{
  "abstract": "The long-time dynamics of complex molecular systems often involves rare transitions across networks of metastable states. Building on transition-path theory, which provides a rigorous framework for describing rare transitions between two metastable states, we introduce the variational multistate committor network (VMCN), a neural framework that learns the probabilities of reaching each metastable state directly from molecular simulation data. From this representation, VMCN identifies state-specific commitment, candidate transition regions and committor-consistent pathways between state pairs, and an effective kinetic network characterized by transition rates. The model is trained using finite time-lag trajectory data together with boundary conditions defined on conservative state cores. Applications to a triple-well potential, trialanine isomerization, and the $c$--ring rotation in the V$_{\\rm o}$ domain of a vacuolar ATPase show that VMCN recovers metastable organization, provides committor-consistent descriptions of transition mechanisms, and estimates state-to-state kinetics. VMCN further provides diagnostics for incomplete state decompositions and enables adaptive exploration of candidate metastable states and their connecting regions. By integrating VMCN with generative committor-guided path sampling (Gen-COMPAS) for chignolin, we start from two end point structures, identify a misfolded state and a candidate folding intermediate, and we direct subsequent sampling toward the resulting multistate transition network.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.04449",
  "author_total": 4,
  "authors": [
    {
      "name": "Chenyu Tang"
    },
    {
      "name": "Cheng Giuseppe Chen"
    },
    {
      "name": "Benoît Roux"
    },
    {
      "name": "Christophe Chipot"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/774zgcgx9n6tt.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.04449",
  "fulltext_url": null,
  "id": "774zgcgx9n6tt",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.04449",
  "language": null,
  "licence": "CC-BY-NC-SA-4.0",
  "licence_label": "CC BY-NC-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "physics.chem-ph"
    ],
    [
      "arxiv",
      "physics.comp-ph"
    ],
    [
      "arxiv",
      "physics.data-an"
    ],
    [
      "openalex",
      "1312|Protein Structure and Dynamics"
    ]
  ],
  "openalex": "W7211908536",
  "pdf_url": "https://arxiv.org/pdf/2609.04449",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-03",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/774zgcgx9n6tt.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:14Z",
      "native_id": "2609.04449",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.04449"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "arxiv:physics.chem-ph",
      "subfield": "physical"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.comp-ph",
      "subfield": "computational"
    }
  ],
  "title": "Learning multistate kinetics with a variational multistate committor network",
  "title_text": "Learning multistate kinetics with a variational multistate committor network",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:14Z",
  "url": "https://research.draconitic.com/paper/774zgcgx9n6tt",
  "venue": "arXiv",
  "versions": []
}