Fixed an issue where TSEBRA failed because LIFTOFF lifted non-protein…

… coding genes

.github/workflows/branch.yml

@@ -1,15 +1,15 @@
 name: nf-core branch protection
-# This workflow is triggered on PRs to master branch on the repository
-# It fails when someone tries to make a PR against the nf-core `master` branch instead of `dev`
+# This workflow is triggered on PRs to main branch on the repository
+# It fails when someone tries to make a PR against the Plant-Food-Research-Open `main` branch instead of `dev`
 on:
   pull_request_target:
-    branches: [master]
+    branches: [main]
 
 jobs:
   test:
     runs-on: ubuntu-latest
     steps:
-      # PRs to the nf-core repo master branch are only ok if coming from the nf-core repo `dev` or any `patch` branches
+      # PRs to the nf-core repo main branch are only ok if coming from the nf-core repo `dev` or any `patch` branches
       - name: Check PRs
         if: github.repository == 'Plant-Food-Research-Open/genepal'
         run: |
@@ -22,7 +22,7 @@ jobs:
         uses: mshick/add-pr-comment@b8f338c590a895d50bcbfa6c5859251edc8952fc # v2
         with:
           message: |
-            ## This PR is against the `master` branch :x:
+            ## This PR is against the `main` branch :x:
 
             * Do not close this PR
             * Click _Edit_ and change the `base` to `dev`
@@ -32,9 +32,9 @@ jobs:
 
             Hi @${{ github.event.pull_request.user.login }},
 
-            It looks like this pull-request is has been made against the [${{github.event.pull_request.head.repo.full_name }}](https://github.com/${{github.event.pull_request.head.repo.full_name }}) `master` branch.
-            The `master` branch on nf-core repositories should always contain code from the latest release.
-            Because of this, PRs to `master` are only allowed if they come from the [${{github.event.pull_request.head.repo.full_name }}](https://github.com/${{github.event.pull_request.head.repo.full_name }}) `dev` branch.
+            It looks like this pull-request is has been made against the [${{github.event.pull_request.head.repo.full_name }}](https://github.com/${{github.event.pull_request.head.repo.full_name }}) `main` branch.
+            The `main` branch should always contain code from the latest release.
+            Because of this, PRs to `main` are only allowed if they come from the [${{github.event.pull_request.head.repo.full_name }}](https://github.com/${{github.event.pull_request.head.repo.full_name }}) `dev` branch.
 
             You do not need to close this PR, you can change the target branch to `dev` by clicking the _"Edit"_ button at the top of this page.
             Note that even after this, the test will continue to show as failing until you push a new commit.

.github/workflows/download_pipeline.yml

@@ -2,7 +2,7 @@ name: Test successful pipeline download with 'nf-core pipelines download'
 
 # Run the workflow when:
 #  - dispatched manually
-#  - when a PR is opened or reopened to master branch
+#  - when a PR is opened or reopened to main branch
 #  - the head branch of the pull request is updated, i.e. if fixes for a release are pushed last minute to dev.
 on:
   workflow_dispatch:
@@ -17,10 +17,10 @@ on:
       - edited
       - synchronize
     branches:
-      - master
+      - main
   pull_request_target:
     branches:
-      - master
+      - main
 
 env:
   NXF_ANSI_LOG: false

.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 +3,22 @@
 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 - [04-Dec-2024]
+
+### `Added`
+
+### `Fixed`
+
+1. Fixed an issue where TSEBRA failed because LIFTOFF lifted non-protein coding genes [#121](https://github.com/Plant-Food-Research-Open/genepal/issues/121)
+2. Switched branch name from `master` to `main` in the GHA CIs
+
+### `Dependencies`
+
+1. Nextflow!>=24.04.2
+2. [email protected]
+
+### `Deprecated`
+
 ## 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

@@ -35,7 +35,7 @@
   - Merge multi-reference liftoffs
   - Remove liftoff transcripts marked by _valid_ORF=False_
   - Remove liftoff genes with any intron shorter than 10 bp
-  - Remove rRNA and tRNA from liftoff
+  - Remove rRNA, tRNA and other non-protein coding models from liftoff
   - Optionally, allow or remove iso-forms
   - Remove BRAKER models from Liftoff loci
   - Merge Liftoff and BRAKER models

