Post date: Oct 14, 2013 9:33:0 PM
#to ssh to greenhouse to sunflower
ssh llucas@147.26.169.195
ssh lauren@sunflower.uwyo.edu
#I first unzipped the file in /data/local/august13_ut/ with gunzip filename
#ID the phix contaminants
tap_contam_analysis --db /data/public/contaminants/phix174 --pct 50 TXState14_NoIndex_L005_R1_001.fastq > phix_TXState14_NoIndex_L005_R1_001.txt &
#Get rid of the contaminants and make new, clean fastq file:
cat TXState14_NoIndex_L005_R1_001.fastq | fqu_cull -r phix_TXState14_NoIndex_L005_R1_001.txt > clean_TXState14_NoIndex_L005_R1_001.fastq &
#Number of reads I got rid of:
wc -l phix_TXState14_NoIndex_L005_R1_001.txt
#1297001
#Number of "clean" reads:
wc -l clean_TXState14_NoIndex_L005_R1_001.fastq
#809845064
#I copied the barcode file to sunflower: Esosorum_barcodes.csv
#Then I parsed barcodes on node4.
cp /data/local/july13_ut/parse_barcodes768.pl ./
./parse_barcodes768.pl Esosorum_barcodes.csv clean_TXState14_NoIndex_L005_R1_001.fastq HWI-ST1097 &
#Esosorum barcode parsing results:
Good mids count: 187121522
Bad mids count: 15314821
*Number of seqs with potential MSE adapter in seq: 55269590
Seqs that were too short after removing MSE and beyond: 24901
All individuals have data.
*On par with Stygoparnus results:
Good mids count: 149068564
Bad mids count: 19423164
Number of seqs with potential MSE adapter in seq: 52534660
Seqs that were too short after removing MSE and beyond: 17560