Skip to content

Commit 78ad48b

Browse files
maxulyssemaxulysse
authored
Remove unused modules (bowtie2/build, fastqscreen/buildfromindex) (#177)
* Remove unused modules + move PREPARE_GENOME to root main.nf * Actually not using BOWTIE2 * CHANGELOG * snapshot * regenerate snapshot * auto-format * Apply suggestion from @maxulysse
1 parent 1c4e615 commit 78ad48b

26 files changed

Lines changed: 694 additions & 938 deletions

File tree

‎CHANGELOG.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -82,6 +82,8 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
8282
- [#174](https://github.com/nf-core/seqinspector/pull/174) No params included in workflows
8383
- [#175](https://github.com/nf-core/seqinspector/pull/175) Update all modules and migrate the whole pipeline to using topic versions
8484
- [#176](https://github.com/nf-core/seqinspector/pull/176) No modules binaries
85+
- [#177](https://github.com/nf-core/seqinspector/pull/177) Remove non used modules
86+
- [#177](https://github.com/nf-core/seqinspector/pull/177) Move PREPARE_GENOME to the root main.nf script
8587

8688
### `Dependencies`
8789

‎CITATIONS.md‎

Lines changed: 0 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -10,10 +10,6 @@
1010
1111
## Pipeline tools
1212

13-
- [Bowtie2](https://www.nature.com/articles/nmeth.1923)
14-
15-
> Langmead B, Salzberg SL. Fast gapped-read alignment with Bowtie 2. Nat Methods. 2012 Apr;9(4):357-9. doi: 10.1038/nmeth.1923. PubMed PMID: 22388286.
16-
1713
- [BWAMEM2](https://ieeexplore.ieee.org/abstract/document/8820962)
1814

1915
> Vasimuddin Md, Misra S, Li H, Aluru S. Efficient Architecture-Aware Acceleration of BWA-MEM for Multicore Systems. In: 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE; 2019:314-324. doi:10.1109/IPDPS.2019.00041

‎README.md‎

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -54,7 +54,6 @@ If provided, nf-core/seqinspector can also parse statistics from an Illumina run
5454

5555
| Tool | Version |
5656
| ----------- | ------- |
57-
| bowtie2 | 2.5.4 |
5857
| bwamem2 | 2.3 |
5958
| fastqc | 0.12.1 |
6059
| fastqscreen | 0.16.0 |

‎conf/base.config‎

Lines changed: 20 additions & 20 deletions
Original file line numberDiff line numberDiff line change
@@ -9,9 +9,9 @@
99
*/
1010

1111
process {
12-
cpus = { 1 * task.attempt }
13-
memory = { 6.GB * task.attempt }
14-
time = { 4.h * task.attempt }
12+
cpus = { 1 * task.attempt }
13+
memory = { 6.GB * task.attempt }
14+
time = { 4.h * task.attempt }
1515

1616
errorStrategy = { task.exitStatus in ((130..145) + 104 + 175) ? 'retry' : 'finish' }
1717
maxRetries = 1
@@ -23,36 +23,36 @@ process {
2323
// If possible, it would be nice to keep the same label naming convention when
2424
// adding in your local modules too.
2525
// See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
26-
withLabel:process_single {
27-
cpus = { 1 }
26+
withLabel: process_single {
27+
cpus = { 1 }
2828
memory = { 6.GB * task.attempt }
29-
time = { 4.h * task.attempt }
29+
time = { 4.h * task.attempt }
3030
}
31-
withLabel:process_low {
32-
cpus = { 2 * task.attempt }
31+
withLabel: process_low {
32+
cpus = { 2 * task.attempt }
3333
memory = { 12.GB * task.attempt }
34-
time = { 4.h * task.attempt }
34+
time = { 4.h * task.attempt }
3535
}
36-
withLabel:process_medium {
37-
cpus = { 6 * task.attempt }
36+
withLabel: process_medium {
37+
cpus = { 6 * task.attempt }
3838
memory = { 36.GB * task.attempt }
39-
time = { 8.h * task.attempt }
39+
time = { 8.h * task.attempt }
4040
}
41-
withLabel:process_high {
42-
cpus = { 12 * task.attempt }
41+
withLabel: process_high {
42+
cpus = { 12 * task.attempt }
4343
memory = { 72.GB * task.attempt }
44-
time = { 16.h * task.attempt }
44+
time = { 16.h * task.attempt }
4545
}
46-
withLabel:process_long {
47-
time = { 20.h * task.attempt }
46+
withLabel: process_long {
47+
time = { 20.h * task.attempt }
4848
}
49-
withLabel:process_high_memory {
49+
withLabel: process_high_memory {
5050
memory = { 200.GB * task.attempt }
5151
}
52-
withLabel:error_ignore {
52+
withLabel: error_ignore {
5353
errorStrategy = 'ignore'
5454
}
55-
withLabel:error_retry {
55+
withLabel: error_retry {
5656
errorStrategy = 'retry'
5757
maxRetries = 2
5858
}

