refact: Allow using refs from GenCode

commit 88282b8 Author: jvfe <[email protected]> Date: Sun Sep 29 13:53:22 2024 -0300 fix: Add missing dot to regex commit 5efc0b4 Author: jvfe <[email protected]> Date: Sun Sep 29 10:56:45 2024 -0300 refact: Try handling bars in IDs
dalmolingroup · Sep 29, 2024 · 658471f · 658471f
1 parent 37f73aa
commit 658471f
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 1 deletion.
diff --git a/bin/gen_tx2gene.r b/bin/gen_tx2gene.r
@@ -26,6 +26,9 @@ txdf <- AnnotationDbi::select(
 tab <- table(txdf$GENEID)
 txdf$ntx <- tab[match(txdf$GENEID, names(tab))]
 
+txdf$TXNAME <- gsub("\\..*", "",  txdf$TXNAME)
+txdf$GENEID <- gsub("\\..*", "",  txdf$GENEID)
+
 tx2gene <- data.frame(
     tx = txdf$TXNAME,
     gene = txdf$GENEID

diff --git a/bin/tximport.r b/bin/tximport.r
@@ -20,6 +20,7 @@ txi_gene <- tximport(
     type = "kallisto",
     tx2gene = tx2gene,
     ignoreTxVersion = TRUE,
+    ignoreAfterBar = TRUE,
     dropInfReps=TRUE
 )
 
@@ -28,6 +29,7 @@ txi_tx <- tximport(
     type = "kallisto",
     txOut = TRUE,
     ignoreTxVersion = TRUE,
+    ignoreAfterBar = TRUE,
     dropInfReps=TRUE
 )
 
@@ -37,6 +39,7 @@ txi_tx_scaled <- tximport(
     txOut = TRUE,
     countsFromAbundance = "scaledTPM",
     ignoreTxVersion = TRUE,
+    ignoreAfterBar = TRUE,
     dropInfReps=TRUE
 )
 

diff --git a/nextflow.config b/nextflow.config
@@ -195,7 +195,7 @@ manifest {
     description     = 'Workflow for pre-processing, alignment and quantification of bulk RNA-Seq data'
     mainScript      = 'main.nf'
     nextflowVersion = '!>=22.10.1'
-    version = '0.5.0'
+    version = '0.6.0'
     doi             = ''
 }