您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

CardiOT: Towards Interpretable Drug Cardiotoxicity Prediction Using Optimal Transport and Kolmogorov--Arnold Networks

文献类型： 外文期刊

作者： Zhang, Xinyu 1 ; Wang, Hao 2 ; Du, Zhenya 3 ; Zhuo, Linlin 1 ; Fu, Xiangzheng 4 ; Cao, Dongsheng 5 ; Xie, Boqia 6 ; Li, Keqin 7 ;

作者机构： 1.Wenzhou Univ Technol, Sch Data Sci & Artificial Intelligence, Wenzhou 325027, Peoples R China

2.Chinese Acad Agr Sci, Inst Crop Sci, Beijing 100081, Peoples R China

3.Guangzhou Xinhua Univ, Guangzhou 510520, Peoples R China

4.Hunan Univ, Coll Informat Sci & Engn, Changsha 410082, Peoples R China

5.Cent South Univ, Xiangya Sch Pharmaceut Sci, Changsha 410003, Peoples R China

6.Capital Med Univ, Beijing Chaoyang Hosp, Cardiovasc Imaging Ctr, Dept Cardiol, Beijing 100020, Peoples R China

7.State Univ New York, Dept Comp Sci, New York, NY 12561 USA

关键词： Drugs; Compounds; Predictive models; Ions; Chemicals; Safety; Data models; Accuracy; Toxicology; Prediction algorithms; Cardiac drug safety; compound cardiotoxicity (CCT); inhibitory effects of drugs; Kolmogorov--Arnold networks (KANs); optimal transport (OT); uneven distribution and data scarcity

期刊名称：IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS （ 影响因子：6.8； 五年影响因子：7.0 ）

ISSN： 2168-2194

年卷期： 2025 年 29 卷 3 期

页码：

收录情况： SCI

摘要： Investigating the inhibitory effects of compounds on cardiac ion channels is essential for assessing cardiac drug safety. Consequently, researchers have developed computational models to evaluate combined cardiotoxicity (CCT) on cardiac ion channels. However, limitations in experimental data often cause issues like uneven data distribution and scarcity. Additionally, existing models primarily emphasize atomic information flow within graph neural networks (GNNs) while overlooking chemical bonds, leading to inadequate recognition of key structures. Therefore, this study integrates optimal transport (OT), structure remapping (SR), and Kolmogorov-Arnold networks (KANs) into a GNN-based CCT prediction model, CardiOT. First, the proposed CardiOT model employs OT pooling to optimize sample-feature joint distribution using expectation maximization, identifying "important" sample-feature pairs. Additionally, SR technology is used to emphasize the role of chemical bond information in message propagation. KAN technology is integrated to greatly enhance model interpretability. In summary, the model mitigates challenges related to uneven data distribution and scarcity. Multiple experiments on public datasets confirm the model's robust performance. We anticipate that this model will provide deeper insights into compound inhibition mechanisms on cardiac ion channels and reduce toxicity risks.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台