def constructor(self):
self.input("bams", Array(BamBai()))
self.input("createIndex", Boolean, default=True)
self.input("maxRecordsInRam", Int, default=5000000)
self.input("sample_name", str)
self.step(
"mergeSamFiles",
Gatk4MergeSamFiles_4_1_2(
bams=self.bams,
useThreading=True,
createIndex=self.createIndex,
maxRecordsInRam=self.maxRecordsInRam,
validationStringency="SILENT",
sampleName=self.sample_name,
),
)
## Include step here to filter out -F 0x100 using samtools as secondary reads don't get mate cigar info
self.step(
"filterSecondary",
SamToolsView_1_9(
sam=self.mergeSamFiles.out,
doNotOutputAlignmentsWithBitsSet="0x100",
),
)
self.step("indexFilterBam",
SamToolsIndex_1_9(bam=self.filterSecondary.out))
self.step(
"fixMateInfo",
Gatk4FixMateInformation_4_1_2_0(
inputBam=self.indexFilterBam.out,
ignoreMissingMates=False,
addMateCigar=True,
sortOrder="coordinate",
outputPrefix=self.sample_name,
),
)
self.step(
"markDuplicatesUMI",
Gatk4UmiAwareMarkDuplicatesWithMateCigar_4_1_2_0(
inputBam=self.fixMateInfo.out,
umiTagName="RX",
maxEditDistanceToJoin=1,
outputPrefix=self.sample_name,
),
)
self.output("out", source=self.markDuplicatesUMI.out)
self.output("umimetrics", source=self.markDuplicatesUMI.umimetrics)
self.output("metrics", source=self.markDuplicatesUMI.metrics)
def constructor(self):
# Inputs
self.input("bam", BamBai)
self.input("genecoverage_bed", Bed)
self.input("region_bed", Bed)
self.input("sample_name", String)
self.input("genome_file", TextFile)
# Steps
# Add a step to remove secondary alignments
self.step(
"rmsecondaryalignments",
SamToolsView_1_9(sam=self.bam,
doNotOutputAlignmentsWithBitsSet="0x100"),
)
self.step("indexbam",
SamToolsIndex_1_9(bam=self.rmsecondaryalignments.out))
self.step(
"gatk4collectinsertsizemetrics",
Gatk4CollectInsertSizeMetrics_4_1_2(bam=self.indexbam.out),
)
self.step(
"bamflagstat",
SamToolsFlagstat_1_9(bam=self.rmsecondaryalignments.out),
)
self.step(
"samtoolsview",
SamToolsView_1_9(
sam=self.rmsecondaryalignments.out,
doNotOutputAlignmentsWithBitsSet="0x400",
),
)
self.step("rmdupbamflagstat",
SamToolsFlagstat_1_9(bam=self.samtoolsview.out))
self.step(
"bedtoolsintersectbed",
BedToolsIntersectBed_2_29_2(
inputABam=self.samtoolsview.out,
inputBBed=self.region_bed,
genome=self.genome_file,
sorted=True,
),
)
self.step(
"targetbamflagstat",
SamToolsFlagstat_1_9(bam=self.bedtoolsintersectbed.out),
)
self.step(
"bedtoolscoveragebed",
BedToolsCoverageBed_2_29_2(
inputABed=self.region_bed,
inputBBam=self.bedtoolsintersectbed.out,
genome=self.genome_file,
sorted=True,
histogram=True,
),
)
# Give all the output files to performance summary script
self.step(
"performancesummary",
PerformanceSummaryLatest(
flagstat=self.bamflagstat.out,
collectInsertSizeMetrics=self.gatk4collectinsertsizemetrics.
