MLACNN: an attention mechanism-based CNN architecture for predicting genome-wide DNA methylation

• Published in: Theory in biosciences = Theorie in den Biowissenschaften Vol. 142; no. 4; pp. 359 - 370
• Main Authors: Bai, JianGuo, Yang, Hai, Wu, ChangDe
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.11.2023; Springer Nature B.V
• Subjects: Artificial intelligence; Bioinformatics; Biology; Biomedical and Life Sciences; Complex Systems; Deep learning; DNA methylation; Epigenetics; Evolutionary Biology; Gene regulation; Genomes; Learning algorithms; Life Sciences; Machine learning; Mathematical and Computational Biology; Nucleotide sequence; Original; Original Article; Philosophy of Biology; Theoretical Ecology/Statistics; Genome wide methylation detection; Attention CNN; Hybrid neural network
• ISSN: 1431-7613; 1611-7530; 1611-7530
• DOI: 10.1007/s12064-023-00402-3

Methylation is an important epigenetic regulation of methylation genes that plays a crucial role in regulating biological processes. While traditional methods for detecting methylation in biological experiments are constantly improving, the development of artificial intelligence has led to the emergence of deep learning and machine learning methods as a new trend. However, traditional machine learning-based methods rely heavily on manual feature extraction, and most deep learning methods for studying methylation extract fewer features due to their simple network structures. To address this, we propose a bottomneck network based on an attention mechanism and use new methods to ensure that the deep network can learn more effective features while minimizing overfitting. This approach enables the model to learn more features from nucleotide sequences and make better predictions of methylation. The model uses three coding methods to encode the original DNA sequence and then applies feature fusion based on attention mechanisms to obtain the best fusion method. Our results demonstrate that MLACNN outperforms previous methods and achieves more satisfactory performance.