Merge branch 'enhancement/hg38_update' of github.com:mskcc/forte into…

… enhancement/hg38_update
mskcc · Oct 10, 2024 · 6fcb29c · 6fcb29c
2 parents 7f8c7c0 + 32507d5
commit 6fcb29c
Show file tree

Hide file tree

Showing 5 changed files with 11 additions and 4 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -19,6 +19,8 @@ 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`

diff --git a/bin/final_generate_v75_gene_bed.R b/bin/final_generate_v75_gene_bed.R
@@ -41,13 +41,14 @@ gtf_df <- gtf_df[!grepl("NF",gtf_df$tag),]
 
 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")) %>%
-    mutate(gene_name = ifelse(is.na(gene_name),gene_id,gene_name))
+    mutate(gene_name = ifelse(is.na(gene_name),gene_id,gene_name)) %>% mutate(start = start-1)
 
 
 #START CLOCK

diff --git a/modules/local/metafusion/genebed/main.nf b/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}":

diff --git a/modules/local/metafusion/genebed/resources/usr/bin/final_generate_v75_gene_bed.R b/modules/local/metafusion/genebed/resources/usr/bin/final_generate_v75_gene_bed.R
@@ -41,13 +41,15 @@ gtf_df <- gtf_df[!grepl("NF",gtf_df$tag),]
 
 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")) %>%
-    mutate(gene_name = ifelse(is.na(gene_name),gene_id,gene_name))
+    mutate(gene_name = ifelse(is.na(gene_name),gene_id,gene_name)) %>% mutate(start = start-1)
+
 
 
 #START CLOCK

diff --git a/subworkflows/local/prepare_references.nf b/subworkflows/local/prepare_references.nf
@@ -107,7 +107,8 @@ workflow PREPARE_REFERENCES {
     )
 
     METAFUSION_GENEBED(
-        AGAT_SPADDINTRONS.out.gff
+        AGAT_SPADDINTRONS.out.gff,
+        params.ensembl_version
     )
 
     METAFUSION_GENEINFO(