发表机构
School of Mathematics, Renmin University of China（中国人民大学数学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CurvFlow-DTA提出双图加权Forman曲率流与成对条件选择器，在药物和蛋白质图上自适应利用几何，提升冷启动DTA预测性能，在Davis和KIBA上显著降低MSE。
AI 中文摘要
图神经网络被广泛用于药物-靶点亲和力（DTA）预测，离散里奇曲率最近被用于表征分子图几何。现有的曲率感知DTA方法主要使用药物图上的静态曲率，同时主要用序列衍生特征表示蛋白质。这导致图几何的成对自适应使用未被充分探索，可能限制在冷启动设置中对未见实体的适应，而冷启动设置与实际筛选相关。我们提出CurvFlow-DTA，用加权Forman曲率流替换单一的静态曲率表示，应用于分子图和蛋白质残基-残基接触图。为每个实体预先计算标签无关的流轨迹，成对条件选择器决定双分支Flow-GINE读取的视界。冻结的ESM-2提供残基级表示和用于构建蛋白质图的接触分数。推理仅需SMILES字符串和蛋白质序列，无需结合复合物结构。在Davis和KIBA上，CurvFlow-DTA在每种热启动和冷启动设置中均优于协议匹配的Ricci-GraphDTA基线。热启动均方误差（MSE）在Davis上降低19.9%，在KIBA上降低18.9%。在六种冷启动比较中，MSE降低14.3%至27.4%，且一致性指数（CI）全程更高。在我们整理的文献基线集合中，CurvFlow-DTA在两个热启动基准和六种冷启动评估设置中的四种上取得最低MSE。
英文摘要
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.