out,
targetFlagstat=self.targetbamflagstat.out,
coverage=self.bedtoolscoveragebed.out,
rmdupFlagstat=self.rmdupbamflagstat.out,
outputPrefix=self.sample_name,
),
)
# Steps - Gene Coverage
self.step(
"bedtoolscoverage",
BedToolsCoverageBed_2_29_2(
inputABed=self.genecoverage_bed,
inputBBam=self.samtoolsview.out,
genome=self.genome_file,
sorted=True,
histogram=True,
),
)
self.step(
"genecoverage",
GeneCoveragePerSampleLatest(
sampleName=self.sample_name,
bedtoolsOutputPath=self.bedtoolscoverage.out,
),
)
# Outputs
self.output("out", source=self.performancesummary.out)
self.output("geneFileOut", source=self.genecoverage.geneFileOut)
self.output("regionFileOut", source=self.genecoverage.regionFileOut)
def constructor(self):
##INPUTS
self.input("bam", BamBai())
self.input("sample_name", String())
self.input("reference_folder", Directory())
self.input("intervals", Bed())
self.input("gemini_chromosomes", String(optional=True))
self.input("ploidy", String(optional=True), default="somatic")
self.input("min_bq", Int(optional=True))
self.input("min_mq", Int(optional=True))
self.input("min_dp", Int(optional=True))
self.input("min_vaf", Float(optional=True))
self.input("vc_min_vq", Int(optional=True))
self.input("noise_level", Int(optional=True))
self.input("vqr_min_vq", Int(optional=True))
self.input("pisces_awk_script", File())
## STEPS
self.step(
"primary_only",
SamToolsView_1_9(sam=self.bam,
doNotOutputAlignmentsWithBitsSet="0x100"),
)
self.step(
"index_primary_only_bam",
SamToolsIndex_1_9(bam=self.primary_only.out),
)
self.step(
"gemini_read_preprocessing",
PiscesGemini_5_3_0_0(
inputBam=self.index_primary_only_bam,
referenceFolder=self.reference_folder,
samtoolsExecutable="samtools",
chromosomeFilter=self.gemini_chromosomes,
outputDir=".",
piscesVersion="5.3.0.0",
),
)
self.step(
"pisces",
PiscesVariantCaller_5_3_0_0(
inputBam=self.gemini_read_preprocessing.bam,
referenceFolder=self.reference_folder,
outputDir=".",
intervalBedFile=self.intervals,
ploidy=self.ploidy,
minimumBaseQuality=self.min_bq,
minimumMappingQuality=self.min_mq,
minimumVariantFrequency=self.min_vaf,
noiseLevelForQModel=self.noise_level,
minimumVariantFrequencyFilter=self.min_vaf,
enableSingleStrandFilter="True",
outputSBFiles="True",
callMNVs="False",
maxMNVLength=1,
RMxNFilter="5,9,0.35",
variantQualityFilter=self.vc_min_vq,
crushVCF="False",
gVCF="False",
piscesVersion="5.3.0.0",
),
)
self.step(
"vqr",
PiscesVariantQualityRecalibration_5_3_0_0(
inputVcf=self.pisces.vcf,
outputDir=".",
baselineNoise=self.noise_level,
minVariantQuality=self.vqr_min_vq,
piscesVersion="5.3.0.0",
),
)
piscesVcf = FirstOperator([self.vqr.vcf, self.pisces.vcf])
self.step(
"fixSource",
Awk(script=self.pisces_awk_script, input_files=piscesVcf),
)
self.step("sort", BcfToolsSort_1_9(vcf=self.fixSource.out))
self.step("normalise", BcfToolsNorm_1_9(vcf=self.sort.out))
self.step("uncompress", UncompressArchive(file=self.normalise.out))
self.step(
"filterpass",
VcfToolsvcftools_0_1_16(
vcf=self.uncompress.out.as_type(Vcf),
removeFileteredAll=True,
recode=True,
recodeINFOAll=True,
),
)
## OUTPUTS
self.output("variants", source=self.sort.out)
self.output("out", source=self.filterpass.out)
self.output("out_bam", source=self.gemini_read_preprocessing.bam)
def constructor(self):
## INPUTS
self.input("bam", BamBai())
self.input("sample_name", String())
self.input("reference_folder", Directory())
self.input("intervals", Bed())
self.input("ploidy", String(optional=True), default="somatic")
self.input("min_bq", Int(optional=True))
