annotate snpEff_2_1a/snpEff_2_1a/scripts/data/SL2.40/create.sh @ 3:c052639fa666 default tip

Uploaded
author pcingola
date Fri, 20 Apr 2012 11:22:59 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
3
c052639fa666 Uploaded
pcingola
parents:
diff changeset
1 #!/bin/sh
c052639fa666 Uploaded
pcingola
parents:
diff changeset
2
c052639fa666 Uploaded
pcingola
parents:
diff changeset
3 # wget ftp://ftp.solgenomics.net/genomes/Solanum_lycopersicum/wgs/assembly/build_2.40/S_lycopersicum_chromosomes.2.40.fa.gz
c052639fa666 Uploaded
pcingola
parents:
diff changeset
4
c052639fa666 Uploaded
pcingola
parents:
diff changeset
5 # GFF has to be downloaded manually from
c052639fa666 Uploaded
pcingola
parents:
diff changeset
6 #
c052639fa666 Uploaded
pcingola
parents:
diff changeset
7 # http://solgenomics.net/itag/release/2.3/list_files#
c052639fa666 Uploaded
pcingola
parents:
diff changeset
8 # File ITAG2.3_gene_models.gff3
c052639fa666 Uploaded
pcingola
parents:
diff changeset
9 #
c052639fa666 Uploaded
pcingola
parents:
diff changeset
10 #
c052639fa666 Uploaded
pcingola
parents:
diff changeset
11
c052639fa666 Uploaded
pcingola
parents:
diff changeset
12 # Create genes.gff
c052639fa666 Uploaded
pcingola
parents:
diff changeset
13 echo Decompressing the file
c052639fa666 Uploaded
pcingola
parents:
diff changeset
14 cp ITAG2.3_gene_models.gff3.gz genes.gff.gz
c052639fa666 Uploaded
pcingola
parents:
diff changeset
15 rm -f genes.gff
c052639fa666 Uploaded
pcingola
parents:
diff changeset
16 gunzip genes.gff.gz
c052639fa666 Uploaded
pcingola
parents:
diff changeset
17
c052639fa666 Uploaded
pcingola
parents:
diff changeset
18 echo Fixing start-end problem
c052639fa666 Uploaded
pcingola
parents:
diff changeset
19 cat genes.gff | ./fixStartEnd.pl > g
c052639fa666 Uploaded
pcingola
parents:
diff changeset
20 mv g genes.gff
c052639fa666 Uploaded
pcingola
parents:
diff changeset
21
c052639fa666 Uploaded
pcingola
parents:
diff changeset
22 # Append FASTA Sequences
c052639fa666 Uploaded
pcingola
parents:
diff changeset
23 echo "###" >> genes.gff
c052639fa666 Uploaded
pcingola
parents:
diff changeset
24 echo "##FASTA" >> genes.gff
c052639fa666 Uploaded
pcingola
parents:
diff changeset
25 zcat S_lycopersicum_chromosomes.2.40.fa.gz >> genes.gff
c052639fa666 Uploaded
pcingola
parents:
diff changeset
26