{
  "abstract": "RNA-binding small molecules represent a validated therapeutic modality, yet pinpointing their exact RNA binding sites remains critical for mechanistic understanding and drug optimization. Experimental methods, while precise, are costly and low-throughput, necessitating robust computational alternatives. Approaches based on static feature concatenation may overlook input-dependent relationships between RNA residues and ligand functional groups. Here we present LigRNA, a graph neural network framework that predicts RNA-ligand binding sites through joint cross-modal encoding of both molecules. LigRNA integrates structure-guided language model embeddings with physicochemical features-solvent-accessible surface area and secondary structure types, to construct comprehensive RNA representations. Ligands are encoded as attributed molecular graphs via graph attention networks, preserving atom-level chemical topology rather than compressing molecules into fixed fingerprints. A cross-attention mechanism then enables dynamic, ligand-dependent modulation of RNA nucleotide attention, capturing context-specific interaction patterns. Benchmarked on TE9 and TE18 datasets, LigRNA achieves F1 scores of 0.73 and 0.58, improving on GATRsite by 7.4% and 18.4%, respectively. Ablation studies identify the RNA residual encoder as the most consistent contributor across the two benchmarks. The source code is freely available at https://github.com/WillowWang0216/LigRNA.",
  "abstract_shown": true,
  "affiliations": [
    "University of Science and Technology of China Suzhou Institute for Advanced Research"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 10,
  "authors": [
    {
      "name": "X. Wang"
    },
    {
      "name": "H. Zhu"
    },
    {
      "name": "H. Li"
    },
    {
      "name": "A. Chang"
    },
    {
      "name": "F. Zhang"
    },
    {
      "name": "H. Chen"
    },
    {
      "name": "C. Wang"
    },
    {
      "name": "K. Chen"
    },
    {
      "name": "S. K. Zhou"
    },
    {
      "affs": [
        0
      ],
      "name": "P. Xiong"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/64wjtengaj32z.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.15.759315",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759315v1.full",
  "id": "64wjtengaj32z",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759315v1",
  "language": null,
  "licence": "CC-BY-NC",
  "licence_label": "CC BY-NC",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7222895313",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759315v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/64wjtengaj32z.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:21Z",
      "native_id": "10.64898/2026.10.15.759315",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.15.759315v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "LigRNA: High-accuracy prediction of RNA-ligand binding sites via dynamic chemical complementarity and language model encoding",
  "title_text": "LigRNA: High-accuracy prediction of RNA-ligand binding sites via dynamic chemical complementarity and language model encoding",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:21Z",
  "url": "https://research.draconitic.com/paper/64wjtengaj32z",
  "venue": "bioRxiv",
  "versions": []
}