AN-IHP: Incompatible Herb Pairs Prediction by Attention Networks
- 3 January 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Biology and Bioinformatics
- Vol. 22 (1) , 124-135
Abstract
The adverse drug-drug interaction (DDI) is a crucial safety concern in drug development. The intricate combinations of traditional Chinese medicine (TCM), while powerful in their therapeutic potentials, also harbor potential risks when incompatibly paired. Some methods have been proposed to infer incompatible herb pairs (IHPs), but most of them focus on revealing and analyzing the adverse reactions of known IHPs, despite that there are still a number of undiscovered IHPs at intervals. This paper introduces a deep attention network (AN-IHP) that effectively exploits diverse types of data for IHPs prediction. AN-IHP designs an attention-aggregation block to learn the ingredient-level features towards herbs and use similarity profiles to represent the efficacy and property. Then it defines commonality and specificity constraints to enhance the representations from different types of features. After that, it makes dynamic representation fusion across herb pairs using a gated attention unit (GAU) and leverages a deep neural network (DNN) to predict IHPs. The experimental results on the collected IHPTCM dataset demonstrate that AN-IHP outperforms competitive methods. AN-IHP provides interpretability for analyzing IHPs at the ingredient level, proves beneficial for wet-lab experiments. It is also capable of predicting DDIs.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFC3502101)
- National Natural Science Foundation of China (62031003, 62072380, 62272276)
- Taishan scholars project special funding
- Xiaomi Young Talents Program
This publication has 37 references indexed in Scilit:
- Semen raphani weakened the action of ginseng under chronic fatigue conditionJournal of Ethnopharmacology, 2022
- MDF-SA-DDI: predicting drug–drug interaction events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanismBriefings in Bioinformatics, 2021
- Network-based modeling of herb combinations in traditional Chinese medicineBriefings in Bioinformatics, 2021
- Physiologically Based Pharmacokinetic Models of Probenecid and Furosemide to Predict Transporter Mediated Drug-Drug InteractionsPharmaceutical Research, 2020
- MTMA: Multi-task multi-attribute learning for the prediction of adverse drug–drug interactionKnowledge-Based Systems, 2020
- Investigation of the mechanism of incompatible herb pair gansui-gancao-induced hepatotoxicity and nephrotoxicity and the attenuated effect of gansuibanxia decoction by UHPLC-FT-ICR-MS-based plasma metabonomic analysisJournal of Pharmaceutical and Biomedical Analysis, 2019
- IHPreten: A novel supervised learning framework with attribute regularization for prediction of incompatible herb pair in traditional Chinese medicineNeurocomputing, 2019
- Quantifying Drug Combination Synergy along Potency and Efficacy AxesCell Systems, 2019
- Mechanism of Incompatible Herb Pairs, Panax ginseng and Veratrum nigrum L.: Material Basis and Metabolic Profiles of Ginsenosides in Rat Intestinal BacteriaChinese Journal of Chemistry, 2015
- Extended-Connectivity FingerprintsJournal of Chemical Information and Modeling, 2010