‎conf/igenomes.config‎

Lines changed: 408 additions & 408 deletions
Large diffs are not rendered by default.

‎conf/modules.config‎

Lines changed: 34 additions & 34 deletions
Original file line numberDiff line numberDiff line change
@@ -11,21 +11,20 @@
1111
*/
1212

1313
process {
14-
1514
publishDir = [
1615
path: { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
1716
mode: params.publish_dir_mode
1817
]
1918

20-
withName: 'SEQTK_SAMPLE' {
19+
withName: SEQTK_SAMPLE {
2120
ext.args = '-s100'
2221
}
2322

24-
withName: 'FASTQC' {
23+
withName: FASTQC {
2524
ext.args = '--quiet'
2625
}
2726

28-
withName: 'SEQFU_STATS' {
27+
withName: SEQFU_STATS {
2928
ext.args = ''
3029
publishDir = [
3130
path: { "${params.outdir}/seqfu_stats" },
@@ -34,93 +33,94 @@ process {
3433
]
3534
}
3635

37-
withName: 'BWAMEM2_INDEX' {
36+
withName: BWAMEM2_INDEX {
3837
publishDir = [
3938
path: { "${params.outdir}/bwamem2_index" },
4039
mode: params.publish_dir_mode
4140
]
4241
}
4342

44-
withName: 'PICARD_CREATESEQUENCEDICTIONARY' {
43+
withName: PICARD_CREATESEQUENCEDICTIONARY {
4544
publishDir = [
4645
path: { "${params.outdir}/picard_createsequencedictionary" },
4746
mode: params.publish_dir_mode
4847
]
4948
}
5049

51-
withName: 'BWAMEM2_MEM' {
50+
withName: BWAMEM2_MEM {
5251
publishDir = [
5352
path: { "${params.outdir}/bwamem2_mem" },
5453
mode: params.publish_dir_mode
5554
]
5655
}
5756

58-
withName: 'PICARD_COLLECTMULTIPLEMETRICS' {
57+
withName: PICARD_COLLECTMULTIPLEMETRICS {
5958
publishDir = [
6059
path: { "${params.outdir}/picard_collectmultiplemetrics" },
6160
mode: params.publish_dir_mode
6261
]
6362
}
6463

65-
withName: 'PICARD_COLLECTHSMETRICS' {
64+
withName: PICARD_COLLECTHSMETRICS {
65+
ext.args = { "--TMP_DIR ." }
6666
publishDir = [
6767
path: { "${params.outdir}/picard_collecthsmetrics" },
6868
mode: params.publish_dir_mode
6969
]
70-
ext.args = {"--TMP_DIR ."}
7170
}
7271

73-
withName: 'SAMTOOLS_FAIDX' {
72+
withName: SAMTOOLS_FAIDX {
7473
publishDir = [
7574
path: { "${params.outdir}/samtools_faidx" },
7675
mode: params.publish_dir_mode
7776
]
7877
}
7978

80-
withName: 'SAMTOOLS_INDEX' {
79+
withName: SAMTOOLS_INDEX {
8180
publishDir = [
8281
path: { "${params.outdir}/bwamem2_mem" },
8382
mode: params.publish_dir_mode
8483
]
8584
}
8685

