{
  "abstract": "Graph neural networks are widely used for drug--target affinity (DTA) prediction, and discrete Ricci curvature has recently been used to characterize molecular graph geometry. Existing curvature-aware DTA approaches mainly use static curvature on the drug graph while representing proteins primarily with sequence-derived features. This leaves pair-adaptive use of graph geometry underexplored, which may limit adaptation to unseen entities in cold-start settings relevant to practical screening. We present CurvFlow-DTA, which replaces a single static curvature representation with weighted Forman curvature flow on both molecular and protein residue--residue contact graphs. A label-independent flow trajectory is precomputed for each entity, and a pair-conditioned selector determines the horizons read by a dual-branch Flow-GINE. A frozen ESM-2 supplies residue-level representations and contact scores used to construct the protein graph. Inference requires only SMILES strings and protein sequences, without a bound complex structure. On Davis and KIBA, CurvFlow-DTA improves on the protocol-matched Ricci-GraphDTA baseline in every warm and cold-start setting. Warm-split mean squared error (MSE) decreases by $19.9\\%$ on Davis and $18.9\\%$ on KIBA. Across the six cold-start comparisons, MSE decreases by $14.3$--$27.4\\%$, with higher concordance index (CI) throughout. Within our compiled set of literature baselines, CurvFlow-DTA achieves the lowest MSE on both warm benchmarks and across four out of six cold-start evaluation settings.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.22862",
  "author_total": 4,
  "authors": [
    {
      "name": "Jicheng Ma"
    },
    {
      "name": "Yunyan Yang"
    },
    {
      "name": "Juan Zhao"
    },
    {
      "name": "Liang Zhao"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/6ymy3txq4ehj4.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.22862",
  "fulltext_url": null,
  "id": "6ymy3txq4ehj4",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.22862",
  "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",
      "math.DG"
    ],
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7214028119",
  "pdf_url": "https://arxiv.org/pdf/2609.22862",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-19",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/6ymy3txq4ehj4.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:27Z",
      "native_id": "2609.22862",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.22862"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:math.DG",
      "subfield": "geometry-topology"
    }
  ],
  "title": "CurvFlow-DTA: dual-graph discrete Ricci curvature flow for drug--target affinity prediction",
  "title_text": "CurvFlow-DTA: dual-graph discrete Ricci curvature flow for drug--target affinity prediction",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:27Z",
  "url": "https://research.draconitic.com/paper/6ymy3txq4ehj4",
  "venue": "arXiv",
  "versions": []
}