---
file_transformation: 
  - # Simplify gene deflines - RNA
  - perl -pe 's/^>(\S+)\s+.+OriSeqID=(\S+)\s+OriID=(\S+)\s+OriGeneID=(\S+)/>$3 $4 $2 $1/' GWHAAEV00000000.RNA.fasta > glyma.Zh13.gnm1.ann1.8VV3.protein.cds.fna
  - # Simplify gene deflines - protein
  - perl -pe 's/^>(\S+)\s+.+OriTrascriptID=(\S+)\s+OriGeneID=(\S+)\s+OriSeqID=(\S+)/>$2 $3 $4 $1/' GWHAAEV00000000.Protein.faa > glyma.Zh13.gnm1.ann1.8VV3.protein.faa
  - # Get a hash of GWH IDs and DataStore names from assembly
  - grep '>' ../Zh13.gnm1.8VV3/glyma.Zh13.gnm1.8VV3.genome_main.fna | perl -pe 's/>glyma.Zh13.gnm1.(\S+)\s+(\S+)/$2\t$1/' > hsh.ref_GWH_DS
  - # Hash DataStore names into GFF
  - hash_into_gff_refID.pl -gff GWHAAEV00000000.gff -hash hsh.ref_GWH_DS | perl -pe 's/;Accession.+//; s/;Parent_Accession=.+//i' > glyma.Zh13.gnm1.ann1.8VV3.gene_models_main.gff3

changes:
  - 2019-05-13 Initial repository creation
  - 2019-06-10 Add AHRD functional descriptors and make repository public
  - 2019-07-03 Add "glyma." to IDs in CDS files
  - 2020-04-14 Re-sorted glyma.Zh13.gnm1.ann1.8VV3.gene_models_main.gff3 with gff3sort.pl --precise
  - 2020-09-22 added gene family assignments
  - 2021-05-25 updated gene family assignments to use score instead of e-value
  - 2022-01-21 SCannon - Rename primaryTranscript.fna.gz file to canonical mrna_primary.fna
      mv glyma.Zh13.gnm1.ann1.8VV3.primaryTranscript.fna.gz glyma.Zh13.gnm1.ann1.8VV3.mrna_primary.fna.gz