Skip to content

Commit d8d021c

Browse files
authored
Merge pull request #105 from PMCC-BioinformaticsCore/reduce-test-files
Reduce test files
2 parents 408128b + dca6046 commit d8d021c

File tree

103 files changed

+131
-1422922
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

103 files changed

+131
-1422922
lines changed

janis_bioinformatics/tools/babrahambioinformatics/fastqc/base.py

Lines changed: 5 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -248,21 +248,14 @@ def outputs(self) -> List[ToolOutput]:
248248
]
249249

250250
def tests(self):
251+
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
251252
return [
252253
TTestCase(
253254
name="basic",
254255
input={
255256
"reads": [
256-
os.path.join(
257-
BioinformaticsTool.test_data_path(),
258-
"wgsgermline_data",
259-
"NA12878-BRCA1_R1.fastq.gz",
260-
),
261-
os.path.join(
262-
BioinformaticsTool.test_data_path(),
263-
"wgsgermline_data",
264-
"NA12878-BRCA1_R2.fastq.gz",
265-
),
257+
f"{remote_dir}/NA12878-BRCA1_R1.fastq.gz",
258+
f"{remote_dir}/NA12878-BRCA1_R2.fastq.gz",
266259
],
267260
"threads": 1,
268261
},
@@ -284,16 +277,8 @@ def tests(self):
284277
name="minimal",
285278
input={
286279
"reads": [
287-
os.path.join(
288-
BioinformaticsTool.test_data_path(),
289-
"wgsgermline_data",
290-
"NA12878-BRCA1_R1.fastq.gz",
291-
),
292-
os.path.join(
293-
BioinformaticsTool.test_data_path(),
294-
"wgsgermline_data",
295-
"NA12878-BRCA1_R2.fastq.gz",
296-
),
280+
f"{remote_dir}/NA12878-BRCA1_R1.fastq.gz",
281+
f"{remote_dir}/NA12878-BRCA1_R2.fastq.gz",
297282
],
298283
"threads": 1,
299284
},

janis_bioinformatics/tools/bcftools/sort/base.py

Lines changed: 2 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -116,16 +116,13 @@ def bind_metadata(self):
116116
)
117117

118118
def tests(self):
119+
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
119120
return [
120121
TTestCase(
121122
name="basic",
122123
input={
123124
"outputType": "z",
124-
"vcf": os.path.join(
125-
BioinformaticsTool.test_data_path(),
126-
"wgsgermline_data",
127-
"NA12878-BRCA1.generated.gathered.vcf.gz",
128-
),
125+
"vcf": f"{remote_dir}/NA12878-BRCA1.generated.gathered.vcf.gz",
129126
},
130127
output=CompressedVcf.basic_test(
131128
"out",

janis_bioinformatics/tools/bedtools/genomecoveragebed/base.py

Lines changed: 3 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -180,20 +180,13 @@ def outputs(self):
180180
]
181181

182182
def tests(self):
183+
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
183184
return [
184185
TTestCase(
185186
name="basic",
186187
input={
187-
"inputBam": os.path.join(
188-
BioinformaticsTool.test_data_path(),
189-
"wgsgermline_data",
190-
"NA12878-BRCA1.markduped.bam.bam",
191-
),
192-
"genome": os.path.join(
193-
BioinformaticsTool.test_data_path(),
194-
"wgsgermline_data",
195-
"NA12878-BRCA1.genome_file.txt",
196-
),
188+
"inputBam": f"{remote_dir}/NA12878-BRCA1.markduped.bam.bam",
189+
"genome": f"{remote_dir}/NA12878-BRCA1.genome_file.txt",
197190
},
198191
output=TextFile.basic_test(
199192
"out",

janis_bioinformatics/tools/bwa/mem/base.py

Lines changed: 8 additions & 35 deletions
Original file line numberDiff line numberDiff line change
@@ -287,61 +287,34 @@ def bind_metadata(self):
287287
]
288288

