DeepMC-iNABP: Deep learning for multiclass identification and classification of nucleic acid-binding proteins

Feifei Cui; Shuang Li; Zilong Zhang; Miaomiao Sui; Chen Cao; Abd El-Latif Hesham; Quan Zou

doi:10.1016/j.csbj.2022.04.029

DeepMC-iNABP: Deep learning for multiclass identification and classification of nucleic acid-binding proteins

Comput Struct Biotechnol J. 2022 Apr 26:20:2020-2028. doi: 10.1016/j.csbj.2022.04.029. eCollection 2022.

Authors

Feifei Cui^{1

2

3}, Shuang Li⁴, Zilong Zhang^{1

2

3}, Miaomiao Sui⁵, Chen Cao⁶, Abd El-Latif Hesham⁷, Quan Zou^{2

3}

Affiliations

¹ School of Computer Science and Technology, Hainan University, Haikou 570228, China.
² Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 610054, China.
³ Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou 324000, China.
⁴ Beidahuang Industry Group General Hospital, Harbin 150001, China.
⁵ Graduate School Agricultural and Life Science, The University of Tokyo, Tokyo 1138657, Japan.
⁶ School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing 211166, China.
⁷ Genetics Department, Faculty of Agriculture, Beni-Suef University, Beni-Suef 62511, Egypt.

Abstract

Nucleic acid-binding proteins (NABPs), including DNA-binding proteins (DBPs) and RNA-binding proteins (RBPs), play vital roles in gene expression. Accurate identification of these proteins is crucial. However, there are two existing challenges: one is the problem of ignoring DNA- and RNA-binding proteins (DRBPs), and the other is a cross-predicting problem referring to DBP predictors predicting DBPs as RBPs, and vice versa. In this study, we proposed a computational predictor, called DeepMC-iNABP, with the goal of solving these difficulties by utilizing a multiclass classification strategy and deep learning approaches. DBPs, RBPs, DRBPs and non-NABPs as separate classes of data were used for training the DeepMC-iNABP model. The results on test data collected in this study and two independent test datasets showed that DeepMC-iNABP has a strong advantage in identifying the DRBPs and has the ability to alleviate the cross-prediction problem to a certain extent. The web-server of DeepMC-iNABP is freely available at http://www.deepmc-inabp.net/. The datasets used in this research can also be downloaded from the website.

Keywords: DNA-binding protein; Deep learning; Multiclass classification; Nucleic acid-binding protein; RNA-binding protein.