{
  "abstract": "Proteins move and deform to ensure their biological functions. Despite significant progress in protein structure prediction, approximating conformational ensembles under physiological conditions remains a fundamental open problem. This paper presents a novel perspective on the problem by directly targeting continuous compact representations of protein motions inferred from sparse experimental observations. We develop a task-specific loss function enforcing data symmetries, including scaling and permutation operations. Our method PETIMOT (Protein sEquence and sTructure-based Inference of MOTions) leverages transfer learning from pre-trained protein language models through an SE(3)-equivariant graph neural network. When trained and evaluated on the Protein Data Bank, PETIMOT shows superior performance in time and accuracy, capturing protein dynamics, particularly large/slow conformational changes, compared with state-of-the-art diffusion and flow-matching approaches, as well as traditional physics-based models. Our code and protocols are available at https://github.com/PhyloSofS-Team/PETIMOT.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": null,
  "author_total": 4,
  "authors": [
    {
      "name": "Valentin Lombard"
    },
    {
      "name": "Julien Nguyen Van"
    },
    {
      "name": "Sergei Grudinin"
    },
    {
      "name": "Elodie Laine"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2b3k1pprmejjp.bib",
  "cited_by": 1,
  "doi": "10.1107/s2059798326006054",
  "fulltext_url": null,
  "id": "2b3k1pprmejjp",
  "issns": [
    "2059-7983",
    "2059-7983"
  ],
  "landing_url": "https://hal.sorbonne-universite.fr/hal-05334844v2",
  "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": [
    [
      "hal",
      "0.sdv"
    ],
    [
      "hal",
      "1.sdv.bibs"
    ],
    [
      "openalex",
      "1312|Protein Structure and Dynamics"
    ]
  ],
  "openalex": "W7169756361",
  "pdf_url": "https://hal.sorbonne-universite.fr/hal-05334844/document",
  "pmcid": null,
  "pmid": null,
  "published": "2026-07-20",
  "publisher": "International Union of Crystallography",
  "ris": "https://research.draconitic.com/paper/2b3k1pprmejjp.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:01Z",
      "native_id": "hal-05334844",
      "source": "hal",
      "url": "https://hal.sorbonne-universite.fr/hal-05334844v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "hal:1.sdv.bibs",
      "subfield": "bioinformatics"
    }
  ],
  "title": "Petimot: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks",
  "title_text": "Petimot: A Novel Framework for Inferring Protein Motions from Sparse Data Using SE(3)-Equivariant Graph Neural Networks",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:18:01Z",
  "url": "https://research.draconitic.com/paper/2b3k1pprmejjp",
  "venue": "Acta crystallographica Section D : Structural biology [1993-...]",
  "versions": []
}