---
directories:
    work_dir: /usr/local/www/data/private/Vigna/GENUS
    from_pan_dir: out_pandagma
prefixes:
    from_pan_prefix: 
collection_info:
    genus: Vigna
    pan_ver: pan3
    pan_key: V294
readme_info:
    provenance: "The files in this directory are a product of the staff of the SoyBase and LegumeInfo project teams. The method is described here: https://github.com/legumeinfo/pandagma"
    source: "https://data.legumeinfo.org"
    synopsis: "Pangene set for Vigna species, based primarily on V. unguiculata but also including V. angularis and V. radiata. This pangene set includes 12 annotation sets."
    taxid: "3913"
    annotations_main: vigun.CB5-2.gnm1.ann1, vigun.IT97K-499-35.gnm1.ann2, vigun.Sanzi.gnm1.ann1, vigun.Suvita2.gnm1.ann1, vigun.TZ30.gnm1.ann2, vigun.UCR779.gnm1.ann1, vigun.ZN016.gnm1.ann2
    annotations_extra: vigun.IT97K-499-35.gnm1.ann1, vigan.Gyeongwon.gnm3.ann1, vigan.Shumari.gnm1.ann1, vigra.VC1973A.gnm6.ann1, vigra.VC1973A.gnm7.ann1
    description: "Pan-gene set for Vigna species, spanning 3 species and 12 annotation sets, calculated using the pandagma pipeline, version 2.0 (February, 2024)"
    bioproject: 
    sraproject: 
    dataset_doi_genome: 
    dataset_doi_annot: 
    genbank_accession: 
    original_file_creation_date: 2024-02-14
    local_file_creation_date: 2024-02-14
    dataset_release_date: 2024-02-14
    contributors: Steven Cannon
    publication_doi: 
    citation: 
    publication_title: 
    data_curators: Steven Cannon
    public_access_level: public
    license: Open
    keywords: "Vigna, cowpea, mung bean, pan-gene, pangene, orthogroup"
from_to_pan_tsv:
  - 
    from: 18_syn_pan_aug_extra.clust.tsv
    to: clust.tsv
    description: "Pan-gene sets, in cluster format: ID in first column, followed by tab-separated gene list."
  - 
    from: 18_syn_pan_aug_extra.counts.tsv
    to: counts.tsv
    description: "Matrix of counts of genes per annotation set for each pan-gene set."
  - 
    from: 18_syn_pan_aug_extra.hsh.tsv
    to: hsh.tsv
    description: "Pan-gene sets, in a two-column hash format, with the set ID in the first column and genes in the second."
  -
    from: 18_syn_pan_aug_extra.table.tsv
    to: table.tsv
    description: "Table of genes in each family or pangene, in columns by accession"
from_to_pan_fasta:
  - 
    from: 21_pan_fasta_clust_rep_cds.fna
    to: inclusive_cds.fna
    description: "CDS pan-gene sequence, inclusive (not filtered by minimum cluster size or annotation-set representation)."
  - 
    from: 21_pan_fasta_clust_rep_prot.faa
    to: inclusive_protein.faa
    description: "Protein pan-gene sequence, inclusive (not filtered by minimum cluster size or annotation-set representation)."
  - 
    from: 23_syn_pan_pctl25_posn_cds.fna
    to: pctl25_named_cds.fna
    strip: '\w+\.pan\d+\.'
    description: "CDS pan-gene sequence, omitting pan-genes smaller than 25% of the mode, with derived pan-gene IDs corresponding with consensus chromosome and ordinal position."
  - 
    from: 23_syn_pan_pctl25_posn_prot.faa
    to: pctl25_named_protein.faa
    strip: '\w+\.pan\d+\.'
    description: "Protein pan-gene sequence, omitting pan-genes smaller than 25% of the mode, with derived pan-gene IDs corresponding with consensus chromosome and ordinal position."
from_to_pan_as_is:
  - 
    from: 18_syn_pan_aug_extra_complement.fna
    to: complement.fna
    description: "Complement of genes in this pan-gene set; i.e. not clustered, presumed to be singletons."
  - 
    from: stats.txt
    to: stats.txt
    description: "Descriptive statistics about program parameters, input sequences, and pan-gene products."