Mercurial > repos > mvdbeek > r_goseq_1_22_0

diff get_length_and_gc_content.r @ 7:15ce6435ab83 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/goseq_1_22_0 commit fdd0811efc61c31f88ff17096fbe8ee8cfacd766-dirty
author mvdbeek
date Thu, 25 Feb 2016 06:09:34 -0500
parents d4b5942ed347
children 7f8d888e3355
line wrap: on
line diff
--- a/get_length_and_gc_content.r	Thu Feb 25 05:49:08 2016 -0500
+++ b/get_length_and_gc_content.r	Thu Feb 25 06:09:34 2016 -0500
@@ -21,9 +21,9 @@
 
 #Load the annotation and reduce it
 GTF <- import.gff(GTFfile, format="gtf", genome=NA, feature.type="exon")
-grl <- reduce(split(GTF, elementMetadata(GTF)$gene_name))
+grl <- reduce(split(GTF, elementMetadata(GTF)$gene_id))
 reducedGTF <- unlist(grl, use.names=T)
-elementMetadata(reducedGTF)$gene_name <- rep(names(grl), elementLengths(grl))
+elementMetadata(reducedGTF)$gene_id <- rep(names(grl), elementLengths(grl))
 
 #Open the fasta file
 FASTA <- FaFile(FASTAfile)
@@ -39,7 +39,7 @@
     width = sum(elementMetadata(x)$widths)
     c(width, nGCs/width)
 }
-output <- t(sapply(split(reducedGTF, elementMetadata(reducedGTF)$gene_name), calc_GC_length))
+output <- t(sapply(split(reducedGTF, elementMetadata(reducedGTF)$gene_id), calc_GC_length))
 colnames(output) <- c("Length", "GC")
 
 write.table(output, file="GC_lengths.tsv", sep="\t")
\ No newline at end of file