Skip to content

Commit 284ced5

Browse files
lyh970817lyh970817
committed
test(gcta/bivariateremlldms): strengthen ldms assertions
1 parent 7e06c13 commit 284ced5

3 files changed

Lines changed: 256 additions & 98 deletions

File tree

‎modules/nf-core/gcta/bivariateremlldms/tests/helpers/makegrm/main.nf‎

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
process GCTA_MAKEGRM_HELPER {
2+
tag "${meta.id}"
3+
label "process_medium"
4+
conda "${projectDir}/modules/nf-core/gcta/bivariateremlldms/environment.yml"
5+
container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
6+
'docker://community.wave.seqera.io/library/gcta:1.94.1--9bc35dc424fcf6e9' :
7+
'community.wave.seqera.io/library/gcta:1.94.1--9bc35dc424fcf6e9'}"
8+
9+
input:
10+
tuple val(meta), path(bed), path(bim), path(fam)
11+
tuple val(meta2), path(extract_file)
12+
13+
output:
14+
tuple val(meta), path("${meta.id}.grm.id"), path("${meta.id}.grm.bin"), path("${meta.id}.grm.N.bin"), emit: grm_files
15+
16+
script:
17+
def extract_param = extract_file ? "--extract ${extract_file}" : ""
18+
def bfile_prefix = bed.baseName
19+
"""
20+
set -euo pipefail
21+
22+
gcta \\
23+
--bfile "${bfile_prefix}" \\
24+
${extract_param} \\
25+
--make-grm \\
26+
--out "${meta.id}" \\
27+
--thread-num ${task.cpus}
28+
"""
29+
30+
stub:
31+
"""
32+
touch "${meta.id}.grm.id"
33+
touch "${meta.id}.grm.bin"
34+
touch "${meta.id}.grm.N.bin"
35+
"""
36+
}

‎modules/nf-core/gcta/bivariateremlldms/tests/main.nf.test‎

Lines changed: 71 additions & 37 deletions
Original file line numberDiff line numberDiff line change
@@ -7,7 +7,7 @@ nextflow_process {
77
tag "modules_nfcore"
88
tag "gcta"
99
tag "gcta/bivariateremlldms"
10-
tag "gcta/makegrmpart"
10+
tag "tests/helpers/makegrm"
1111
tag "gawk"
1212

1313
setup {
@@ -73,24 +73,15 @@ nextflow_process {
7373
}
7474
}
7575

76-
run("GCTA_MAKEGRMPART", alias: "GCTA_MAKEGRMPART_LDMS1") {
77-
script "../../makegrmpart/main.nf"
76+
run("GCTA_MAKEGRM_HELPER", alias: "GCTA_MAKEGRM_LDMS1") {
77+
script "../tests/helpers/makegrm/main.nf"
7878
process {
7979
"""
80-
file('plink_simulated.mbfile').text = 'plink_simulated\\n'
81-
8280
input[0] = [
83-
[ id:'plink_simulated_ldms1', part_gcta_job:1, nparts_gcta:1 ],
84-
file('plink_simulated.mbfile'),
85-
[
86-
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bed', checkIfExists: true)
87-
],
88-
[
89-
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bim', checkIfExists: true)
90-
],
91-
[
92-
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.fam', checkIfExists: true)
93-
]
81+
[ id:'plink_simulated_ldms1.part_1_1' ],
82+
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bed', checkIfExists: true),
83+
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bim', checkIfExists: true),
84+
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.fam', checkIfExists: true)
9485
]
9586
input[1] = [
9687
[ id:'plink_random_selected_snp' ],
@@ -100,24 +91,15 @@ nextflow_process {
10091
}
10192
}
10293

103-
run("GCTA_MAKEGRMPART", alias: "GCTA_MAKEGRMPART_LDMS2") {
104-
script "../../makegrmpart/main.nf"
94+
run("GCTA_MAKEGRM_HELPER", alias: "GCTA_MAKEGRM_LDMS2") {
95+
script "../tests/helpers/makegrm/main.nf"
10596
process {
10697
"""
107-
file('plink_simulated.mbfile').text = 'plink_simulated\\n'
108-
10998
input[0] = [
110-
[ id:'plink_simulated_ldms2', part_gcta_job:1, nparts_gcta:1 ],
111-
file('plink_simulated.mbfile'),
112-
[
113-
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bed', checkIfExists: true)
114-
],
115-
[
116-
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bim', checkIfExists: true)
117-
],
118-
[
119-
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.fam', checkIfExists: true)
120-
]
99+
[ id:'plink_simulated_ldms2.part_1_1' ],
100+
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bed', checkIfExists: true),
101+
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.bim', checkIfExists: true),
102+
file(params.modules_testdata_base_path + 'genomics/homo_sapiens/popgen/plink_simulated.fam', checkIfExists: true)
121103
]
122104
input[1] = GAWK_COMPLEMENT_VARIANTS.out.output
123105
"""
@@ -134,8 +116,8 @@ nextflow_process {
134116
.of('plink_simulated_ldms1.part_1_1\\nplink_simulated_ldms2.part_1_1')
135117
.collectFile(name:'plink_simulated_ldms.mgrm', newLine: true)
136118

