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 tests(self):
return [
TTestCase(
name="basic",
input={
"vcf":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.haplotype_uncompressed.stdout",
),
"reference":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
},
output=Vcf.basic_test(
"out",
51462,
221,
["GATKCommandLine"],
"5e48624cb5ef379a7d6d39cec44bc856",
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"inputVcf":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.sorted.uncompressed.stdout",
),
"mpileup":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.mpileup.stdout",
),
"type":
"germline",
},
output=Vcf.basic_test(
"out",
69225,
230,
["GATKCommandLine"],
"db09c6c37c52771bd058e32d5c6b94c1",
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"reference":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
},
output=TextFile.basic_test("out", 15, "chr17\t83257441\n", 1),
),
TTestCase(
name="minimal",
input={
"reference":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.chr17.fasta",
),
},
output=self.minimal_test(),
),
]
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):
return [
TTestCase(
name="basic",
input={
"bam": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam",
),
"genome_file": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.genome_file.txt",
),
"sample_name": "NA12878-BRCA1",
"samtoolsview_doNotOutputAlignmentsWithBitsSet": "0x400",
"performancesummary_genome": True,
},
output=TextFile.basic_test(
tag="performanceSummaryOut",
min_size=948,
line_count=2,
md5="575354942cfb8d0367725f9020181443",
expected_file_path=os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1_performance_summary.csv",
),
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"fastq": [
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",
),
],
"qualityCutoff":
15,
"minimumLength":
50,
"outputPrefix":
"output",
},
output=FastqGzPair.basic_test(
"out",
1090240,
1163374,
),
),
TTestCase(
name="minimal",
input={
"fastq": [
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",
),
],
"qualityCutoff":
15,
"minimumLength":
50,
"outputPrefix":
"output",
},
output=self.minimal_test(),
),
]
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",
),
"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",
),
"haplotype_caller_pairHmmImplementation":
"LOGLESS_CACHING",
},
output=Vcf.basic_test(
"out",
51000,
221,
["GATKCommandLine"],
"5e48624cb5ef379a7d6d39cec44bc856",
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"flagstat": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam.flagstat",
),
"collectInsertSizeMetrics": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.metrics.txt",
),
"coverage": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.genomeCoverageBed.stdout",
),
"rmdupFlagstat": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam.bam.flagstat",
),
"genome": True,
},
output=TextFile.basic_test(
tag="out",
min_size=948,
line_count=2,
md5="575354942cfb8d0367725f9020181443",
expected_file_path=os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1_performance_summary.csv",
),
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"fastqc_datafiles": [
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.fastqc_data.txt",
)
],
"cutadapt_adaptors_lookup":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"contaminant_list.txt",
),
},
output=[],
),
]
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",
),
"knownSites": [
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz",
),
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz",
),
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz",
),
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz",
),
],
"intervals": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"BRCA1.hg38.bed",
),
"javaOptions": ["-Xmx12G"],
},
output=TextFile.basic_test(
"out", 1131758, "#:GATKReport.v1.1:5", 10376
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"file": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.generated.gathered.vcf",
),
},
output=CompressedVcf.basic_test(
"out",
11500,
221,
["GATKCommandLine"],
"b7acb0a9900713cc7da7aeed5160c971",
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"outputType": "z",
"vcf": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.generated.gathered.vcf.gz",
),
},
output=CompressedVcf.basic_test(
"out",
11602,
221,
["GATKCommandLine"],
"fcc35adbb0624abc91f6de2e9042f749",
),
)
]