Merge pull request #38 from PlantandFoodResearch/fix/is_masked

Fixed a bug where `is_masked` was ignored by the pipeline
Plant-Food-Research-Open · Jun 18, 2024 · 6713761 · 6713761
2 parents 87508dc + 1f957a2
commit 6713761
Show file tree

Hide file tree

Showing 7 changed files with 54 additions and 31 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,24 @@
 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).
 
+## 0.3.3 - [18-Jun-2024]
+
+### `Added`
+
+1. Added a stub test to evaluate the case where an assembly is soft masked but has no annotations
+
+### `Fixed`
+
+1. Fixed a bug where `is_masked` was ignored by the pipeline
+2. Fixed a bug in param validation which allowed specification of `braker_hints` without `braker_gff3`
+
+### `Dependencies`
+
+1. NextFlow!>=23.04.4
+2. nf-validation=1.1.3
+
+### `Deprecated`
+
 ## 0.3.2 - [13-May-2024]
 
 ### `Added`

diff --git a/assets/schema_input.json b/assets/schema_input.json
@@ -61,7 +61,8 @@
                         "maxLength": 0
                     }
                 ],
-                "errorMessage": "BRAKER hints GFF/GFF3 file path cannot contain spaces and must have extension '.gff.gz', '.gff3.gz', '.gff' or '.gff3'"
+                "errorMessage": "BRAKER hints GFF/GFF3 file path cannot contain spaces and must have extension '.gff.gz', '.gff3.gz', '.gff' or '.gff3'",
+                "dependentRequired": ["braker_gff3"]
             }
         },
         "required": ["tag", "fasta", "is_masked"]

diff --git a/nextflow.config b/nextflow.config
@@ -58,7 +58,7 @@ manifest {
     description                 = """A NextFlow pipeline for pan-genome annotation"""
     mainScript                  = 'main.nf'
     nextflowVersion             = '!>=23.04.4'
-    version                     = '0.3.2'
+    version                     = '0.3.3'
     doi                         = ''
 }
 

diff --git a/subworkflows/local/prepare_assembly.nf b/subworkflows/local/prepare_assembly.nf
@@ -14,6 +14,7 @@ workflow PREPARE_ASSEMBLY {
     te_library                  // channel: [ meta, fasta ]
     repeat_annotator            // val(String), 'repeatmodeler' or 'edta'
     exclude_assemblies          // channel: val(assembly_x,assembly_y)
+    ch_is_masked                // channel: [ meta, val(true|false) ]
 
     main:
     ch_versions                 = Channel.empty()
@@ -63,26 +64,35 @@ workflow PREPARE_ASSEMBLY {
     ch_versions                 = ch_versions.mix(GUNZIP_TE_LIBRARY.out.versions.first())
 
     // SUBWORKFLOW: FASTA_EDTA_LAI
-    ch_annotator_inputs         = ch_validated_assembly
+    ch_unmasked_masked_branch   = ch_validated_assembly
+                                | combine( exclude_assemblies )
+                                | map { meta, fasta, ex_assemblies ->
+                                    ex_assemblies.tokenize(",").contains( meta.id )
+                                    ? null
+                                    : [ meta, fasta ]
+                                }
+                                | join(
+                                    ch_is_masked
+                                )
+                                | branch { meta, fasta, is_masked ->
+                                    unmasked: ! is_masked
+                                        return [ meta, fasta ]
+                                    masked: is_masked
+                                        return [ meta, fasta ]
+                                }
+
+    ch_annotator_inputs         = ch_unmasked_masked_branch.unmasked
                                 | join(
                                     ch_gunzip_te_library, remainder: true
                                 )
                                 | filter { meta, assembly, teLib ->
-                                    teLib == null
+                                    teLib == null && ( assembly != null )
                                 }
-                                | map { meta, assembly, teLib -> [meta, assembly] }
+                                | map { meta, assembly, teLib -> [ meta, assembly ] }
 
     ch_edta_inputs              = repeat_annotator != 'edta'
                                 ? Channel.empty()
                                 : ch_annotator_inputs
-                                | combine( exclude_assemblies )
-                                | map { meta, fasta, ex_assemblies ->
-                                    def ex_list = ex_assemblies.split(",")
-
-                                    if ( !( ex_list.contains( meta.id ) ) ) {
-                                        [ meta, fasta ]
-                                    }
-                                }
 
