超越随机划分：在化学和生物学驱动的分布偏移下评估药物-靶点亲和力模型
Beyond Random Splits: Evaluating Drug-Target Affinity Models Under Chemically and Biologically Motivated Distribution Shifts Copy
- Georgia Institute of Technology（佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究通过化学和生物学分布偏移评估药物-靶点亲和力模型，发现架构选择依赖于外推形式，而非仅平均误差，建议基准匹配部署场景。
AI中文摘要：
药物-靶点亲和力（DTA）预测被广泛用于在昂贵的实验筛选之前对候选化合物进行优先级排序。DTA模型通常仅在单一数据划分下进行比较，尽管部署时可能需要外推至新的化学系列、新的蛋白质靶点或两者兼有。我们探究评估所用的分布偏移是否会改变哪种架构表现最佳。我们从ChEMBL和BindingDB数据集中整理了718,800个独特的药物-蛋白质对。我们将Morgan指纹+蛋白质CNN基线模型与12种受控架构进行比较，这些架构结合了四种药物表示和三种ESM-2相互作用模式。平均验证RMSE从脚手架和指纹聚类分布外（OOD）下的0.950和0.945增加到蛋白质聚类和双重OOD下的1.299和1.321。模型排名在两种化学偏移下相似（tau=0.79），但与脚手架OOD的一致性在蛋白质OOD下下降（tau=0.39），并在双重OOD下发生逆转（tau=-0.55）。留出评估、重复种子、分组感知自助法分析以及大小匹配对照均支持相同结论：架构选择取决于外推形式，而不仅仅取决于平均误差或训练集大小。因此，DTA基准应匹配部署时预期的化学和靶点偏移。
英文摘要：
Drug-target affinity (DTA) prediction is widely used to prioritize candidate compounds before costly experimental screening. DTA models are often compared under a single data split, even though deployment may require extrapolation to new chemical series, new protein targets, or both. We ask whether the distribution shift used for evaluation changes which architecture appears best. We curate 718,800 unique drug-protein pairs from the ChEMBL and BindingDB datasets. We compare a Morgan-fingerprint + protein-CNN baseline with 12 controlled architectures that combine four drug representations with three ESM-2 interaction modes. Mean validation RMSE increases from 0.950 and 0.945 under scaffold and fingerprint-cluster OOD to 1.299 and 1.321 under protein-cluster and dual OOD. Model rankings are similar across the two chemical shifts (tau = 0.79), but agreement with scaffold OOD falls under protein OOD (tau = 0.39) and reverses under dual OOD (tau = -0.55). Held-out evaluation, repeated seeds, group-aware bootstrap analysis, and a size-matched control support the same conclusion: architecture selection depends on the form of extrapolation, not only on average error or training-set size. DTA benchmarks should therefore match the chemical and target shifts expected at deployment.
