Elementolab/SNVseeqer AddingNewSpecies

From Icbwiki

Jump to: navigation, search
# getting the genome
wget http://hgdownload.cse.ucsc.edu/goldenPath/mm9/bigZips/chromFa.tar.gz
tar xvfz chromFa.tar.gz
# getting annot
wget http://hgdownload.cse.ucsc.edu/goldenPath/mm9/database/refGene.txt.gz
gunzip refGene.txt.gz
mv refGene.txt refGene.txt.25MAY2010
# rebuild genomic RefSeq
$SNVSEEQERDIR/rebuildRefSeqFromRefGene -refgene refGene.txt.25MAY2010 -chrdir . -chrdata ../mm9.chrdata > refGene.txt.25MAY2010.fa
fasta_lengths.pl refGene.txt.25MAY2010.fa   | sort_column.pl 1  | less
# remove non-unique sequences
fasta_retain_unique_sequences.pl refGene.txt.25MAY2010.fa > tmp
mv tmp refGene.txt.25MAY2010.fa

# quick check 
grep ">" refGene.txt.25MAY2010.fa | wc -l
26500
wc -l refGene.txt.25MAY2010 
27083 refGene.txt.25MAY2010
# build BWA index
bwa index -p refMrnaMM925MAY2010idx -a bwtsw refGene.txt.25MAY2010.fa
# SNVseeqer
perl $SNVSEEQERDIR/SCRIPTS/PBS_SNPseeqerPB_RefSeq --files="*.txt.gz" --readlen=40 --submit=1 --annotate=1 --genome=mm9
Personal tools