{
  "abstract": "RNA-targeted drug discovery requires both RNA-compound interaction prediction and nucleotide-level binding-site (BS) localization. These two tasks rely on different levels of interaction information: DTI prediction summarizes overall RNA-compound compatibility, whereas BS localization requires preserving nucleotide-level compound-associated signals. However, existing multitask models often use shared cross-modal representations for both tasks before task-specific prediction layers, which may limit their ability to preserve task-dependent interaction patterns. We therefore propose ReTIF (Relation-enhanced Task-specific Interaction Framework), which constructs separate cross-modal interaction representations for DTI prediction and BS localization before aggregation. ReTIF integrates multi-source RNA-compound representations from frozen RNA-FM, StructRFM, Mole-BERT, and MolFormer encoders, and builds separate interaction representations for DTI scoring and BS localization. The DTI branch captures global compatibility through aggregation, whereas the BS branch preserves nucleotide-compound resolution and enhances local evidence through relation-guided propagation with RNA structural and compound topological priors. An asymmetric DTI-derived compatibility signal provides global context to BS prediction while maintaining local evidence. Across five-fold evaluations under unseen pair, RNA, compound, and joint shifts with 13 baselines, ReTIF has the highest mean in 13 of 16 scenario-metric combinations, including BS AUPR in all four settings.",
  "abstract_shown": true,
  "affiliations": [
    "University of Science and Technology of China"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 9,
  "authors": [
    {
      "name": "A. Chang"
    },
    {
      "name": "H. Zhu"
    },
    {
      "name": "H. Chen"
    },
    {
      "name": "C. Wang"
    },
    {
      "name": "X. Wang"
    },
    {
      "name": "X. Zeng"
    },
    {
      "name": "Y. Ding"
    },
    {
      "name": "P. Xiong"
    },
    {
      "affs": [
        0
      ],
      "name": "S. K. Zhou"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/atjnhgjsm03jz.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.09.02.748859",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.09.02.748859v1.full",
  "id": "atjnhgjsm03jz",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.09.02.748859v1",
  "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": "W7211899057",
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.09.02.748859v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/atjnhgjsm03jz.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:47Z",
      "native_id": "10.64898/2026.09.02.748859",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.09.02.748859v1"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "ReTIF: Granularity-Aware Multitask Interaction Routing for RNA-Compound Interaction Prediction and Binding-Site Localization",
  "title_text": "ReTIF: Granularity-Aware Multitask Interaction Routing for RNA-Compound Interaction Prediction and Binding-Site Localization",
  "type": "preprint",
  "updated_at": "2026-10-30T12:19:47Z",
  "url": "https://research.draconitic.com/paper/atjnhgjsm03jz",
  "venue": "bioRxiv",
  "versions": []
}