Wei Lin, Fang Yihe, Chen Peng, Wei Zigong
State Key Laboratory of Biocatalysis and Enzyme Engineering, School of Life Sciences, Hubei University, Wuhan, Hubei, People's Republic of China.
Hubei Province Key Laboratory of Biotechnology of Chinese Traditional Medicine, National and Local Joint Engineering Research Center of High- throughput Drug Screening Technology, School of life sciences, Hubei University, Wuhan, Hubei, People's Republic of China.
J Comput Aided Mol Des. 2025 Aug 19;39(1):68. doi: 10.1007/s10822-025-00649-6.
High failure rates in drug development are predominantly driven by suboptimal ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties, with human oral bioavailability (HOB) serving as a critical determinant of therapeutic efficacy and safety. Traditional HOB assessment methods, reliant on animal models and clinical trials, face inherent limitations in cost, scalability, and reproducibility. To address these challenges, this study proposes a deep learning framework integrating the directed message-passing neural network (D-MPNN) from the Chemprop tool with RDKit-derived molecular descriptors, enhancing predictive accuracy through hybrid representations of atomic/bond-level graph features and global physicochemical properties. Bayesian optimization automated hyperparameter tuning, while ensemble learning (20 models) ensured robustness for model development. The optimized model achieved an AUC of 0.8299 and accuracy of 77.65% on internal validation, outperforming existing tools with 75% accuracy on external FDA-approved drugs. Interpretability analysis identified critical substructures correlated with high HOB, providing actionable insights for rational drug design. This work establishes a novel method for high-throughput screening of candidates with favorable bioavailability, highlighting the potential of deep learning to decode complex structure-property relationships in pharmaceutical optimization.
药物研发中的高失败率主要由欠佳的ADMET（吸收、分布、代谢、排泄和毒性）特性驱动，其中人体口服生物利用度（HOB）是治疗效果和安全性的关键决定因素。传统的HOB评估方法依赖动物模型和临床试验，在成本、可扩展性和可重复性方面存在固有局限性。为应对这些挑战，本研究提出了一个深度学习框架，将Chemprop工具中的定向消息传递神经网络（D-MPNN）与源自RDKit的分子描述符相结合，通过原子/键级图特征和全局物理化学性质的混合表示提高预测准确性。贝叶斯优化自动进行超参数调整，而集成学习（20个模型）确保了模型开发的稳健性。优化后的模型在内部验证中AUC达到0.8299，准确率为77.65%，优于现有工具，后者对FDA批准的外部药物的准确率为75%。可解释性分析确定了与高HOB相关的关键子结构，为合理的药物设计提供了可操作的见解。这项工作建立了一种高通量筛选具有良好生物利用度候选物的新方法，突出了深度学习在药物优化中解码复杂结构-性质关系的潜力。
