|
0
|
1 #!/bin/sh
|
|
|
2
|
|
|
3 #-------------------------------------------------------------------------------
|
|
|
4 # Convert the gene names in order to be used in an R script
|
|
|
5 #
|
|
|
6 # Usage: cat snpEff_genes.txt | ./scripts/genesTxtColumnNames.sh > genes.txt
|
|
|
7 #
|
|
|
8 # Once in R, you can:
|
|
|
9 # - Load this table:
|
|
|
10 # data <- read.csv("genes.txt", sep= "\t", header=TRUE);
|
|
|
11 #
|
|
|
12 # - Access the data:
|
|
|
13 # data$countINTRON
|
|
|
14 #
|
|
|
15 # - Add missing or empty columns:
|
|
|
16 # if( is.null(data$countINTRON ) { data$countINTRON <- 0 * (1:length(data$geneId) ); }
|
|
|
17 #
|
|
|
18 # Pablo Cingolani
|
|
|
19 #-------------------------------------------------------------------------------
|
|
|
20
|
|
|
21 cat \
|
|
|
22 | grep -v "^# The following"\
|
|
|
23 | sed "s/Bases affected (/bases/g" \
|
|
|
24 | sed "s/Length (/len/g" \
|
|
|
25 | sed "s/Count (/count/g" \
|
|
|
26 | sed "s/Total score (/score/g" \
|
|
|
27 | sed "s/)//g" \
|
|
|
28 | sed "s/#GeneId/geneId/" \
|
|
|
29 | sed "s/GeneName/geneName/" \
|
|
|
30 | sed "s/BioType/bioType/" \
|
|
|
31 | sed "s/_PRIME//g" \
|
|
|
32 | sed "s/SPLICE_SITE_//g" \
|
|
|
33 | sed "s/SYNONYMOUS_CODING/SYN/g" \
|
