Skip to content

Commit b85bbda

Browse files
jonasscheidjonasscheid
authored
Merge pull request #320 from nf-core/copilot/bump-default-reference-grch38
Set default genome reference to GRCh38
2 parents 6713737 + 8f1d4a3 commit b85bbda

14 files changed

Lines changed: 697 additions & 263 deletions

‎CHANGELOG.md‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -21,6 +21,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
2121
### `Changed`
2222

2323
- [#316](https://github.com/nf-core/epitopeprediction/pull/316) Added parameter `--biomart_dump` in `epaa.py` ([@SusiJo](https://github.com/SusiJo/)).
24+
- [#320](https://github.com/nf-core/epitopeprediction/pull/320) Set default genome reference to GRCh38 ([@jonasscheid](https://github.com/jonasscheid/)).
2425

2526
## 3.1.0 - Lustnau - 2025-10-22
2627

conf/test_grch38.config renamed to conf/test_grch37.config

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44
* -------------------------------------------------
55
* Defines bundled input files and everything required
66
* to run a fast and simple test. Use as follows:
7-
* nextflow run nf-core/epitopeprediction -profile test_grch38,<docker/singularity> --outdir <OUTDIR>
7+
* nextflow run nf-core/epitopeprediction -profile test_grch37,<docker/singularity> --outdir <OUTDIR>
88
*/
99

1010
process {
@@ -16,11 +16,11 @@ process {
1616
}
1717

1818
params {
19-
config_profile_name = 'Test GRCh38 profile'
19+
config_profile_name = 'Test GRCh37 profile'
2020
config_profile_description = 'Minimal test dataset to check pipeline function'
2121

2222
input = params.pipelines_testdata_base_path + 'epitopeprediction/testdata/sample_sheets/sample_sheet_variants.csv'
23-
genome_reference = 'grch38'
23+
genome_reference = 'grch37'
2424
// Reduce number of possible peptide lengths to speed up test
2525
min_peptide_length_classI = 9
2626
max_peptide_length_classI = 10

conf/test_grch38_offline.config renamed to conf/test_offline.config

Lines changed: 2 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@
44
* -------------------------------------------------
55
* Defines bundled input files and everything required
66
* to run a fast and simple test. Use as follows:
7-
* nextflow run nf-core/epitopeprediction -profile test_grch38_offline,<docker/singularity> --outdir <OUTDIR>
7+
* nextflow run nf-core/epitopeprediction -profile test_offline,<docker/singularity> --outdir <OUTDIR>
88
*/
99

1010
process {
@@ -16,12 +16,11 @@ process {
1616
}
1717

1818
params {
19-
config_profile_name = 'Test GRCh38 profile and offline biomart'
19+
config_profile_name = 'Test profile for offline biomart'
2020
config_profile_description = 'Minimal test dataset to check pipeline function'
2121

2222
input = params.pipelines_testdata_base_path + 'epitopeprediction/testdata/sample_sheets/sample_sheet_variants.csv'
2323
biomart_dump_path = params.pipelines_testdata_base_path + 'epitopeprediction/testdata/biomart_dupms/grch38p14_biomart_dump.tsv'
24-
genome_reference = 'grch38'
2524
// Reduce number of possible peptide lengths to speed up test
2625
min_peptide_length_classI = 9
2726
max_peptide_length_classI = 10

‎docs/usage.md‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@ An [example samplesheet](../assets/samplesheet.csv) has been provided with the p
3737
> [!IMPORTANT]
3838
> Please note that genomic variants have to be annotated. Currently, we support variants that have been annotated using [SnpEff](http://pcingola.> github.io/SnpEff/) and [VEP](https://www.ensembl.org/info/docs/tools/vep/index.html).
3939
40-
For genomic variants, reference information from `Ensembl BioMart` is used. The default database version is the most recent `GRCh37` version. If you want to do the predictions based on `GRCh38` as the reference genome, please specify `--genome_reference grch38` in your pipeline call. You can also specify valid `Ensembl BioMart` archive version urls as `--genome_reference` value, e.g. [the archive version of December 2021](http://dec2021.archive.ensembl.org/).
40+
For genomic variants, reference information from `Ensembl BioMart` is used. The default database version is the most recent `GRCh38` version. If you want to do the predictions based on `GRCh37` as the reference genome, please specify `--genome_reference grch37` in your pipeline call. You can also specify valid `Ensembl BioMart` archive version urls as `--genome_reference` value, e.g. [the archive version of December 2021](http://dec2021.archive.ensembl.org/).
4141

4242
> [!IMPORTANT]
4343
> Please note that old archive versions are regularly retired, therefore it might be possible that a used version is not available anymore at a later point.

‎nextflow.config‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -21,7 +21,7 @@ params {
2121
biomart_dump_path = null // Path to local Biomart dump (for offline usage)
2222

2323
// References
24-
genome_reference = 'grch37'
24+
genome_reference = 'grch38'
2525
genome = null
2626

2727
// Options: Predictions
@@ -200,8 +200,8 @@ profiles {
200200

201201
test { includeConfig 'conf/test.config' }
202202
test_norm { includeConfig 'conf/test_norm.config' }
203-
test_grch38 { includeConfig 'conf/test_grch38.config' }
204-
test_grch38_offline { includeConfig 'conf/test_grch38_offline.config' }
203+
test_grch37 { includeConfig 'conf/test_grch37.config' }
204+
test_offline { includeConfig 'conf/test_offline.config' }
205205
test_peptides { includeConfig 'conf/test_peptides.config' }
206206
test_proteins { includeConfig 'conf/test_proteins.config' }
207207
test_mhcnuggets { includeConfig 'conf/test_mhcnuggets.config' }

