可解释性
人工智能
深度学习
计算机科学
条件随机场
数量结构-活动关系
机器学习
机制(生物学)
物理
量子力学
作者
Cheng Cao,Hao Wang,Junyi Yang,Qiang Chen,Yuxin Guo,Jian-Zhong Chen
标识
DOI:10.1016/j.compbiomed.2024.108037
摘要
The development of deep learning models for predicting toxicological endpoints has shown great promise, but one of the challenges in the field is the accuracy and interpretability of these models. The bioactive conformation of a compound plays a critical role for it to bind in the target. It is a big issue to figure out the bioactive conformation in deep learning without the co-crystal structure or highly precise molecular simulations. In this study, we developed a deep learning framework of Multi-Conformation Point Network (MCPNET) to construct classification and regression models, respectively, based on electrostatic potential distributions on vdW surfaces around multiple conformations of the compound using a dataset of compounds with developmental toxicity in zebrafish embryo. MCPNET applied 3D multi-conformational surface point cloud to extract the molecular features for model training, which may be critical for capturing the structural diversity of compounds. The models achieved an accuracy of 85 % on the classification task and R2 of 0.66 on the regression task, outperforming traditional machine learning models and other deep learning models. The key feature of our model is its interpretability with the component visualization to identify the factors contributing to the prediction and to understand the compound action mechanism. MCPNET may predict the conformation quietly close to the bioactive conformation of a compound by attention-based multi-conformation pooling mechanism. Our results demonstrated the potential of deep learning based on 3D molecular representations in accurately predicting developmental toxicity. The source code is publicly available at https://github.com/Superlit-CC/MCPNET.
科研通智能强力驱动
Strongly Powered by AbleSci AI