     FASTA_EDTA_LAI(
         ch_edta_inputs,
@@ -96,14 +106,6 @@ workflow PREPARE_ASSEMBLY {
     ch_repeatmodeler_inputs     = repeat_annotator != 'repeatmodeler'
                                 ? Channel.empty()
                                 : ch_annotator_inputs
-                                | combine( exclude_assemblies )
-                                | map { meta, fasta, ex_assemblies ->
-                                    def ex_list = ex_assemblies.split(",")
-
-                                    if ( !( ex_list.contains( meta.id ) ) ) {
-                                        [ meta, fasta ]
-                                    }
-                                }
 
     REPEATMODELER_BUILDDATABASE ( ch_repeatmodeler_inputs )
 
@@ -112,7 +114,7 @@ workflow PREPARE_ASSEMBLY {
     // MODULE: REPEATMODELER_REPEATMODELER
     REPEATMODELER_REPEATMODELER ( REPEATMODELER_BUILDDATABASE.out.db )
 
-    ch_assembly_and_te_lib      = ch_validated_assembly
+    ch_assembly_and_te_lib      = ch_unmasked_masked_branch.unmasked
                                 | join(
                                     repeat_annotator == 'edta'
                                     ? FASTA_EDTA_LAI.out.te_lib_fasta.mix(ch_gunzip_te_library)
@@ -123,21 +125,21 @@ workflow PREPARE_ASSEMBLY {
 
     // MODULE: REPEATMASKER
     REPEATMASKER(
-        ch_assembly_and_te_lib.map { meta, assembly, teLib -> [meta, assembly] },
+        ch_assembly_and_te_lib.map { meta, assembly, teLib -> [ meta, assembly ] },
         ch_assembly_and_te_lib.map { meta, assembly, teLib -> teLib },
     )
 
+    ch_masked_assembly          = ch_unmasked_masked_branch.masked
+                                | mix(REPEATMASKER.out.fasta_masked)
     ch_versions                 = ch_versions.mix(REPEATMASKER.out.versions.first())
 
     // MODULE: STAR_GENOMEGENERATE
     ch_genomegenerate_inputs    = ch_validated_assembly
                                 | combine( exclude_assemblies )
                                 | map { meta, fasta, ex_assemblies ->
-                                    def ex_list = ex_assemblies.split(",")
-
-                                    if ( !( ex_list.contains( meta.id ) ) ) {
-                                        [ meta, fasta ]
-                                    }
+                                    ex_assemblies.tokenize(",").contains( meta.id )
+                                    ? null
+                                    : [ meta, fasta ]
                                 }
 
 
@@ -151,7 +153,7 @@ workflow PREPARE_ASSEMBLY {
 
     emit:
     target_assemby              = ch_validated_assembly         // channel: [ meta, fasta ]
-    masked_target_assembly      = REPEATMASKER.out.fasta_masked // channel: [ meta, fasta ]
+    masked_target_assembly      = ch_masked_assembly            // channel: [ meta, fasta ]
     target_assemby_index        = ch_assembly_index             // channel: [ meta, star_index ]
     versions                    = ch_versions                   // channel: [ versions.yml ]
 }
diff --git a/tests/stub/assemblysheet.csv b/tests/stub/assemblysheet.csv
@@ -1,3 +1,4 @@
 tag,fasta,is_masked,te_lib,braker_gff3,braker_hints
 red5_v2p1,tests/stub/target/red5_v2p1_chr1.fasta.gz,no,,tests/stub/braker/red5_v2p1.gff3.gz,tests/stub/braker/red5_v2p1.hints.gff.gz
 donghong,tests/stub/target/donghong.chr1.fsa.gz,no,tests/stub/te_lib/donghong.TElib.fa.gz,tests/stub/braker/red5_v2p1.gff3.gz,tests/stub/braker/red5_v2p1.hints.gff.gz
+red5_v3,tests/stub/target/red5_v3_chr1.fasta,yes
diff --git a/tests/stub/target/red5_v3_chr1.fasta b/tests/stub/target/red5_v3_chr1.fasta
diff --git a/workflows/pangene.nf b/workflows/pangene.nf
@@ -42,7 +42,7 @@ workflow PANGENE {
                                     it.join(",")
                                 }
 
-    ch_masked                   = ch_input
+    ch_is_masked                = ch_input
                                 | map { it ->
                                     def tag         = it[0]
                                     def is_masked   = it[2]
@@ -144,7 +144,8 @@ workflow PANGENE {
         ch_target_assembly,
         ch_te_library,
         params.repeat_annotator,
-        ch_braker_ex_asm_str
+        ch_braker_ex_asm_str,
+        ch_is_masked
     )
 
     ch_valid_target_assembly    = PREPARE_ASSEMBLY.out.target_assemby