文献类型：期刊文献

英文题名：Discovery of Bioactive Constituents for Colitis From Traditional Chinese Medicine Prescription via Deep Neural Network

作者：Ren, Zhixiang[1];Ren, Yiming[1];Liu, Pengfei[2];Shu, Qi[3,4];Ma, Huijuan[3,5,6];Xu, Huan[3,5,6]

机构：[1]Peng Cheng Lab, Shenzhen 518055, Peoples R China;[2]Sun Yat Sen Univ, Sch Comp Sci & Engn, Guangzhou 528406, Peoples R China;[3]East China Univ Sci & Technol, Shanghai Frontiers Sci Ctr Optogenet Tech Cell Met, Shanghai 200237, Peoples R China;[4]East China Univ Sci & Technol, Sch Pharm, Shanghai Key Lab New Drug Design, Shanghai 200237, Peoples R China;[5]Anhui Univ Sci & Technol, Joint Res Ctr Occupat Med & Hlth IHM, Hefei 231131, Peoples R China;[6]Anhui Univ Sci & Technol, Sch Publ Hlth, Hefei 231131, Peoples R China

年份：2025

卷号：22

期号：2

起止页码：946

外文期刊名：IEEE TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS

收录：;EI(收录号：20253919245897);WOS:【SCI-EXPANDED(收录号:WOS:001482999800001)】；

基金：The authors appreciate Yue Zhou from Peng Cheng Laboratory for the technical advice and Zhaoqian Ding, Ying Xie, Tingqian Wang, Linyi Li from East China University of Science and Technology for the collection of TCM prescriptions from books. The research was supported by the Peng Cheng Laboratory and Peng Cheng Cloud-Brain.

语种：英文

外文关键词：Training; Pharmacology; Compounds; Diseases; Medical diagnostic imaging; Data mining; Computational biology; Bioinformatics; Artificial neural networks; Proteins; Deep neural network; bioactive constituents; colitis; anti-inflammation; network pharmacology; traditional Chinese medicine prescriptions

摘要：Colitis is a commonly encountered inflammatory disease in colon tissue, which can be triggered by various causes. Although a few ingredients in traditional Chinese medicine (TCM) have been identified as effective for the treatment of colitis, it remains a great challenge to discover the potential therapeutic bioactive constituents and their modes of action among thousands of ingredients in TCM prescriptions. To address this issue, we propose a pipeline that combines deep neural network (DNN) with network pharmacology to discover bioactive constituents. By integrating the herbal information network of 9,845 nodes and 161,950 edges, which includes detailed information on bioactive molecules and protein targets, with a prescription list expanded through a novel data augmentation strategy, the DNN can recommend diverse herbal combinations. Network pharmacology study revealed that the 10 most frequent constituents in recommended prescriptions were associated with multiple inflammatory signaling pathways. To verify the bioactive constituents in the recommended prescriptions, 5 selected constituents were administrated to BALB/c mice with colitis. Suppressive effects of disease progression and pro-inflammatory factors comparable to sulfasalazin were observed with these compounds, revealing the effectiveness of our artificial intelligence strategy in discovering bioactive constituents from TCM prescriptions.