def outputs(self) -> List[ToolOutput]:
return [
ToolOutput(
"out",
ZipFile(),
glob=InputSelector("read", remove_file_extension=True) +
"_fastqc.zip",
),
ToolOutput(
"out_datafile",
File,
glob=InputSelector("read", remove_file_extension=True) +
"_fastqc/fastqc_data.txt",
),
ToolOutput(
"out_html",
HtmlFile,
glob=InputSelector("read", remove_file_extension=True) +
"_fastqc.html",
),
ToolOutput(
"out_directory",
Directory,
selector=InputSelector("read", remove_file_extension=True) +
"_fastqc",
),
]
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 test_string_formatter(self):
wf = WorkflowBuilder("wf")
wf.input("sampleName", str)
wf.input("platform", str)
wf.input(
"readGroupHeaderLine",
String(optional=True),
default=StringFormatter(
"@RG\\tID:{name}\\tSM:{name}\\tLB:{name}\\tPL:{pl}",
name=InputSelector("sampleName"),
pl=InputSelector("platform"),
),
)
wf.step("print", EchoTestTool(inp=wf.readGroupHeaderLine))
wf.output("out", source=wf.print)
d, _ = cwl.CwlTranslator.translate_workflow(
wf, with_container=False, allow_empty_container=True
)
stepinputs = d.save()["steps"][0]["in"]
self.assertEqual(4, len(stepinputs))
expression = stepinputs[-1]["valueFrom"]
expected = (
"$((inputs._print_inp_readGroupHeaderLine != null) "
"? inputs._print_inp_readGroupHeaderLine "
': "@RG\\\\tID:{name}\\\\tSM:{name}\\\\tLB:{name}\\\\tPL:{pl}".replace(/\\{name\\}/g, inputs._print_inp_sampleName).replace(/\\{pl\\}/g, inputs._print_inp_platform))'
)
self.assertEqual(expected, expression)
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 outputs(self):
return [
ToolOutput(
"out",
VcfTabix,
glob=InputSelector("outputFilename"),
doc="To determine type",
),
ToolOutput(
"stats",
TextFile(extension=".stats"),
glob=InputSelector("outputFilename") + ".stats",
doc="To determine type",
),
ToolOutput(
"f1f2r_out",
TarFileGz,
glob=InputSelector("f1r2TarGz_outputFilename"),
doc="To determine type",
),
ToolOutput(
"bam",
BamBai(optional=True),
glob=InputSelector("outputBamName"),
doc="File to which assembled haplotypes should be written",
secondaries_present_as={".bai": "^.bai"},
),
]
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 outputs(self):
return [
ToolOutput("out", Vcf(), glob=InputSelector("outputFilename")),
ToolOutput("assembly",
Bam(),
glob=InputSelector("assemblyFilename")),
]
def outputs(self) -> List[ToolOutput]:
return [
ToolOutput("std", Stdout),
ToolOutput("out", File, glob=InputSelector("outputFilename")),
ToolOutput(
"stats", File(extension=".html"), glob=InputSelector("statsFile")
),
]
def test_evaluate_from_input_selector_resolved(self):
namesel = InputSelector("name")
adjsel = InputSelector("adjsel")
b = StringFormatter("{name} is {adjective}",
name=namesel,
adjective=adjsel)
inp = {"name": "Janis", "adjsel": "pretty good"}
self.assertEqual("Janis is pretty good", b.evaluate(inp))
def arguments(self):
return [
# BWA MEM command
ToolArgument("bwa", position=0, shell_quote=False),
ToolArgument("mem", position=1, shell_quote=False),
ToolArgument(
StringFormatter(
"@RG\\tID:{name}\\tSM:{name}\\tLB:{name}\\tPL:{pl}",
name=InputSelector("sampleName"),
pl=InputSelector("platformTechnology"),
),
prefix="-R",
position=3,
doc="Complete read group header line.",
),
ToolArgument(
CpuSelector(),
prefix="-t",
position=3,
shell_quote=False,
doc="Number of threads. (default = 1)",
),
ToolArgument("|", position=6, shell_quote=False),
# Alt Aware Post Processing command
ToolArgument("k8", position=7, shell_quote=False),
ToolArgument("/opt/conda/bin/bwa-postalt.js",
position=7,
shell_quote=False),
# Samtools View command
ToolArgument("|", position=10, shell_quote=False),
ToolArgument("samtools", position=11, shell_quote=False),
ToolArgument("view", position=12, shell_quote=False),
ToolArgument(
InputSelector("reference"),
prefix="-T",
position=13,
shell_quote=False,
),
ToolArgument(
CpuSelector(),
position=13,
prefix="--threads",
doc="(@) Number of additional threads to use [0]",
shell_quote=False,
),
ToolArgument(
"-h",
position=13,
shell_quote=False,
doc="Include header in the output",
),
ToolArgument(
"-b",
position=13,
shell_quote=False,
doc="Output in the BAM format.",
),
]
def outputs(self):
return [
ToolOutput("out",
File,
glob=InputSelector("outdir") + "/abundance.tsv"),
ToolOutput("stats",
File,
glob=InputSelector("outdir") + "/run_info.json"),
]
def outputs(self):
return [
ToolOutput("out", TextFile(), glob=InputSelector("outputFilename")),
ToolOutput(
"outHistogram",
File(extension=".pdf"),
glob=InputSelector("outputHistogram"),
),
]
def outputs(self):
return [
ToolOutput("geneFileOut",
TextFile(),
