("interop",
output_type=Array(File()),
glob=WildcardSelector("InterOp/*")),
]
def outputs(self) -> List[ToolOutput]:
return [
ToolOutput("vcf", Vcf(), glob=WildcardSelector("*.vcf")),
ToolOutput(
"used_options",
File(optional=True),
glob=WildcardSelector("PiscesLogs/*.json"),
),
ToolOutput(
"strandmetrics",
File(optional=True),
glob=WildcardSelector("*ReadStrandBias.txt"),
),
]
def outputs(self):
return [
ToolOutput(
"contOut",
File(),
glob=InputSelector("contaminationFileOut"),
doc="contamination Table",
),
ToolOutput(
"segOut",
File(),
glob=InputSelector("segmentationFileOut"),
doc="segmentation based on baf",
),
]
def outputs(self) -> List[ToolOutput]:
return [
ToolOutput("out", Bam(), glob=WildcardSelector("*")),
ToolOutput("used_options",
File(optional=True),
glob=WildcardSelector("HygeaLogs/*.json")),
]
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) -> 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 [
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 outputs(self) -> List[ToolOutput]:
return [
ToolOutput("std", Stdout),
ToolOutput("out", File, glob=InputSelector("outputFilename")),
ToolOutput(
"stats", File(extension=".html"), glob=InputSelector("statsFile")
),
]
def outputs(self):
return [
ToolOutput("out", TextFile(), glob=InputSelector("outputFilename")),
ToolOutput(
"outHistogram",
File(extension=".pdf"),
glob=InputSelector("outputHistogram"),
),
]
def outputs(self) -> List[ToolOutput]:
return [
ToolOutput("vcf",
Vcf(optional=True),
glob=WildcardSelector("*.vcf.recal")),
ToolOutput(
"used_options",
File(optional=True),
glob=WildcardSelector("VQRLogs/*.json"),
),
]
def outputs(self) -> List[ToolOutput]:
return [
ToolOutput(
"configPickle",
File(),
glob=InputSelector("relativeStrelkaDirectory") +
"/runWorkflow.py.config.pickle",
),
ToolOutput(
"script",
File(),
glob=InputSelector("relativeStrelkaDirectory") +
"/runWorkflow.py",
),
ToolOutput(
"stats",
Tsv(),
glob=InputSelector("relativeStrelkaDirectory") +
"/results/stats/runStats.tsv",
doc=
"A tab-delimited report of various internal statistics from the variant calling process: "
"Runtime information accumulated for each genome segment, excluding auxiliary steps such "
"as BAM indexing and vcf merging. Indel candidacy statistics",
),
ToolOutput(
"variants",
VcfTabix(),
glob=InputSelector("relativeStrelkaDirectory") +
"/results/variants/variants.vcf.gz",
doc=
"Primary variant inferences are provided as a series of VCF 4.1 files",
),
ToolOutput(
"genome",
VcfTabix(),
glob=InputSelector("relativeStrelkaDirectory") +
"/results/variants/genome.vcf.gz",
),
]
def inputs(self) -> List[ToolInput]:
return [
ToolInput("file", File(), position=100, doc="File to bgzip compress"),
ToolInput(
"outputFilename",
Filename(
prefix=InputSelector("file").basename(),
extension=".gz",
),
position=102,
),
*self.additional_args,
]
def inputs(self):
return [
ToolInput("inp", str),
ToolInput("inpOptional", Optional[str]),
ToolInput("fileInp", File(extension=".txt")),
ToolInput("fileInpOptional", File(extension=".txt",
optional=True)),
ToolInput(
"generatedInp",
Filename(prefix=InputSelector("inp"), extension=""),
position=0,
),
ToolInput(
"generatedInpOptional",
Filename(prefix=InputSelector("inpOptional")),
position=0,
),
ToolInput(
"generatedFileInp",
Filename(
prefix=InputSelector("fileInp",
remove_file_extension=True),
suffix=".transformed",
extension=".fnp",
),
position=0,
),
ToolInput(
"generatedFileInpOptional",
Filename(
prefix=InputSelector("fileInpOptional",
remove_file_extension=True),
suffix=".optional",
extension=".txt",
),
position=0,
),
]
def constructor(self):
self.input("normalBam", CramCrai)
self.input("tumorBam", CramCrai)
self.input("reference", FastaFai)
self.input("callRegions", BedTabix(optional=True))
self.input("exome", Boolean(optional=True), default=False)
self.input("configStrelka", File(optional=True))
self.step(
"manta",
Manta(
bam=self.normalBam,
tumorBam=self.tumorBam,
reference=self.reference,
callRegions=self.callRegions,
exome=self.exome,
),
)
self.step(
"strelka",
Strelka(
indelCandidates=self.manta.candidateSmallIndels,
normalBam=self.normalBam,
tumorBam=self.tumorBam,
reference=self.reference,
callRegions=self.callRegions,
exome=self.exome,
config=self.configStrelka,
),
)
self.step(
"normaliseSNVs",
BcfToolsNorm(vcf=self.strelka.snvs, reference=self.reference),
)
