Skip to content

Commit 8f825ad

Browse files
jasonshillerjasonshiller
authored
Merge pull request #137 from Plant-Food-Research-Open/feat/append_genome_prefix_to_feature_ids
Added parameter append_genome_prefix_to_feature_ids
2 parents cdb351b + 79728ef commit 8f825ad

13 files changed

+57
-34
lines changed

‎.nf-core.yml

+1-1
Original file line numberDiff line numberDiff line change
@@ -30,5 +30,5 @@ template:
3030
outdir: .
3131
skip_features:
3232
- igenomes
33-
version: 0.6.0
33+
version: 0.6.1dev
3434
update: null

‎CHANGELOG.md

+11
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,17 @@
33
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
44
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
55

6+
## v0.6.1dev - [05-March-2025]
7+
8+
### 'Added'
9+
10+
1. Added parameter `append_genome_prefix_to_feature_ids` which allows the user to add genome prefixes defined in the assemblysheet to the final Gff/Fasta files [#135](https://github.com/Plant-Food-Research-Open/genepal/issues/135)
11+
12+
### `Dependencies`
13+
14+
1. Nextflow!>=24.04.2
15+
2. nf-schema@2.1.1
16+
617
## v0.6.0 - [20-Dec-2024]
718

819
### 'Added'

‎CITATION.cff

+1-1
Original file line numberDiff line numberDiff line change
@@ -31,7 +31,7 @@ authors:
3131
- family-names: "Thomson"
3232
given-names: "Susan"
3333
title: "genepal: A Nextflow pipeline for genome and pan-genome annotation"
34-
version: 0.6.0
34+
version: 0.6.1dev
3535
date-released: 2024-11-21
3636
url: "https://github.com/Plant-Food-Research-Open/genepal"
3737
doi: 10.5281/zenodo.14195006

‎assets/multiqc_config.yml

+1-1
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
report_comment: >
22
This report has been generated by the <a href="https://github.com/plant-food-research-open/genepal" target="_blank">plant-food-research-open/genepal</a>
33
analysis pipeline. For information about how to interpret these results, please see the
4-
<a href="https://github.com/plant-food-research-open/genepal/blob/0.6.0/docs/usage.md" target="_blank">documentation</a>.
4+
<a href="https://github.com/plant-food-research-open/genepal/blob/dev/docs/usage.md" target="_blank">documentation</a>.
55
66
report_section_order:
77
"plant-food-research-open-genepal-methods-description":

‎docs/parameters.md

+13-11
Original file line numberDiff line numberDiff line change
@@ -59,20 +59,22 @@ A Nextflow pipeline for consensus, phased and pan-genome annotation.
5959

6060
## Post-annotation filtering options
6161

62-
| Parameter | Description | Type | Default | Required | Hidden |
63-
| ----------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- | ------- | -------- | ------ |
64-
| `allow_isoforms` | Allow multiple isoforms for gene models | `boolean` | True | | |
65-
| `enforce_full_intron_support` | Require every model to have external evidence for all its introns | `boolean` | True | | |
66-
| `filter_liftoff_by_hints` | Use BRAKER hints to filter Liftoff models | `boolean` | True | | |
67-
| `eggnogmapper_purge_nohits` | Purge transcripts which do not have a hit against eggnog | `boolean` | | | |
68-
| `filter_genes_by_aa_length` | Filter genes with open reading frames shorter than the specified number of amino acids excluding the stop codon. If set to `null`, this filter step is skipped. | `integer` | 24 | | |
62+
| Parameter | Description | Type | Default | Required | Hidden |
63+
| ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | --------- | ------- | -------- | ------ |
64+
| `allow_isoforms` | Allow multiple isoforms for gene models | `boolean` | True | | |
65+
| `enforce_full_intron_support` | Require every model to have external evidence for all its introns | `boolean` | True | | |
66+
| `filter_liftoff_by_hints` | Use BRAKER hints to filter Liftoff models | `boolean` | True | | |
67+
| `eggnogmapper_purge_nohits` | Purge transcripts which do not have a hit against eggnog | `boolean` | | | |
68+
| `filter_genes_by_aa_length` | Filter genes with open reading frames shorter than the specified number of amino acids excluding the stop codon. If set to `null`, this filter step is |
69+
| skipped. | `integer` | 24 | | |
6970

