def tests(self):
return [
TTestCase(
name="basic",
input={
"positions": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.sorted.uncompressed.stdout",
),
"reference": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
"bam": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam",
),
"countOrphans": True,
"noBAQ": True,
"maxDepth": 10000,
"minBQ": 0,
},
output=TextFile.basic_test(
"out",
19900,
"chr17\t43044391\tG\t19\tA,A,,A.a,,A,,A..,,a\tDJCJ:FHDDBJBBJJIDDB",
187,
"53c3e03c20730ff45411087444379b1b",
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"bams": [
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.sorted.bam",
)
],
"maxRecordsInRam":
5000000,
"createIndex":
True,
"mergeSamFiles_useThreading":
True,
"mergeSamFiles_validationStringency":
"SILENT",
},
output=BamBai.basic_test(
"out",
2829000,
3780,
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam.flagstat",
),
),
),
TTestCase(
name="minimal",
input={
"bams": [
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.sorted.bam",
)
],
"maxRecordsInRam":
5000000,
"createIndex":
True,
"mergeSamFiles_useThreading":
True,
"mergeSamFiles_validationStringency":
"SILENT",
},
output=self.minimal_test(),
),
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"sam":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.bwamem.stdout",
),
"reference":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
"threads":
16,
},
output=Bam.basic_test(
"out",
2740774,
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.bam.flagstat",
),
"9a6af420f287df52a122ac723f41b535",
),
),
TTestCase(
name="minimal",
input={
"sam":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.bwamem.stdout",
),
"reference":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
"threads":
16,
},
output=self.minimal_test(),
),
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"bam":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam",
),
"reference":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
"vcf":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.sorted.uncompressed.stdout",
),
"samtoolsmpileup_countOrphans":
True,
"samtoolsmpileup_noBAQ":
True,
"samtoolsmpileup_maxDepth":
10000,
"samtoolsmpileup_minBQ":
0,
"addbamstats_type":
"germline",
},
output=Vcf.basic_test(
"out",
69225,
230,
["GATKCommandLine"],
"db09c6c37c52771bd058e32d5c6b94c1",
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"bam": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam",
),
"reference": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
"snps_dbsnp": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz",
),
"snps_1000gp": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz",
),
"known_indels": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz",
),
"mills_indels": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz",
),
"intervals": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"BRCA1.hg38.bed",
),
},
output=BamBai.basic_test(
"out",
2600000,
21000,
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.recalibrated.flagstat",
),
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"bam":
os.path.join(BioinformaticsTool.test_data_path(),
"small.bam"),
},
output=[
TTestExpectedOutput(
tag="out",
preprocessor=TTestPreprocessor.FileMd5,
operator=operator.eq,
expected_value="c9c318de134643665ff1fed6cfaec49c",
),
],
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"reference": os.path.join(
BioinformaticsTool.test_data_path(), "hg38-brca1.fasta"
),
},
output=[
TTestExpectedOutput(
tag="out",
preprocessor=TTestPreprocessor.FileMd5,
operator=operator.eq,
expected_value="768915f0ceff3bae0bac0ace5f7ccad0",
),
],
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"bam":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam",
),
},
output=TextFile.basic_test(
"out",
410,
"19486 + 0 in total (QC-passed reads + QC-failed reads)",
13,
"ddbcfe52e60b925d222fb8bc1517a7a0",
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"bam": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam",
),
"reference": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
"recalFile": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.table",
),
"intervals": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"BRCA1.hg38.bed",
),
},
output=BamBai.basic_test(
"out",
2600000,
21000,
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.recalibrated.flagstat",
),
),
),
TTestCase(
name="minimal",
input={
"bam": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam",
),
"reference": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
"recalFile": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.table",
),
"intervals": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"BRCA1.hg38.bed",
),
},
output=self.minimal_test(),
),
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"reads": [
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1_R1.fastq.gz",
),
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1_R2.fastq.gz",
),
],
"reference":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
"markShorterSplits":
True,
"readGroupHeaderLine":
"@RG\tID:NA12878-BRCA1\tSM:NA12878-BRCA1\tLB:NA12878-BRCA1\tPL:ILLUMINA",
"threads":
16,
},
output=Bam.basic_test(
"out",
8628527,
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.bwamem.flagstat",
),
),
),
TTestCase(
name="minimal",
input={
"reads": [
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1_R1.fastq.gz",
),
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1_R2.fastq.gz",
),
],
"reference":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
"markShorterSplits":
True,
"readGroupHeaderLine":
"@RG\tID:NA12878-BRCA1\tSM:NA12878-BRCA1\tLB:NA12878-BRCA1\tPL:ILLUMINA",
"threads":
16,
},
output=self.minimal_test(),
),
]