---
directories:
    work_dir: /usr/local/www/data/private/Acacia/crassicarpa/Acra3RX.gnm1.ann1
    from_annot_dir: derived
    from_genome_dir: derived
prefixes:
    from_annot_prefix: "Acra_USDA_v1."
    from_genome_prefix: "Acra_USDA_v1."
collection_info:
    genus: Acacia
    species: crassicarpa
    scientific_name_abbrev: acacr
    coll_genotype: Acra3RX
    gnm_ver: gnm1
    ann_ver: ann1
    genome_key: YX4L
    annot_key: 6C0V
readme_info:
    provenance: "The files in this directory originated from https://doi.org/10.5061/dryad.573n5tbdr, submitted by Isabelle Massaro, Scott Poethig, Neelima Sinha, and Aaron Leichty in 2023. The Dryad 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, SoyBase, 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. 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/10.5061/dryad.573n5tbdr"
    synopsis_genome: Genome assembly 1 of Acacia crassicarpa
    synopsis_annot: Annotation 1 of the Acacia crassicarpa genome
    taxid: "499986"
    genotype: Acra3RX
    description_genome: "Genome assembly 1 for Acacia crassicarpa, accession Acra3RX. Sequence reads were generated with PacBio Sequel and Illumina NextSeq. The genome were assembled using hifiasm using Omni-C reads to generate haplotype-resolved assemblies. The larger of the two haplotype assemblies was then used for scaffolding using SALSA and the Omni-C reads."
    chromosome_prefix: 
    supercontig_prefix: scaffold
    description_annot: "BRAKER3 was used to identify protein coding genes of the softmasked genome on scaffolds larger than 1 Mb."
    bioproject: PRJNA975180
    sraproject: JAWXYG000000000
    dataset_doi_genome: 10.5061/dryad.573n5tbdr
    dataset_doi_annot: 10.5061/dryad.573n5tbdr
    genbank_accession: GCA_034222035.1
    original_file_creation_date: "2023-11-27"
    local_file_creation_date: "2024-02-13"
    dataset_release_date: "2024-02-20"
    contributors: "Isabelle Massaro, Scott Poethig, Neelima Sinha, and Aaron Leichty"
    publication_doi: 10.1093/g3journal/jkad284
    citation: "Massaro I, Poethig RS, Sinha NR, Leichty AR. Genome Report: Chromosome-level genome of the transformable northern wattle, Acacia crassicarpa. G3 (Bethesda). 2023 Dec 14:jkad284. doi: 10.1093/g3journal/jkad284. Epub ahead of print. PMID: 38096217."
    publication_title: "Chromosome-level genome of the transformable northern wattle, Acacia crassicarpa."
    data_curators: Steven Cannon
    public_access_level: public
    license: open
    keywords: "Acacia crassicarpa, northern wattle, lancewood"
from_to_genome:
  - 
    from: genome.fasta.gz
    to: genome_main.fna
    description: "Primary genome assembly"
original_readme_and_usage:
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 - longest variant for each gene"
  -     
    from: transcripts.fna.gz
    to: transcripts.fna
    description: "Transcripts - main"
  - 
    from: transcripts_primary.fna.gz
    to: transcripts_primary.fna
    description: "Transcripts - longest variant for each transcript"
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 - longest variant for each gene"
from_to_gff:
  - 
    from: genes.gff3.gz
    to: gene_models_main.gff3
    description: "Gene models - main"
  - 
    from: genes_exons.gff3.gz
    to: gene_models_exons.gff3
    description: "Gene models, with exons"