137-
ldms_grm_files = GCTA_MAKEGRMPART_LDMS1.out.grm_files
138-
.mix(GCTA_MAKEGRMPART_LDMS2.out.grm_files)
119+
ldms_grm_files = GCTA_MAKEGRM_LDMS1.out.grm_files
120+
.mix(GCTA_MAKEGRM_LDMS2.out.grm_files)
139121
.map { meta, grm_id, grm_bin, grm_n_bin -> [grm_id, grm_bin, grm_n_bin] }
140122
.collect()
141123
.map { rows -> rows.flatten() }
@@ -156,16 +138,26 @@ nextflow_process {
156138
{ assert process.out.bivariate_results.size() == 1 },
157139
{ assert process.out.log_file.size() == 1 },
158140
{ assert process.out.bivariate_results.get(0).get(0).id == "Trait1__Trait2" },
141+
{ assert file(process.out.bivariate_results.get(0).get(1)).name == "Trait1__Trait2.hsq" },
159142
{ assert file(process.out.log_file.get(0).get(1)).name == "Trait1__Trait2.log" },
160143
{ assert file(process.out.log_file.get(0).get(1)).exists() },
161144
{
162145
def resultFile = file(process.out.bivariate_results.get(0).get(1))
146+
def parsedRows = resultFile.readLines()
147+
.collect { it.tokenize() }
148+
.findAll { row -> !row.isEmpty() && row[0] != 'Source' }
149+
.collect { row -> [row[0], row[1..-1]] }
150+
def valueBySource = parsedRows.collectEntries { row -> [(row[0]): row[1]] }
151+
assert valueBySource["V(G1)_tr1"] == ["0.000006", "0.210395"]
152+
assert valueBySource["C(G1)_tr12"] == ["0.607507", "0.601887"]
153+
assert valueBySource["logL"] == ["-844.942"]
154+
assert valueBySource["n"] == ["400"]
163155
assert snapshot(
164156
[
165157
[
166158
process.out.bivariate_results.get(0).get(0),
167159
resultFile.name,
168-
resultFile.readLines().collect { it.tokenize()[0] }
160+
parsedRows
169161
]
170162
],
171163
process.out.findAll { key, val -> key.startsWith('versions') }
@@ -175,6 +167,39 @@ nextflow_process {
175167
}
176168
}
177169

170+
test("homo_sapiens popgen - bivariate phenotype fails when mgrm references missing GRM basename") {
171+
config "./nextflow.config"
172+
when {
173+
process {
174+
"""
175+
broken_mgrm_file = Channel
176+
.of('plink_simulated_ldms_missing.part_1_1')
177+
.collectFile(name:'plink_simulated_ldms_broken.mgrm', newLine: true)
178+
179+
ldms_grm_files = GCTA_MAKEGRM_LDMS1.out.grm_files
180+
.mix(GCTA_MAKEGRM_LDMS2.out.grm_files)
181+
.map { meta, grm_id, grm_bin, grm_n_bin -> [grm_id, grm_bin, grm_n_bin] }
182+
.collect()
183+
.map { rows -> rows.flatten() }
184+
185+
input[0] = GAWK_BIVARIATE_PHENO.out.output
186+
input[1] = broken_mgrm_file
187+
.combine(ldms_grm_files)
188+
.map { row -> [[ id:'plink_simulated_ldms' ], row[0], row[1..-1]] }
189+
input[2] = [[ id:'covariates_quant' ], []]
190+
input[3] = [[ id:'covariates_cat' ], []]
191+
"""
192+
}
193+
}
194+
195+
then {
196+
assertAll(
197+
{ assert !process.success },
198+
{ assert process.exitStatus != 0 }
199+
)
200+
}
201+
}
202+
178203
test("homo_sapiens popgen - bivariate phenotype with ldms mgrm - stub") {
179204
options "-stub"
180205
config "./nextflow.config"
@@ -186,8 +211,8 @@ nextflow_process {
186211
.of('plink_simulated_ldms1.part_1_1\\nplink_simulated_ldms2.part_1_1')
187212
.collectFile(name:'plink_simulated_ldms.mgrm', newLine: true)
188213

189-
ldms_grm_files = GCTA_MAKEGRMPART_LDMS1.out.grm_files
190-
.mix(GCTA_MAKEGRMPART_LDMS2.out.grm_files)
214+
ldms_grm_files = GCTA_MAKEGRM_LDMS1.out.grm_files
215+
.mix(GCTA_MAKEGRM_LDMS2.out.grm_files)
191216
.map { meta, grm_id, grm_bin, grm_n_bin -> [grm_id, grm_bin, grm_n_bin] }
192217
.collect()
193218
.map { rows -> rows.flatten() }
@@ -205,7 +230,16 @@ nextflow_process {
205230
then {
206231
assertAll(
207232
{ assert process.success },
208-
{ assert snapshot(process.out).match() }
233+
{ assert process.out.bivariate_results.get(0).get(0).id == "Trait1__Trait2" },
234+
{ assert file(process.out.bivariate_results.get(0).get(1)).name == "Trait1__Trait2.hsq" },
235+
{ assert file(process.out.log_file.get(0).get(1)).name == "Trait1__Trait2.log" },
236+
{
237+
assert snapshot(
238+
process.out.bivariate_results,
239+
process.out.log_file,
240+
process.out.findAll { key, val -> key.startsWith('versions') }
241+
).match()
242+
}
209243
)
210244
}
211245
}

0 commit comments

Comments
 (0)