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

@@ -199,7 +199,7 @@ process { // SUBWORKFLOW: FASTA_LIFTOFF
     }
 
     withName: '.*:FASTA_LIFTOFF:GFFREAD_BEFORE_LIFTOFF' {
-        ext.args = '--no-pseudo --keep-genes'
+        ext.args = '--no-pseudo --keep-genes -C'
     }
 
     withName: '.*:FASTA_LIFTOFF:MERGE_LIFTOFF_ANNOTATIONS' {
@@ -212,7 +212,7 @@ process { // SUBWORKFLOW: FASTA_LIFTOFF
 
     withName: '.*:FASTA_LIFTOFF:GFFREAD_AFTER_LIFTOFF' {
         ext.prefix = { "${meta.id}.liftoff" }
-        ext.args = '--keep-genes'
+        ext.args = '--no-pseudo --keep-genes -C'
     }
 
     withName: '.*:FASTA_LIFTOFF:GFF_TSEBRA_SPFILTERFEATUREFROMKILLLIST:AGAT_CONVERTSPGFF2GTF' {

nextflow.config

@@ -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'
 }
 

subworkflows/local/fasta_liftoff.nf → subworkflows/local/fasta_liftoff/main.nf

@@ -1,30 +1,30 @@
-include { GUNZIP as GUNZIP_FASTA                                } from '../../modules/nf-core/gunzip/main'
-include { GUNZIP as GUNZIP_GFF                                  } from '../../modules/nf-core/gunzip/main'
-include { GFFREAD as GFFREAD_BEFORE_LIFTOFF                     } from '../../modules/nf-core/gffread/main'
-include { LIFTOFF                                               } from '../../modules/nf-core/liftoff/main'
-include { AGAT_SPMERGEANNOTATIONS as MERGE_LIFTOFF_ANNOTATIONS  } from '../../modules/nf-core/agat/spmergeannotations/main'
-include { AGAT_SPFLAGSHORTINTRONS                               } from '../../modules/gallvp/agat/spflagshortintrons/main'
-include { AGAT_SPFILTERFEATUREFROMKILLLIST                      } from '../../modules/nf-core/agat/spfilterfeaturefromkilllist/main'
-include { GFFREAD as GFFREAD_AFTER_LIFTOFF                      } from '../../modules/nf-core/gffread/main'
-include { GFF_TSEBRA_SPFILTERFEATUREFROMKILLLIST                } from '../../subworkflows/local/gff_tsebra_spfilterfeaturefromkilllist'
+include { GUNZIP as GUNZIP_FASTA                                } from '../../../modules/nf-core/gunzip/main'
+include { GUNZIP as GUNZIP_GFF                                  } from '../../../modules/nf-core/gunzip/main'
+include { GFFREAD as GFFREAD_BEFORE_LIFTOFF                     } from '../../../modules/nf-core/gffread/main'
+include { LIFTOFF                                               } from '../../../modules/nf-core/liftoff/main'
+include { AGAT_SPMERGEANNOTATIONS as MERGE_LIFTOFF_ANNOTATIONS  } from '../../../modules/nf-core/agat/spmergeannotations/main'
+include { AGAT_SPFLAGSHORTINTRONS                               } from '../../../modules/gallvp/agat/spflagshortintrons/main'
+include { AGAT_SPFILTERFEATUREFROMKILLLIST                      } from '../../../modules/nf-core/agat/spfilterfeaturefromkilllist/main'
+include { GFFREAD as GFFREAD_AFTER_LIFTOFF                      } from '../../../modules/nf-core/gffread/main'
+include { GFF_TSEBRA_SPFILTERFEATUREFROMKILLLIST                } from '../../../subworkflows/local/gff_tsebra_spfilterfeaturefromkilllist'
 
 workflow FASTA_LIFTOFF {
     take:
-    target_assemby                  // Channel: [ meta, fasta ]
-    xref_fasta                      // Channel: [ meta2, fasta ]
-    xref_gff                        // Channel: [ meta2, gff3 ]
+    target_assembly                 // Channel: [ meta, fasta ]
+    xref_fasta                      // Channel: [ meta2, fasta(.gz)? ]
+    xref_gff                        // Channel: [ meta2, gff3(.gz)? ]
     val_filter_liftoff_by_hints     // val(true|false)
     braker_hints                    // [ meta, gff ]
     tsebra_config                   // Channel: [ cfg ]
-    allow_isoforms                  // val(true|false)
+    val_allow_isoforms              // val(true|false)
 
 
     main:
     ch_versions                     = Channel.empty()
 
     // MODULE: GUNZIP as GUNZIP_FASTA
     ch_xref_fasta_branch            = xref_fasta
-                                    | branch { meta, file ->
+                                    | branch { _meta, file ->
                                         gz: "$file".endsWith(".gz")
                                         rest: !"$file".endsWith(".gz")
                                     }
@@ -40,7 +40,7 @@ workflow FASTA_LIFTOFF {
 
     // MODULE: GUNZIP as GUNZIP_GFF
     ch_xref_gff_branch              = xref_gff
-                                    | branch { meta, file ->
+                                    | branch { _meta, file ->
                                         gz: "$file".endsWith(".gz")
                                         rest: !"$file".endsWith(".gz")
                                     }
@@ -61,7 +61,7 @@ workflow FASTA_LIFTOFF {
     ch_versions                     = ch_versions.mix(GFFREAD_BEFORE_LIFTOFF.out.versions.first())
 
