---
directories:
    work_dir: /usr/local/www/data/private/Trifolium/pratense/HEN17-A07.gnm1.ann1
    from_annot_dir: derived
    from_genome_dir: derived
prefixes:
    from_annot_prefix: "GCF_020283565.1." 
    from_genome_prefix: "GCF_020283565.1."
collection_info:
    genus: Trifolium
    species: pratense
    scientific_name_abbrev: tripr
    coll_genotype: HEN17-A07
    gnm_ver: gnm1
    ann_ver: ann1
    genome_key: Y8WV
    annot_key: LHG2
readme_info:
    provenance: "The files in this directory originated from GenBank, for RefSeq genome sequence GCF_020283565.1. submitted by USDA ARS in 2021. The GenBank source 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 Peanutbase 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 project. 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://www.ncbi.nlm.nih.gov/datasets/genome/GCF_020283565.1"
    synopsis_genome: Genome assembly 1 for Trifolium pratense, genotype HEN17-A07
    synopsis_annot: GenBank RefSeq annotation for Genome assembly 1 for Trifolium pratense, genotype HEN17-A07
    taxid: "57577"
    genotype: HEN17-A07
    description_genome: "Genome assembly 1 for Trifolium pratense, genotype HEN17-A07, with sequenced generated using PacBio Improved Phased Assembler, HiFi assembler version 1.3.0, and approximately 55–60× predicted coverage of HiFi reads. See publication for information about additional assembly and scaffolding details." 
    chromosome_prefix: Chr
    supercontig_prefix: scaffold
    description_annot: "This annotation was produced by GenBank on the RefSeq assembly GCF_020283565.1 in 2022."
    bioproject: "PRJNA754186"
    sraproject: 
    dataset_doi_genome: 
    dataset_doi_annot: 
    genbank_accession: "GCF_020283565.1."
    original_file_creation_date: "2021-10-13"
    local_file_creation_date: "2024-04-18"
    dataset_release_date: "2024-05-01"
    contributors: "Derek Bickhart, Lisa Koch, Timothy Smith, Heathcliffe Riday, Michael Sullivan"
    publication_doi: "10.46471/gigabyte.42"
    citation: "Bickhart DM, Koch LM, Smith TPL, Riday H, Sullivan ML. Chromosome-scale assembly of the highly heterozygous genome of red clover (Trifolium pratense L.), an allogamous forage crop species. GigaByte. 2022 Feb 18;2022:gigabyte42. doi: 10.46471/gigabyte.42. PMID: 36824517; PMCID: PMC9650271."
    publication_title: "Chromosome-scale assembly of the highly heterozygous genome of red clover (Trifolium pratense L.), an allogamous forage crop species"
    data_curators: Steven Cannon, Wei Huang, Andrew Farmer
    public_access_level: public
    license: open
    keywords: "Trifolium pratense, red clover, peavine clover"
from_to_genome:
  - 
    from: modID.genome.fasta.gz
    to: genome_main.fna
    description: "Primary genome assembly"
original_readme_and_usage:
from_to_genome_as_is:
  - 
    from: initial_seqid_map.tsv
    to: initial_seqid_map.tsv
    description: "Mapping between original and modified sequence IDs"
from_to_cds_mrna:
  - 
    from: modID.CDS.fna.gz
    to: cds.fna
    description: "cds sequences"
  - 
    from: modID.CDS_primary.fna.gz
    to: cds_primary.fna
    description: "cds sequences - longest variant for each gene"
  - 
    from: modID.transcripts.fna.gz
    to: mrna.fna
    description: "mRNA sequences"
  - 
    from: modID.transcripts_primary.fna.gz
    to: mrna_primary.fna
    description: "mRNA sequences - longest variant for each gene"
from_to_protein:
  - 
    from: modID.protein.faa.gz
    to: protein.faa
    description: "Protein sequences"
  - 
    from: modID.protein_primary.faa.gz
    to: protein_primary.faa
    description: "Protein sequences - longest variant for each gene"
from_to_gff:
  - 
    from: modID.genes_exons.gff3.gz
    to: gene_models_main.gff3
    description: "Gene models - main"
from_to_gff_as_is:
  - 
    from: modID.noncoding.gff3.gz
    to: noncoding.gff3
    description: "Noncoding features"