Add gffread EXTRACT_CDNA and EXTRACT_CDS feature to outputs

.github/workflows/ci.yml

@@ -55,7 +55,7 @@ jobs:
         uses: actions/[email protected]
 
       - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v2
+        uses: nf-core/setup-nextflow@v2.0.0
         with:
           version: "${{ matrix.NXF_VER }}"
 

.github/workflows/download_pipeline.yml

@@ -30,7 +30,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v2
+        uses: nf-core/setup-nextflow@v2.0.0
 
       - name: Disk space cleanup
         uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1

.github/workflows/linting.yml

@@ -34,7 +34,7 @@ jobs:
         uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
 
       - name: Install Nextflow
-        uses: nf-core/setup-nextflow@v2
+        uses: nf-core/setup-nextflow@v2.0.0
 
       - uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5
         with:

.nf-core.yml

@@ -30,5 +30,5 @@ template:
   outdir: .
   skip_features:
     - igenomes
-  version: 0.5.0
+  version: 0.6.0
 update: null

CHANGELOG.md

@@ -3,6 +3,12 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## v0.6.0 - [4-Dec-2024]
+
+### 'Added'
+
+1. Added cDNA and CDS outputs to <OUTPUT_DIR>/annotations/<SAMPLE> directory [#118](https://github.com/Plant-Food-Research-Open/genepal/issues/118)
+
 ## v0.5.0 - [21-Nov-2024]
 
 ### `Added`

CITATION.cff

@@ -31,7 +31,7 @@ authors:
   - family-names: "Thomson"
     given-names: "Susan"
 title: "genepal: A Nextflow pipeline for genome and pan-genome annotation"
-version: 0.5.0
+version: 0.6.0
 date-released: 2024-11-21
 url: "https://github.com/Plant-Food-Research-Open/genepal"
 doi: 10.5281/zenodo.14195006

README.md

@@ -97,7 +97,7 @@ sbatch ./pfr_genepal
 
 plant-food-research-open/genepal workflows were originally scripted by Jason Shiller ([@jasonshiller](https://github.com/jasonshiller)). Usman Rashid ([@gallvp](https://github.com/gallvp)) wrote the Nextflow pipeline.
 
-We thank the following people for their extensive assistance in the development of this pipeline:
+We thank the following people for extensive assistance in the development of the pipeline,
 
 - Cecilia Deng [@CeciliaDeng](https://github.com/CeciliaDeng)
 - Charles David [@charlesdavid](https://github.com/charlesdavid)
@@ -107,6 +107,10 @@ We thank the following people for their extensive assistance in the development
 - Susan Thomson [@cflsjt](https://github.com/cflsjt)
 - Ting-Hsuan Chen [@ting-hsuan-chen](https://github.com/ting-hsuan-chen)
 
+and for contributions to the codebase,
+
+- Liam Le Lievre [@liamlelievre](https://github.com/liamlelievre)
+
 The pipeline uses nf-core modules contributed by following authors:
 
 <a href="https://github.com/gallvp"><img src="https://github.com/gallvp.png" width="50" height="50"></a>
@@ -139,6 +143,7 @@ The pipeline uses nf-core modules contributed by following authors:
 <a href="https://github.com/charles-plessy"><img src="https://github.com/charles-plessy.png" width="50" height="50"></a>
 <a href="https://github.com/bunop"><img src="https://github.com/bunop.png" width="50" height="50"></a>
 <a href="https://github.com/abhi18av"><img src="https://github.com/abhi18av.png" width="50" height="50"></a>
+<a href="https://github.com/liamlelievre"><img src="https://github.com/liamlelievre.png" width="50" height="50"></a>
 
 ## Contributions and Support
 

assets/multiqc_config.yml

@@ -1,7 +1,7 @@
 report_comment: >
   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>
   analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://github.com/plant-food-research-open/genepal/blob/0.5.0/docs/usage.md" target="_blank">documentation</a>.
+  <a href="https://github.com/plant-food-research-open/genepal/blob/0.6.0/docs/usage.md" target="_blank">documentation</a>.
 
