def constructor(self):
self.input("bam", BamBai)
self.input("intervals", Bed)
self.input("sample_name", String)
self.input("header_lines", File)
self.input("reference", FastaWithDict)
# vardict options
self.input("allele_freq_threshold", Float, default=0.05)
self.input("min_mapping_qual", Int(optional=True))
self.input("filter", String(optional=True))
self.input("no_sv_call", Boolean(optional=True))
self.step(
"vardict",
VarDictGermline_1_6_0(
intervals=self.intervals,
bam=self.bam,
reference=self.reference,
sampleName=self.sample_name,
var2vcfSampleName=self.sample_name,
alleleFreqThreshold=self.allele_freq_threshold,
var2vcfAlleleFreqThreshold=self.allele_freq_threshold,
vcfFormat=True,
chromColumn=1,
regStartCol=2,
geneEndCol=3,
threads=4,
minMappingQual=self.min_mapping_qual,
filter=self.filter,
noStructuralVariants=self.no_sv_call,
),
)
self.step(
"annotate",
BcfToolsAnnotate_1_5(vcf=self.vardict.out,
headerLines=self.header_lines),
)
self.step("compressvcf",
BGZipLatest(file=self.annotate.out, stdout=True))
self.step("tabixvcf", TabixLatest(inp=self.compressvcf.out))
self.step(
"splitnormalisevcf",
SplitMultiAllele(vcf=self.annotate.out, reference=self.reference),
)
self.step("trim", TrimIUPAC_0_0_5(vcf=self.splitnormalisevcf.out))
self.step(
"filterpass",
VcfToolsvcftoolsLatest(
vcf=self.trim.out,
removeFileteredAll=True,
recode=True,
recodeINFOAll=True,
),
)
self.output("variants", source=self.tabixvcf.out)
self.output("out", source=self.filterpass.out)
def constructor(self):
self.input("bam", BamBai)
self.input(
"intervals",
Bed(optional=True),
doc="This optional interval supports processing by regions. If this input resolves "
"to null, then GATK will process the whole genome per each tool's spec",
)
self.input("reference", FastaWithDict)
self.input("snps_dbsnp", VcfTabix)
self.input("snps_1000gp", VcfTabix)
self.input("known_indels", VcfTabix)
self.input("mills_indels", VcfTabix)
self.step(
"split_bam",
gatk4.Gatk4SplitReads_4_1_3(bam=self.bam, intervals=self.intervals),
)
self.step(
"base_recalibrator",
gatk4.Gatk4BaseRecalibrator_4_1_3(
bam=self.split_bam,
intervals=self.intervals,
reference=self.reference,
knownSites=[
self.snps_dbsnp,
self.snps_1000gp,
self.known_indels,
self.mills_indels,
],
),
)
self.step(
"apply_bqsr",
gatk4.Gatk4ApplyBqsr_4_1_3(
bam=self.split_bam,
intervals=self.intervals,
recalFile=self.base_recalibrator.out,
reference=self.reference,
),
)
self.step(
"haplotype_caller",
gatk4.Gatk4HaplotypeCaller_4_1_3(
inputRead=self.apply_bqsr,
intervals=self.intervals,
reference=self.reference,
dbsnp=self.snps_dbsnp,
),
)
self.step(
"split_multi_allele",
SplitMultiAllele(reference=self.reference, vcf=self.haplotype_caller),
)
self.output("out", source=self.split_multi_allele)
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 constructor(self):
self.input("normal_bam", BamBai)
self.input("tumor_bam", BamBai)
self.input("normal_name", String)
self.input("tumor_name", String)
self.input("intervals", Bed)
self.input("header_lines", File)
self.input("reference", FastaWithDict)
# vardict options
self.input("allele_freq_threshold", Float(), 0.05)
self.input("minMappingQual", Int(optional=True))
self.input("filter", String(optional=True))
self.step(
"vardict",
VarDictSomatic_1_6_0(
normalBam=self.normal_bam,
tumorBam=self.tumor_bam,
intervals=self.intervals,
reference=self.reference,
