AMPFinder: A computational model to identify antimicrobial peptides and their functions based on sequence-derived information

• Published in: Analytical biochemistry Vol. 673; p. 115196
• Main Authors: Yang, Sen, Yang, Zexi, Ni, Xinye
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 15.07.2023
• Subjects: Antimicrobial Cationic Peptides - chemistry; Antimicrobial Cationic Peptides - pharmacology; Antimicrobial peptide identification; Antimicrobial Peptides; Deep learning; Function prediction; Fungi; Pre-train language model; Software; Deep learning; Function prediction; Antimicrobial peptide identification; Pre-train language model
• ISSN: 0003-2697; 1096-0309
• DOI: 10.1016/j.ab.2023.115196

Antimicrobial peptides (AMPs) called host defense peptides have existed among all classes of life with 5–100 amino acids generally and can kill mycobacteria, envelop viruses, bacteria, fungi, cancerous cells and so on. Owing to the non-drug resistance of AMP, it has been a wonderful agent to find novel therapies. Therefore, it is urgent to identify AMPs and predict their function in a high-throughput way. In this paper, we propose a cascaded computational model to identify AMPs and their functional type based on sequence-derived and life language embedding, called AMPFinder. Compared with other state-of-the-art methods, AMPFinder obtains higher performance both on AMP identification and AMP function prediction. AMPFinder shows better performance with improvement of F1-score (1.45%–6.13%), MCC (2.92%–12.86%) and AUC (5.13%–8.56%) and AP (9.20%–21.07%) on an independent test dataset. And AMPFinder achieve lower bias of R2 on a public dataset by 10-fold cross-validation with an improvement of (18.82%–19.46%). The comparison with other state-of-the-art methods shows that AMP can accurately identify AMP and its function types. The datasets, source code and user-friendly application are available at https://github.com/abcair/AMPFinder. [Display omitted] •AMPFinder aims to distinguish AMPs and non-AMPs and predict their function types by a cascaded computational model.•Sequence-derived and life language embedding methods show positive effects to predict AMPs and their function types.•A deep learning model with a new attention mechanism is utilized to predict the function types of AMPs.•AMPFinder provides a cross-platform and graphical user interface (GUI) application to identify AMP and their functions.