{
  "abstract": "Structural annotation remains a bottleneck for translating the growing catalog of high-quality plant genomes into biological insights, as current pipelines rely on RNA-seq and homologous protein evidence that are often unavailable for non-model species. Existing ab initio tools are constrained by model scale and perform poorly in complex plant genomic regions. We present PlantGeneAnn, a plant-optimized ab initio gene annotation tool fine-tuned from a genome foundation model. It combines a Mamba-MoE DNA encoder with a U-Net-style embedding decoder and a semi-Markov decoding pipeline. Trained on 40 angiosperm species, PlantGeneAnn establishes a new state-of-the-art (SOTA) across a stringent 20-species benchmark, significantly outperforming Helixer, Tiberius, and ANNEVO at exon-, intron-, and locus-levels, with mean F1 scores of 0.856, 0.880, and 0.707, respectively. It also enables efficient customized fine-tuning: LoRA fine-tuning increased the locus-level F1 of the out-of-distribution bryophyte Physcomitrium patens from 0.581 to 0.736, with performance plateauing at 40% of the fine-tuning data. Notably, PlantGeneAnn requires substantially lower peak memory usage than other baseline tools, allowing annotation of large plant genomes on standard personal workstations. PlantGeneAnn thus provides accurate, hardware-friendly ab initio annotation for diverse plant genomes, particularly newly assembled genomes, population-scale projects, and non-model plants.",
  "abstract_shown": true,
  "affiliations": [
    "Huazhong Agricultural University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "name": "Z. Qizhe"
    },
    {
      "name": "Z. Zhengyang"
    },
    {
      "name": "L. Kepeng"
    },
    {
      "name": "J. Wang"
    },
    {
      "name": "D. Kaixuan"
    },
    {
      "name": "X. Wei"
    },
    {
      "name": "Y. Qing-Yong"
    },
    {
      "affs": [
        0
      ],
      "name": "H. Xuehai"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0jd57vkz3dsrp.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.06.25.733695",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.06.25.733695v2.full",
  "id": "0jd57vkz3dsrp",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.06.25.733695v2",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1312|Genomics and Phylogenetic Studies"
    ]
  ],
  "openalex": "W7166093456",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.06.25.733695v2.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-06-25",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0jd57vkz3dsrp.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:27:46Z",
      "native_id": "10.64898/2026.06.25.733695",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.06.25.733695v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "PlantGeneAnn: a high-accuracy ab initio plant gene annotation tool fine-tuned from a genome foundation model",
  "title_text": "PlantGeneAnn: a high-accuracy ab initio plant gene annotation tool fine-tuned from a genome foundation model",
  "type": "preprint",
  "updated_at": "2026-10-30T12:27:46Z",
  "url": "https://research.draconitic.com/paper/0jd57vkz3dsrp",
  "venue": "bioRxiv",
  "versions": []
}