A1 Journal article (refereed)
SoftVoting6mA : An improved ensemble-based method for predicting DNA N6-methyladenine sites in cross-species genomes (2024)

Yin, Z., Lyu, J., Zhang, G., Huang, X., Ma, Q., & Jiang, J. (2024). SoftVoting6mA : An improved ensemble-based method for predicting DNA N6-methyladenine sites in cross-species genomes. Mathematical Biosciences and Engineering, 21(3), 3798-3815. https://doi.org/10.3934/mbe.2024169

JYU authors or editors

Publication details

All authors or editors: Yin, Zhaoting; Lyu, Jianyi; Zhang, Guiyang; Huang, Xiaohong; Ma, Qinghua; Jiang, Jinyun

Journal or series: Mathematical Biosciences and Engineering

ISSN: 1547-1063

eISSN: 1551-0018

Publication year: 2024

Publication date: 19/02/2024

Volume: 21

Issue number: 3

Pages range: 3798-3815

Publisher: American Institute of Mathematical Sciences

Publication country: United States

Publication language: English

DOI: https://doi.org/10.3934/mbe.2024169

Research data link: https://github.com/yinzhaoting/Softvoting-6mA

Publication open access: Openly available

Publication channel open access: Open Access channel

Abstract

The DNA N6-methyladenine (6mA) is an epigenetic modification, which plays a pivotal role in biological processes encompassing gene expression, DNA replication, repair, and recombination. Therefore, the precise identification of 6mA sites is fundamental for better understanding its function, but challenging. We proposed an improved ensemble-based method for predicting DNA N6-methyladenine sites in cross-species genomes called SoftVoting6mA. The SoftVoting6mA selected four (electron–ion-interaction pseudo potential, One-hot encoding, Kmer, and pseudo dinucleotide composition) codes from 15 types of encoding to represent DNA sequences by comparing their performances. Similarly, the SoftVoting6mA combined four learning algorithms using the soft voting strategy. The 5-fold cross-validation and the independent tests showed that SoftVoting6mA reached the state-of-the-art performance. To enhance accessibility, a user-friendly web server is provided at http://www.biolscience.cn/SoftVoting6mA/.

Keywords: DNA; gene expression; machine learning; neural networks (information technology); servers; bioinformatics

Free keywords: DNA N6-methyladenine; convolution neural network; soft voting; cross-species; feature fusion; webserver

Contributing organizations

Ministry reporting: Yes

Preliminary JUFO rating: 1