Random Fourier features-based sparse representation classifier for identifying DNA-binding proteins

Xiaoyi Guo; Prayag Tiwari; Ying Zhang; Shuguang Han; Yansu Wang; Yijie Ding

doi:10.1016/j.compbiomed.2022.106268

Random Fourier features-based sparse representation classifier for identifying DNA-binding proteins

Comput Biol Med. 2022 Dec;151(Pt A):106268. doi: 10.1016/j.compbiomed.2022.106268. Epub 2022 Nov 9.

Authors

Xiaoyi Guo¹, Prayag Tiwari², Ying Zhang³, Shuguang Han⁴, Yansu Wang⁵, Yijie Ding⁶

Affiliations

¹ Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, 610054, PR China; Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324000, PR China. Electronic address: kerry.guoxiaoyi@163.com.
² School of Information Technology, Halmstad University, Sweden. Electronic address: prayag.tiwari@ieee.org.
³ Beidahuang Industry Group General Hospital, Harbin 150088, PR China. Electronic address: zhangying_biggh@163.com.
⁴ Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324000, PR China. Electronic address: shughan@uestc.edu.cn.
⁵ Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu, 610054, PR China. Electronic address: Wangys_c@hotmail.com.
⁶ Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324000, PR China. Electronic address: wuxi_dyj@163.com.

PMID: 36370585
DOI: 10.1016/j.compbiomed.2022.106268

Abstract

DNA-binding proteins (DBPs) protect DNA from nuclease hydrolysis, inhibit the action of RNA polymerase, prevents replication and transcription from occurring simultaneously on a piece of DNA. Most of the conventional methods for detecting DBPs are biochemical methods, but the time cost is high. In recent years, a variety of machine learning-based methods that have been used on a large scale for large-scale screening of DBPs. To improve the prediction performance of DBPs, we propose a random Fourier features-based sparse representation classifier (RFF-SRC), which randomly map the features into a high-dimensional space to solve nonlinear classification problems. And L_2,1-matrix norm is introduced to get sparse solution of model. To evaluate performance, our model is tested on several benchmark data sets of DBPs and 8 UCI data sets. RFF-SRC achieves better performance in experimental results.

Keywords: Biological sequence features; Random features; Sequence classification; Sparse representation-based classifier.

Publication types

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

MeSH terms

Algorithms*
DNA
DNA-Binding Proteins*
Machine Learning

Substances

DNA-Binding Proteins
DNA