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={
"reads": [
f"{remote_dir}/NA12878-BRCA1_R1.fastq.gz",
f"{remote_dir}/NA12878-BRCA1_R2.fastq.gz",
],
"threads":
1,
},
output=FastqGzPair.basic_test("out", 824000, 408000, 416000) +
Array.array_wrapper([TextFile.basic_test(
"datafile",
81000,
)]),
),
TTestCase(
name="minimal",
input={
"reads": [
f"{remote_dir}/NA12878-BRCA1_R1.fastq.gz",
f"{remote_dir}/NA12878-BRCA1_R2.fastq.gz",
],
"threads":
1,
},
output=self.minimal_test(),
),
]
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={
"positions":
f"{remote_dir}/NA12878-BRCA1.sorted.uncompressed.stdout",
"reference":
f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
"bam": f"{remote_dir}/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):
# The first 5 lines of the file include headers that change with every run (time, etc)
with open(
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.metrics.txt",
),
"r",
) as f:
for i in range(5):
next(f)
expected_content = f.read()
return [
TTestCase(
name="basic",
input={
"bam": os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam",
),
"javaOptions": ["-Xmx6G"],
},
output=TextFile.basic_test("out", 7260, expected_content, 905)
+ [
TTestExpectedOutput(
tag="outHistogram",
preprocessor=TTestPreprocessor.FileSize,
operator=operator.ge,
expected_value=15600,
),
],
)
]
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={
"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):
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
# The first 5 lines of the file include headers that change with every run (time, etc)
with open(
os.path.join(
BioinformaticsTool.test_data_path(),
"NA12878-BRCA1.markduped.metrics.txt",
),
"r",
) as f:
for i in range(5):
next(f)
expected_content = f.read()
return [
TTestCase(
name="basic",
input={
"bam": f"{remote_dir}/NA12878-BRCA1.markduped.bam",
"javaOptions": ["-Xmx6G"],
},
output=TextFile.basic_test("out", 7260, expected_content, 905)
+ [
TTestExpectedOutput(
tag="outHistogram",
preprocessor=TTestPreprocessor.FileSize,
operator=operator.ge,
expected_value=15600,
),
],
)
]
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={
"flagstat":
f"{remote_dir}/NA12878-BRCA1.markduped.bam.flagstat",
"collectInsertSizeMetrics":
f"{remote_dir}/NA12878-BRCA1.markduped.metrics.txt",
"coverage":
f"{remote_dir}/NA12878-BRCA1.genomeCoverageBed.stdout",
"rmdupFlagstat":
f"{remote_dir}/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=
f"{remote_dir}/NA12878-BRCA1_performance_summary.csv",
),
)
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"inputBam":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.markduped.bam.bam",
),
"genome":
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.genome_file.txt",
),
},
output=TextFile.basic_test(
"out",
7432,
"chr17\t0\t83144233\t83257441\t0.99864",
220,
"f2007353bbd18f0a04eae9499d7c6a91",
),
)
]
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):
parent_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics"
somatic_data = f"{parent_dir}/wgssomatic_data"
return [
TTestCase(
name="basic",
input={
"javaOptions": ["-Xmx6G"],
"pileupTable": f"{somatic_data}/generated.txt",
"segmentationFileOut": "generated.txt.mutect2_segments",
},
output=TextFile.basic_test(
"contOut",
59,
"sample\tcontamination\terror\nNA12878-NA24385-mixture\t0.0\t0.0",
)
+ TextFile.basic_test(
"segOut",
125,
"contig\tstart\tend\tminor_allele_fraction\nchr17\t43045941\t43098543\t0.28541019662496847",
),
),
]
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):
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",
},
output=TextFile.basic_test(
"out",
410,
"19486 + 0 in total (QC-passed reads + QC-failed reads)",
13,
"ddbcfe52e60b925d222fb8bc1517a7a0",
),
)
]
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={
"inputBam":
f"{remote_dir}/NA12878-BRCA1.markduped.bam.bam",
"genome": f"{remote_dir}/NA12878-BRCA1.genome_file.txt",
},
output=TextFile.basic_test(
"out",
7432,
"chr17\t0\t83144233\t83257441\t0.99864",
220,
"f2007353bbd18f0a04eae9499d7c6a91",
),
)
]
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={
"reference":
f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
},
output=TextFile.basic_test("out", 15, "chr17\t83257441\n", 1),
),
TTestCase(
name="minimal",
input={
"reference":
f"{remote_dir}/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.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={
"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):
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={
"javaOptions": ["-Xmx48G"],
"bam": [
f"{somatic_data}/NA12878-NA24385-mixture.markduped.recalibrated.bam"
],
"sites": f"{somatic_data}/af-only-gnomad.hg38.BRCA1.vcf.gz",
"intervals": f"{germline_data}/BRCA1.hg38.bed",
},
output=TextFile.basic_test(
"out",
2592,
md5="54672b8b13d46aaef25c56351c82a3f4",
),
),
]
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",
"knownSites": [
f"{remote_dir}/Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz",
f"{remote_dir}/Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz",
f"{remote_dir}/Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz",
f"{remote_dir}/1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz",
],
"intervals":
f"{remote_dir}/BRCA1.hg38.bed",
"javaOptions": ["-Xmx12G"],
},
output=TextFile.basic_test("out", 1131758,
"#:GATKReport.v1.1:5", 10376),
)
]