Mercurial > repos > greg > snpeff_v2_from_pablo
diff snpEff_2_1a/scripts/genesTxtColumnNames.sh @ 0:f8eaa3f8194b default tip
Uploaded snpEff_v2_1a_core.tgz from Pablo Cingolani
| author | greg |
|---|---|
| date | Fri, 20 Apr 2012 14:47:09 -0400 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/snpEff_2_1a/scripts/genesTxtColumnNames.sh Fri Apr 20 14:47:09 2012 -0400 @@ -0,0 +1,33 @@ +#!/bin/sh + +#------------------------------------------------------------------------------- +# Convert the gene names in order to be used in an R script +# +# Usage: cat snpEff_genes.txt | ./scripts/genesTxtColumnNames.sh > genes.txt +# +# Once in R, you can: +# - Load this table: +# data <- read.csv("genes.txt", sep= "\t", header=TRUE); +# +# - Access the data: +# data$countINTRON +# +# - Add missing or empty columns: +# if( is.null(data$countINTRON ) { data$countINTRON <- 0 * (1:length(data$geneId) ); } +# +# Pablo Cingolani +#------------------------------------------------------------------------------- + +cat \ + | grep -v "^# The following"\ + | sed "s/Bases affected (/bases/g" \ + | sed "s/Length (/len/g" \ + | sed "s/Count (/count/g" \ + | sed "s/Total score (/score/g" \ + | sed "s/)//g" \ + | sed "s/#GeneId/geneId/" \ + | sed "s/GeneName/geneName/" \ + | sed "s/BioType/bioType/" \ + | sed "s/_PRIME//g" \ + | sed "s/SPLICE_SITE_//g" \ + | sed "s/SYNONYMOUS_CODING/SYN/g" \