PSAC-6mA: 6mA site identifier using self-attention capsule network based on sequence-positioning

• Published in: Computers in biology and medicine 2024-03, Vol.171, p.108129, Article 108129
• Main Authors: Zhou, Zheyu, Xiao, Cuilin, Yin, Jinfen, She, Jiayi, Duan, Hao, Liu, Chunling, Fu, Xiuhao, Cui, Feifei, Qi, Qi, Zhang, Zilong
• Format: Article
• Language: English
• Subjects: Accuracy; Adenine; Biological activity; Capsule network; Cell cycle; Datasets; Deep learning; Dimensional analysis; DNA - genetics; DNA Methylation; Epigenetics; Feature extraction; Gene Regulatory Networks; Genome; Genomes; Localization; Mathematical models; N6-methyladenine; N6-methyladenosine; Neural networks; Nucleotide sequence; Optimization; Parameters; Position (location); Self-attention
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108129

DNA N6-methyladenine (6mA) modifications play a pivotal role in the regulation of growth, development, and diseases in organisms. As a significant epigenetic marker, 6mA modifications extensively participate in the intricate regulatory networks of the genome. Hence, gaining a profound understanding of how 6mA is intricately involved in these biological processes is imperative for deciphering the gene regulatory networks within organisms. In this study, we propose PSAC-6mA (Position-self-attention Capsule-6mA), a sequence-location-based self-attention capsule network. The positional layer in the model enables positional relationship extraction and independent parameter setting for each base position, avoiding parameter sharing inherent in convolutional approaches. Simultaneously, the self-attention capsule network enhances dimensionality, capturing correlation information between capsules and achieving exceptional results in feature extraction across multiple spatial dimensions within the model. Experimental results demonstrate the superior performance of PSAC-6mA in recognizing 6mA motifs across various species. •New method for 6mA site identification, focusing on the role of DNA modification in biology.•Utilizes sequence-location-based self-attention capsule network for innovative 6mA detection.•Introduces unique positional layer for precise relationship extraction at each base position.•Model accurately Identifies 6mA motifs across species, demonstrating exceptional generalization performance.