PLM-IL4: Enhancing IL-4-inducing peptide prediction with protein language model

Despite progress in developing antiviral drugs and vaccines, infections continue to be a significant challenge. Interleukin-4 (IL-4) is crucial for regulating immune responses and mediating allergic reactions. This research aims to improve the predictive accuracy of IL-4-inducing peptides by tackling data imbalance and enhancing feature extraction. Specifically, we introduce a new approach that utilizes SMOTE and ENN for balancing the dataset and applies a 30-layer ESM-2 model for extracting deep features. The extracted features are subsequently processed through a Gated Recurrent Unit (GRU) model, which is optimized through hyperparameter tuning. Our method achieves notable improvements, with an AUC of 0.98 and an accuracy of 93.1 %, highlighting its potential to support future immunotherapy and vaccine development efforts. The PLM-IL4 web server is freely accessible at http://www.bioai-lab.com/PLM-IL4, and the datasets used in this research are also available for download from the website.