#WBL 10 June 2014 
#use baraCUDA 0.6.2 to create BWA index for NCBI release 37.p5 of the
#reference human genome. Ie the same files as we used in bowtie2gp
#experiments.

#cf http://edwards.sdsu.edu/labsite/index.php/robert/282-how-to-create-a-database-for-bwa-and-bwa-sw

#run on spark
echo "starting make_h_sapiens_37.5_asm.bat $HOST " `date`

setenv start `pwd`

#kept same directory name as used on sumit
cd ~/barracuda/ncbi_hs_ref/bowtie-0.12.7
if($status) exit $status;

cat \
hs_ref_GRCh37.p5_chr1.fa \
hs_ref_GRCh37.p5_chr2.fa \
hs_ref_GRCh37.p5_chr3.fa \
hs_ref_GRCh37.p5_chr4.fa \
hs_ref_GRCh37.p5_chr5.fa \
hs_ref_GRCh37.p5_chr6.fa \
hs_ref_GRCh37.p5_chr7.fa \
hs_ref_GRCh37.p5_chr8.fa \
hs_ref_GRCh37.p5_chr9.fa \
hs_ref_GRCh37.p5_chr10.fa \
hs_ref_GRCh37.p5_chr11.fa \
hs_ref_GRCh37.p5_chr12.fa \
hs_ref_GRCh37.p5_chr13.fa \
hs_ref_GRCh37.p5_chr14.fa \
hs_ref_GRCh37.p5_chr15.fa \
hs_ref_GRCh37.p5_chr16.fa \
hs_ref_GRCh37.p5_chr17.fa \
hs_ref_GRCh37.p5_chr18.fa \
hs_ref_GRCh37.p5_chr19.fa \
hs_ref_GRCh37.p5_chr20.fa \
hs_ref_GRCh37.p5_chr21.fa \
hs_ref_GRCh37.p5_chr22.fa \
hs_ref_GRCh37.p5_chrX.fa \
hs_ref_GRCh37.p5_chrY.fa \
hs_ref_GRCh37.p5_chrMT.fa \
hs_ref_GRCh37.p5_unlocalized.fa \
hs_ref_GRCh37.p5_unplaced.fa \
> /tmp/hs_ref_GRCh37.p5.fa

if($status) exit $status;

echo "Created /tmp/hs_ref_GRCh37.p5.fa" `date`
echo "Did not remove Ns"
echo "Did not remove duplicate sequences or rename sequence identifiers"

cd ~/barracuda/
if($status) exit $status;

bin/barracuda index -p h_sapiens_37.5_asm /tmp/hs_ref_GRCh37.p5.fa

echo "Done make_h_sapiens_37.5_asm.bat $status " `date`

#