‎nextflow_schema.json‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -56,7 +56,7 @@
5656
},
5757
"genome_reference": {
5858
"type": "string",
59-
"default": "grch37",
59+
"default": "grch38",
6060
"help_text": "This defines against which human Ensembl genome reference the pipeline performs the analysis including the incorporation of genetic variants. If `grch37` or `grch38` are specified, the most recent Ensembl Biomart version for genome versions will be used. Alternatively, an Ensembl Biomart (archive) version can be specified, e.g. http://jan2020.archive.ensembl.org/.",
6161
"description": "Specifies the Ensembl genome reference version that will be used."
6262
},

‎tests/default.nf.test.snap‎

Lines changed: 5 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -99,10 +99,8 @@
9999
"mhcnuggets/sample1_sample1_variants_chr1_chunk_0_predicted_mhcnuggets.csv",
100100
"mhcnuggets/sample1_sample1_variants_chr20_chunk_0_predicted_mhcnuggets.csv",
101101
"mhcnuggets/sample1_sample1_variants_chr21_chunk_0_predicted_mhcnuggets.csv",
102-
"mhcnuggets/sample1_sample1_variants_chr22_chunk_0_predicted_mhcnuggets.csv",
103102
"mhcnuggets/sample1_sample1_variants_chr2_chunk_0_predicted_mhcnuggets.csv",
104103
"mhcnuggets/sample1_sample1_variants_chr3_chunk_0_predicted_mhcnuggets.csv",
105-
"mhcnuggets/sample1_sample1_variants_chr4_chunk_0_predicted_mhcnuggets.csv",
106104
"mhcnuggets/sample1_sample1_variants_chr5_chunk_0_predicted_mhcnuggets.csv",
107105
"mhcnuggets/sample1_sample1_variants_chr6_chunk_0_predicted_mhcnuggets.csv",
108106
"mhcnuggets/sample1_sample1_variants_chr7_chunk_0_predicted_mhcnuggets.csv",
@@ -122,10 +120,8 @@
122120
"mhcnuggets/sample2_sample2_variants_chr1_chunk_0_predicted_mhcnuggets.csv",
123121
"mhcnuggets/sample2_sample2_variants_chr20_chunk_0_predicted_mhcnuggets.csv",
124122
"mhcnuggets/sample2_sample2_variants_chr21_chunk_0_predicted_mhcnuggets.csv",
125-
"mhcnuggets/sample2_sample2_variants_chr22_chunk_0_predicted_mhcnuggets.csv",
126123
"mhcnuggets/sample2_sample2_variants_chr2_chunk_0_predicted_mhcnuggets.csv",
127124
"mhcnuggets/sample2_sample2_variants_chr3_chunk_0_predicted_mhcnuggets.csv",
128-
"mhcnuggets/sample2_sample2_variants_chr4_chunk_0_predicted_mhcnuggets.csv",
129125
"mhcnuggets/sample2_sample2_variants_chr5_chunk_0_predicted_mhcnuggets.csv",
130126
"mhcnuggets/sample2_sample2_variants_chr6_chunk_0_predicted_mhcnuggets.csv",
131127
"mhcnuggets/sample2_sample2_variants_chr7_chunk_0_predicted_mhcnuggets.csv",
@@ -209,17 +205,17 @@
209205
"bcftools_stats_vqc_Count_Transversions.txt:md5,e301b8c8760fdd149b2e8924d8f9e9b7",
210206
"multiqc_bcftools_stats.txt:md5,a3aca1d8f180bbbe0053a9210681ca5a",
211207
"multiqc_binder_length_distribution.txt:md5,9fbb7555888c124b4458791617ced876",
212-
"multiqc_binder_rank_distribution.txt:md5,0a6ab01f856c295e45128c0d0e58fd6e",
213-
"multiqc_binding_affinity_distribution.txt:md5,50cb7bb5538c048505e073838340d14c",
208+
"multiqc_binder_rank_distribution.txt:md5,04c38d0e18af2a2865209403dadb27f5",
209+
"multiqc_binding_affinity_distribution.txt:md5,790bb528d25dc8e898a122681bd4c3e9",
214210
"multiqc_citations.txt:md5,5cbab4ecbe14049d965fd97bd61d252b",
215211
"multiqc_general_stats.txt:md5,a2861dfd886f449d522e37c92889a474",
216-
"multiqc_peptide_binding_prediction_stats.txt:md5,a6ae4c99a2f2a4bb158f3f6f909d24c0"
212+
"multiqc_peptide_binding_prediction_stats.txt:md5,02b02b1e76ce42dca08fb8f5b6a4f8f6"
217213
]
218214
],
219215
"meta": {
220216
"nf-test": "0.9.3",
221-
"nextflow": "25.10.2"
217+
"nextflow": "25.04.8"
222218
},
223-
"timestamp": "2025-12-15T11:35:28.681429461"
219+
"timestamp": "2026-01-08T16:03:51.946358805"
224220
}
225221
}

tests/grch38.nf.test renamed to tests/grch37.nf.test

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,9 +3,9 @@ nextflow_pipeline {
33
name "Test pipeline"
44
script "../main.nf"
55
tag "pipeline"
6-
profile "test_grch38"
6+
profile "test_grch37"
77

8-
test("-profile test_grch38") {
8+
test("-profile test_grch37") {
99

1010
when {
1111
params {

0 commit comments

Comments
 (0)