7071
## Annotation output options
7172

72-
| Parameter | Description | Type | Default | Required | Hidden |
73-
| ---------------------------------- | --------------------------------------------- | --------- | ------- | -------- | ------ |
74-
| `braker_save_outputs` | Save BRAKER files | `boolean` | | | |
75-
| `add_attrs_to_proteins_cds_fastas` | Add gff attributes to proteins/cDNA/CDS fasta | `boolean` | | | |
73+
| Parameter | Description | Type | Default | Required | Hidden |
74+
| ------------------------------------- | ------------------------------------------------------------------ | --------- | ------- | -------- | ------ |
75+
| `braker_save_outputs` | Save BRAKER files | `boolean` | | | |
76+
| `add_attrs_to_proteins_cds_fastas` | Add gff attributes to proteins/cDNA/CDS fasta | `boolean` | | | |
77+
| `append_genome_prefix_to_feature_ids` | Add genome prefix to all the features in the final Gff/Fasta files | `boolean` | True | | |
7678

7779
## Evaluation options
7880

‎nextflow.config

+2-1
Original file line numberDiff line numberDiff line change
@@ -59,6 +59,7 @@ params {
5959
// Annotation output options
6060
braker_save_outputs = false
6161
add_attrs_to_proteins_cds_fastas = false
62+
append_genome_prefix_to_feature_ids = true
6263

6364
// Evaluation options
6465
busco_skip = false
@@ -262,7 +263,7 @@ manifest {
262263
description = """A Nextflow pipeline for consensus, phased and pan-genome annotation."""
263264
mainScript = 'main.nf'
264265
nextflowVersion = '!>=24.04.2'
265-
version = '0.6.0'
266+
version = '0.6.1dev'
266267
doi = 'https://doi.org/10.5281/zenodo.14195006'
267268
}
268269

‎nextflow_schema.json

+6
Original file line numberDiff line numberDiff line change
@@ -298,6 +298,12 @@
298298
"type": "boolean",
299299
"description": "Add gff attributes to proteins/cDNA/CDS fasta",
300300
"fa_icon": "fas fa-question-circle"
301+
},
302+
"append_genome_prefix_to_feature_ids": {
303+
"type": "boolean",
304+
"fa_icon": "fas fa-question-circle",
305+
"description": "Add genome prefix to all the features in the final Gff/Fasta files",
306+
"default": true
301307
}
302308
}
303309
},

‎pfr/params.json

+1
Original file line numberDiff line numberDiff line change
@@ -35,6 +35,7 @@
3535
"filter_genes_by_aa_length": 24,
3636
"braker_save_outputs": false,
3737
"add_attrs_to_proteins_cds_fastas": false,
38+
"append_genome_prefix_to_feature_ids": true,
3839
"busco_skip": false,
3940
"busco_lineage_datasets": "embryophyta_odb10"
4041
}

‎subworkflows/local/gff_merge_cleanup.nf

+2-1
Original file line numberDiff line numberDiff line change
@@ -8,6 +8,7 @@ workflow GFF_MERGE_CLEANUP {
88
ch_braker_gff // Channel: [ meta, gff ]
99
ch_liftoff_gff // Channel: [ meta, gff ]
1010
val_filter_by_aa_length // val(null|Integer)
11+
val_append_genome_prefix // val(true|false)
1112

1213
main:
1314
ch_versions = Channel.empty()
@@ -154,7 +155,7 @@ workflow GFF_MERGE_CLEANUP {
154155

155156
if (feat == 'gene') {
156157
gene_counter += 1
157-
def new_gene_id = append_genome_prefix ? "${meta.id}.g${gene_counter}" : "g${gene_counter}"
158+
def new_gene_id = val_append_genome_prefix ? "${meta.id}.g${gene_counter}" : "g${gene_counter}"
158159
def updated_atts = atts.replaceAll(/ID=[^;]+/, "ID=${new_gene_id}")
159160
tx_formatted_lines << (cols[0..7] + [updated_atts]).join('\t')
160161
current_gene_id = new_gene_id

