---

# Initial work, by Annie Brown, in fall 2020:
file_transformation:
  - filtered original VCF file for MAF
  - bcftools_concatCommand=concat /project/shared_files/legume_project/* .vcf | bcftools_viewCommand=view -i MAF[0]>0.01 --output-type z --compression-level 9 --threads 20 -o /home/anne.brown/An_FUll_filtered1.vcf
  - extracted non-Synonymous SNPs from GTF files.
  - zcat *.gtf.gz | grep "non-Synonymous" > AnLab_all_nonSyn_SNPs.gft

# Final formatting by S. Cannon, in Oct 2021:
# Change to new naming convention, and add prefixes:
  cd /usr/local/www/data/private/Glycine/max/diversity/Wm82.gnm2.div.FL3Z
  basedir="/usr/local/www/data/private/Glycine/max/diversity"
  newdir="$basedir/Wm82.gnm2.div.Zhang_Jiang_2020"
  olddir="$basedir/Wm82.gnm2.div.FL3Z"
  base="glyma.Wm82.gnm2.div.Zhang_Jiang_2020"

  cd $basedir
  mkdir $newdir

  cat $olddir/glyma.Wm82.gnm2.div.FL3Z.Accessions.txt > $newdir/$base.info_accessions.txt

  gzcat $olddir/glyma.Wm82.gnm2.div.FL3Z.nonSyn_SNPs.gtf.gz |
     perl -pe 's/Chr/glyma.Wm82.gnm2.Gm/' > $newdir/$base.nonSyn_SNPs.gtf &

  nohup gzcat $olddir/glyma.Wm82.gnm2.div.FL3Z.SNPData_Full.vcf.gz |
     perl -pe 's/Chr/glyma.Wm82.gnm2.Gm/' > $newdir/$base.SNPdata_full.vcf & 

  nohup gzcat $olddir/glyma.Wm82.gnm2.div.FL3Z.SNPData_filtered.01.vcf.gz |
     perl -pe 's/Chr/glyma.Wm82.gnm2.Gm/' > $newdir/$base.SNPdata_maf01.vcf & 

  nohup gzcat $olddir/glyma.Wm82.gnm2.div.FL3Z.SNPData_filtered.05.vcf.gz |
     perl -pe 's/Chr/glyma.Wm82.gnm2.Gm/' > $newdir/$base.SNPdata_maf05.vcf & 

  cat $olddir/MANIFEST.FL3Z.correspondence.yml | perl -pe 's/FL3Z/Zhang_Jiang_2020/' |
    cat > $newdir/MANIFEST.Wm82.gnm2.div.Zhang_Jiang_2020.correspondence.yml

  cat $olddir/MANIFEST.FL3Z.descriptions.yml | perl -pe 's/FL3Z/Zhang_Jiang_2020/; s/SNPData_filtered./SNPdata_maf/' |
    cat > $newdir/MANIFEST.Wm82.gnm2.div.Zhang_Jiang_2020.descriptions.yml

  cat $olddir/README.FL3Z.yml | perl -pe 's/.YAML.+/---/; s/FL3Z/Zhang_Jiang_2020/' |
    cat > $newdir/README.Wm82.gnm2.div.Zhang_Jiang_2020.yml

  cd $newdir
  for file in *txt *gtf *vcf; do nohup bgzip $file & 
  done

  for file in *.vcf.gz; do tabix $file &
  done

  cat AnLab_1.5K.NS_SNPs_minusd2.5proveanAlleleFreq.01.vcf |
    perl -pe 's/Chr/glyma.Wm82.gnm2.Gm/' > $newdir/$base.NonsynSNPs_provean_freq01.vcf

  cat AnLab_1.5K.NS_SNPs_minusd2.5proveanAlleleFreq.01.gtf |
    perl -pe 's/Chr/glyma.Wm82.gnm2.Gm/' > $newdir/$base.NonsynSNPs_provean_freq01.gtf