87-
withName: 'RUNDIRPARSER' {
88-
publishDir = [
89-
path: { "${params.outdir}/rundirparser" },
90-
mode: params.publish_dir_mode,
86+
withName: RUNDIRPARSER {
9187
// The process _mqc.txt outputs should have identical names for the same sequencing platforms
9288
// in order to be grouped together in the MultiQC report, but here we need to enforce uniqueness
9389
// to avoid overwriting results in the publishDir.
94-
saveAs: { filename -> "${meta.dirname}_${filename}" }
95-
]
90+
publishDir = [
91+
path: { "${params.outdir}/rundirparser" },
92+
mode: params.publish_dir_mode,
93+
saveAs: { filename -> "${meta.dirname}_${filename}" }]
9694
}
9795

98-
withName: 'MULTIQC_GLOBAL' {
99-
ext.args = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
96+
withName: MULTIQC_GLOBAL {
97+
ext.args = { params.multiqc_title ? "--title \"${params.multiqc_title}\"" : '' }
10098
publishDir = [
10199
path: { "${params.outdir}/multiqc/global_report" },
102100
mode: params.publish_dir_mode
103101
]
104102
}
105103

106-
withName: 'MULTIQC_PER_TAG' {
107-
ext.args = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' }
104+
withName: MULTIQC_PER_TAG {
105+
ext.args = { params.multiqc_title ? "--title \"${params.multiqc_title}\"" : '' }
108106
publishDir = [
109107
path: { "${params.outdir}/multiqc/group_reports" },
110108
mode: params.publish_dir_mode,
111109
saveAs: { filename ->
112-
if (filename == 'versions.yml') {
113-
return null
114-
} else if (filename =~/\[TAG:.+\]_multiqc_(report\.html|plots|data)/) {
115-
def tag = (filename =~ /\[TAG:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
116-
def new_filename = filename.replaceFirst(
117-
"(?<prefix>.*)\\[TAG:${tag}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
118-
'${prefix}${suffix}')
119-
return "${tag}/${new_filename}"
120-
} else {
121-
return filename
122-
}
110+
if (filename == 'versions.yml') {
111+
return null
123112
}
124-
]
113+
else if (filename =~ /\[TAG:.+\]_multiqc_(report\.html|plots|data)/) {
114+
def tag = (filename =~ /\[TAG:(.+)\]_multiqc_(report\.html|plots|data)/)[0][1]
115+
def new_filename = filename.replaceFirst(
116+
"(?<prefix>.*)\\[TAG:${tag}\\]_(?<suffix>multiqc_(report\\.html|plots|data).*)",
117+
'${prefix}${suffix}',
118+
)
119+
return "${tag}/${new_filename}"
120+
}
121+
else {
122+
return filename
123+
}
124+
}]
125125
}
126126
}

‎conf/test.config‎

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -15,11 +15,11 @@ params {
1515
config_profile_description = 'Minimal test dataset to check pipeline function'
1616

1717
// Input data
18-
input = params.pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet.csv'
19-
fastq_screen_references = "${projectDir}/assets/example_fastq_screen_references.csv"
18+
input = params.pipelines_testdata_base_path + 'seqinspector/testdata/NovaSeq6000/samplesheet.csv'
19+
fastq_screen_references = "${projectDir}/assets/example_fastq_screen_references.csv"
2020

2121
// Genome references
22-
genome = 'R64-1-1'
22+
genome = 'R64-1-1'
2323
}
2424

2525
process {
@@ -28,5 +28,4 @@ process {
2828
memory: '8.GB',
2929
time: '1.h'
3030
]
31-
3231
}

‎conf/test_full.config‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -16,8 +16,8 @@ params {
1616
config_profile_description = 'Full test dataset to check pipeline function'
1717

1818
// Input data for full size test
19-
input = params.pipelines_testdata_base_path + 'seqinspector/full_tests/SampleSheet.csv'
19+
input = params.pipelines_testdata_base_path + 'seqinspector/full_tests/SampleSheet.csv'
2020

2121
// Genome references
22-
genome = 'R64-1-1'
22+
genome = 'R64-1-1'
2323
}

0 commit comments

Comments
 (0)