{
  "abstract": "Ribonucleic acid (RNA) functions through conformational changes that are not fully captured by static structures. However, large-scale standardized RNA dynamics data remain limited, and existing approaches typically treat trajectory generation and dynamics understanding as separate objectives. Here, we introduce RNADynBench, a standardized RNA molecular dynamics (MD) benchmark with 2585 quality-controlled 100-ns all-atom trajectories and leakage-controlled splits. Building on RNADynBench, we develop RNADynNet, a unified model for RNA dynamics learning that uses a shared backbone for both trajectory generation and dynamics fingerprint extraction from a single conformer. It combines coordinate denoising, single-frame-to-trajectory alignment, and physical grounding to connect all-atom trajectory generation with dynamics representation learning. Physical grounding improves both generated dynamics and the physical information recoverable from these fingerprints. Across both test sets, including the high-flexibility challenge set, the generated trajectories achieve RMSF correlations of 0.875 and 0.766, while single-conformer predictions show comparable agreement with MD-derived dynamics. RNADynBench and RNADynNet together establish a benchmark and unified modeling framework for generating and understanding RNA dynamics.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.03712",
  "author_total": 5,
  "authors": [
    {
      "name": "Yiming Huang"
    },
    {
      "name": "Lennart Bastian"
    },
    {
      "name": "Hanqun Cao"
    },
    {
      "name": "Luis Vollmers"
    },
    {
      "name": "Tolga Birdal"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/70xevts8k3g4z.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.03712",
  "fulltext_url": null,
  "id": "70xevts8k3g4z",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.03712",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.bio-ph"
    ],
    [
      "arxiv",
      "q-bio.BM"
    ],
    [
      "openalex",
      "1312|RNA and protein synthesis mechanisms"
    ]
  ],
  "openalex": "W7220367135",
  "pdf_url": "https://arxiv.org/pdf/2610.03712",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/70xevts8k3g4z.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:26:45Z",
      "native_id": "2610.03712",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.03712"
    }
  ],
  "subjects": [
    {
      "field": "biochemistry",
      "origin": "arxiv:q-bio.BM",
      "subfield": "biophysics"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.bio-ph",
      "subfield": "biological-medical"
    }
  ],
  "title": "RNADyn: A Benchmark for Generating and Understanding RNA Dynamics",
  "title_text": "RNADyn: A Benchmark for Generating and Understanding RNA Dynamics",
  "type": "preprint",
  "updated_at": "2026-10-30T12:26:50Z",
  "url": "https://research.draconitic.com/paper/70xevts8k3g4z",
  "venue": "arXiv",
  "versions": []
}