{
  "abstract": "Summary: Deep learning can scale image-based plant phenotyping but typically targets predefined traits, whereas manual phenotypic description is more flexible but difficult to scale. We present Phenotype eXplorer Generative Plant Traits (pxGPT), a Python framework that converts multi-view plant images into structured phenotype records. The workflow combines free-text description, dataset-specific schema generation with human review, and schema-constrained information extraction. We evaluated the extraction stage on three Brassica datasets using 78 973 annotations from 10 annotators who had no access to pxGPT predictions. For 38–45 qualitative traits per dataset, pxGPT-human agreement ranged from 0.572 to 0.712, compared with 0.620 to 0.739 agreement among human annotators. All 32 736 required trait fields were present; 93 values were empty, and no qualitative descriptor violations were recorded. For selected morphological structures, pooled false-positive rates were 0.5%–8.0%, while sensitivity varied across structure types in one mature-plant dataset (37.5%–100%). The curated schemas were applied unchanged with two commercial models and one locally hosted open-weight model, with differences in mean accuracy of 0.03 or less. In the evaluated Brassica datasets, these results support schema-guided extraction of visible plant traits without separate model training for each trait. Human-guided schema development offers a path to extend pxGPT to other crops and imaging conditions, with accuracy requiring validation in each new setting.\n\nAvailability and implementation: The software is available at https://github.com/YaoChengLab/pxgpt and an archival version of the source code is available on Zenodo (https://doi.org/10.5281/zenodo.22931745). Curated schemas used in this study, annotation guides, phenotype records, and human annotations are available at https://doi.org/10.5281/zenodo.22907554.",
  "abstract_shown": true,
  "affiliations": [
    "Biotechnology Center in Southern Taiwan, Academia Sinica , Tainan 711010,",
    "Agricultural Biotechnology Research Center, Academia Sinica , Taipei 115201,",
    "Biotechnology Center, National Chung Hsing University , Taichung 402202,"
  ],
  "article_type": "brief report",
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Po-Xing Zheng",
      "orcid": "0000-0001-5827-5865"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Jheng-Yan Ou",
      "orcid": "0000-0001-5811-4471"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Yu-Lin Wu",
      "orcid": "0009-0003-8596-9047"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Ruei-Shiuan Wang",
      "orcid": "0009-0007-5159-1129"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Ting-Li Wu",
      "orcid": "0000-0002-2018-9387"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Te-Chang Hsu"
    },
    {
      "affs": [
        0,
        1,
        2
      ],
      "name": "Yao-Cheng Lin",
      "orcid": "0000-0002-9390-795X"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5yxdmycwdwq9c.bib",
  "cited_by": 0,
  "doi": "10.1093/bioinformatics/btag781",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13719227/",
  "id": "5yxdmycwdwq9c",
  "issns": [
    "1367-4803",
    "1367-4811"
  ],
  "landing_url": "https://academic.oup.com/bioinformatics/article/doi/10.1093/bioinformatics/btag781/8956098",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "AcademicSubjects/SCI01060"
    ],
    [
      "heading",
      "Applications Note"
    ],
    [
      "heading",
      "Data and Text Mining"
    ],
    [
      "openalex",
      "1110|Smart Agriculture and AI"
    ]
  ],
  "openalex": "W7223127960",
  "pdf_url": "https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btag781/72201337/btag781.pdf",
  "pmcid": "PMC13719227",
  "pmid": "42902794",
  "published": "2026-10-20",
  "publisher": "Oxford University Press (OUP)",
  "ris": "https://research.draconitic.com/paper/5yxdmycwdwq9c.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:38Z",
      "native_id": "10.1093/bioinformatics/btag781",
      "source": "crossref",
      "url": "https://academic.oup.com/bioinformatics/article/doi/10.1093/bioinformatics/btag781/8956098"
    },
    {
      "first_seen": "2026-11-02T12:23:05Z",
      "native_id": "PMC13719227",
      "source": "pmc",
      "url": "https://doi.org/10.1093/bioinformatics/btag781"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "openalex:1110|Smart Agriculture and AI",
      "subfield": "plant-biology"
    }
  ],
  "title": "pxGPT: a schema-constrained multimodal large language model framework for plant phenotyping",
  "title_text": "pxGPT: a schema-constrained multimodal large language model framework for plant phenotyping",
  "type": "peer-reviewed",
  "updated_at": "2026-11-02T12:23:05Z",
  "url": "https://research.draconitic.com/paper/5yxdmycwdwq9c",
  "venue": "Bioinformatics",
  "versions": []
}