manipulateGenomeSeqFile.txt

##############################################################
##  Create index for mm10 that:                             ##
##   -  does not contain extra contig or mitochondrial DNA  ##
##   -  does include sequences for synthetic spike-ins      ##
##                                                          ##
##  Created 3/13/14 by LMS                                  ##
##############################################################

## eliminate any chromosome that starts with 'JH' or 'GL' or 'MT'

sed '/>JH/,/>/{//!d}' mm10.fa | sed '/>JH/d' | sed '/>GL/,/>/{//!d}' | sed '/>GL/d' | sed '/>MT/,/>/{//!d}' | sed '/>MT/d' > mm10.revised.fa

export PATH=$HOME/bin:$PATH
export PYTHONPATH=$HOME/bin:$PYTHONPATH

cd /data/Tabastore3/LauraS/LXS/RNA-Seq/index/

## add synthetic spike-in sequences for alignment
cat /data/Tabastore3/LauraS/BXD/RNA-Seq/GeneNetwork/index/mm10.revised.fa /data/Tabastore3/LauraS/BxH.HxB.Rats/RNA-Seq/spikeSource/ERCC92.fa > mm10.revised.wSpikes.fa

##  create bowtie indices
bowtie2-build mm10.revised.wSpikes.fa mm10.revised.wSpikes