normalName=self.normal_name,
tumorName=self.tumor_name,
alleleFreqThreshold=self.allele_freq_threshold,
vcfFormat=True,
chromColumn=1,
regStartCol=2,
geneEndCol=3,
threads=4,
minMappingQual=self.minMappingQual,
filter=self.filter,
),
)
self.step(
"annotate",
BcfToolsAnnotate_1_5(vcf=self.vardict.out,
headerLines=self.header_lines),
)
self.step("compressvcf",
BGZipLatest(file=self.annotate.out, stdout=True))
self.step("tabixvcf", TabixLatest(inp=self.compressvcf.out))
self.step(
"splitnormalisevcf",
SplitMultiAllele(vcf=self.annotate.out, reference=self.reference),
)
self.step("trim", TrimIUPAC_0_0_5(vcf=self.splitnormalisevcf.out))
self.step("filterpass", FilterVardictSomaticVcf(vcf=self.trim.out))
self.output("variants", source=self.tabixvcf.out)
self.output("out", source=self.filterpass.out)
def constructor(self):
self.input("normal_bam", BamBai)
self.input("tumor_bam", BamBai)
self.input("normal_name", String)
self.input("tumor_name", String)
self.input("intervals", Bed)
self.input("allele_freq_threshold", Float(), 0.05)
self.input("header_lines", File)
self.input("reference", FastaWithDict)
self.step(
"vardict",
VarDictSomatic_1_6_0(
normalBam=self.normal_bam,
tumorBam=self.tumor_bam,
intervals=self.intervals,
reference=self.reference,
normalName=self.normal_name,
tumorName=self.tumor_name,
alleleFreqThreshold=self.allele_freq_threshold,
chromNamesAreNumbers=True,
vcfFormat=True,
chromColumn=1,
regStartCol=2,
geneEndCol=3,
),
)
self.step(
"annotate",
BcfToolsAnnotate_1_5(file=self.vardict.out,
headerLines=self.header_lines),
)
self.step(
"split_multi_allele",
SplitMultiAllele(reference=self.reference, vcf=self.annotate.out),
)
self.step("trim", TrimIUPAC_0_0_5(vcf=self.split_multi_allele.out))
self.output("vardict_variants", source=self.vardict.out)
self.output("out", source=self.trim.out)
def constructor(self):
self.input("bam", BamBai)
self.input("reference", FastaWithDict)
self.input("intervals", BedTabix(optional=True))
self.input("is_exome", Boolean(optional=True))
self.step(
"manta",
Manta_1_5_0(
bam=self.bam,
reference=self.reference,
callRegions=self.intervals,
exome=self.is_exome,
),
)
self.step(
"strelka",
StrelkaGermline_2_9_10(
bam=self.bam,
reference=self.reference,
indelCandidates=self.manta.candidateSmallIndels,
callRegions=self.intervals,
exome=self.is_exome,
),
)
self.step(
"bcfview",
BcfToolsView_1_5(file=self.strelka.variants,
applyFilters=["PASS"]),
)
self.step(
"split_multi_allele",
SplitMultiAllele(vcf=self.bcfview.out, reference=self.reference),
)
self.output("diploid", source=self.manta.diploidSV)
self.output("variants", source=self.strelka.variants)
self.output("out", source=self.split_multi_allele.out)
def constructor(self):
self.input("bam", BamBai)
self.input("intervals", Bed)
self.input("sample_name", String)
self.input("allele_freq_threshold", Float, default=0.5)
self.input("header_lines", File)
self.input("reference", FastaWithDict)
self.step(
"vardict",
VarDictGermline_1_6_0(
intervals=self.intervals,
bam=self.bam,
reference=self.reference,
sampleName=self.sample_name,
var2vcfSampleName=self.sample_name,
alleleFreqThreshold=self.allele_freq_threshold,
var2vcfAlleleFreqThreshold=self.allele_freq_threshold,
chromNamesAreNumbers=True,
vcfFormat=True,
chromColumn=1,
regStartCol=2,
geneEndCol=3,
),
)
self.step(
"annotate",
BcfToolsAnnotate_1_5(file=self.vardict.out,
