Prediction of drug-target interactions via neural tangent kernel extraction feature matrix factorization model

Yu Wang; Yu Zhang; Jianchun Wang; Fang Xie; Dequan Zheng; Xiang Zou; Mian Guo; Yijie Ding; Jie Wan; Ke Han

doi:10.1016/j.compbiomed.2023.106955

Prediction of drug-target interactions via neural tangent kernel extraction feature matrix factorization model

Comput Biol Med. 2023 Jun:159:106955. doi: 10.1016/j.compbiomed.2023.106955. Epub 2023 Apr 19.

Authors

Yu Wang¹, Yu Zhang², Jianchun Wang², Fang Xie², Dequan Zheng², Xiang Zou³, Mian Guo⁴, Yijie Ding⁵, Jie Wan⁶, Ke Han⁷

Affiliations

¹ School of Computer and Information Engineering, Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing, Harbin University of Commerce, Harbin, 150028, China; Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou, 324000, China.
² School of Computer and Information Engineering, Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing, Harbin University of Commerce, Harbin, 150028, China.
³ Pharmaceutical Engineering Technology Research Center, Harbin University of Commerce, Harbin, 150076, China.
⁴ Department of Neurosurgery, The Second Affiliated Hospital of Harbin Medical University, 150086, China.
⁵ Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou, 324000, China. Electronic address: wuxi_dyj@163.com.
⁶ Laboratory for Space Environment and Physical Sciences, Harbin Institute of Technology, Harbin, 150001, China. Electronic address: wanjie@hit.edu.cn.
⁷ School of Computer and Information Engineering, Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing, Harbin University of Commerce, Harbin, 150028, China; Pharmaceutical Engineering Technology Research Center, Harbin University of Commerce, Harbin, 150076, China. Electronic address: thruster@163.com.

PMID: 37094465
DOI: 10.1016/j.compbiomed.2023.106955

Abstract

Drug discovery is a complex and lengthy process that often requires years of research and development. Therefore, drug research and development require a lot of investment and resource support, as well as professional knowledge, technology, skills, and other elements. Predicting of drug-target interactions (DTIs) is an important part of drug development. If machine learning is used to predict DTIs, the cost and time of drug development can be significantly reduced. Currently, machine learning methods are widely used to predict DTIs. In this study neighborhood regularized logistic matrix factorization method based on extracted features from a neural tangent kernel (NTK) to predict DTIs. First, the potential feature matrix of drugs and targets is extracted from the NTK model, then the corresponding Laplacian matrix is constructed according to the feature matrix. Next, the Laplacian matrix of the drugs and targets is used as the condition for matrix factorization to obtain two low-dimensional matrices. Finally, the matrix of the predicted DTIs was obtained by multiplying these two low-dimensional matrices. For the four gold standard datasets, the present method is significantly better than the other methods that is compared to, indicating that the automatic feature extraction method using the deep learning model is competitive compared with the manual feature selection method.

Keywords: Drug-target interactions; Feature extraction; Matrix factorization; Neural tangent kernel; Regularized by neighborhood.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Drug Development*
Drug Discovery* / methods
Drug Interactions
Machine Learning