def tumor_normal_inputs():
return [
ToolInput(
"tumor",
BamBai(),
position=6,
prefix="-I",
doc="BAM/SAM/CRAM file containing reads",
),
ToolInput(
"tumorName",
String(),
position=6,
prefix="-tumor",
doc=
"BAM sample name of tumor. May be URL-encoded as output by GetSampleName with -encode.",
),
ToolInput(
"normal",
BamBai(),
position=5,
prefix="-I",
doc="BAM/SAM/CRAM file containing reads",
),
ToolInput(
"normalName",
String(),
position=6,
prefix="-normal",
doc=
"BAM sample name of normal. May be URL-encoded as output by GetSampleName with -encode.",
),
]
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 tests(self) -> Optional[List[TTestCase]]:
parent_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics"
germline_data = f"{parent_dir}/wgsgermline_data"
somatic_data = f"{parent_dir}/wgssomatic_data"
return [
TTestCase(
name="basic",
input={
"normal_inputs": [[
f"{somatic_data}/NA24385-BRCA1_R1.fastq.gz",
f"{somatic_data}/NA24385-BRCA1_R21.fastq.gz",
]],
"normal_name":
"NA24385-BRCA1",
"tumor_inputs": [[
f"{somatic_data}/NA12878-NA24385-mixture-BRCA1_R1.fastq.gz",
f"{somatic_data}/NA12878-NA24385-mixture-BRCA1_R2.fastq.gz",
]],
"tumor_name":
"NA12878-NA24385-mixture",
"reference":
f"{germline_data}/Homo_sapiens_assembly38.chr17.fasta",
"gridss_blacklist":
f"{somatic_data}/consensusBlacklist.hg38.chr17.bed",
"gnomad":
f"{somatic_data}/af-only-gnomad.hg38.BRCA1.vcf.gz",
"gatk_intervals": [f"{germline_data}/BRCA1.hg38.bed"],
"known_indels":
f"{germline_data}/Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz",
"mills_indels":
f"{germline_data}/Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz",
"snps_1000gp":
f"{germline_data}/1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz",
"snps_dbsnp":
f"{germline_data}/Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz",
"cutadapt_adapters":
f"{germline_data}/contaminant_list.txt",
},
output=BamBai.basic_test("out_normal_bam", 3265300, 49500) +
BamBai.basic_test("out_tumor_bam", 3341700, 49000) +
TextFile.basic_test(
"out_normal_performance_summary",
950,
md5="e3205735e5fe8c900f05050f8ed73f19",
) + TextFile.basic_test(
"out_tumor_performance_summary",
950,
md5="122bfa2ece90c0f030015feba4ba7d84",
) +
FastqGzPair.basic_test("out_normal_fastqc_reports", 881300) +
FastqGzPair.basic_test("out_tumor_fastqc_reports", 874900),
)
]
def tests(self):
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
return [
TTestCase(
name="basic",
input={
"bams": [
f"{remote_dir}/NA12878-BRCA1.sorted.bam",
],
"maxRecordsInRam": 5000000,
"createIndex": True,
"mergeSamFiles_useThreading": True,
"mergeSamFiles_validationStringency": "SILENT",
},
output=BamBai.basic_test(
"out",
2829000,
3780,
f"{remote_dir}/NA12878-BRCA1.markduped.bam.flagstat",
),
),
TTestCase(
name="minimal",
input={
"bams": [
f"{remote_dir}/NA12878-BRCA1.sorted.bam",
],
"maxRecordsInRam": 5000000,
"createIndex": True,
"mergeSamFiles_useThreading": True,
"mergeSamFiles_validationStringency": "SILENT",
},
output=self.minimal_test(),
),
]
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 [
*super(Gatk4DepthOfCoverageBase, self).inputs(),
ToolInput(
"bam",
BamBai(),
prefix="-I",
doc="The SAM/BAM/CRAM file containing reads.",
secondaries_present_as={".bai": "^.bai"},
),
ToolInput(
"reference", FastaWithDict(), prefix="-R", doc="Reference sequence"
),
ToolInput(
"outputPrefix",
String(),
prefix="-O",
doc="An output file created by the walker. Will overwrite contents if file exists",
),
ToolInput(
"intervals",
Array(Bed),
prefix="--intervals",
doc="-L (BASE) One or more genomic intervals over which to operate",
prefix_applies_to_all_elements=True,
),
*self.additional_args,
]
def inputs(self):
return [
ToolInput("bams", Array(BamBai()), 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):
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 tests(self):
return [
TTestCase(
name="basic",
input={
"bam": [
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.merged.bam",