 report_section_order:
   "plant-food-research-open-genepal-methods-description":

conf/modules.config

@@ -286,7 +286,7 @@ process { // SUBWORKFLOW: GFF_STORE
     }
 
     withName: '.*:GFF_STORE:EXTRACT_PROTEINS' {
-        ext.args = params.add_attrs_to_proteins_fasta ? '-F -D -y' : '-y'
+        ext.args = params.add_attrs_to_proteins_cds_fastas ? '-F -D -y' : '-y'
         ext.prefix = { "${meta.id}.pep" }
 
         publishDir = [
@@ -295,6 +295,27 @@ process { // SUBWORKFLOW: GFF_STORE
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
     }
+
+    withName: '.*:GFF_STORE:EXTRACT_CDS' {
+        ext.args = params.add_attrs_to_proteins_cds_fastas ? '-F -D -x' : '-x'
+        ext.prefix = { "${meta.id}.cds" }
+
+        publishDir = [
+            path: { "${params.outdir}/annotations/$meta.id" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+        ]
+    }
+    withName: '.*:GFF_STORE:EXTRACT_CDNA' {
+        ext.args = params.add_attrs_to_proteins_cds_fastas ? '-F -D -w' : '-w'
+        ext.prefix = { "${meta.id}.cdna" }
+
+        publishDir = [
+            path: { "${params.outdir}/annotations/$meta.id" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+        ]
+    }
 }
 
 process { // SUBWORKFLOW: FASTA_ORTHOFINDER

docs/output.md

@@ -169,6 +169,8 @@ If more than one genome is included in the pipeline, [ORTHOFINDER](https://githu
   - `Y/`
     - `Y.gt.gff3`: Final annotation file for genome `Y` which contains gene models and their functional annotations
     - `Y.pep.fasta`: Protein sequences for the gene models
+    - 'Y.cdna.fasta': cDNA sequences for the gene models
+    - 'Y.cds.fasta': Coding sequences for the gene models
 
 </details>
 

docs/parameters.md

@@ -68,10 +68,10 @@ A Nextflow pipeline for consensus, phased and pan-genome annotation.
 
 ## Annotation output options
 
-| Parameter                     | Description                          | Type      | Default | Required | Hidden |
-| ----------------------------- | ------------------------------------ | --------- | ------- | -------- | ------ |
-| `braker_save_outputs`         | Save BRAKER files                    | `boolean` |         |          |        |
-| `add_attrs_to_proteins_fasta` | Add gff attributes to proteins fasta | `boolean` |         |          |        |
+| Parameter                          | Description                                   | Type      | Default | Required | Hidden |
+| ---------------------------------- | --------------------------------------------- | --------- | ------- | -------- | ------ |
+| `braker_save_outputs`              | Save BRAKER files                             | `boolean` |         |          |        |
+| `add_attrs_to_proteins_cds_fastas` | Add gff attributes to proteins/cDNA/CDS fasta | `boolean` |         |          |        |
 
 ## Evaluation options
 

nextflow.config

@@ -57,7 +57,7 @@ params {
 
     // Annotation output options
     braker_save_outputs                 = false
-    add_attrs_to_proteins_fasta         = false
+    add_attrs_to_proteins_cds_fastas    = false
 
     // Evaluation options
     busco_skip                          = false
@@ -261,7 +261,7 @@ manifest {
     description     = """A Nextflow pipeline for consensus, phased and pan-genome annotation."""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=24.04.2'
-    version         = '0.5.0'
+    version         = '0.6.0'
     doi             = 'https://doi.org/10.5281/zenodo.14195006'
 }
 

nextflow_schema.json

@@ -287,10 +287,10 @@
                     "description": "Save BRAKER files",
                     "fa_icon": "fas fa-question-circle"
                 },
-                "add_attrs_to_proteins_fasta": {
+                "add_attrs_to_proteins_cds_fastas": {
                     "type": "boolean",
-                    "fa_icon": "fas fa-question-circle",
-                    "description": "Add gff attributes to proteins fasta"
+                    "description": "Add gff attributes to proteins/cDNA/CDS fasta",
+                    "fa_icon": "fas fa-question-circle"
                 }
             }
         },