289289
def tests(self):
290+
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
290291
return [
291292
TTestCase(
292293
name="basic",
293294
input={
294295
"reads": [
295-
os.path.join(
296-
BioinformaticsTool.test_data_path(),
297-
"wgsgermline_data",
298-
"NA12878-BRCA1_R1.fastq.gz",
299-
),
300-
os.path.join(
301-
BioinformaticsTool.test_data_path(),
302-
"wgsgermline_data",
303-
"NA12878-BRCA1_R2.fastq.gz",
304-
),
296+
f"{remote_dir}/NA12878-BRCA1_R1.fastq.gz",
297+
f"{remote_dir}/NA12878-BRCA1_R2.fastq.gz",
305298
],
306-
"reference": os.path.join(
307-
BioinformaticsTool.test_data_path(),
308-
"wgsgermline_data",
309-
"Homo_sapiens_assembly38.chr17.fasta",
310-
),
299+
"reference": f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
311300
"markShorterSplits": True,
312301
"readGroupHeaderLine": "@RG\tID:NA12878-BRCA1\tSM:NA12878-BRCA1\tLB:NA12878-BRCA1\tPL:ILLUMINA",
313302
"threads": 16,
314303
},
315304
output=Bam.basic_test(
316305
"out",
317306
8628527,
318-
os.path.join(
319-
BioinformaticsTool.test_data_path(),
320-
"wgsgermline_data",
321-
"NA12878-BRCA1.bwamem.flagstat",
322-
),
307+
f"{remote_dir}/NA12878-BRCA1.bwamem.flagstat",
323308
),
324309
),
325310
TTestCase(
326311
name="minimal",
327312
input={
328313
"reads": [
329-
os.path.join(
330-
BioinformaticsTool.test_data_path(),
331-
"wgsgermline_data",
332-
"NA12878-BRCA1_R1.fastq.gz",
333-
),
334-
os.path.join(
335-
BioinformaticsTool.test_data_path(),
336-
"wgsgermline_data",
337-
"NA12878-BRCA1_R2.fastq.gz",
338-
),
314+
f"{remote_dir}/NA12878-BRCA1_R1.fastq.gz",
315+
f"{remote_dir}/NA12878-BRCA1_R2.fastq.gz",
339316
],
340-
"reference": os.path.join(
341-
BioinformaticsTool.test_data_path(),
342-
"wgsgermline_data",
343-
"Homo_sapiens_assembly38.chr17.fasta",
344-
),
317+
"reference": f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
345318
"markShorterSplits": True,
346319
"readGroupHeaderLine": "@RG\tID:NA12878-BRCA1\tSM:NA12878-BRCA1\tLB:NA12878-BRCA1\tPL:ILLUMINA",
347320
"threads": 16,

janis_bioinformatics/tools/common/bwaaligner.py

Lines changed: 8 additions & 35 deletions
Original file line numberDiff line numberDiff line change
@@ -85,28 +85,17 @@ def bind_metadata(self):
8585
self.metadata.version = "1.1"
8686

8787
def tests(self):
88+
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
8889
return [
8990
TTestCase(
9091
name="basic",
9192
input={
9293
"sample_name": "NA12878-BRCA1",
9394
"fastq": [
94-
os.path.join(
95-
BioinformaticsTool.test_data_path(),
96-
"wgsgermline_data",
97-
"NA12878-BRCA1_R1.fastq.gz",
98-
),
99-
os.path.join(
100-
BioinformaticsTool.test_data_path(),
101-
"wgsgermline_data",
102-
"NA12878-BRCA1_R2.fastq.gz",
103-
),
95+
f"{remote_dir}/NA12878-BRCA1_R1.fastq.gz",
96+
f"{remote_dir}/NA12878-BRCA1_R2.fastq.gz",
10497
],
105-
"reference": os.path.join(
106-
BioinformaticsTool.test_data_path(),
107-
"wgsgermline_data",
108-
"Homo_sapiens_assembly38.chr17.fasta",
109-
),
98+
"reference": f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
11099
"cutadapt_qualityCutoff": 15,
111100
"cutadapt_minimumLength": 50,
112101
"bwamem_markShorterSplits": True,
@@ -120,34 +109,18 @@ def tests(self):
120109
"out",
121110
2826000,
122111
49688,
123-
os.path.join(
124-
BioinformaticsTool.test_data_path(),
125-
"wgsgermline_data",
126-
"NA12878-BRCA1.bam.flagstat",
127-
),
112+
f"{remote_dir}/NA12878-BRCA1.bam.flagstat",
128113
),
129114
),
130115
TTestCase(
131116
name="minimal",
132117
input={
133118
"sample_name": "NA12878-BRCA1",
134119
"fastq": [
135-
os.path.join(
136-
BioinformaticsTool.test_data_path(),
137-
"wgsgermline_data",
138-
"NA12878-BRCA1_R1.fastq.gz",
139-
),
140-
os.path.join(
141-
BioinformaticsTool.test_data_path(),
142-
"wgsgermline_data",
143-
"NA12878-BRCA1_R2.fastq.gz",
144-
),
120+
f"{remote_dir}/NA12878-BRCA1_R1.fastq.gz",
121+
f"{remote_dir}/NA12878-BRCA1_R2.fastq.gz",
145122
],
146-
"reference": os.path.join(
147-
BioinformaticsTool.test_data_path(),
148-
"wgsgermline_data",
149-
"Homo_sapiens_assembly38.chr17.fasta",
150-
),
123+
"reference": f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
151124
"cutadapt_qualityCutoff": 15,
152125
"cutadapt_minimumLength": 50,
153126
"bwamem_markShorterSplits": True,

janis_bioinformatics/tools/common/gatkbasecalbam.py

Lines changed: 9 additions & 40 deletions
Original file line numberDiff line numberDiff line change
@@ -77,55 +77,24 @@ def bind_metadata(self):
7777
)
7878

