---
file_transformation: 
  - #in this directory
  - for file in *.f??; do
     perl -pi -e 's/^>Glyma/>glyma.Fiskeby.gnm1.ann1.Glyma/' $file;
  - # Prefix gff3 and strip off.v1.1 suffixes that Phytozome uses after applying our prefixing
  - perl -pe 's/^/glyma.Fiskeby.gnm1./ if (! /##/); s/Glyma/glyma.Fiskeby.gnm1.ann1.Glyma/g; s/Name=glyma.Fiskeby.gnm1.ann1.Glyma/Name=Glyma/; s/\.v1\.1//g' \ 
glyma.Fiskeby.gnm1.ann1.SS25.gene.gff3 >glyma.Fiskeby.gnm1.ann1.SS25.gene_models_main.gff3
  - perl -pe 's/^/glyma.Fiskeby.gnm1./ if (! /##/); s/Glyma/glyma.Fiskeby.gnm1.ann1.Glyma/g; s/Name=glyma.Fiskeby.gnm1.ann1.Glyma/Name=Glyma/; s/\.v1\.1//g' \
glyma.Fiskeby.gnm1.ann1.SS25.gene_exons.gff3 >glyma.Fiskeby.gnm1.ann1.SS25.gene_exons.gff3
  - #sort gff3
  - /usr/local/www/data/about_the_data_store/scripts/gff3sort/gff3sort.pl glyma.Fiskeby.gnm1.ann1.SS25.gene_models_main.gff3 >tmp.gff3.sorted
  - mv tmp.gff3.sorted glyma.Fiskeby.gnm1.ann1.SS25.gene_models_main.gff 
  - # order and sort
  - perl -ne '@rows = split("\t", $_); if ($rows[3] > $rows[4]){ $line = $rows[0]."\t".$rows[1]."\t".$rows[2]."\t".$rows[4]."\t".$rows[3]."\t".$rows[5]."\t".$rows[6]."\t".$rows[7]."\t".$rows[8]; print "$line";}else {$line2 = join ("\t", @rows); print "$line2";}' glyma.Fiskeby.gnm1.ann1.SS25.gene_exons.gff3 >tmp.gff3
  - mv tmp.gff3 glyma.Fiskeby.gnm1.ann1.SS25.gene_exons.gff3
  - /usr/local/www/data/about_the_data_store/scripts/gff3sort/gff3sort.pl glyma.Fiskeby.gnm1.ann1.SS25.gene_exons.gff3 >tmp.gff3.sorted
  - mv tmp.gff3.sorted glyma.Fiskeby.gnm1.ann1.SS25.gene_exons.gff3
  - # Manually: removed the .p suffix from IDs in the protein files.

changes:
  - 2021-04-19 Initial repository creation
  - 2021-05-24 removed .p suffix from glyma.Fiskeby.gnm1.ann1.SS25.protein_primaryTranscriptOnly.faa.gz as well; added fai indexes
  - 2021-06-30 Change all file names with Fiskeby to FiskebyIII
  - 2021-06-30 Change Fiskeby ti FiskebyIII in all files 
  - perl -pi -e 's/Fiskeby/FiskebyIII/g' * 
  - 2021-07-13 Rename primaryTranscriptOnly to primaryTranscript
  - adf: 2021-08-11 correct gene names for unanchored scaffolds in glyma.FiskebyIII.gnm1.ann1.SS25.legfed_v1_0.M65K.gfa.tsv
  - 2021-09-14 WH Add AHRD annotation to the main gene model gff
  - 2023-05-23 adf: add AHRD with GO/IPR in descriptors
  - 2024-04-11 sbc: update synopsis to include JGI numbering