Rhesus genome

From wubrowse wiki
Revision as of 22:51, 11 April 2015 by Dli (Talk | contribs)

(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search
Date: 12/6/2013

mkdir /srv/epgg/data/data/subtleKnife/rheMac3
mkdir /srv/epgg/data/data/subtleKnife/rheMac3/config
mkdir /srv/epgg/data/data/subtleKnife/rheMac3/session
sudo chown www-data.www-data /srv/epgg/data/data/subtleKnife/rheMac3/session

mkdir /srv/epgg/data/data/browserLoad/rheMac3
mkdir ~/subtleKnife/config/rheMac3


cd /home/xzhou/data
mkdir rheMac3
wget http://hgdownload.soe.ucsc.edu/goldenPath/rheMac3/bigZips/rheMac3.fa.gz
gunzip rheMac3.fa.gz 
python ~/subtleKnife/script/fa2tabix.py rheMac3.fa rheMac3
mv rheMac3.gz* /srv/epgg/data/data/subtleKnife/seq/



wget http://hgdownload.soe.ucsc.edu/goldenPath/rheMac3/database/rmsk.txt.gz
gunzip rmsk.txt.gz 
python ~/subtleKnife/script/rmsk.py rmsk.txt 
mv *.gz* /srv/epgg/data/data/subtleKnife/rheMac3/
mv decorInfo ~/subtleKnife/config/rheMac3/decorInfo_rmsk
mv track2Style ~/subtleKnife/config/rheMac3/track2Style_rmsk
mv track2Detail ~/subtleKnife/config/rheMac3/track2Detail_rmsk
/bin/rm *.bed
cat > cateInfo
DNA 4
DNA? 4
LINE 2
LINE? 2
Low_complexity 7
LTR 3
LTR? 3
Other 9
RC 9
RC? 9
RNA 8
rRNA 8
Satellite 6
scRNA 8
Simple_repeat 5
SINE 1
SINE? 1
snRNA 8
srpRNA 8
tRNA 8
Unknown 10

python ~/subtleKnife/script/rmsk2ensembleCate.py cateInfo rmsk.txt > rmsk_ensemble
bgzip rmsk_ensemble 
tabix -p bed rmsk_ensemble.gz 
mv rmsk_ensemble.gz* /srv/epgg/data/data/subtleKnife/rheMac3/


cat >> ~/subtleKnife/config/rheMac3/decorInfo_rmsk
rmsk_ensemble RepeatMasker all classes \N 4 12 0 \N


cp ~/subtleKnife/config/hg19/track2Categorical ~/subtleKnife/config/rheMac3/


wget http://hgdownload.soe.ucsc.edu/goldenPath/rheMac3/bigZips/rheMac3.2bit
~/bin/x86_64/hgGcPercent -win=5 -file=rheMac3.wig -wigOut rn4 rheMac3.2bit  -noDots
~/bin/x86_64/wigToBigWig rheMac3.wig size rheMac3.bigWig
mv rheMac3.bigWig /srv/epgg/data/data/subtleKnife/rheMac3/



cat > ~/subtleKnife/config/rheMac3/decorInfo
gc5Base    GC percent    \N    3    8    0    \N


wget http://hgdownload.soe.ucsc.edu/goldenPath/rheMac3/database/refGene.txt.gz
wget http://hgdownload.soe.ucsc.edu/goldenPath/rheMac3/database/refLink.txt.gz
wget http://hgdownload.soe.ucsc.edu/goldenPath/rheMac3/database/xenoRefGene.txt.gz

python ~/subtleKnife/script/genescript/ucscsimplegene.py refGene.txt refGene
python ~/subtleKnife/script/genescript/ucscsimplegene.py xenoRefGene.txt xenoRefGene
mv *gz *tbi /srv/epgg/data/data/subtleKnife/rheMac3/
mv *load /srv/epgg/data/data/browserLoad/rheMac3/

cat > /srv/epgg/data/data/browserLoad/rheMac3/load.sql
drop table if exists refGene;
create table refGene (
chrom varchar(20) not null,
start int unsigned not null,
stop int unsigned not null,
name varchar(100) not null
) ENGINE=MyISAM DEFAULT CHARSET=latin1;
load data local infile 'refGene_load' into table refGene;
create index name on refGene (name);

drop table if exists xenoRefGene;
create table xenoRefGene (
chrom varchar(20) not null,
start int unsigned not null,
stop int unsigned not null,
name varchar(100) not null
) ENGINE=MyISAM DEFAULT CHARSET=latin1;
load data local infile 'xenoRefGene_load' into table xenoRefGene;
create index name on xenoRefGene (name);

mv *gz *tbi /srv/epgg/data/data/subtleKnife/rheMac3/


from http://www.genome.jp/kegg-bin/get_htext?br08601.keg get KEGG genome code: mcc
from NCBI get Rhesus monkey taxonomy ID: 9544
cd /home/xzhou/data/rheMac3/gene
wget http://rest.kegg.jp/conv/mcc/ncbi-geneid
wget ftp://ftp.ncbi.nih.gov/gene/DATA/gene2accession.gz
python ~/subtleKnife/script/genescript/kegg2refgene.py ncbi-geneid 9544 > /srv/epgg/data/data/browserLoad/rheMac3/kegg2refgene
cat >> /srv/epgg/data/data/browserLoad/rheMac3/load.sql 
drop table if exists kegg2refgene;
create table kegg2refgene (
kegg char(100) not null primary key,
refgene char(100) not null
);
load data local infile 'kegg2refgene' into table kegg2refgene;



mysql> create database rheMac3;
cd /srv/epgg/data/data/browserLoad/rheMac3/
cat load.sql |mysql -uroot -pxzhou rheMac3
cd ~/subtleKnife/config/rheMac3/
cp ../rn4/makeDb.sql .
-- make edits to makeDb.sql as see fit --

python ~/subtleKnife/script/makescaffold_human.py chromInfo.txt > ~/subtleKnife/config/rheMac3/scaffoldInfo
cat makeDb.sql ../sessionUtils.sql |mysql -uroot -pxzhou rheMac3


Add an entry for rheMac3 into "treeoflife" file, located in /srv/epgg/data/data/subtleKnife/treeoflife