diff snpEff_2_1a/snpEff_2_1a/scripts/data/gmax1.09v8/create.sh @ 3:c052639fa666 default tip

Uploaded
author pcingola
date Fri, 20 Apr 2012 11:22:59 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/snpEff_2_1a/snpEff_2_1a/scripts/data/gmax1.09v8/create.sh	Fri Apr 20 11:22:59 2012 -0400
@@ -0,0 +1,35 @@
+#!/bin/sh -e
+
+echo "Processing GFF file"
+gunzip -c Gmax_109_gene.gff3.gz > genes.gff
+#	| sed "s/.five_prime_UTR.1//" \
+#	| sed "s/.three_prime_UTR.1//" \
+#	> genes.gff
+
+echo "Adding FASTA sequence"
+( echo "###" ; echo "##FASTA" ; gunzip -c Gmax_109.fa.gz ) >> genes.gff
+
+ehco "Create CDS file"
+gunzip -c Gmax_109_cds.fa.gz \
+	| sed "s/|PACid:/|PAC:/" \
+	| sed "s/Glyma.*|//" \
+	> cds.fa 
+
+echo "Create protein file"
+gunzip -c Gmax_109_peptide.fa.gz \
+	| sed "s/|PACid:/|PAC:/" \
+	| sed "s/Glyma.*|//" \
+	> protein.fa
+
+# Build databse
+cd $HOME/snpEff
+
+./scripts/snpEffM.sh build -v -gff3 gmax1.09v8 2>&1 | tee gmax1.09v8.build
+
+# CDS test
+./scripts/snpEffM.sh cds -v gmax1.09v8 data/gmax1.09v8/cds.fa 2>&1 | tee gmax1.09v8.cds
+
+cd -
+
+echo Done!
+