self.step("indexSNVs", BcfToolsIndex(vcf=self.normaliseSNVs.out))
self.step(
"normaliseINDELs",
BcfToolsNorm(vcf=self.strelka.indels, reference=self.reference),
)
self.step("indexINDELs", BcfToolsIndex(vcf=self.normaliseINDELs.out))
self.output("diploid", source=self.manta.diploidSV)
self.output("candIndels", source=self.manta.candidateSmallIndels)
self.output("indels", source=self.indexINDELs.out)
self.output("snvs", source=self.indexSNVs.out)
self.output("somaticSVs", source=self.manta.somaticSVs)
def inputs(self):
return [
ToolInput(
"inputFile",
File(),
prefix="-i",
doc="Gatk3 DepthOfCoverage interval_summary output",
),
ToolInput(
"outputFilename",
Filename(extension=".txt"),
prefix="-o",
doc="Output file name",
),
ToolInput("bed", Bed(), prefix="-bed", doc="Annotated bed file"),
]
def process_subpipeline(**connections):
w = WorkflowBuilder("somatic_subpipeline")
w.input("reference", FastaWithDict)
w.input("reads", Array(FastqGzPair))
w.input("cutadapt_adapters", File(optional=True))
w.input("sample_name", String)
w.step("fastqc", FastQC_0_11_5(reads=w.reads), scatter="reads")
w.step(
"getfastqc_adapters",
ParseFastqcAdaptors(
fastqc_datafiles=w.fastqc.datafile,
cutadapt_adaptors_lookup=w.cutadapt_adapters,
),
scatter="fastqc_datafiles",
)
w.step(
"align_and_sort",
BwaAligner(
fastq=w.reads,
reference=w.reference,
sample_name=w.sample_name,
sortsam_tmpDir=".",
cutadapt_adapter=w.getfastqc_adapters,
cutadapt_removeMiddle3Adapter=w.getfastqc_adapters,
),
scatter=[
"fastq", "cutadapt_adapter", "cutadapt_removeMiddle3Adapter"
],
)
w.step(
"merge_and_mark",
MergeAndMarkBams_4_1_3(bams=w.align_and_sort.out,
sampleName=w.sample_name),
)
w.output("out", source=w.merge_and_mark.out)
w.output("reports",
source=w.fastqc.out,
output_folder=[w.sample_name, "reports"])
return w(**connections)
def constructor(self):
self.input("normalBam", self.getStrelka2InputType())
self.input("tumorBam", self.getStrelka2InputType())
self.input("reference", FastaFai)
self.input("callRegions", BedTabix(optional=True))
self.input("exome", Boolean(optional=True), default=False)
self.input("configStrelka", File(optional=True))
self.input("indelCandidates", Array(VcfTabix))
self.input("strelkaSNVs", Array(VcfTabix))
# self.input("strelkaIndels", Array(VcfTabix))
self.step(
"strelka2pass",
self.getStrelka2Tool()(
indelCandidates=self.indelCandidates,
# indelCandidates=self.strelkaIndels,
forcedgt=self.strelkaSNVs,
normalBam=self.normalBam,
tumorBam=self.tumorBam,
reference=self.reference,
callRegions=self.callRegions,
exome=self.exome,
config=self.configStrelka,
),
)
self.step(
"normaliseSNVs",
BcfToolsNorm(vcf=self.strelka2pass.snvs, reference=self.reference),
)
self.step("indexSNVs", BcfToolsIndex(vcf=self.normaliseSNVs.out))
self.step(
"normaliseINDELs",
BcfToolsNorm(vcf=self.strelka2pass.indels,
reference=self.reference),
)
self.step("indexINDELs", BcfToolsIndex(vcf=self.normaliseINDELs.out))
self.output("indels", source=self.indexINDELs.out)
self.output("snvs", source=self.indexSNVs.out)
def inputs(self):
return [
*super(Gatk4CalculateContaminationBase, self).inputs(),
*Gatk4CalculateContaminationBase.additional_args,
ToolInput(
"pileupTable",
File(),
prefix="-I",
doc="pileup table from summarize pileup",
),
ToolInput(
"segmentationFileOut",
Filename(),
prefix="--tumor-segmentation",
doc="Reference sequence file",
),
ToolInput("contaminationFileOut",
Filename(),
position=2,
prefix="-O"),
]
def inputs(self) -> List[ToolInput]:
return [
ToolInput("reference",
FastaWithDict(),
position=3,
shell_quote=False),
ToolInput("reference_alt", File(), position=9, shell_quote=False),
ToolInput("reads", FastqGzPair, position=4, shell_quote=False),
ToolInput(
"mates",
FastqGzPair(optional=True),
separator=" ",
position=5,
shell_quote=False,
doc=None,
),
ToolInput(
"outputFilename",
Filename(prefix=InputSelector("sampleName"), extension=".bam"),
shell_quote=False,
prefix="-o",
position=13,
doc="output file name [stdout]",
),
ToolInput(
"sampleName",
String(),
doc="Used to construct the readGroupHeaderLine with format: "
"'@RG\\tID:{name}\\tSM:{name}\\tLB:{name}\\tPL:ILLUMINA'",
),
ToolInput(
"platformTechnology",
String(optional=True),
doc=
"(ReadGroup: PL) Used to construct the readGroupHeaderLine, defaults: ILLUMINA",
default="ILLUMINA",
),
*self.bwa_additional_inputs,
*self.samtools_additional_args,
]