Caps-ac4C: An effective computational framework for identifying N4-acetylcytidine sites in human mRNA based on deep learning.

Journal: Journal of molecular biology
PMID:

Abstract

N4-acetylcytidine (ac4C) is a crucial post-transcriptional modification in human mRNA, involving the acetylation of the nitrogen atom at the fourth position of cytidine. This modification, catalyzed by N-acetyltransferases such as NAT10, is primarily found in mRNA's coding regions and enhances translation efficiency and mRNA stability. ac4C is closely associated with various diseases, including cancer. Therefore, accurately identifying ac4C in human mRNA is essential for gaining deeper insights into disease pathogenesis and provides potential pathways for the development of novel medical interventions. In silico methods for identifying ac4C are gaining increasing attention due to their cost-effectiveness, requiring minimal human and material resources. In this study, we propose an efficient and accurate computational framework, Caps-ac4C, for the precise detection of ac4C in human mRNA. Caps-ac4C utilizes chaos game representation to encode RNA sequences into "images" and employs capsule networks to learn global and local features from these RNA "images". Experimental results demonstrate that Caps-ac4C achieves state-of-the-art performance, achieving 95.47% accuracy and 0.912 MCC on the test set, surpassing the current best methods by 10.69% accuracy and 0.216 MCC. In summary, Caps-ac4C represents the most accurate tool for predicting ac4C sites in human mRNA, highlighting its significant contribution to RNA modification research. For user convenience, we developed a user-friendly web server, which can be accessed for free at:https://awi.cuhk.edu.cn/~Caps-ac4C/index.php.

Authors

  • Lantian Yao
    Warshel Institute for Computational Biology, The Chinese University of Hong Kong, Shenzhen, PR China, and also in the School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, PR China.
  • Peilin Xie
    Kobilka Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China.
  • Danhong Dong
    School of Medicine, The Chinese University of Hong Kong, 2001 Longxiang Road, 518172 Shenzhen, China.
  • Yilin Guo
    School of Medicine, The Chinese University of Hong Kong, 2001 Longxiang Road, 518172 Shenzhen, China.
  • Jiahui Guan
    Nvidia, Boston, United States.
  • Wenyang Zhang
    School of Medicine, The Chinese University of Hong Kong, Shenzhen, China.
  • Chia-Ru Chung
    Department of Computer Science and Information Engineering, National Central University.
  • Zhihao Zhao
    Kobilka Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong, 2001 Longxiang Road, 518172 Shenzhen, China.
  • Ying-Chih Chiang
    Kobilka Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong, Shenzhen, China.
  • Tzong-Yi Lee