7979
def tests(self):
80+
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
8081
return [
8182
TTestCase(
8283
name="basic",
8384
input={
84-
"bam": os.path.join(
85-
BioinformaticsTool.test_data_path(),
86-
"wgsgermline_data",
87-
"NA12878-BRCA1.markduped.bam",
88-
),
89-
"reference": os.path.join(
90-
BioinformaticsTool.test_data_path(),
91-
"wgsgermline_data",
92-
"Homo_sapiens_assembly38.chr17.fasta",
93-
),
94-
"snps_dbsnp": os.path.join(
95-
BioinformaticsTool.test_data_path(),
96-
"wgsgermline_data",
97-
"Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz",
98-
),
99-
"snps_1000gp": os.path.join(
100-
BioinformaticsTool.test_data_path(),
101-
"wgsgermline_data",
102-
"1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz",
103-
),
104-
"known_indels": os.path.join(
105-
BioinformaticsTool.test_data_path(),
106-
"wgsgermline_data",
107-
"Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz",
108-
),
109-
"mills_indels": os.path.join(
110-
BioinformaticsTool.test_data_path(),
111-
"wgsgermline_data",
112-
"Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz",
113-
),
114-
"intervals": os.path.join(
115-
BioinformaticsTool.test_data_path(),
116-
"wgsgermline_data",
117-
"BRCA1.hg38.bed",
118-
),
85+
"bam": f"{remote_dir}/NA12878-BRCA1.markduped.bam",
86+
"reference": f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
87+
"snps_dbsnp": f"{remote_dir}/Homo_sapiens_assembly38.dbsnp138.BRCA1.vcf.gz",
88+
"snps_1000gp": f"{remote_dir}/1000G_phase1.snps.high_confidence.hg38.BRCA1.vcf.gz",
89+
"known_indels": f"{remote_dir}/Homo_sapiens_assembly38.known_indels.BRCA1.vcf.gz",
90+
"mills_indels": f"{remote_dir}/Mills_and_1000G_gold_standard.indels.hg38.BRCA1.vcf.gz",
91+
"intervals": f"{remote_dir}/BRCA1.hg38.bed",
11992
},
12093
output=BamBai.basic_test(
12194
"out",
12295
2600000,
12396
21000,
124-
os.path.join(
125-
BioinformaticsTool.test_data_path(),
126-
"wgsgermline_data",
127-
"NA12878-BRCA1.recalibrated.flagstat",
128-
),
97+
f"{remote_dir}/NA12878-BRCA1.recalibrated.flagstat",
12998
),
13099
)
131100
]

janis_bioinformatics/tools/common/mergeandmark/mergeandmark_4_1_3.py

Lines changed: 4 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -66,16 +66,13 @@ def bind_metadata(self):
6666
)
6767

6868
def tests(self):
69+
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
6970
return [
7071
TTestCase(
7172
name="basic",
7273
input={
7374
"bams": [
74-
os.path.join(
75-
BioinformaticsTool.test_data_path(),
76-
"wgsgermline_data",
77-
"NA12878-BRCA1.sorted.bam",
78-
)
75+
f"{remote_dir}/NA12878-BRCA1.sorted.bam",
7976
],
8077
"maxRecordsInRam": 5000000,
8178
"createIndex": True,
@@ -86,22 +83,14 @@ def tests(self):
8683
"out",
8784
2829000,
8885
3780,
89-
os.path.join(
90-
BioinformaticsTool.test_data_path(),
91-
"wgsgermline_data",
92-
"NA12878-BRCA1.markduped.bam.flagstat",
93-
),
86+
f"{remote_dir}/NA12878-BRCA1.markduped.bam.flagstat",
9487
),
9588
),
9689
TTestCase(
9790
name="minimal",
9891
input={
9992
"bams": [
100-
os.path.join(
101-
BioinformaticsTool.test_data_path(),
102-
"wgsgermline_data",
103-
"NA12878-BRCA1.sorted.bam",
104-
)
93+
f"{remote_dir}/NA12878-BRCA1.sorted.bam",
10594
],
10695
"maxRecordsInRam": 5000000,
10796
"createIndex": True,

janis_bioinformatics/tools/common/splitmultiallele.py

Lines changed: 3 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -151,20 +151,13 @@ def doc(self):
151151
""".strip()
152152

153153
def tests(self):
154+
remote_dir = "https://swift.rc.nectar.org.au/v1/AUTH_4df6e734a509497692be237549bbe9af/janis-test-data/bioinformatics/wgsgermline_data"
154155
return [
155156
TTestCase(
156157
name="basic",
157158
input={
158-
"vcf": os.path.join(
159-
BioinformaticsTool.test_data_path(),
160-
"wgsgermline_data",
161-
"NA12878-BRCA1.haplotype_uncompressed.stdout",
162-
),
163-
"reference": os.path.join(
164-
BioinformaticsTool.test_data_path(),
165-
"wgsgermline_data",
166-
"Homo_sapiens_assembly38.chr17.fasta",
167-
),
159+
"vcf": f"{remote_dir}/NA12878-BRCA1.haplotype_uncompressed.stdout",
160+
"reference": f"{remote_dir}/Homo_sapiens_assembly38.chr17.fasta",
168161
},
169162
output=Vcf.basic_test(
170163
"out",

0 commit comments

Comments
 (0)