---
directories:
    work_dir: /usr/local/www/data/private/Phaseolus/coccineus/PHA8298.gnm1.ann1
    from_annot_dir: v1.1/annotation
    from_genome_dir: v1.1/assembly
prefixes:
    from_annot_prefix: "Pcoccineus_703_v1.1."
    from_genome_prefix: "Pcoccineus_703_v1.0."
collection_info:
    genus: Phaseolus
    species: coccineus
    scientific_name_abbrev: phaco
    coll_genotype: PHA8298
    gnm_ver: gnm1
    ann_ver: ann1
    genome_key: PYJ1
    annot_key: 0Q14
readme_info:
    provenance: "The files in this directory originated from http://phytozome.jgi.doe.gov. The Phytozome repository is considered the primary repository and authoritative; files in this present directory are derived, and may have changes, as noted below. The files here are held as part of the LegumeInfo and SoyBase projects, and are made available here for the purpose of reproducibility of analyses at these sites (e.g. gene family alignments and phylogenies, genome browsers, etc.) and for further use by researchers, as that research extends other analyses at the LegumeInfo and SoyBase projects. If you are conducting research on large-scale data sets for this species, please consider retrieving the data from the primary repositories. If you use the data in the present directory, please respect any usage restrictions in the present and original repositories, and cite the data appropriately."
    source: "https://phytozome-next.jgi.doe.gov/info/Pcoccineus_v1_1"
    synopsis_genome: Phaseolus coccineus accession PHA8298, genome assembly v1
    synopsis_annot: Annotation 1 for Phaseolus coccineus accession PHA8298, genome assembly v1
    genotype: PHA8298
    taxid: "3886"
    description_genome: "This release (Phaseolus coccineus var. PHA8298, Pc_12) was sequenced within the European project BEAN_ADAPT, in collaboration with the HudsonAlpha Institute for Biotechnology. The BEAN_ADAPT projects, funded through the 2nd ERA-CAPS call, ERA-NET for Coordinating Action in Plant Science, was designed to investigate the genetic basis and phenotypic consequences of the adaptation to new environments of the common bean and its sister species, the runner bean, through the study of their introduction and expansion through Europe, as a recent and historically well-defined event of rapid adaptation. Please see https://phytozome-next.jgi.doe.gov/info/Pcoccineus_v1_1 for additional information."
    chromosome_prefix: Chr
    supercontig_prefix: scaffold
    description_annot: "Gene annotation resources. See full description at Phytozome/JGI repository (address above)."
    bioproject: 
    sraproject: 
    dataset_doi_genome: 
    dataset_doi_annot: 
    genbank_accession: 
    original_file_creation_date: 2022-11-08
    local_file_creation_date: 2024-02-10
    dataset_release_date: 2024-02-15
    contributors: Roberto Papa, Elisa Bellucci, Elena Bitocchi, Tania Gioia, Scott Jackson, Jeremy Schmutz
    publication_doi: 
    citation: "Guerra-Garcia A, Rojas-Barrera IC, Ross-Ibarra J, Papa R, Pinero D. The genomic signature of wild-to-crop introgression during the domestication of scarlet runner bean (Phaseolus coccineus L.). Evol Lett. 2022 Jun 15;6(4):295-307. doi: 10.1002/evl3.285. PMID: 35937471; PMCID: PMC9346085."
    publication_title: "The genomic signature of wild-to-crop introgression during the domestication of scarlet runner bean (Phaseolus coccineus L.)"
    data_curators: Steven Cannon
    public_access_level: public
    license: Restricted, with usage agreement
    keywords: "Scarlet runner bean"
from_to_genome:
  - 
    from: fa.gz
    to: genome_main.fna
    description: "Primary genome assembly"
  - 
    from: hardmasked.fa.gz
    to: genome_hardmasked.fna
    description: "Genome assembly - softmasked"
  - 
    from: softmasked.fa.gz
    to: genome_softmasked.fna
    description: "Genome assembly - hardmasked"
original_readme_and_usage:
  - 
    from_full_filename: Pcoccineus_703_v1.1.DataReleasePolicy.html
    to: DataReleasePolicy.html
    description: "Original JGI data release policy"
  - 
    from_full_filename: Pcoccineus_703_v1.1.readme.txt
    to: original_readme.txt
    description: "Original JGI data README file"
from_to_annot_as_is:
  - 
    from: annotation_info.txt.gz
    to: annotation_info.txt
    description: "Table of gene annotations from JGI"
  - 
    from: defline.txt.gz
    to: defline.txt
    description: "Defline for genes from JGI"
#  - 
#    from: locus_transcript_name_map.txt.gz
#    to: locus_transcript_name_map.txt
#    description: "Table of gene ID correspondences among Wm82 assemblies"
from_to_genome_as_is:
from_to_cds_mrna:
  - 
    from: cds.fa.gz
    to: cds.fna
    description: "cds sequences"
  - 
    from: cds_primaryTranscriptOnly.fa.gz
    to: cds_primary.fna
    description: "cds sequences - primary only"
  - 
    from: transcript.fa.gz
    to: mrna.fna
    description: "Transcript sequences"
  - 
    from: transcript_primaryTranscriptOnly.fa.gz
    to: mrna_primary.fna
    description: "Transcript sequences - primary only"
from_to_protein:
  - 
    from: protein_primaryTranscriptOnly.fa.gz
    to: protein_primary.faa
    strip: '\.p'
    description: "Protein sequences - primary only"
  - 
    from: protein.fa.gz
    to: protein.faa
    strip: '\.p'
    description: "Protein sequences"
from_to_gff:
  - 
    from: gene_exons_strip.gff3.gz
    to: gene_models_exons.gff3
    strip: '\.v1\.1'
    description: "Gene models, with exon features"
  - 
    from: gene_strip.gff3.gz
    to: gene_models_main.gff3
    strip: '\.v1\.1'
    description: "Gene models - main"