new version of bambu added into module, not tested yet within worklfow but tested independently, haven't run full test yet, added gzipped symbolic files for references

Author: number-25

bin/run_bambu.r

@@ -18,6 +18,7 @@
 ################################################
 ################################################
 library(bambu)
+library(GenomeInfoDb)
 
 ################################################
 ################################################

conf/test_full.config

@@ -88,7 +88,7 @@ validation {
     help {
         enabled     = true
         beforeText  = "Welcome to LongTranscriptomics, I see you are seeking help."
-        afterText   = "Farewell, hopefully this was helpful. "Please cite the pipeline owners when using this pipeline."
+        afterText   = "Farewell, hopefully this was helpful. Please cite the pipeline owners when using this pipeline."
         command     = "nextflow run . -profile <profile> --outdir <outdir>"
     }
 }

modules/local/bambu/bambu/main.nf

@@ -3,8 +3,11 @@ process BAMBU {
     label 'process_medium'
     conda "conda-forge::r-base=4.0.3 bioconda::bioconductor-bambu=3.0.8 bioconda::bioconductor-bsgenome=1.66.0"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/bioconductor-bambu:3.0.8--r42hc247a5b_0' :
-        'docker://quay.io/biocontainers/bioconductor-bambu:3.0.8--r42hc247a5b_0' }"
+        'number25/bambu:3.12.0' :
+        'number25/bambu:3.12.0' }"
+
+       // 'docker://quay.io/biocontainers/bioconductor-bambu:3.0.8--r42hc247a5b_0' }"
+       // 'docker://quay.io/biocontainers/bioconductor-bambu:3.0.8--r42hc247a5b_0' }"
    //containerOptions = '-u $(id -u):$(id -g)'
         //'number25/bambu:3.8.0':
         //'docker://quay.io/number_25/bambu:latest' }"
@@ -18,23 +21,14 @@ process BAMBU {
     tuple val(meta), path(bam)
 
     output:
-    path "counts_gene.txt"               , emit: ch_gene_counts
-    path "counts_transcript.txt"         , emit: ch_transcript_counts
-    tuple val(meta)                      , path("extended_annotations.gtf") , emit: bambu_extended_gtf
-    //path "allTranscriptModels.gtf"       , emit: bambu_all_gtf
-    //path "supportedTranscriptModels.gtf" , emit: bambu_supported_gtf
-    //path "novelTranscripts.gtf"          , emit: bambu_novel_only_gtf
-    path "versions.yml"                  , emit: versions
+    //path "counts_gene.txt"                                  , emit: ch_gene_counts
+    //path "counts_transcript.txt"                            , emit: ch_transcript_counts
+    path "extended_annotations.gtf"                         , emit: bambu_extended_gtf
+    path "allTranscriptModels.gtf"                          , emit: bambu_all_gtf
+    path "novelTranscripts.gtf"                             , emit: bambu_novel_only_gtf
+    tuple val(meta), path("supportedTranscriptModels.gtf")  , emit: bambu_supported_gtf
+    path "versions.yml"                                     , emit: versions
 
-/*
-    tuple val(meta), path("extendedAnnotations.gtf"),        emit: bambu_extended_gtf
-    //tuple val(meta), path("*_counts_gene.txt")         , emit: bambu_gene_counts
-    //tuple val(meta), path("*_counts_transcript.txt")   , emit: bambu_transcript_counts
-    tuple val(meta), path("allTranscriptModels.gtf"),       emit: bambu_transcript_models
-    tuple val(meta), path("supportedTranscriptModels.gtf"), emit: bambu_supported_transcript_models
-    tuple val(meta), path("novelTranscripts.gtf"),     emit: bambu_novel_transcript_models
-    path "versions.yml",                                        emit: versions
-*/
     when:
     task.ext.when == null || task.ext.when
     //def prefix = task.ext.prefix ?: "${meta.id}_${meta.replicate}_bambu"

workflows/directrna.nf

@@ -355,13 +355,11 @@ workflow DIRECTRNA{
     // BAMBU
     if (!params.skip_bambu) {
         BAMBU( ch_genome_fasta, ch_annotation_gtf, ch_bam )
-        ch_bambu_extended_gtf = BAMBU.out.bambu_extended_gtf
-        //ch_bambu_supported_gtf = BAMBU.out.bambu_supported_gtf
+        ch_bambu_supported_gtf = BAMBU.out.bambu_supported_gtf
         ch_versions = ch_versions.mix(BAMBU.out.versions.first())
-        // MIX genome fasta with fasta index as this will improve GFFREADs speed
-        //GFFREAD_GETFASTA_BAMBU( ch_bambu_extended_gtf, ch_genome_fasta_with_index, 'bambu' )
-        //ch_bambu_transcripts = GFFREAD_GETFASTA_BAMBU.out.transcripts_fa
-        //ch_versions = ch_versions.mix(GFFREAD_GETFASTA_BAMBU.out.versions.first())
+        GFFREAD_GETFASTA_BAMBU( ch_bambu_supported_gtf, ch_genome_fasta_with_index, 'bambu' )
+        ch_bambu_transcripts = GFFREAD_GETFASTA_BAMBU.out.transcripts_fa
+        ch_versions = ch_versions.mix(GFFREAD_GETFASTA_BAMBU.out.versions.first())
         }
 
     // ISOQUANT
@@ -406,11 +404,11 @@ workflow DIRECTRNA{
             ch_multiqc_files = ch_multiqc_files.mix(ch_flair_gffcompare_stats.ifEmpty([]))
         }
         // TODO - this version of bambu currently only outputs the "extended annotation", which is the reference annotation + the detected transcripts in the sample, so there's no point to doing gffcompare as sensitivity and accuracy are 100%
-        //if (!params.skip_bambu) {
-        //    GFFCOMPARE_BAMBU( ch_genome_fasta_with_index, ch_bambu_extended_gtf, ch_annotation_gtf, 'bambu' )
-        //    ch_bambu_gffcompare_stats = GFFCOMPARE_BAMBU.out.gffcompare_stats.collect{it[1]}.flatten()
-        //    ch_multiqc_files = ch_multiqc_files.mix(ch_bambu_gffcompare_stats.ifEmpty([]))
-        //}
+        if (!params.skip_bambu) {
+            GFFCOMPARE_BAMBU( ch_genome_fasta_with_index, ch_bambu_supported_gtf, ch_annotation_gtf, 'bambu' )
+            ch_bambu_gffcompare_stats = GFFCOMPARE_BAMBU.out.gffcompare_stats.collect{it[1]}.flatten()
+            ch_multiqc_files = ch_multiqc_files.mix(ch_bambu_gffcompare_stats.ifEmpty([]))
+        }
         if (!params.skip_isoquant) {
             GFFCOMPARE_ISOQUANT(ch_genome_fasta_with_index, ch_isoquant_gtf, ch_annotation_gtf, 'isoquant' )
             ch_isoquant_gffcompare_stats = GFFCOMPARE_ISOQUANT.out.gffcompare_stats.collect{it[1]}.flatten()