headerLines=self.header_lines),
)
self.step(
"split_multi_allele",
SplitMultiAllele(vcf=self.annotate.out, reference=self.reference),
)
self.step("trim", TrimIUPAC_0_0_5(vcf=self.split_multi_allele.out))
self.output("vardict_variants", source=self.vardict.out)
self.output("out", source=self.trim.out)
def constructor(self):
self.input("bam", BamBai)
self.input(
"intervals",
Bed(optional=True),
doc=
"This optional interval supports processing by regions. If this input resolves "
"to null, then GATK will process the whole genome per each tool's spec",
)
self.input("reference", FastaWithDict)
self.input("snps_dbsnp", VcfTabix)
self.step(
"split_bam",
gatk4.Gatk4SplitReads_4_1_3(bam=self.bam,
intervals=self.intervals),
)
self.step(
"haplotype_caller",
gatk4.Gatk4HaplotypeCaller_4_1_3(
inputRead=self.split_bam.out,
intervals=self.intervals,
reference=self.reference,
dbsnp=self.snps_dbsnp,
pairHmmImplementation="LOGLESS_CACHING",
),
)
self.step("uncompressvcf",
UncompressArchive(file=self.haplotype_caller.out))
self.step(
"splitnormalisevcf",
SplitMultiAllele(vcf=self.uncompressvcf.out,
reference=self.reference),
)
self.output("variants", source=self.haplotype_caller.out)
self.output("out_bam", source=self.haplotype_caller.bam)
self.output("out", source=self.splitnormalisevcf.out)
def constructor(self):
self.input("normal_bam", BamBai)
self.input("tumor_bam", BamBai)
self.input("normal_name", str)
self.input("tumor_name", str)
self.input(
"intervals",
Bed(optional=True),
doc=
"This optional interval supports processing by regions. If this input resolves "
"to null, then GATK will process the whole genome per each tool's spec",
)
self.input("reference", FastaWithDict)
self.input("snps_dbsnp", VcfTabix)
self.input("snps_1000gp", VcfTabix)
self.input("known_indels", VcfTabix)
self.input("mills_indels", VcfTabix)
self.step(
"base_recalibrator_normal",
gatk4.Gatk4BaseRecalibrator_4_0(),
ignore_missing=True,
)
self.step(
"base_recalibrator_tumor",
gatk4.Gatk4BaseRecalibrator_4_0(),
ignore_missing=True,
)
self.step("apply_bqsr_normal",
gatk4.Gatk4ApplyBqsr_4_0(),
ignore_missing=True)
self.step("apply_bqsr_tumor",
gatk4.Gatk4ApplyBqsr_4_0(),
ignore_missing=True)
# S1: BaseRecalibrator(s)
for inp, baseRecal, applyBQSR in [
(self.normal_bam, self.base_recalibrator_normal,
self.apply_bqsr_normal),
(self.tumor_bam, self.base_recalibrator_tumor,
self.apply_bqsr_tumor),
]:
baseRecal["bam"] = inp
baseRecal["intervals"] = self.intervals
baseRecal["reference"] = self.reference
baseRecal["knownSites"] = [
self.snps_dbsnp,
self.snps_1000gp,
self.known_indels,
self.mills_indels,
]
applyBQSR["recalFile"] = baseRecal.out
applyBQSR["bam"] = inp
applyBQSR["intervals"] = self.intervals
applyBQSR["reference"] = self.reference
self.step(
"mutect2",
gatk4.GatkMutect2_4_0(
normal=self.apply_bqsr_normal.out,
tumor=self.apply_bqsr_tumor.out,
normalName=self.normal_name,
tumorName=self.tumor_name,
intervals=self.intervals,
reference=self.reference,
),
)
self.step(
"split_multi_allele",
SplitMultiAllele(reference=self.reference, vcf=self.mutect2.out),
)
self.output("out", source=self.split_multi_allele.out)
def constructor(self):
self.input("normal_bam", BamBai)
self.input("tumor_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.normal_bam,
tumorBam=self.tumor_bam,
reference=self.reference,
callRegions=self.intervals,
exome=self.is_exome,
