---
directories:
    work_dir: /usr/local/www/data/private/Chamaecrista/fasciculata/ISC494698.gnm1.ann1
    from_annot_dir: v1.1/annotation
    from_genome_dir: v1.1/assembly
prefixes:
    from_annot_prefix: "Cfasciculatavar_ISC494698HAP1_854_v1.1."
    from_genome_prefix: "Cfasciculatavar_ISC494698HAP1_854_v1.0."
collection_info:
    genus: Chamaecrista
    species: fasciculata
    scientific_name_abbrev: chafa
    coll_genotype: ISC494698
    gnm_ver: gnm1
    ann_ver: ann1
    genome_key: 8Q19
    annot_key: G7XW
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/Cfasciculatavar_ISC494698HAP1_v1_1"
    synopsis_genome: Chamaecrista fasciculata accession ISC494698, genome assembly v1, haplotype 1
    synopsis_annot: Annotation 1 for Chamaecrista fasciculata accession ISC494698, genome assembly v1, haplotype 1
    genotype: ISC494698
    taxid: "53854"
    description_genome: "This release is from a an accession from Ames, Iowa, registered as accession ISC494698. This accession derived originally from a population on the west side of Minneapolis, Minnesota. The resulting genome assembly was resolved into two haplotype assemblies. For full description of assembly methods and characteristics, see the Phytozome description at the URL above."
    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: 2023-06-28
    local_file_creation_date: 2024-07-01
    dataset_release_date: 2024-08-01
    contributors: Steven Cannon, Jim Leebens-Mack, Jacob Stai, Jeremy Schmutz, Rachel Walstead, Tomas Bruna
    publication_doi: 
    citation: 
    publication_title: 
    data_curators: Steven Cannon
    public_access_level: public, restricted
    license: Open, with usage agreement
    keywords: "partridge pea, Chamaecrista fasciculata"
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: Cfasciculatavar_ISC494698HAP1_854_v1.1.DataReleasePolicy.html
    to: DataReleasePolicy.html
    description: "Original JGI data release policy"
  - 
    from_full_filename: Cfasciculatavar_ISC494698HAP1_854_v1.1.readme.txt
    to: original_readme.txt
    description: "Original JGI data README file"
from_to_annot_as_is:
  - 
    from: repeatmasked_assembly_v1.0.gff3.gz
    to: repeatmasked_assembly.gff
    description: "GFF with repeat-masking coordinates"
  - 
    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_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.fa.gz
    to: protein.faa
    strip: '\.p'
    description: "Protein sequences"
  - 
    from: protein_primaryTranscriptOnly.fa.gz
    to: protein_primary.faa
    strip: '\.p'
    description: "Protein sequences - primary only"
from_to_gff:
# Skip gene_exons because a featid_map isn't generated by default for exon features.
  - 
    from: gene_exons_strip.gff3.gz
    to: gene_models_exons.gff3
    description: "Gene models, with exon features"
  - 
    from: gene_strip.gff3.gz
    to: gene_models_main.gff3
    description: "Gene models - main"