self.input("min_mq", Int(optional=True))
self.input("min_dp", Int(optional=True), default=100)
self.input("min_vaf", Float(optional=True))
self.input("vc_min_vq", Int(optional=True))
self.input("noise_level", Int(optional=True))
self.input("vqr_min_vq", Int(optional=True))
self.input("pisces_awk_script", File())
## STEPS
self.step(
"primary_only",
SamToolsView_1_9(sam=self.bam,
doNotOutputAlignmentsWithBitsSet="0x100"),
)
self.step(
"index_primary_only_bam",
SamToolsIndex_1_9(bam=self.primary_only.out),
)
self.step(
"hygea_realignment",
PiscesHygeaRealigner_5_2_10_49(
inputBam=self.index_primary_only_bam,
outputDir=".",
referenceFolder=self.reference_folder,
skipAndRemoveDuplicates="true",
piscesVersion="5.2.10.49",
),
)
self.step(
"stitcher_read_joining",
PiscesStitcher_5_2_10_49(
inputBam=self.hygea_realignment.out,
outputDir=".",
sampleName=self.sample_name,
piscesVersion="5.2.10.49",
),
)
self.step(
"stitcher_sort",
SamToolsSort_1_9(
bam=self.stitcher_read_joining.out,
outputFilename=self.sample_name + ".bam",
),
)
self.step("stitcher_index",
SamToolsIndex_1_9(bam=self.stitcher_sort.out))
self.step(
"pisces",
PiscesVariantCaller_5_2_10_49(
inputBam=self.stitcher_index.out,
referenceFolder=self.reference_folder,
outputDir=".",
intervalBedFile=self.intervals,
ploidy=self.ploidy,
minimumBaseQuality=self.min_bq,
minimumMappingQuality=self.min_mq,
minimumVariantFrequency=self.min_vaf,
minimumCoverage=self.min_dp,
noiseLevelForQModel=self.noise_level,
minimumVariantFrequencyFilter=self.min_vaf,
enableSingleStrandFilter="true",
callMNVs="false",
maxMNVLength=1,
RMxNFilter="5,9,0.35",
variantQualityFilter=self.vc_min_vq,
crushVCF="false",
gVCF="false",
piscesVersion="5.2.10.49",
),
)
self.step(
"vqr",
PiscesVariantQualityRecalibration_5_2_10_49(
inputVcf=self.pisces.vcf,
outputDir=".",
baselineNoise=self.noise_level,
minVariantQuality=self.vqr_min_vq,
piscesVersion="5.2.10.49",
),
)
piscesVcf = FirstOperator([self.vqr.vcf, self.pisces.vcf])
self.step(
"fixSource",
Awk(script=self.pisces_awk_script, input_files=piscesVcf),
)
self.step("sort", BcfToolsSort_1_9(vcf=self.fixSource.out))
self.step("normalise", BcfToolsNorm_1_9(vcf=self.sort.out))
self.step("uncompress", UncompressArchive(file=self.normalise.out))
self.step(
"filterpass",
VcfToolsvcftools_0_1_16(
vcf=self.uncompress.out.as_type(Vcf),
removeFileteredAll=True,
recode=True,
recodeINFOAll=True,
),
)
## OUTPUTs
self.output("variants", source=self.sort.out)
self.output("out", source=self.filterpass.out)
self.output("out_bam", source=self.stitcher_index.out)
## OPTIONAL OUTPUTs
self.output("hygea_options",
source=self.hygea_realignment.used_options)
self.output("stitcher_options",
source=self.stitcher_read_joining.used_options)
self.output("pisces_options", source=self.pisces.used_options)
self.output("vqr_options", source=self.vqr.used_options)
Bam,
BamBai,
VcfIdx,
Fasta,
FastaWithIndexes,
BedGz,
Bed,
BedTabix,
)
from janis_bioinformatics.tools.samtools import SamToolsIndex_1_9
from janis_bioinformatics.tools.htslib import Tabix_1_9, BGZip_1_9
from janis_bioinformatics.tools.igvtools import IgvIndexFeature_2_5_3
transformations = [
JanisTransformation(Bam, BamBai, SamToolsIndex_1_9(), relevant_tool_input="bam"),
JanisTransformation(Vcf, VcfIdx, IgvIndexFeature_2_5_3()),
JanisTransformation(
Vcf,
CompressedVcf,
BGZip_1_9(),
relevant_tool_input="file",
relevant_tool_output="out",
),
JanisTransformation(
CompressedVcf,
VcfTabix,
Tabix_1_9(),
relevant_tool_input="inp",
relevant_tool_output="out",
),