可解释性
药品
下部结构
计算机科学
特征(语言学)
药物与药物的相互作用
任务(项目管理)
机器学习
人工智能
数据挖掘
药理学
医学
工程类
系统工程
哲学
结构工程
语言学
作者
Qing Zhou,Yang Zhang,Siyuan Wang,Dayu Wu
标识
DOI:10.1016/j.jmgm.2023.108557
摘要
The properties of drugs may undergo changes when multiple drugs are co-administered to treat co-existing or complex diseases, potentially leading to unforeseen drug–drug interactions (DDIs). Therefore, predicting potential drug–drug interactions has been an important task in pharmaceutical research. However, the following challenges remain: (1) existing methods do not work very well in cold-start scenarios, and (2) the interpretability of existing methods is not satisfactory. To address these challenges, we proposed a multi-channel feature fusion method based on local substructure features of drugs and their complements (LSFC). The local substructure features are extracted from each drug, interacted with those of another drug, and then integrated with the global features of two drugs for DDI prediction. We evaluated LSFC on two real-world DDI datasets in worm-start and cold-start scenarios. Comprehensive experiments demonstrate that LSFC consistently improved DDI prediction performance compared with the start-of-the-art methods. Moreover, visual inspection results showed that LSFC can detect crucial substructures of drugs for DDIs, providing interpretable DDI prediction. The source codes and data are available at https://github.com/Zhang-Yang-ops/LSFC.
科研通智能强力驱动
Strongly Powered by AbleSci AI