subworkflows/local/gff_store.nf

@@ -2,6 +2,8 @@ import java.net.URLEncoder
 
 include { GT_GFF3 as FINAL_GFF_CHECK    } from '../../modules/nf-core/gt/gff3/main'
 include { GFFREAD as EXTRACT_PROTEINS   } from '../../modules/nf-core/gffread/main'
+include { GFFREAD as EXTRACT_CDS        } from '../../modules/nf-core/gffread/main'
+include { GFFREAD as EXTRACT_CDNA       } from '../../modules/nf-core/gffread/main'
 
 workflow GFF_STORE {
     take:
@@ -133,9 +135,34 @@ workflow GFF_STORE {
     ch_final_proteins           = EXTRACT_PROTEINS.out.gffread_fasta
     ch_versions                 = ch_versions.mix(EXTRACT_PROTEINS.out.versions.first())
 
+    // MODULE: GFFREAD as EXTRACT_CDS
+    ch_cds_extraction_inputs    = ch_final_gff
+                                | join(ch_fasta)
+
+    EXTRACT_CDS(
+        ch_cds_extraction_inputs.map { meta, gff, fasta -> [ meta, gff ] },
+        ch_cds_extraction_inputs.map { meta, gff, fasta -> fasta }
+    )
+
+    ch_final_cds                = EXTRACT_CDS.out.gffread_fasta
+    ch_versions                 = ch_versions.mix(EXTRACT_CDS.out.versions.first())
+
+    // MODULE: GFFREAD as EXTRACT_CDNA
+    ch_cdna_extraction_inputs    = ch_final_gff
+                                | join(ch_fasta)
+
+    EXTRACT_CDNA(
+        ch_cdna_extraction_inputs.map { meta, gff, fasta -> [ meta, gff ] },
+        ch_cdna_extraction_inputs.map { meta, gff, fasta -> fasta}
+    )
+
+    ch_final_cdna                = EXTRACT_CDNA.out.gffread_fasta
+    ch_versions                  = ch_versions.mix(EXTRACT_CDNA.out.versions.first())
 
     emit:
     final_gff                   = ch_final_gff          // [ meta, gff ]
     final_proteins              = ch_final_proteins     // [ meta, fasta ]
+    final_cds                   = ch_final_cds          // [ meta, fasta ]
+    final_cdna                  = ch_final_cdna         // [ meta, fasta ]
     versions                    = ch_versions           // [ versions.yml ]
 }

tests/minimal/main.nf.test.snap

@@ -2,7 +2,7 @@
     "profile - test": {
         "content": [
             {
-                "successful tasks": 18,
+                "successful tasks": 20,
                 "versions": {
                     "AGAT_CONVERTSPGFF2GTF": {
                         "agat": "v1.4.0"
@@ -25,6 +25,12 @@
                     "CAT_PROTEIN_FASTAS": {
                         "pigz": "2.3.4"
                     },
+                    "EXTRACT_CDNA": {
+                        "gffread": "0.12.7"
+                    },
+                    "EXTRACT_CDS": {
+                        "gffread": "0.12.7"
+                    },
                     "EXTRACT_PROTEINS": {
                         "gffread": "0.12.7"
                     },
@@ -55,10 +61,12 @@
                         "tsebra": "1.1.2.5"
                     },
                     "Workflow": {
-                        "plant-food-research-open/genepal": "v0.5.0"
+                        "plant-food-research-open/genepal": "v0.6.0"
                     }
                 },
                 "stable paths": [
+                    "a_thaliana.cdna.fasta:md5,12b9bef973e488640aec8c04ba3882fe",
+                    "a_thaliana.cds.fasta:md5,b81060419355a590560f92aec8536281",
                     "a_thaliana.gt.gff3:md5,8ab16549095f605ff8715ac4a3de58ed",
                     "a_thaliana.pep.fasta:md5,4994c0393ca0245a1c57966d846d101e",
                     "a_thaliana.gff3:md5,d23d16cd86499d48a30ffb981ed27891",
@@ -67,6 +75,8 @@
                 "stable names": [
                     "annotations",
                     "annotations/a_thaliana",
+                    "annotations/a_thaliana/a_thaliana.cdna.fasta",
+                    "annotations/a_thaliana/a_thaliana.cds.fasta",
                     "annotations/a_thaliana/a_thaliana.gt.gff3",
                     "annotations/a_thaliana/a_thaliana.pep.fasta",
                     "etc",
@@ -81,9 +91,9 @@
             }
         ],
         "meta": {
-            "nf-test": "0.9.0",
-            "nextflow": "24.04.4"
+            "nf-test": "0.9.2",
+            "nextflow": "24.04.2"
         },
-        "timestamp": "2024-11-19T11:35:02.477202"
+        "timestamp": "2024-12-05T07:51:43.818374"
     }
-}
+}

