{
  "abstract": "Recent advances in artificial intelligence have transformed protein structure prediction and design. However, protein function is governed not only by static structures but also by the conformational dynamics that allow proteins to access distinct functional states. Predicting these dynamic transitions, central to many biological processes, remains challenging due to the scarcity of high-resolution experimental data, which limits the training of machine-learning models for dynamic and energetic property prediction. Here, we present AlloPool, a graph neural network (GNN)-based framework that interprets molecular dynamics simulations by iteratively pruning residue–residue interactions to uncover minimal, time-resolved interaction networks that govern protein conformational dynamics and structural responses to chemical or mechanical perturbations, collectively known as allostery. By integrating temporal attention with graph aggregation, AlloPool learns evolving interaction graphs from equilibrium and non-equilibrium molecular dynamics simulations, enabling accurate reconstruction of dynamic trajectories and the interaction networks that drive conformational transitions. Validated across diverse dynamic protein systems, including binding domains, mechanosensors, signaling receptors, and enzymes, AlloPool maps allosteric communication pathways, predicts the effects of ligand binding, mechanical forces, and mutations, discovers transient dynamic states and outperforms existing machine-learning approaches in dynamic trajectory reconstruction. This advance provides a general framework for interpreting protein dynamics with broad implications for drug discovery, synthetic biology, and protein engineering.\n\nProtein function depends on dynamic conformational changes that remain difficult to predict despite advances in AI-based structure modeling. This study develops a graph neural network-based framework called AlloPool that accurately extracts allosteric communication networks from molecular dynamics trajectories.",
  "abstract_shown": true,
  "affiliations": [
    "Interfaculty Institute of Bioengineering, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland",
    "Ludwig Institute for Cancer Research Lausanne, Lausanne, Switzerland"
  ],
  "article_type": "Methods and Resources",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Matthieu Marfoglia"
    },
    {
      "affs": [
        1
      ],
      "name": "Miguel A. Pedraza-Joya"
    },
    {
      "name": "Lucas Guirardel"
    },
    {
      "name": "Aisima Chatzi Souleiman"
    },
    {
      "name": "Patrick Barth"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/df4jtdgnzywbc.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pbio.3004002",
  "fulltext_url": "https://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.3004002",
  "id": "df4jtdgnzywbc",
  "issns": [
    "1545-7885"
  ],
  "landing_url": "https://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.3004002",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1312|Protein Structure and Dynamics"
    ],
    [
      "plos",
      "/Biology and life sciences/Biochemistry/Biochemical simulations"
    ],
    [
      "plos",
      "/Biology and life sciences/Biochemistry/Enzymology/Enzyme chemistry/Enzyme regulation/Allosteric regulation"
    ],
    [
      "plos",
      "/Biology and life sciences/Biochemistry/Proteins/Allosteric regulation"
    ],
    [
      "plos",
      "/Biology and life sciences/Biochemistry/Proteins/Protein structure"
    ],
    [
      "plos",
      "/Biology and life sciences/Biochemistry/Proteins/Protein structure/Protein structure prediction"
    ],
    [
      "plos",
      "/Biology and life sciences/Biochemistry/Proteins/Transmembrane receptors/G protein coupled receptors"
    ],
    [
      "plos",
      "/Biology and life sciences/Cell biology/Signal transduction/Transmembrane receptors/G protein coupled receptors"
    ],
    [
      "plos",
      "/Biology and life sciences/Computational biology/Biochemical simulations"
    ],
    [
      "plos",
      "/Biology and life sciences/Molecular biology/Interaction networks"
    ],
    [
      "plos",
      "/Biology and life sciences/Molecular biology/Macromolecular structure analysis/Protein structure"
    ],
    [
      "plos",
      "/Biology and life sciences/Molecular biology/Macromolecular structure analysis/Protein structure/Protein structure prediction"
    ],
    [
      "plos",
      "/Medicine and health sciences/Pharmacology/Drug interactions"
    ],
    [
      "plos",
      "/Physical sciences/Chemistry/Computational chemistry/Molecular dynamics"
    ]
  ],
  "openalex": "W7213904499",
  "pdf_url": "https://journals.plos.org/plosbiology/article/file?id=10.1371/journal.pbio.3004002&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-21",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/df4jtdgnzywbc.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:43Z",
      "native_id": "10.1371/journal.pbio.3004002",
      "source": "plos",
      "url": "https://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.3004002"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "plos:molecular biology",
      "subfield": "molecular-biology"
    }
  ],
  "title": "AlloPool is a deep learning framework that infers protein allostery from molecular dynamics simulations",
  "title_text": "AlloPool is a deep learning framework that infers protein allostery from molecular dynamics simulations",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:43Z",
  "url": "https://research.draconitic.com/paper/df4jtdgnzywbc",
  "venue": "PLOS Biology",
  "versions": []
}