config=self.manta_config,
),
)
self.step(
"strelka",
StrelkaSomatic_2_9_10(
indelCandidates=self.manta.candidateSmallIndels,
normalBam=self.normal_bam,
tumorBam=self.tumor_bam,
reference=self.reference,
callRegions=self.intervals,
exome=self.is_exome,
config=self.strelka_config,
),
)
self.step(
"concatvcf",
ConcatStrelkaSomaticVcf(
headerVcfs=[self.strelka.snvs, self.strelka.indels],
contentVcfs=[self.strelka.snvs, self.strelka.indels],
),
)
self.step("sortvcf", BcfToolsSort_1_9(vcf=self.concatvcf.out))
self.step(
"splitnormalisevcf",
SplitMultiAllele(vcf=self.sortvcf.out, reference=self.reference),
)
self.step(
"extractaddp",
ExtractStrelkaSomaticADDP_0_1_1(vcf=self.splitnormalisevcf.out),
)
self.step(
"filterpass",
VcfToolsvcftoolsLatest(
vcf=self.extractaddp.out,
removeFileteredAll=True,
recode=True,
recodeINFOAll=True,
),
)
self.output("tumor_sv", source=self.manta.somaticSV)
self.output("normal_sv", source=self.manta.diploidSV)
self.output("variants", source=self.sortvcf.out)
self.output("out", source=self.filterpass.out)
def constructor(self):
self.input("normal_bam", BamBai)
self.input("tumor_bam", BamBai)
self.input("normal_name", String(optional=True))
self.input(
"intervals",
Bed(optional=True),
doc=
"This optional intervals file supports processing by regions. If this file resolves "
"to null, then GATK will process the whole genome per each tool's spec",
)
self.input("reference", FastaWithDict)
self.input("gnomad", VcfTabix)
self.input("panel_of_normals", VcfTabix(optional=True))
# split normal and tumor bam
self.step(
"normal_split_bam",
self.process_subpipeline(bam=self.normal_bam,
intervals=self.intervals),
)
self.step(
"tumor_split_bam",
self.process_subpipeline(bam=self.tumor_bam,
intervals=self.intervals),
)
# variant calling + learn read orientation model
self.step(
"mutect2",
gatk4.GatkMutect2_4_1_3(
normalBams=[self.normal_split_bam.out],
tumorBams=[self.tumor_split_bam.out],
normalSample=self.normal_name,
intervals=self.intervals,
reference=self.reference,
germlineResource=self.gnomad,
panelOfNormals=self.panel_of_normals,
),
)
self.step(
"learnorientationmodel",
gatk4.Gatk4LearnReadOrientationModelLatest(
f1r2CountsFiles=self.mutect2.f1f2r_out, ),
)
# calculate contamination and segmentation
self.step(
"getpileupsummaries",
gatk4.Gatk4GetPileUpSummariesLatest(
bam=self.tumor_split_bam.out,
sites=self.gnomad,
intervals=self.intervals,
),
)
self.step(
"calculatecontamination",
gatk4.Gatk4CalculateContaminationLatest(
pileupTable=self.getpileupsummaries.out, ),
)
self.step(
"filtermutect2calls",
gatk4.Gatk4FilterMutectCallsLatest(
vcf=self.mutect2.out,
reference=self.reference,
segmentationFile=self.calculatecontamination.segOut,
contaminationTable=self.calculatecontamination.contOut,
readOrientationModel=self.learnorientationmodel.out,
statsFile=self.mutect2.stats,
),
)
# normalise and filter "PASS" variants
self.step("uncompressvcf",
UncompressArchive(file=self.filtermutect2calls.out))
self.step(
"splitnormalisevcf",
SplitMultiAllele(vcf=self.uncompressvcf.out,
reference=self.reference),
)
self.step(
"filterpass",
VcfToolsvcftoolsLatest(
vcf=self.splitnormalisevcf.out,
removeFileteredAll=True,
recode=True,
recodeINFOAll=True,
),
)
self.output("variants", source=self.filtermutect2calls.out)
self.output("out_bam", source=self.mutect2.bam)
self.output("out", source=self.filterpass.out)