UC Davis TAMA Tutorial 5 - GenomeRIK/workshop_tutorials GitHub Wiki

Using TAMA ORF/NMD Pipeline

change directory

  cd 6_orf_nmd

Copy over bed file from FLNC TAMA Collapse run

  cp ../3_collapse/2_tc_flnc_nolde_nc/tc_nc_flnc_nolde_mm2_alz_flnc_hg38_sort.bed .

make bash script

  run_bed_to_fasta.sh

fill bash script

  bed='tc_nc_flnc_nolde_mm2_alz_flnc_hg38_sort.bed'
  fasta='/share/workshop/isoseq_workshop/rkuo/1_data/hg38.fa'
  outfile=`echo ${bed} | sed 's/bed/fa/g'`
  bedtools getfasta -name -split -s -fi ${fasta} -bed ${bed} -fo ${outfile} 

run bash script

  sh run_bed_to_fasta.sh

make bash script

  run_orf_seeker.sh

fill bash script

  spath='/share/workshop/isoseq_workshop/rkuo/tama/tama_go/orf_nmd_predictions/'
  pscript='tama_orf_seeker.py'
  fasta='tc_nc_nolde_mm2_alz_flnc_hg38_sort.fa'
  outfile='orf_pred_tc_nc_nolde_mm2_alz_flnc_hg38.fa'
  python ${spath}${pscript} -f ${fasta} -o ${outfile}

run bash script

  sh run_orf_seeker.sh

make folder and go into it

  1_split_fasta

make bash script

  run_fasta_splitter.sh

fill bash script

  spath='/share/workshop/isoseq_workshop/rkuo/tama/tama_go/split_files/'
  pscript='tama_fasta_splitter.py'
  fasta='../orf_pred_tc_nc_flnc_nolde_mm2_alz_flnc_hg38.fa'
  outfile='orf_pred_tc_nc_flnc_nolde_mm2_alz_flnc_hg38'
  numsplits='10'
  python ${spath}${pscript} ${fasta} ${outfile} ${numsplits}

run bash script

  sh run_fasta_splitter.sh

skip blastp because it takes too long

make bash script

  run_parser_bls.sh

fill bash script

  spath='/share/workshop/isoseq_workshop/rkuo/tama/tama_go/orf_nmd_predictions/'
  pscript='tama_orf_blastp_parser.py'
  bpath='./'
  blastp='all_blastp.bls'
  outfile='orf_pred_tc_nc_nolde_mm2_alz_flnc_hg38_prot_onlytophits.txt'
  python ${spath}${pscript} -b ${bpath}${blastp} -o ${outfile}

run bash script

  sh run_parser_bls.sh

make bash script

  run_map_cds.sh

fill bash script

  orf='orf_pred_tc_nc_nolde_mm2_alz_flnc_hg38_prot_onlytophits.txt'
  pbri='tc_nc_flnc_nolde_mm2_alz_flnc_hg38_sort.bed'
  fasta='tc_nc_flnc_nolde_mm2_alz_flnc_hg38_sort.fa'
  outfile='map_cds_tc_nc_nolde_mm2_alz_flnc_hg38.bed'
  spath='/share/workshop/isoseq_workshop/rkuo/tama/tama_go/orf_nmd_predictions/'
  pscript='tama_cds_regions_bed_add.py'
  python ${spath}${pscript} -p ${orf} -a ${pbri} -f ${fasta} -o ${outfile}

run bash script

  sh run_map_cds.sh

download file and view in IGV

  map_cds_tc_nc_nolde_mm2_alz_flnc_hg38.bed