---
directories:
    work_dir: /usr/local/www/data/private/Cercis/chinensis/
    from_annot_dir: GWHBHAK
    from_genome_dir: GWHBHAK
prefixes:
    from_annot_prefix: GWHBHAK00000000.
    from_genome_prefix: GWHBHAK00000000.
collection_info:
    genus: Cercis
    species: chinensis
    scientific_name_abbrev: cerch
    coll_genotype: GXIB
    gnm_ver: gnm1
    ann_ver: ann1
    genome_key: 5DZH
    annot_key: L8L4
readme_info:
    provenance: "The files in this directory originated from the Genome Warehouse of the China National Center for Bioinformation, https://ngdc.cncb.ac.cn/gwh. The Genome Warehouse 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://ngdc.cncb.ac.cn/gwh/Assembly/24066/show
    synopsis_genome: Genome assembly for Cercis chinensis, from a plant at the campus of Guangxi Institute of Botany, Chinese Academy of Sciences.
    synopsis_annot: Gene annotations for Cercis chinensis, from a plant at the campus of Guangxi Institute of Botany, Chinese Academy of Sciences.
    taxid: 161750
    genotype: GXIB
    description_genome: Genome assembly for Cercis chinensis, from a plant at the campus of Guangxi Institute of Botany (GXIB), from Li, Shen et al., 2023.  The genome assembly was derived from PacBio HiFi reads with 130.9x coverage.
    description_annot: Gene annotations for Cercis chinensis were based on deep transcriptome sequencing of five plant tissues, and transcriptome-based, homolog-based, and ab initio methods.
    bioproject: PRJCA007288
    sraproject: 
    dataset_doi_genome: 
    dataset_doi_annot: 
    genbank_accession: GWHBHAK00000000
    original_file_creation_date: "2021-11-20"
    local_file_creation_date: "2024-01-08"
    dataset_release_date: "2024-02-01"
    contributors: Li J, Shen J, Wang R, Chen Y, Zhang T, Wang H, Guo C, Qi J.
    publication_doi: 10.1016/j.xplc.2022.100422
    citation: "Li J, Shen J, Wang R, Chen Y, Zhang T, Wang H, Guo C, Qi J. The nearly complete assembly of the Cercis chinensis genome and Fabaceae phylogenomic studies provide insights into new gene evolution. Plant Commun. 2023 Jan 9;4(1):100422. doi: 10.1016/j.xplc.2022.100422. Epub 2022 Aug 11. PMID: 35957520; PMCID: PMC9860166."
    publication_title: The nearly complete assembly of the Cercis chinensis genome and Fabaceae phylogenomic studies provide insights into new gene evolution
    data_curators: Steven Cannon, Andrew Farmer
    public_access_level: public
    license: open
    keywords: "Chinese redbud tree"
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_genome:
  -
    from: genome_modID.fasta.gz
    to: genome_main.fna
    description: Primary genome assembly
from_to_cds_mrna:
  -
    from: CDS.fna.gz
    to: cds.fna
    description: CDS sequences
  -
    from: mrna.fna.gz
    to: mrna.fna
    description: mRNA sequences
from_to_protein:
  -
    from: protein.faa.gz
    to: protein.faa
    description: Protein sequences
from_to_gff:
  -
    from: modID.gff3.gz
    to: gene_models_main.gff3
    description: Gene models - main