filter_full_study.pbs

# processors on 1 node
#PBS -l nodes=1:ppn=2

#Request walltime/fastq file ~30 min/sample
#PBS -l walltime=120:00:00

#Request 1 gigabyte of memory per process
#PBS -l mem=40gb

#Request that regular output and terminal output go to the same file
#PBS -j oe
#PBS -M Emily.Laplante@bcm.edu
#PBS -m abe


mkdir /scratch/$PBS_JOBID
cd /scratch/$PBS_JOBID

tar -xzvf /mnt/brlstor/Vol6_SP/exrna/readCoverage/EmilyTest/biosample_RBP_out_unzipped/${study}/${study}.tar.gz

awk -v OFS="\t" '
   NR==1{
      for ( i=2; i<=NF; i++ )
       if ( $i ~ /EXR.LLAUR1NPNORNEBS001.BS|EXR.LLAUR1NPNORNEBS002.BS|EXR.LLAUR1NPNORNEBS003.BS|EXR.LLAUR1NPNORNEBS004.BS|EXR.LLAUR1NPNORNEBS005.BS|EXR.LLAUR1NPNORNEBS006.BS|EXR.LLAUR1NPNORNEBS007.BS|EXR.LLAUR1NPNORNEBS008.BS|EXR.LLAUR1NPNORNEBS009.BS|EXR.LLAUR1NPNORNEBS010.BS|EXR.LLAUR1NPNORNEBS011.BS|EXR.LLAUR1NPNORNEBS012.BS|EXR.LLAUR1NPNORNEBS013.BS|EXR.LLAUR1NPNORNEBS014.BS|EXR.LLAUR1NPNORNEBS015.BS|EXR.LLAUR1NPNORNEBS016.BS|EXR.LLAUR1NPNORNEBS017.BS|EXR.LLAUR1NPNORNEBS018.BS|EXR.LLAUR1NPNORNEBS019.BS|EXR.LLAUR1NPNORNEBS020.BS|/ )
       str = str OFS i
       N = split(str, A, OFS)
   }{
      s = $1
      r = $2
      p = $3
      s = s OFS r
      s = s OFS p
      for ( i=2; i<=N; i++ )
         s = s OFS $(A[i])
      $0 = s
   }1
' ${study}.txt > ${study}_serum_healthy.txt

tar -czvf ${study}_serum_healthy.tar.gz ${study}_serum_healthy.txt

mv ${study}_serum_healthy.tar.gz /mnt/brlstor/Vol6_SP/exrna/readCoverage/EmilyTest/biosample_RBP_out_unzipped/${study}/${study}_serum_healthy.tar.gz

rm *.txt