refact: Allow using refs from GenCode

jvfe · jvfe · commit 1de2c99d0508 · 2024-09-29T14:23:44.000-03:00
commit 88282b8 Author: jvfe <jvfecav@gmail.com> Date: Sun Sep 29 13:53:22 2024 -0300 fix: Add missing dot to regex commit 5efc0b4 Author: jvfe <jvfecav@gmail.com> Date: Sun Sep 29 10:56:45 2024 -0300 refact: Try handling bars in IDs
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
 )
 

Original file line number	Diff line number	Diff line change
`@@ -20,6 +20,7 @@ txi_gene <- tximport(`
`20`	`20`	`type = "kallisto",`
`21`	`21`	`tx2gene = tx2gene,`
`22`	`22`	`ignoreTxVersion = TRUE,`
	`23`	`+ ignoreAfterBar = TRUE,`
`23`	`24`	`dropInfReps=TRUE`
`24`	`25`	`)`
`25`	`26`
`@@ -28,6 +29,7 @@ txi_tx <- tximport(`
`28`	`29`	`type = "kallisto",`
`29`	`30`	`txOut = TRUE,`
`30`	`31`	`ignoreTxVersion = TRUE,`
	`32`	`+ ignoreAfterBar = TRUE,`
`31`	`33`	`dropInfReps=TRUE`
`32`	`34`	`)`
`33`	`35`
`@@ -37,6 +39,7 @@ txi_tx_scaled <- tximport(`
`37`	`39`	`txOut = TRUE,`
`38`	`40`	`countsFromAbundance = "scaledTPM",`
`39`	`41`	`ignoreTxVersion = TRUE,`
	`42`	`+ ignoreAfterBar = TRUE,`
`40`	`43`	`dropInfReps=TRUE`
`41`	`44`	`)`
`42`	`45`