{
  "abstract": "Sequence-only predictors can score RNAs without experimental structures, but continuously updated training pools can reabsorb benchmark chains. Test overlap and within-training redundancy are often handled together, although they affect evaluation differently. DUET combines a relational graph tower with two convolutional sequence towers built on frozen RNA language models. We removed 98 of 388 training and validation records reaching 80% identity to canonical test chains, retained 110 sequence-identical records, and isolated 115 homology components across folds. Across 10 paired seeds, DUET reached 0.240 +/- 0.013 MCC versus 0.192 +/- 0.031 for CoBRA-M3 on the same data (Delta = +0.047; Holm p = 0.0073), with parallel gains in AUC and AUPRC. DUET and GRASSP were statistically indistinguishable on external sets (0.246 versus 0.243 MCC). Real three-dimensional topology improved MCC by +0.037 over shuffled edges and by +0.042 over predicted secondary structure. Increasing the training pool from 80 to 290 records raised DUET by +0.135 MCC. Benchmark evaluation therefore requires separate controls for test overlap and within-training redundancy.",
  "abstract_shown": true,
  "affiliations": [
    "Jingdezhen Ceramic University"
  ],
  "article_type": "New results",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "name": "K. Xiong"
    },
    {
      "affs": [
        0
      ],
      "name": "J. Jia"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cjrg5nysxbtyb.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.28.762699",
  "fulltext_url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762699v1.full",
  "id": "cjrg5nysxbtyb",
  "issns": [],
  "landing_url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762699v1",
  "language": null,
  "licence": "CC-BY-NC-ND",
  "licence_label": "CC BY-NC-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "biorxiv",
      "bioinformatics"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762699v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-28",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cjrg5nysxbtyb.ris",
  "sources": [
    {
      "first_seen": "2026-10-31T12:21:07Z",
      "native_id": "10.64898/2026.10.28.762699",
      "source": "biorxiv",
      "url": "https://www.biorxiv.org/content/10.64898/2026.10.28.762699v2"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "biorxiv:bioinformatics",
      "subfield": "bioinformatics"
    }
  ],
  "title": "DUET: sequence-only prediction of RNA-small molecule binding sites",
  "title_text": "DUET: sequence-only prediction of RNA-small molecule binding sites",
  "type": "preprint",
  "updated_at": "2026-11-04T00:21:15Z",
  "url": "https://research.draconitic.com/paper/cjrg5nysxbtyb",
  "venue": "bioRxiv",
  "versions": []
}