GTeX_eQTL_process.qsub

#!/bin/bash -l

# we are going to set these paramenters through cmdline (but you can always hardcoded the parameters if they are going to be fixed.:


# Now let's keep track of some information just in case anything goes wrong
echo "=========================================================="
echo "Starting on : $(date)"
echo "Running on node : $(hostname)"
echo "Current directory : $(pwd)"
echo "Current job ID : $JOB_ID"
echo "Current job name : $JOB_NAME"
echo "Task index number : $SGE_TASK_ID"
echo "=========================================================="



INFILE=`find /restricted/projectnb/chengcancer/Simon/project/T2D/bulk_RNA-seq/merge_170415_NB501164_170506_NB501164/2mapping/QT/GTeX_eQTL/*.v6p.all_snpgene_pairs.txt.gz   | head -${SGE_TASK_ID} |tail -1`
echo "NOW in TASK ${SGE_TASK_ID} : PROCESSING $INFILE ..."



zcat ${INFILE}  | awk '{print $2, " ", $4}' | gzip >  $(basename ${INFILE} .v6p.all_snpgene_pairs.txt.gz).txt.gz
zcat $(basename ${INFILE} .v6p.all_snpgene_pairs.txt.gz).txt.gz  | awk -F_ '{print $1," ",$2, " ", $5}' | awk '{print $1":"$2, " ", $4}'| gzip > $(basename ${INFILE} .v6p.all_snpgene_pairs.txt.gz)_chrpos_pval.txt.gz