Open Access

ARTICLE

Drug Side-Effect Prediction Using Heterogeneous Features and Bipartite Local Models

Yi Zheng^1,2, Wentao Zhao^2,*, Chengcheng Sun², Qian Li¹

1 Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, 2205, Australia.
2 College of Computer, National University of Defense Technology, Changsha, 410073, China.

* Corresponding Author: Wentao Zhao. Email: .

Computers, Materials & Continua 2019, 60(2), 481-496. https://doi.org/10.32604/cmc.2019.05536

Abstract

Drug side-effects impose massive costs on society, leading to almost one-third drug failure in the drug discovery process. Therefore, early identification of potential side-effects becomes vital to avoid risks and reduce costs. Existing computational methods employ few drug features and predict drug side-effects from either drug side or side-effect side separately. In this work, we explore to predict drug side-effects by combining heterogeneous drug features and employing the bipartite local models (BLMs) which fuse predictions from both the drug side and side-effect side. Specifically, we integrate drug chemical structures, drug interacted proteins and drug associated genes into a unified framework to measure the comprehensive similarity between drugs first. Then, high-quality and balanced training samples are selected for individual drugs and individual side-effects using the designed balanced sample selection framework, based on drug comprehensive similarities and side-effect cosine similarities respectively. Trained with corresponding training samples, BLMs first predict drugs associated with a given side-effect, then predict side-effects for a given drug. This produces two independent predictions for each putative drug-side-effect association which are further combined to give a definitive prediction. The performance of the proposed method was evaluated on side-effect prediction for 901 drugs from DrugBank. Particularly, we performed 5-fold cross-validation experiments on the 742 characterized drugs and independent testing experiment on the 159 uncharacterized drugs. The simulative predictions show that the side-effect prediction performance is significantly improved owing to the integration of information from drug chemical, biological and genomic spaces, the proposed sample selection framework, and the implemented BLMs.

---

Keywords

---