User:Lindenb/Notebook/UMR915/20100810
From OpenWetWare
belgium
recuper les noms des HC
gunzip -c 454HC*.gz | egrep GK | cut -d ' ' -f 1 | sort | uniq > hc_names.txt gunzip -c 454Reads.fna.gz | sed -e '/^>/s/[ ].*//' -e '/^>/s/$/#/' | tr -d "\n" | tr "#" "\t" | tr ">" "\n" | fgrep -f hc_names.txt | awk '{printf(">%s\n%s\n",$1,$2);}' > hc_sequences.fa grep ">" hc_sequences.fa | wc -l 35407 wc -l hc_names.txt 35407 hc_names.txt
blat
export MACHTYPE=x86_64 ~lindenb/bin/x86_64/blat -t=dna chrX1andX2.2bit hc_sequences.fa stdout | gzip > hq_chrX1andX2.blat.gz