glob=InputSelector("outputGeneFile")),
ToolOutput("regionFileOut",
TextFile(),
glob=InputSelector("outputRegionFile")),
]
def outputs(self):
return [
ToolOutput("out", Tsv, selector=InputSelector("output_filename")),
ToolOutput(
"out_discarded",
Tsv,
selector=InputSelector("discarded_output_filename"),
),
]
def test_dotproduct_string_formatter(self):
sf = StringFormatter("iteration_{i}_{j}",
i=InputSelector("it1"),
j=InputSelector("it2"))
sfs = sf.evaluate({"it1": [1, 2, 3], "it2": ["a", "b", "c"]})
self.assertEqual(3, len(sfs))
self.assertEqual("iteration_1_a", sfs[0])
self.assertEqual("iteration_2_b", sfs[1])
self.assertEqual("iteration_3_c", sfs[2])
def outputs(self):
return [
ToolOutput(
"out",
BamBai,
glob=InputSelector("outputFilename"),
secondaries_present_as={".bai": "^.bai"},
),
ToolOutput("metrics", Tsv(), glob=InputSelector("metricsFilename")),
]
def outputs(self) -> List[ToolOutput]:
return [
ToolOutput("vcf", Vcf(), glob=InputSelector("outputFilename")),
ToolOutput(
"assembly",
BamBai(),
glob=InputSelector("assemblyFilename"),
secondaries_present_as={".bai": "^.bai"},
),
]
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 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 outputs(self) -> List[ToolOutput]:
return [
ToolOutput(
"out",
FastqGzPair,
selector=[
InputSelector("outputPrefix") + "-R1.fastq.gz",
InputSelector("outputPrefix") + "-R2.fastq.gz",
],
)
]
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 test_string_formatter_two_param(self):
# vardict input format
b = StringFormatter(
"{tumorName}:{normalName}",
tumorName=InputSelector("tumorInputName"),
normalName=InputSelector("normalInputName"),
)
res = cwl.get_input_value_from_potential_selector_or_generator(b)
self.assertEqual(
'$("{tumorName}:{normalName}".replace(/\{tumorName\}/g, inputs.tumorInputName).replace(/\{normalName\}/g, inputs.normalInputName))',
res,
)
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 test_string_formatter_two_param(self):
# vardict input format
d = {
"tumorInputName": ToolInput("tumorInputName", String()),
"normalInputName": ToolInput("normalInputName", String()),
}
b = StringFormatter(
"{tumorName}:{normalName}",
tumorName=InputSelector("tumorInputName"),
normalName=InputSelector("normalInputName"),
)
res = wdl.get_input_value_from_potential_selector_or_generator(b, d)
self.assertEqual("${tumorInputName}:${normalInputName}", res)
def outputs(self) -> List[ToolOutput]:
return [
ToolOutput(
"out",
File,
glob=StringFormatter(
"{output_dir}/{tumor_name}--{normal_name}.pdf",
output_dir=InputSelector("output_dir"),
tumor_name=InputSelector("tumor_name"),
normal_name=InputSelector("normal_name"),
),
)
]
def arguments(self):
return [
ToolArgument("bwa", position=0, shell_quote=False),
ToolArgument("mem", position=1, shell_quote=False),
ToolArgument("|", position=5, shell_quote=False),
ToolArgument("samtools", position=6, shell_quote=False),
ToolArgument("view", position=7, shell_quote=False),
ToolArgument(InputSelector("reference"),
prefix="-T",
position=8,
shell_quote=False),
ToolArgument(
CpuSelector(),
position=8,
shell_quote=False,
prefix="--threads",
doc="(-@) Number of additional threads to use [0]",
),
ToolArgument(
"-h",
position=8,
shell_quote=False,
doc="Include the header in the output.",
),
ToolArgument("-b",
position=8,
shell_quote=False,
doc="Output in the BAM format."),
ToolArgument(
StringFormatter(
"@RG\\tID:{name}\\tSM:{name}\\tLB:{name}\\tPL:{pl}",
name=InputSelector("sampleName"),
pl=InputSelector("platformTechnology"),
),
prefix="-R",
position=2,
doc=
"Complete read group header line. ’\\t’ can be used in STR and will be converted to a TAB"
"in the output SAM. The read group ID will be attached to every read in the output. "
"An example is ’@RG\\tID:foo\\tSM:bar’. (Default=null) "
"https://gatkforums.broadinstitute.org/gatk/discussion/6472/read-groups",
),
ToolArgument(
CpuSelector(),
prefix="-t",
position=2,
shell_quote=False,
doc="Number of threads. (default = 1)",
),
]
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 test_string_formatter_optional_inpselect_no_default(self):
# will throw
ti = {"ti": ToolInput("ti", String(optional=True))}
b = StringFormatter("{place} michael", place=InputSelector("ti"))
self.assertRaises(
Exception, wdl.get_input_value_from_potential_selector_or_generator, b, ti
)
def test_input_selector_base_nostringenv(self):
ti = {"random": ToolInput("random", String())}
input_sel = InputSelector("random")
self.assertEqual(
"random",
wdl.translate_input_selector(input_sel, ti, string_environment=False),
)
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,
]
