Enhancing Antimicrobial Peptide Function Prediction via Knowledge Transfer on Protein Language Models

The excessive use of antibiotics has contributed to the growing resistance of various microbial pathogens, prompting the exploration of alternatives such as antimicrobial peptides (AMPs). However, wet-lab experimental methods for AMP identification are not only time-consuming but also resource-intensive. Machine learning (ML) and deep learning (DL) techniques have been increasingly employed for AMP classification to overcome these limitations. Recently, pre-trained protein language models (pLMs) have emerged, demonstrating their exceptional ability to represent biological sequences in a variety of prediction tasks. Building on these advancements, we present KT-AMPpred, a method for predicting antimicrobial peptides and their specific antimicrobial properties using transfer learning and fine-tuning techniques based on pre-trained protein language models. Utilizing transfer learning, KT-AMPpred effectively integrates knowledge from prior AMP classification tasks to improve the prediction of distinct antimicrobial properties. Additionally, the fine-tuning of pLM within KT-AMPpred further enhances its performance on downstream prediction tasks. The experimental outcomes reveal that KT-AMPpred exceeds current leading approaches on benchmark datasets, with visual analysis confirming its robust feature extraction capabilities, establishing it as an effective tool for antimicrobial peptide prediction.