--- directories: work_dir: /usr/local/www/data/private/Glycine/max/Wm82_NJAU.gnm1.ann1 from_annot_dir: derived from_genome_dir: derived prefixes: from_annot_prefix: GWHCAYC00000000. from_genome_prefix: GWHCAYC00000000. collection_info: genus: Glycine species: max scientific_name_abbrev: glyma coll_genotype: Wm82_NJAU gnm_ver: gnm1 ann_ver: ann1 genome_key: N4GV annot_key: KM71 readme_info: provenance: "The files in this directory originated from https://ngdc.cncb.ac.cn/gwh/Assembly/37536/show. 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/37536/show" synopsis_genome: Glycine max accession Williams 82 from Nanjing Agricultural University (Wm82-NJAU), genome assebly v1 synopsis_annot: Annotation 1 for Glycine max accession Williams 82 from Nanjing Agricultural University (Wm82-NJAU), genome assembly v1 genotype: Wm82_NJAU taxid: 3847 description_genome: "Sequenced using PacBio HiFi, Nanopore ONT ulta-long, and short read Illumina sequencing; assembled with hifisam v0.16.1; minimap2 v2.24; Racon v1.5.0; RagTag v2.1.0" chromosome_prefix: Gm description_annot: "Gene annotation resources. See full description in supplemental methods at Wang, Lomngfei et al., 2023" bioproject: PRJCA015288 sraproject: dataset_doi_genome: dataset_doi_annot: genbank_accession: original_file_creation_date: 2023-08-19 local_file_creation_date: 2023-01-17 dataset_release_date: 2023-02-01 contributors: Longfei Wang, Mengzhu Zhang, Mengna Li, Xinyu Jiang, Wu Jiao, Qingxin Song publication_doi: 10.1016/j.molp.2023.08.012 citation: "Wang L, Zhang M, Li M, Jiang X, Jiao W, Song Q. A telomere-to-telomere gap-free assembly of soybean genome. Mol Plant. 2023 Nov 6;16(11):1711-1714. doi: 10.1016/j.molp.2023.08.012. Epub 2023 Aug 26. PMID: 37634078." publication_title: "A telomere-to-telomere gap-free assembly of soybean genome" data_curators: Jacqueline Campbell, Steven Cannon public_access_level: public license: open keywords: "soybean, Wm82, Williams 82, Wm82_NJAU, Wm82-NJAU" 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_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 - primary only" - from: modID.transcripts.fna.gz to: mrna.fna description: "Transcript sequences" - from: modID.transcripts_primary.fna.gz to: mrna_primary.fna description: "Transcript sequences - primary only" from_to_protein: - from: modID.protein.faa.gz to: protein.faa description: "Protein sequences" - from: modID.protein_primary.faa.gz to: protein_primary.faa.gz description: "Protein sequences - primary only" from_to_gff: - from: modID.genes.gff3.gz to: gene_models_main.gff3 description: "Gene models - main" - from: modID.genes_exons.gff3.gz to: gene_models_exons.gff3 description: "Gene models, with exons"