归因方法揭示了基于指纹的虚拟筛选中的缺陷
Attribution Methods Reveal Flaws in Fingerprint-Based Virtual Screening
摘要：
基于指纹的蛋白质-配体结合模型在基准数据集上取得了巨大的成功;然而，这些模型可能无法学习正确的结合规则。为了评估这一问题，我们使用具有已知约束规则的计算机数据集来开发一个用于评估模型属性的通用框架。该框架识别模型认为达到特定分数所必需的片段，回避了模型可区分的需要。我们的研究结果证实，高性能模型可能无法学习正确的绑定规则，并提出了可以纠正这种情况的具体步骤。我们发现，添加片段匹配的非活性分子（诱饵）的数据减少归因假阴性，而归因假阳性主要来自分子数据的背景相关结构。对这些背景相关性进行归一化有助于揭示真正的绑定逻辑。我们的工作强调了信任高性能模型的归因的危险，并建议更仔细地检查指纹相关结构和更好的诱饵选择可能有助于减少错误归因。
英文摘要：
Fingerprint-based models for protein-ligand binding have demonstrated outstanding success on benchmark datasets; however, these models may not learn the correct binding rules. To assess this concern, we use in silico datasets with known binding rules to develop a general framework for evaluating model attribution. This framework identifies fragments that a model considers necessary to achieve a particular score, sidestepping the need for a model to be differentiable. Our results confirm that high-performing models may not learn the correct binding rule, and suggest concrete steps that can remedy this situation. We show that adding fragment-matched inactive molecules (decoys) to the data reduces attribution false negatives, while attribution false positives largely arise from the background correlation structure of molecular data. Normalizing for these background correlations helps to reveal the true binding logic. Our work highlights the danger of trusting attributions from high-performing models and suggests that a closer examination of fingerprint correlation structure and better decoy selection may help reduce misattributions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