)
],
"javaOptions": ["-Xmx6G"],
"maxRecordsInRam": 5000000,
"createIndex": True,
"tmpDir": "./tmp",
},
output=BamBai.basic_test(
"out",
2829000,
3780,
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam.flagstat",
),
)
+ TextFile.basic_test(
"metrics",
3700,
"NA12878-BRCA1\t193\t9468\t164\t193\t46\t7\t1\t0.003137\t7465518",
112,
),
)
]
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 tests(self):
return [
TTestCase(
name="basic",
input={
"bams": [
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.sorted.bam",
)
],
"createIndex": True,
"validationStringency": "SILENT",
"javaOptions": ["-Xmx6G"],
"maxRecordsInRam": 5000000,
"tmpDir": "./tmp",
"useThreading": True,
},
output=BamBai.basic_test(
"out",
2826968,
49688,
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.bam.flagstat",
),
"963a51f7feed5b829319b947961b8a3e",
"231c10d0e43766170f5a7cd1b8a6d14e",
),
)
]
def inputs(self) -> List[ToolInput]:
return [
ToolInput("piscesVersion", String()),
ToolInput(
"inputBam",
BamBai(),
prefix="-b",
position=4,
shell_quote=False,
doc="Input BAM file",
),
ToolInput(
"outputDir",
String(),
prefix="--outfolder",
position=4,
shell_quote=False,
doc="Output Folder",
),
ToolInput(
"referenceFolder",
Directory(),
prefix="--genomefolders",
position=5,
shell_quote=False,
doc="Folder containing reference genome files",
),
*self.additional_hygea_args,
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"bam": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.recalibrated.bam",
),
"intervals": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"BRCA1.hg38.bed",
),
"javaOptions": ["-Xmx3G"],
"outputFilename": ".",
},
output=BamBai.basic_test(
"out",
2600900,
21300,
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.split.flagstat",
),
),
)
]
def tests(self):
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
return [
TTestCase(
name="basic",
input={
"inputRead": f"{remote_dir}/NA12878-BRCA1.split.bam",
"reference": f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
"intervals": f"{remote_dir}/BRCA1.hg38.bed",
"dbsnp": f"{remote_dir}/Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz",
"javaOptions": ["-Xmx6G"],
"pairHmmImplementation": "LOGLESS_CACHING",
},
output=VcfTabix.basic_test(
"out",
12800,
270,
214,
["GATKCommandLine"],
"0224e24e5fc27286ee90c8d3c63373a7",
)
+ BamBai.basic_test(
"bam",
596698,
21272,
f"{remote_dir}/NA12878-BRCA1.haplotyped.flagstat",
"d83b4c0d8eab24a3be1cc6af4f827753",
"b4bb4028b8679a3a635e3ad87126a097",
),
)
]
def tests(self):
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
return [
TTestCase(
name="basic",
input={
"bams": [
f"{remote_dir}/NA12878-BRCA1.sorted.bam",
],
"createIndex": True,
"validationStringency": "SILENT",
"javaOptions": ["-Xmx6G"],
"maxRecordsInRam": 5000000,
"tmpDir": "./tmp",
"useThreading": True,
},
output=BamBai.basic_test(
"out",
2826968,
49688,
f"{remote_dir}/NA12878-BRCA1.bam.flagstat",
"963a51f7feed5b829319b947961b8a3e",
"231c10d0e43766170f5a7cd1b8a6d14e",
),
)
]
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(
"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 tests(self):
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
return [
TTestCase(
name="basic",
input={
"bam": [f"{remote_dir}/NA12878-BRCA1.merged.bam"],
"javaOptions": ["-Xmx6G"],
"maxRecordsInRam": 5000000,
"createIndex": True,
"tmpDir": "./tmp",
},
output=BamBai.basic_test(
"out",
2829000,
3780,
f"{remote_dir}/NA12878-BRCA1.markduped.bam.flagstat",
) + TextFile.basic_test(
"metrics",
3700,
"NA12878-BRCA1\t193\t9468\t164\t193\t46\t7\t1\t0.003137\t7465518",
112,
),
)
]
def tests(self):
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
return [
TTestCase(
name="basic",
input={
"bam": f"{remote_dir}/NA12878-BRCA1.markduped.bam",
"reference":
f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
"recalFile": f"{remote_dir}/NA12878-BRCA1.markduped.table",
"intervals": f"{remote_dir}/BRCA1.hg38.bed",
},
