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):
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",
"vcf":
f"{remote_dir}/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={
"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):
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={
"normal_id": "NA24385-BRCA1",
"tumor_id": "NA12878-NA24385-mixture",
"normal_bam":
f"{somatic_data}/NA24385-BRCA1.markduped.bam",
"tumor_bam":
f"{somatic_data}/NA12878-NA24385-mixture.markduped.bam",
"reference":
f"{germline_data}/Homo_sapiens_assembly38.chr17.fasta",
"vcf": f"{somatic_data}/uncompressed.stdout",
},
output=Vcf.basic_test(
"out",
44094,
156,
["GATKCommandLine"],
"5fc0e861893e0a23f974808265a6917e",
),
)
]
def tests(self) -> Optional[List[TTestCase]]:
bioinf_base = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics"
hg38 = f"{bioinf_base}/hg38"
chr17 = f"{bioinf_base}/petermac_testdata"
return [
TTestCase(
name="brca1",
input={
"sample_name":
"NA12878",
"reference":
f"{chr17}/Homo_sapiens_assembly38.chr17.fasta",
"fastqs": [[
f"{chr17}/NA12878-BRCA1_R1.fastq.gz",
f"{chr17}/NA12878-BRCA1_R2.fastq.gz",
]],
"gatk_intervals": [f"{chr17}/BRCA1.hg38.bed"],
"known_indels":
f"{chr17}/Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz",
"mills_indels":
f"{chr17}/Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz",
"snps_1000gp":
f"{chr17}/1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz",
"snps_dbsnp":
f"{chr17}/Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz",
"cutadapt_adapters":
f"{chr17}/contaminant_list.txt",
},
output=Vcf.basic_test("out_variants_bamstats", 51300, 230) +
Vcf.basic_test("out_variants_gatk_split", 51300, 221) +
BamBai.basic_test("out_bam", 2822000, 49600) +
TextFile.basic_test(
"out_performance_summary",
948,
md5="575354942cfb8d0367725f9020181443",
) + Array.array_wrapper([
ZipFile.basic_test("out_fastqc_reports", 408000),
ZipFile.basic_test("out_fastqc_reports", 416000),
]),
)
]
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):
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={
"normal_bam": f"{somatic_data}/NA24385-BRCA1.markduped.recalibrated.bam",
"tumor_bam": f"{somatic_data}/NA12878-NA24385-mixture.markduped.recalibrated.bam",
"reference": f"{germline_data}/Homo_sapiens_assembly38.chr17.fasta",
"gnomad": f"{somatic_data}/af-only-gnomad.hg38.BRCA1.vcf.gz",
"intervals": f"{germline_data}/BRCA1.hg38.bed",
"normal_name": "NA24385-BRCA1",
"filterpass_removeFileteredAll": True,
"filterpass_recode": True,
"filterpass_recodeINFOAll": True,
"output_bam_name": "mutect2.bam",
},
output=Vcf.basic_test(
"out",
33000,
147,
["GATKCommandLine"],
"c083775bc8c49397fb65ec12cd435688",
)
+ VcfTabix.basic_test(
"variants",
13000,
260,
182,
["GATKCommandLine"],
"6cfd70dda8599a270978868166ab6545",
)
+ BamBai.basic_test(
"out_bam",
813200,
21200,
f"{somatic_data}/somatic_variant_caller.flagstat",
),
),
]
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={
"javaOptions": ["-Xmx6G"],
"vcfs": [
f"{remote_dir}/NA12878-BRCA1.norm.vcf",
],
},
output=Vcf.basic_test(
"out",
51615,
221,
["GATKCommandLine"],
"b7acb0a9900713cc7da7aeed5160c971",
),
)
]
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={
"inputVcf":
f"{remote_dir}/NA12878-BRCA1.sorted.uncompressed.stdout",
"mpileup": f"{remote_dir}/NA12878-BRCA1.mpileup.stdout",
"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.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):
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={
"vcf": f"{somatic_data}/stdout.norm.vcf",
"removeFileteredAll": True,
"recode": True,
"recodeINFOAll": True,
},
output=Vcf.basic_test(
"out",
34393,
147,
["GATKCommandLine"],
"c083775bc8c49397fb65ec12cd435688",
),
),
]
def tests(self):
return [
TTestCase(
name="basic",
input={
"javaOptions": ["-Xmx6G"],
"vcfs": [
os.path.join(
BioinformaticsTool.test_data_path(),
"wgsgermline_data",
"NA12878-BRCA1.norm.vcf",
)
],
},
output=Vcf.basic_test(
"out",
51615,
221,
["GATKCommandLine"],
"b7acb0a9900713cc7da7aeed5160c971",
),
)
]
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.recalibrated.bam",
"intervals": f"{remote_dir}/BRCA1.hg38.bed",
"reference":
f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
"snps_dbsnp":
f"{remote_dir}/Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz",
"haplotype_caller_pairHmmImplementation":
"LOGLESS_CACHING",
},
output=Vcf.basic_test(
"out",
51000,
221,
["GATKCommandLine"],
"5e48624cb5ef379a7d6d39cec44bc856",
),
)
]
def tests(self) -> Optional[List[TTestCase]]:
bioinf_base = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics"
chr17 = f"{bioinf_base}/petermac_testdata"
return [
TTestCase(
name="basic",
input={
"normal_inputs": [[
f"{chr17}/NA24385-BRCA1_R1.fastq.gz",
f"{chr17}/NA24385-BRCA1_R21.fastq.gz",
]],
"normal_name":
"NA24385-BRCA1",
"tumor_inputs": [[
f"{chr17}/NA12878-NA24385-mixture-BRCA1_R1.fastq.gz",
f"{chr17}/NA12878-NA24385-mixture-BRCA1_R2.fastq.gz",
]],
"tumor_name":
"NA12878-NA24385-mixture",
"reference":
f"{chr17}/Homo_sapiens_assembly38.chr17.fasta",
"gridss_blacklist":
f"{chr17}/consensusBlacklist.hg38.chr17.bed",
"gnomad":
f"{chr17}/af-only-gnomad.hg38.BRCA1.vcf.gz",
"gatk_intervals": [f"{chr17}/BRCA1.hg38.bed"],
"known_indels":
f"{chr17}/Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz",
"mills_indels":
f"{chr17}/Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz",
"snps_1000gp":
f"{chr17}/1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz",
"snps_dbsnp":
f"{chr17}/Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz",
"cutadapt_adapters":
f"{chr17}/contaminant_list.txt",
},
output=BamBai.basic_test("out_normal_bam", 3265300, 49500) +
BamBai.basic_test("out_tumor_bam", 3341700, 49000) +
TextFile.basic_test(
"out_normal_performance_summary",
950,
md5="e3205735e5fe8c900f05050f8ed73f19",
) + TextFile.basic_test(
"out_tumor_performance_summary",
950,
md5="122bfa2ece90c0f030015feba4ba7d84",
) + CompressedVcf.basic_test(
"out_variants_gatk",
9040,
147,
["GATKCommandLine"],
"a2e4f96c451754ef8cba80494ed98a70",
) + Vcf.basic_test(
"out_variants",
44090,
156,
["GATKCommandLine"],
"5fc0e861893e0a23f974808265a6917e",
) + Array.array_wrapper([
Vcf.basic_test(
"out_variants_split",
34390,
147,
["GATKCommandLine"],
"c083775bc8c49397fb65ec12cd435688",
)
]) + FastqGzPair.basic_test("out_normal_fastqc_reports",
441500, 439800) +
FastqGzPair.basic_test("out_tumor_fastqc_reports", 434900,
440000),
)
]
