Novel Fine-Tuning Strategy on Pre-trained Protein Model Enhances ACP Functional Type Classification

Cancer remains one of the most formidable health challenges globally. Anti-cancer peptides (ACPs) have recently emerged as a promising new therapeutic strategy, recognized for their targeted and efficient anti-cancer properties. To fully discover the potential of ACPs, computational methods that can accurately predict their functional types are indispensable. By leveraging a pre-trained protein sequence model, we present ACP-FT that fine-tuned specifically for predicting the functional types of ACPs. Employing a novel fine-tuning approach alongside an adversarial model training technique, our model surpasses existing methods in classification performance on two public datasets. Additionally, we provide a thorough analysis of our training strategy's effectiveness. The experimental results demonstrate that our two-step fine-tuning approach effectively prevents catastrophic forgetting in the pretrained model, while adversarial training enhances the model's robustness. Together, these techniques significantly increase the accuracy of ACP functional type predictions.