Abstract:
As the best substitute for antibiotics, antimicrobial peptides (AMPs) have important research significance. How to accurately identify AMPs using computational methods has been a key issue in the field of bioinformatics in recent years. However, traditional machine learning methods require autonomous extraction and selection of features from sequence information, resulting in low AMPs identification accuracy. Faced with the above challenges, a deep learning prediction methods based on Bidirectional Encoder Representation from Transformers (BERT) is proposed. In order to conduct a comprehensive evaluation of existing BERT-based AMP tools and further improve the performance of AMP calculation methods, four existing BERT-based AMP prediction tools in terms of pre-training strategies, word vector embeddings, and prediction performance are compared, and thus a novel AMP prediction tool based on the idea of ensemble learning is proposed. The experimental results show that the proposed model has been improved on several performance evaluation indexes.