DE-MHAIPs: Identification of SARS-CoV-2 phosphorylation sites based on differential evolution multi-feature learning and multi-head attention mechanism

• Published in: Computers in biology and medicine 2023-06, Vol.160, p.106935-106935, Article 106935
• Main Authors: Wang, Minghui, Yan, Lu, Jia, Jihua, Lai, Jiali, Zhou, Hongyan, Yu, Bin
• Format: Article
• Language: English
• Subjects: Algorithms; Amino acid sequence; Amino acids; Bioinformatics; Coronaviruses; COVID-19; Datasets; Deep learning; Differential evolution algorithm; Eigenvectors; Evolutionary algorithms; Evolutionary computation; Feature extraction; Group LASSO; Humans; Infections; Information processing; Learning; Long short-term memory; Machine learning; Multi-head attention mechanism; Multi-view feature fusion; Neural networks; Phosphorylation; Prediction models; Proteins; Research methodology; SARS-CoV-2; SARS-CoV-2 phosphorylation sites; Severe acute respiratory syndrome coronavirus 2
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2023.106935

The rapid spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) around the world affects the normal lives of people all over the world. The computational methods can be used to accurately identify SARS-CoV-2 phosphorylation sites. In this paper, a new prediction model of SARS-CoV-2 phosphorylation sites, called DE-MHAIPs, is proposed. First, we use six feature extraction methods to extract protein sequence information from different perspectives. For the first time, we use a differential evolution (DE) algorithm to learn individual feature weights and fuse multi-information in a weighted combination. Next, Group LASSO is used to select a subset of good features. Then, the important protein information is given higher weight through multi-head attention. After that, the processed data is fed into long short-term memory network (LSTM) to further enhance model's ability to learn features. Finally, the data from LSTM are input into fully connected neural network (FCN) to predict SARS-CoV-2 phosphorylation sites. The AUC values of the S/T and Y datasets under 5-fold cross-validation reach 91.98% and 98.32%, respectively. The AUC values of the two datasets on the independent test set reach 91.72% and 97.78%, respectively. The experimental results show that the DE-MHAIPs method exhibits excellent predictive ability compared with other methods. •A novel method (DE-MHAIPs) is used to predict anti-coronavirus peptides.•The AAindex, DDE, CTD, PseAAC, EAAC, and BLOSUM62 methods are fused to extract proteins sequence features information.•The Group LASSO is used to screen optimal feature subset for the first time.•We firstly build a new deep learning framework which combines the LSTM and Multi-head attention to predict the SARS-CoV-2 phosphorylation sites.•DE-MHAIPs increases the prediction performance compared with other methods.