MCTASmRNA: A deep learning framework for alternative splicing events classification.

Journal: International journal of biological macromolecules
PMID: 39842565

Abstract

Alternative splicing (AS) plays crucial post-transcriptional gene function regulation roles in eukaryotic. Despite progress in studying AS at the RNA level, existing methods for AS event identification face challenges such as inefficiency, lengthy processing times, and limitations in capturing the complexity of RNA sequences. To overcome these challenges, we evaluated 10 AS detection tools and selected rMATS for dataset construction. We then developed a multi-scale convolutional and Transformer-based model (MCTASmRNA) to classify AS events in mRNA sequences without relying on a reference genome. To handle the problem of large intra-class and small inter-class difference in AS event sequences, we incorporated an efficient channel attention mechanism and designed a new joint loss function to optimize MCTASmRNA training. MCTASmRNA outperformed baseline models, with an accuracy improvement and exhibited enhanced cross-species generalizability. This model provides valuable support for AS research across different organisms. Future work will focus on optimizing and expanding the model to further explore the complex mechanisms underlying AS.

Authors

  • Juan-Yu Zheng
    School of Information Science and Technology, School of Artificial Intelligence, Beijing Forestry University, Beijing 100083, People's Republic of China.
  • Gao Jiang
    School of Information Science and Technology, School of Artificial Intelligence, Beijing Forestry University, Beijing 100083, People's Republic of China.
  • Fu-Hai Gao
    School of Information Science and Technology, School of Artificial Intelligence, Beijing Forestry University, Beijing 100083, People's Republic of China.
  • Shu-Ning Ren
    State Key Laboratory of Tree Genetics and Breeding, National Engineering Research Center of Tree Breeding and Ecological Restoration, College of Biological Sciences and Technology, Beijing Forestry University, Beijing 100083, People's Republic of China.
  • Chen-Yu Zhu
    Department of Dermatology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China.
  • Jianbo Xie
    State Key Laboratory of Tree Genetics and Breeding, National Engineering Research Center of Tree Breeding and Ecological Restoration, College of Biological Sciences and Technology, Beijing Forestry University, Beijing 100083, People's Republic of China.
  • Zhonghai Li
    State Key Laboratory of Tree Genetics and Breeding, National Engineering Research Center of Tree Breeding and Ecological Restoration, College of Biological Sciences and Technology, Beijing Forestry University, Beijing 100083, People's Republic of China.
  • Weilun Yin
    State Key Laboratory of Tree Genetics and Breeding, National Engineering Research Center of Tree Breeding and Ecological Restoration, College of Biological Sciences and Technology, Beijing Forestry University, Beijing 100083, People's Republic of China.
  • Xinli Xia
    State Key Laboratory of Tree Genetics and Breeding, National Engineering Research Center of Tree Breeding and Ecological Restoration, College of Biological Sciences and Technology, Beijing Forestry University, Beijing 100083, People's Republic of China.
  • Yun Li
    School of Public Health, University of Michigan, Ann Arbor, MI, USA.
  • Hou-Ling Wang
    State Key Laboratory of Tree Genetics and Breeding, National Engineering Research Center of Tree Breeding and Ecological Restoration, College of Biological Sciences and Technology, Beijing Forestry University, Beijing 100083, People's Republic of China. Electronic address: whling@bjfu.edu.cn.

Keywords

External Resources

Popular Topics
Recent Journals