Modify generation of gene bed to ensure 0-based start site

CHANGELOG.md

@@ -17,6 +17,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 - [#125](https://github.com/mskcc/forte/pull/125) - update upload-artifact version because the version previously in use (v2) is deprecated.
 
+- [#124](https://github.com/mskcc/forte/pull/124) - ensure genebed file as 0based start site
+
 - [#127](https://github.com/mskcc/forte/pull/127) - allow dynamic increase of memory for process_single label
 
 ### `Dependencies`

bin/final_generate_v75_gene_bed.R

@@ -38,12 +38,13 @@ gtf_df <- as.data.frame(gtf)
 
 file.to_write <- args[2]
 
+### ensure start is 0 based
 gtf_df <- gtf_df %>%
     rename(
         chr = seqnames
     ) %>%
     select(c(chr, start, end, transcript_id, type, strand, gene_name, gene_id)) %>%
-    filter(type %in% c("exon","intron","UTR","CDS","cds","utr"))
+    filter(type %in% c("exon","intron","UTR","CDS","cds","utr")) %>% mutate(start = start-1)
 
 
 #START CLOCK

modules/local/metafusion/genebed/main.nf

@@ -9,6 +9,7 @@ process METAFUSION_GENEBED {
 
     input:
     tuple val(meta), path(gff)
+    val ensembl_version
 
     output:
     tuple val(meta), path("*.metafusion.gene.bed"), emit: metafusion_gene_bed
@@ -23,7 +24,7 @@ process METAFUSION_GENEBED {
     """
     final_generate_v75_gene_bed.R \\
         $gff \\
-        ${prefix}.metafusion.gene.bed
+        ${ensembl_version}.metafusion.gene.bed
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/local/metafusion/genebed/resources/usr/bin/final_generate_v75_gene_bed.R

@@ -38,12 +38,13 @@ gtf_df <- as.data.frame(gtf)
 
 file.to_write <- args[2]
 
+### ensure start is 0 based
 gtf_df <- gtf_df %>%
     rename(
         chr = seqnames
     ) %>%
     select(c(chr, start, end, transcript_id, type, strand, gene_name, gene_id)) %>%
-    filter(type %in% c("exon","intron","UTR","CDS","cds","utr"))
+    filter(type %in% c("exon","intron","UTR","CDS","cds","utr")) %>% mutate(start = start-1)
 
 
 #START CLOCK

subworkflows/local/prepare_references.nf

@@ -90,7 +90,8 @@ workflow PREPARE_REFERENCES {
     )
 
     METAFUSION_GENEBED(
-        AGAT_SPADDINTRONS.out.gff
+        AGAT_SPADDINTRONS.out.gff,
+        params.ensembl_version
     )
 
     METAFUSION_GENEINFO(