Machine Learning-Based Prediction of Drug-Drug Interactions for Histamine Antagonist Using Hybrid Chemical Features
Luong Huu Dang,
Nguyen Tan Dung,
Ly Xuan Quang,
Le Quang Hung,
Ngoc Hoang Le,
Nhi Thao Ngoc Le,
Nguyen Thi Diem,
Nguyen Thi Thuy Nga,
Shih-Han Hung,
Nguyen Quoc Khanh Le
Affiliations
Luong Huu Dang
Department of Otolaryngology, Faculty of Medicine, University of Medicine and Pharmacy at Ho Chi Minh City, Ho Chi Minh City 70000, Vietnam
Nguyen Tan Dung
Department of Rehabilitation, Da Nang Hospital of C, Da Nang City 50000, Vietnam
Ly Xuan Quang
Department of Otolaryngology, Faculty of Medicine, University of Medicine and Pharmacy at Ho Chi Minh City, Ho Chi Minh City 70000, Vietnam
Le Quang Hung
Department of Otolaryngology, University Medical Center, Ho Chi Minh City 70000, Vietnam
Ngoc Hoang Le
Graduate Institute of Biomedical Materials and Tissue Engineering, College of Biomedical Engineering, Taipei Medical University, Taipei City 110, Taiwan
Nhi Thao Ngoc Le
Graduate Institute of Biomedical Materials and Tissue Engineering, College of Biomedical Engineering, Taipei Medical University, Taipei City 110, Taiwan
Nguyen Thi Diem
Department of Otolaryngology, Cai Lay Regional General Hospital, Cai Lay 84000, Vietnam
Nguyen Thi Thuy Nga
Faculty of Nursing and Midwifery, Hanoi Medical University, Ha Noi 10000, Vietnam
Shih-Han Hung
International Master/Ph.D. Program in Medicine, College of Medicine, Taipei Medical University, Taipei City 110, Taiwan
Nguyen Quoc Khanh Le
Professional Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei 106, Taiwan
The requesting of detailed information on new drugs including drug-drug interactions or targets is often unavailable and resource-intensive in assessing adverse drug events. To shorten the common evaluation process of drug-drug interactions, we present a machine learning framework-HAINI to predict DDI types for histamine antagonist drugs using simplified molecular-input line-entry systems (SMILES) combined with interaction features based on CYP450 group as inputs. The data used in our research consisted of approved drugs of histamine antagonists that are connected to 26,344 DDI pairs from the DrugBank database. Various classification algorithms such as Naive Bayes, Decision Tree, Random Forest, Logistic Regression, and XGBoost were used with 5-fold cross-validation to approach a large-scale DDIs prediction among histamine antagonist drugs. The prediction performance shows that our model outperformed previously published works on DDI prediction with the best precision of 0.788, a recall of 0.921, and an F1-score of 0.838 among 19 given DDIs types. An important finding of the study is that our prediction is based solely on the SMILES and CYP450 and thus can be applied at the early stage of drug development.