---
file_transformation: 
  # Strip citation and chromosome location from deflines - since locations refer to assembly 1 and will generally not be useful
  # relative to other assemblies or accessions
    cat SoyBase_TE_Fasta.txt | 
      perl -pe 's/>name=(\S+) .+ (Class=.+)/>$1 $2/; s/ Chromosome=.+//; s/ Unanchored_scaffold.+//' |
      perl -pe 's/ Description=$/ Description=none/' > SOY_TEdb.fna
  # The file SOY_TE_LIB_id60.fna has centroid sequences at 60% identity, as identified by usearch:
    usearch -cluster_fast SOY_TE_LIB.fna -id 0.60 -centroids SOY_TE_LIB_id60.fna

changes: 
  - 2024-02-21 sbc: Initial Data Store collection, ported from https://soybase.org/soytedb/