Mathew Ezek, Emmitte Kyle A, Liu Jin
Department of Microbiology and Immunology, The University of North Texas Health Science Center, 3500 Camp Bowie Blvd, Fort Worth, Texas 76107, United States.
Department of Pharmaceutical Sciences, University of North Texas System College of Pharmacy, The University of North Texas Health Science Center, 3500 Camp Bowie Blvd, Fort Worth, Texas 76107, United States.
ACS Omega. 2025 Jul 21;10(30):32968-32986. doi: 10.1021/acsomega.5c02173. eCollection 2025 Aug 5.
Designing selective and potent ligands for target receptors remains a significant challenge in drug discovery. Computational approaches, particularly advancements in machine learning (ML), offer transformative potential in addressing this challenge. In this study, our goal was to develop a composite ML model capable of predicting ligand selectivity and potency with high accuracy while also providing interpretable insights to guide ligand optimization. To achieve this goal, we first compiled a data set of 757 ligands, including metabotropic glutamate receptor subtype 2 (mGlu2) negative allosteric modulators (NAMs), metabotropic glutamate receptor subtype 3 (mGlu3) NAMs, and nonselective dual mGlu2/3 NAMs from patent filings. In three phases, we developed an ML model with Interpretable Graph Attention (I-GAT) networks for drug optimization. In phase 1, we created a composite model that can accurately predict selectivity and potency metrics by integrating graph architecture with transfer learning methodologies. Our model demonstrated over 97% accuracy in predicting ligand NAM selectivity and upward of 78% accuracy in potency prediction. Phase 2 used attention mechanisms to enhance model interpretability, effectively illuminating the "black box" of ML decision-making. Finally, in phase 3, we utilized attention gradients to intelligently modify known ligands, leading to the design of a novel ligand with predicted superior properties compared to the original. Our approach demonstrates the dual benefits of predictive accuracy and atom-level interpretability, offering a powerful framework for ligand design. When applied to external data, our model matched and, in some cases, exceeded the performance of current state-of-the-art chemistry-focused ML models across multiple data sets. Ultimately, our model has the potential to be adapted to other receptors and molecular properties, paving the way for a more efficient and targeted drug discovery process.
在药物研发中，为目标受体设计选择性强且有效的配体仍然是一项重大挑战。计算方法，尤其是机器学习（ML）的进展，为应对这一挑战提供了变革性的潜力。在本研究中，我们的目标是开发一种复合ML模型，该模型能够高精度地预测配体的选择性和效力，同时还能提供可解释的见解以指导配体优化。为实现这一目标，我们首先汇编了一个包含757种配体的数据集，这些配体包括来自专利申请的代谢型谷氨酸受体2型（mGlu2）负变构调节剂（NAMs）、代谢型谷氨酸受体3型（mGlu3）NAMs以及非选择性双mGlu2/3 NAMs。我们分三个阶段开发了一种用于药物优化的具有可解释图注意力（I-GAT）网络的ML模型。在第一阶段，我们创建了一个复合模型，通过将图架构与迁移学习方法相结合，可以准确预测选择性和效力指标。我们的模型在预测配体NAM选择性方面的准确率超过97%，在效力预测方面的准确率超过78%。第二阶段使用注意力机制来增强模型的可解释性，有效地揭示了ML决策的“黑箱”。最后，在第三阶段，我们利用注意力梯度智能地修饰已知配体，从而设计出一种预测性能优于原始配体的新型配体。我们的方法展示了预测准确性和原子级可解释性的双重优势，为配体设计提供了一个强大的框架。当应用于外部数据时，我们的模型在多个数据集上与当前最先进的以化学为重点的ML模型的性能相匹配，在某些情况下还超过了它们。最终，我们的模型有潜力适用于其他受体和分子特性，为更高效、有针对性的药物发现过程铺平道路。