tests/short/main.nf.test.snap

@@ -5,18 +5,18 @@
                 "successful tasks": 0,
                 "versions": {
                     "Workflow": {
-                        "plant-food-research-open/genepal": "v0.5.0"
+                        "plant-food-research-open/genepal": "v0.6.0"
                     }
                 },
                 "stable paths": [
-
+                    
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-10-22T11:39:43.110621"
+        "timestamp": "2024-12-05T16:37:07.37961"
     }
-}
+}

tests/stub/main.nf.test.snap

@@ -2,7 +2,7 @@
     "full - stub": {
         "content": [
             {
-                "successful tasks": 154,
+                "successful tasks": 162,
                 "versions": {
                     "AGAT_CONVERTSPGFF2GTF": {
                         "agat": "v1.4.0"
@@ -55,6 +55,12 @@
                     "EGGNOGMAPPER": {
                         "eggnog-mapper": "2.1.12"
                     },
+                    "EXTRACT_CDNA": {
+                        "gffread": "0.12.7"
+                    },
+                    "EXTRACT_CDS": {
+                        "gffread": "0.12.7"
+                    },
                     "EXTRACT_PROTEINS": {
                         "gffread": "0.12.7"
                     },
@@ -143,25 +149,33 @@
                         "tsebra": "1.1.2.5"
                     },
                     "Workflow": {
-                        "plant-food-research-open/genepal": "v0.5.0"
+                        "plant-food-research-open/genepal": "v0.6.0"
                     }
                 },
                 "stable paths": [
+                    "donghong.cdna.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
+                    "donghong.cds.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "donghong.emapper.annotations:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "donghong.emapper.hits:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "donghong.emapper.seed_orthologs:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "donghong.gt.gff3:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "donghong.pep.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
+                    "red5_v2p1.cdna.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
+                    "red5_v2p1.cds.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red5_v2p1.emapper.annotations:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red5_v2p1.emapper.hits:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red5_v2p1.emapper.seed_orthologs:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red5_v2p1.gt.gff3:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red5_v2p1.pep.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
+                    "red5_v3.cdna.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
+                    "red5_v3.cds.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red5_v3.emapper.annotations:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red5_v3.emapper.hits:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red5_v3.emapper.seed_orthologs:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red5_v3.gt.gff3:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red5_v3.pep.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
+                    "red7_v5.cdna.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
+                    "red7_v5.cds.fasta:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red7_v5.emapper.annotations:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red7_v5.emapper.hits:md5,d41d8cd98f00b204e9800998ecf8427e",
                     "red7_v5.emapper.seed_orthologs:md5,d41d8cd98f00b204e9800998ecf8427e",
@@ -188,9 +202,9 @@
             }
         ],
         "meta": {
-            "nf-test": "0.9.0",
-            "nextflow": "24.04.4"
+            "nf-test": "0.9.2",
+            "nextflow": "24.04.2"
         },
-        "timestamp": "2024-11-21T12:34:14.056074"
+        "timestamp": "2024-12-05T07:56:38.915238"
     }
-}
+}