{
  "abstract": "Accurate generation of intricate 3D molecular structures is a fundamental challenge in computational chemistry. Transition states (TS), the transient structures that dictate reaction kinetics, exemplify this challenge, as their calculation remains a major bottleneck in elucidating reaction mechanisms. While generative AI has shown promise in automating TS generation, existing methods are largely confined to simple systems, struggling with the complex structures like those in transition metal catalysis. Here we show a unified framework for general-purpose TS generation, comprising the UniTS-Lib library of 4,391 high-quality structures spanning 42 elements and diverse chemical transformations, coupled with the UniTS-Gen diffusion model that generates 3D TS configurations from 2D reactant graphs using a custom-designed higher-degree equivariant network. Validation demonstrates UniTS-Gen's superior accuracy and robust generalization to unseen chemical systems. We show that UniTS-Gen provides reliable initial guesses and accelerates discovery by locating kinetically favored conformations. This work provides a scalable and transferable solution for automating mechanistic studies in organic synthesis and beyond.",
  "abstract_shown": true,
  "affiliations": [
    "Golab Inc, Shanghai, China. xulicheng@sais.org.cn",
    "Shanghai Academy of Artificial Intelligence for Science, Shanghai, China. xulicheng@sais.org.cn",
    "Golab Inc, Shanghai, China",
    "Shanghai Academy of Artificial Intelligence for Science, Shanghai, China",
    "Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China",
    "School of Physical Science and Technology, ShanghaiTech University, Shanghai, China",
    "Golab Inc, Shanghai, China. caofenglei@sais.org.cn",
    "Shanghai Academy of Artificial Intelligence for Science, Shanghai, China. caofenglei@sais.org.cn",
    "Artificial Intelligence Innovation and Incubation Institute, Fudan University, Shanghai, China. qiyuan@fudan.edu.cn",
    "Shanghai Academy of Artificial Intelligence for Science, Shanghai, China. qiyuan@fudan.edu.cn"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 7,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Li‐Cheng Xu",
      "orcid": "0000-0002-9553-0412"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Junyi An"
    },
    {
      "affs": [
        4,
        3
      ],
      "name": "Weiqi Liu",
      "orcid": "0000-0002-8371-293X"
    },
    {
      "affs": [
        2,
        3
      ],
      "name": "Yunfei Shi",
      "orcid": "0000-0003-2178-4230"
    },
    {
      "affs": [
        5
      ],
      "name": "Chong‐Lei Ji",
      "orcid": "0000-0001-7930-2324"
    },
    {
      "affs": [
        6,
        7
      ],
      "name": "Fenglei Cao",
      "orcid": "0000-0001-8148-8578"
    },
    {
      "affs": [
        8,
        9
      ],
      "name": "Yuan Qi",
      "orcid": "0009-0002-9377-5755"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f1npytf9az421.bib",
  "cited_by": 7,
  "doi": "10.1038/s41467-026-77230-8",
  "fulltext_url": null,
  "id": "f1npytf9az421",
  "issns": [
    "2041-1723"
  ],
  "landing_url": "https://doi.org/10.1038/s41467-026-77230-8",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "3002|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7204453207",
  "pdf_url": "https://www.nature.com/articles/s41467-026-77230-8_reference.pdf",
  "pmcid": "PMC13616924",
  "pmid": "42802179",
  "published": "2026-08-27",
  "publisher": "Nature Portfolio",
  "ris": "https://research.draconitic.com/paper/f1npytf9az421.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:21:00Z",
      "native_id": "W7204453207",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s41467-026-77230-8"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:3002|Computational Drug Discovery Methods",
      "subfield": "medicinal"
    }
  ],
  "title": "Automated transition state generation for mechanistic exploration in organic synthesis",
  "title_text": "Automated transition state generation for mechanistic exploration in organic synthesis",
  "type": "peer-reviewed",
  "updated_at": "2026-11-07T13:21:00Z",
  "url": "https://research.draconitic.com/paper/f1npytf9az421",
  "venue": "Nature Communications",
  "versions": []
}