‎tests/minimal/main.nf.test.snap

+8-8
Original file line numberDiff line numberDiff line change
@@ -64,15 +64,15 @@
6464
"tsebra": "1.1.2.5"
6565
},
6666
"Workflow": {
67-
"plant-food-research-open/genepal": "v0.6.0"
67+
"plant-food-research-open/genepal": "v0.6.1dev"
6868
}
6969
},
7070
"stable paths": [
71-
"a_thaliana.cdna.fasta:md5,12b9bef973e488640aec8c04ba3882fe",
72-
"a_thaliana.cds.fasta:md5,b81060419355a590560f92aec8536281",
73-
"a_thaliana.gt.gff3:md5,528459cf9596523bf66de99d24c37e20",
74-
"a_thaliana.pep.fasta:md5,4994c0393ca0245a1c57966d846d101e",
75-
"a_thaliana.gff3:md5,30adac1b21d7aaed6ca7fb71ab33f32d",
71+
"a_thaliana.cdna.fasta:md5,f44a6acdc245b85a935ef9ed3fc62967",
72+
"a_thaliana.cds.fasta:md5,4fd5a251a3912b452844e1f7332f514d",
73+
"a_thaliana.gt.gff3:md5,2ce78be84046266da89a2b8256b1ac3c",
74+
"a_thaliana.pep.fasta:md5,38ae660abc78eb57d467bb48b5170f19",
75+
"a_thaliana.gff3:md5,a95b8141ed7d90935a7d6c0a389fb53f",
7676
"summary_stats.json:md5,007ba5cf2b7a2fd395a27d9458ca2d2e"
7777
],
7878
"stable names": [
@@ -108,8 +108,8 @@
108108
],
109109
"meta": {
110110
"nf-test": "0.9.2",
111-
"nextflow": "24.04.4"
111+
"nextflow": "24.10.4"
112112
},
113-
"timestamp": "2024-12-12T09:36:52.952048"
113+
"timestamp": "2025-03-05T14:07:05.189463"
114114
}
115115
}

‎tests/short/main.nf.test.snap

+6-6
Original file line numberDiff line numberDiff line change
@@ -5,18 +5,18 @@
55
"successful tasks": 0,
66
"versions": {
77
"Workflow": {
8-
"plant-food-research-open/genepal": "v0.6.0"
8+
"plant-food-research-open/genepal": "v0.6.1dev"
99
}
1010
},
1111
"stable paths": [
12-
12+
1313
]
1414
}
1515
],
1616
"meta": {
17-
"nf-test": "0.9.0",
18-
"nextflow": "24.04.4"
17+
"nf-test": "0.9.2",
18+
"nextflow": "24.10.4"
1919
},
20-
"timestamp": "2024-12-05T16:37:07.37961"
20+
"timestamp": "2025-03-05T13:37:02.87085"
2121
}
22-
}
22+
}

‎tests/stub/main.nf.test.snap

+3-3
Original file line numberDiff line numberDiff line change
@@ -134,7 +134,7 @@
134134
"tsebra": "1.1.2.5"
135135
},
136136
"Workflow": {
137-
"plant-food-research-open/genepal": "v0.6.0"
137+
"plant-food-research-open/genepal": "v0.6.1dev"
138138
}
139139
},
140140
"stable paths": [
@@ -188,8 +188,8 @@
188188
],
189189
"meta": {
190190
"nf-test": "0.9.2",
191-
"nextflow": "24.04.4"
191+
"nextflow": "24.10.5"
192192
},
193-
"timestamp": "2024-12-16T13:24:49.69503"
193+
"timestamp": "2025-03-05T14:53:07.564693"
194194
}
195195
}

‎workflows/genepal.nf

+2-1
Original file line numberDiff line numberDiff line change
@@ -179,7 +179,8 @@ workflow GENEPAL {
179179
GFF_MERGE_CLEANUP(
180180
ch_braker_purged_gff,
181181
ch_liftoff_gff3,
182-
params.filter_genes_by_aa_length
182+
params.filter_genes_by_aa_length,
183+
params.append_genome_prefix_to_feature_ids
183184
)
184185

185186
ch_merged_gff = GFF_MERGE_CLEANUP.out.gff

0 commit comments

Comments
 (0)