---
directories:
    work_dir: /usr/local/www/data/private/Glycine/max/JD17
    from_annot_dir: annot_orig
    from_genome_dir: annot_orig
prefixes:
    from_annot_prefix: "jd17_"
    from_genome_prefix: "jd17_"
collection_info:
    genus: Glycine
    species: max
    scientific_name_abbrev: glyma
    coll_genotype: JD17
    gnm_ver: gnm1
    ann_ver: ann1
    genome_key: TW7L
    annot_key: CLFP
readme_info:
    provenance: "The files in this directory originated from https://doi.org/10.25387/g3.17065499, with the assembly corresponding to the one at GenBank under accession GCA_021733175.1. Those two repositories are considered the primary and authoritative for this data; 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://doi.org/10.25387/g3.17065499"
    synopsis_genome: Glycine max accession Jidou 17 (JD17), genome assembly 1
    synopsis_annot: Annotation 1 for Glycine max accession Jidou 17 (JD17), genome assembly 1
    genotype: JD17
    taxid: "3847"
    description_genome: "Sequenced using PacBio RSII; assembled with CANU v. 1.4; FALCON v. 1.8.7 23 Mar 2017; HGAP v. SMRT Link v 5.0.1.9585; GPM v. Aug-2017"
    chromosome_prefix: Chr
    supercontig_prefix: PGA_scaffold
    description_annot: "Gene annotation resources. See full description at Yi, Liu et al., 2020"
    bioproject: PRJNA412346
    sraproject: 
    dataset_doi_genome: 
    dataset_doi_annot: 
    genbank_accession: GCA_021733175.1
    original_file_creation_date: 2022-02-03
    local_file_creation_date: 2023-08-29
    dataset_release_date: 2023-10-01
    contributors: Yi X, Liu J, Chen S, Wu H, Liu M, Xu Q, Lei L, Lee S, Zhang B, Kudrna D, Fan W, Wing RA, Wang X, Zhang M, Zhang J, Yang C, Chen N.
    publication_doi: 10.1093/g3journal/jkac017
    citation: "Yi X, Liu J, Chen S, Wu H, Liu M, Xu Q, Lei L, Lee S, Zhang B, Kudrna D, Fan W, Wing RA, Wang X, Zhang M, Zhang J, Yang C, Chen N. Genome assembly of the JD17 soybean provides a new reference genome for comparative genomics. G3 (Bethesda). 2022 Apr 4;12(4):jkac017. doi: 10.1093/g3journal/jkac017. PMID: 35188189; PMCID: PMC8982393."
    publication_title: "Genome assembly of the JD17 soybean provides a new reference genome for comparative genomics"
    data_curators: Steven Cannon
    public_access_level: public
    license: Open, with usage agreement
    keywords: "soybean, JD17, Jidou 17"
from_to_genome:
  - 
    from: genome_figshare.fna.gz
    to: genome_main.fna
    description: "Primary genome assembly"
original_readme_and_usage:
from_to_annot_as_is:
from_to_genome_as_is:
from_to_cds_mrna:
  - 
    from: CDS.fna.gz
    to: cds.fna
    description: "cds sequences"
  - 
    from: CDS_primary.fna.gz
    to: cds_primary.fna
    description: "cds sequences - primary only"
  - 
    from: transcripts.fna.gz
    to: mrna.fna
    description: "Transcript sequences"
  - 
    from: transcripts_primary.fna.gz
    to: mrna_primary.fna
    description: "Transcript sequences - primary only"
from_to_protein:
  - 
    from: protein.faa.gz
    to: protein.faa
    description: "Protein sequences"
  - 
    from: protein_primary.faa.gz
    to: protein_primary.faa
    description: "Protein sequences - primary only"
from_to_gff:
  - 
    from: final.rename.gff3.gz
    to: gene_models_main.gff3
    description: "Gene models - main"