Using attribution to decode binding mechanism in neural network models for chemistry
Using attribution to decode binding mechanism in neural network models for chemistry
复制标题
DOI：
10.1073/pnas.1820657116
复制
发表时间：
2019-06-11
影响因子：
11.1
通讯作者：
Colwell, Lucy J.
中科院分区：
文献类型：
--
作者：
McCloskey, Kevin;Taly, Ankur;Colwell, Lucy J.
深度神经网络在对分子是否与特定蛋白质靶标结合进行分类方面已经达到了最先进的准确性。如果这些模型能够揭示因果性地参与结合的药效团片段，那么就会出现一个关键的突破。从网络中提取结合的化学细节可以使有关药物作用机制的科学发现成为可能。然而，这样做需要将光线照射到经过训练的神经网络模型的黑匣子中，事实证明这项任务在许多领域都很困难。在这里，我们展示了如何使用最近描述的归因方法来询问深度神经网络模型学习的绑定机制。我们首先使用精心构建的合成数据集，其中负责“结合”的分子特征是完全已知的。我们发现，在保留的测试数据集上实现完美准确性的网络仍然会学习虚假相关性，并且我们能够利用这种非鲁棒性来构建欺骗模型的对抗性示例。这使得这些模型无法可靠地准确揭示有关蛋白质-配体结合机制的信息。根据我们的发现，我们提出了一项测试来检查是否可以学习假设的机制。如果测试失败，则表明必须简化或正则化模型和/或训练数据集需要增强。
Deep neural networks have achieved state-of-the-art accuracy at classifying molecules with respect to whether they bind to specific protein targets. A key breakthrough would occur if these models could reveal the fragment pharmacophores that are causally involved in binding. Extracting chemical details of binding from the networks could enable scientific discoveries about the mechanisms of drug actions. However, doing so requires shining light into the black box that is the trained neural network model, a task that has proved difficult across many domains. Here we show how the binding mechanism learned by deep neural network models can be interrogated, using a recently described attribution method. We first work with carefully constructed synthetic datasets, in which the molecular features responsible for "binding" are fully known. We find that networks that achieve perfect accuracy on held-out test datasets still learn spurious correlations, and we are able to exploit this nonrobustness to construct adversarial examples that fool the model. This makes these models unreliable for accurately revealing information about the mechanisms of protein-ligand binding. In light of our findings, we prescribe a test that checks whether a hypothesized mechanism can be learned. If the test fails, it indicates that the model must be simplified or regularized and/or that the training dataset requires augmentation.