     // MODULE: LIFTOFF
-    ch_liftoff_inputs               = target_assemby
+    ch_liftoff_inputs               = target_assembly
                                     | combine(
                                         ch_xref_gunzip_fasta
                                         | join(
@@ -72,7 +72,7 @@ workflow FASTA_LIFTOFF {
                                         [
                                             [
                                                 id: "${meta.id}.from.${ref_meta.id}",
-                                                target_assemby: meta.id
+                                                target_assembly: meta.id
                                             ],
                                             target_fa,
                                             ref_fa,
@@ -81,21 +81,21 @@ workflow FASTA_LIFTOFF {
                                     }
 
     LIFTOFF(
-        ch_liftoff_inputs.map { meta, target_fa, ref_fa, ref_gff -> [ meta, target_fa ] },
-        ch_liftoff_inputs.map { meta, target_fa, ref_fa, ref_gff -> ref_fa },
-        ch_liftoff_inputs.map { meta, target_fa, ref_fa, ref_gff -> ref_gff },
+        ch_liftoff_inputs.map { meta, target_fa, _ref_fa, _ref_gff -> [ meta, target_fa ] },
+        ch_liftoff_inputs.map { _meta, _target_fa, ref_fa, _ref_gff -> ref_fa },
+        ch_liftoff_inputs.map { _meta, _target_fa, _ref_fa, ref_gff -> ref_gff },
         []
     )
 
     ch_liftoff_gff3                 = LIFTOFF.out.polished_gff3
-                                    | map { meta, gff -> [ [ id: meta.target_assemby ], gff ] }
+                                    | map { meta, gff -> [ [ id: meta.target_assembly ], gff ] }
                                     | groupTuple
 
     ch_versions                     = ch_versions.mix(LIFTOFF.out.versions.first())
 
     // MODULE: AGAT_SPMERGEANNOTATIONS as MERGE_LIFTOFF_ANNOTATIONS
     ch_merge_inputs                 = ch_liftoff_gff3
-                                    | branch { meta, list_polished ->
+                                    | branch { _meta, list_polished ->
                                         one: list_polished.size() == 1
                                         many: list_polished.size() > 1
                                     }
@@ -119,23 +119,29 @@ workflow FASTA_LIFTOFF {
     ch_flagged_gff                  = AGAT_SPFLAGSHORTINTRONS.out.gff
     ch_versions                     = ch_versions.mix(AGAT_SPFLAGSHORTINTRONS.out.versions.first())
 
-    // COLLECTFILE: Kill list for valid_ORF=False transcripts
-    // tRNA, rRNA
-    // gene with any intron marked as 'pseudo=' by AGAT/SPFLAGSHORTINTRONS
+    // collectFile: Kill list for valid_ORF=False transcripts
+    // tRNA, rRNA, gene with any intron marked as
+    // 'pseudo=' by AGAT/SPFLAGSHORTINTRONS
     ch_kill_list                    = ch_flagged_gff
                                     | map { meta, gff ->
 
                                         def tx_from_gff = gff.readLines()
                                             .findAll { it ->
+                                                // Can't add to kill list
                                                 if ( it.startsWith('#') ) { return false }
 
                                                 def cols = it.split('\t')
                                                 def feat = cols[2]
 
-                                                if ( feat in [ 'tRNA', 'rRNA' ] ) { return true }
-                                                if ( feat !in [ 'transcript', 'mRNA', 'gene' ] ) { return false }
+                                                // Add to kill list anything other than standard features
+                                                if ( feat !in [ 'gene', 'transcript', 'mRNA', 'exon', 'CDS', 'five_prime_UTR', 'three_prime_UTR' ] ) { return true }
+
+                                                // Ignore [ 'exon', 'CDS', 'five_prime_UTR', 'three_prime_UTR' ]
+                                                if ( feat !in [ 'gene', 'transcript', 'mRNA' ] ) { return false }
 
                                                 def attrs = cols[8]
+
+                                                // Add [ 'gene', 'transcript', 'mRNA' ] with 'valid_ORF=False' or 'pseudo=' attributes to kill list
                                                 ( attrs.contains('valid_ORF=False') || attrs.contains('pseudo=') )
                                             }
                                             .collect {
@@ -160,8 +166,8 @@ workflow FASTA_LIFTOFF {
 
 
     AGAT_SPFILTERFEATUREFROMKILLLIST(
-        ch_agat_kill_inputs.map { meta, gff, kill -> [ meta, gff ] },
-        ch_agat_kill_inputs.map { meta, gff, kill -> kill },
+        ch_agat_kill_inputs.map { meta, gff, _kill -> [ meta, gff ] },
+        ch_agat_kill_inputs.map { _meta, _gff, kill -> kill },
         [] // default config
     )
 
@@ -179,7 +185,7 @@ workflow FASTA_LIFTOFF {
         val_filter_liftoff_by_hints ? ch_attr_trimmed_gff : Channel.empty(),
         braker_hints,
         tsebra_config,
-        allow_isoforms,
+        val_allow_isoforms,
         'liftoff'
     )