output=BamBai.basic_test(
"out",
2600000,
21000,
f"{remote_dir}/NA12878-BRCA1.recalibrated.flagstat",
),
),
TTestCase(
name="minimal",
input={
"bam": f"{remote_dir}/NA12878-BRCA1.markduped.bam",
"reference":
f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
"recalFile": f"{remote_dir}/NA12878-BRCA1.markduped.table",
"intervals": f"{remote_dir}/BRCA1.hg38.bed",
},
output=self.minimal_test(),
),
]
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 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 constructor(self):
self.input("bams", Array(BamBai()))
self.input("createIndex", Boolean, default=True)
self.input("maxRecordsInRam", Int, default=5000000)
self.input("sampleName", String(optional=True))
self.step(
"mergeSamFiles",
Gatk4MergeSamFiles_4_1_2(
bams=self.bams,
useThreading=True,
createIndex=self.createIndex,
maxRecordsInRam=self.maxRecordsInRam,
validationStringency="SILENT",
sampleName=self.sampleName,
),
)
self.step(
"markDuplicates",
Gatk4MarkDuplicates_4_1_2(
bam=self.mergeSamFiles.out,
createIndex=self.createIndex,
maxRecordsInRam=self.maxRecordsInRam,
),
)
self.output("out", source=self.markDuplicates.out)
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(),
*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 [
*super(Gatk4BaseRecalibratorBase, self).inputs(),
*Gatk4BaseRecalibratorBase.additional_args,
ToolInput(
"bam",
BamBai(),
position=6,
prefix="-I",
doc="BAM/SAM/CRAM file containing reads",
secondaries_present_as={".bai": "^.bai"},
),
ToolInput(
"knownSites",
Array(VcfTabix()),
prefix="--known-sites",
position=28,
prefix_applies_to_all_elements=True,
doc=
"**One or more databases of known polymorphic sites used to exclude "
"regions around known polymorphisms from analysis.** "
"This algorithm treats every reference mismatch as an indication of error. However, real "
"genetic variation is expected to mismatch the reference, so it is critical that a "
"database of known polymorphic sites is given to the tool in order to skip over those sites. "
"This tool accepts any number of Feature-containing files (VCF, BCF, BED, etc.) for use as "
"this database. For users wishing to exclude an interval list of known variation simply "
"use -XL my.interval.list to skip over processing those sites. Please note however "
"that the statistics reported by the tool will not accurately reflected those sites "
"skipped by the -XL argument.",
),
ToolInput(
"reference",
FastaWithDict(),
position=5,
prefix="-R",
doc="Reference sequence file",
),
ToolInput(
"outputFilename",
Filename(prefix=InputSelector("bam"), extension=".table"),
position=8,
prefix="-O",
doc="**The output recalibration table filename to create.** "
"After the header, data records occur one per line until the end of the file. The first "
"several items on a line are the values of the individual covariates and will change "
"depending on which covariates were specified at runtime. The last three items are the "
"data- that is, number of observations for this combination of covariates, number of "
"reference mismatches, and the raw empirical quality score calculated by phred-scaling "
"the mismatch rate. Use '/dev/stdout' to print to standard out.",
),
ToolInput(
"intervals",
Bed(optional=True),
prefix="--intervals",
doc=
"-L (BASE) One or more genomic intervals over which to operate",
),
]
def outputs(self):
return [
ToolOutput(
"out",
BamBai(),
glob=InputSelector("outputFilename"),
secondaries_present_as={".bai": "^.bai"},
)
]
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):
return [
ToolOutput(
"out",
BamBai(),
glob=InputSelector("outputFilename"),
doc="BAM to write extracted reads to",
secondaries_present_as={".bai": "^.bai"},
)
]
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):
return [
ToolOutput(
"out",
BamBai(),
glob=InputSelector("outputFilename"),
doc=
"BAM file with reads split at N CIGAR elements and CIGAR strings updated.",
secondaries_present_as={".bai": "^.bai"},
)
]
