CPPGAN-ESM: GAN-Enhanced ESM Prediction Model for Cell-Penetrating Peptide

Cell-penetrating peptide, with their ability to traverse cell membranes and access the intracellular environment, has garnered significant attention in contemporary medical research. Predicting cell-penetrating peptide can expand the therapeutic scope, improve the therapeutic effect, and promote the development of drug delivery, gene therapy, and other fields. Compared with the traditional wet-lab method, predicting cell-penetrating peptide by computational methods has the advantages of low cost and accuracy. However, due to the difficulty of collecting cell-penetrating peptide datasets and the performance limitation of traditional feature extractors, Predicting the performance of cell-penetrating peptide using traditional computational methods has limitations. To address these problems, a cell-penetrating peptide prediction method named CPPGAN-ESM is proposed in this paper. CPPGAN-ESM firstly augments the cell-penetrating peptide dataset by using Deep Convolutional Generative Adversarial Network, and then fine-tunes the predictor based on the Evolutionary Scale Modeling 2 pre-trained feature extractor with the augmented dataset, to realize the prediction of the cell-penetrating peptide. Extensive experiments on a public dataset show that the method achieves an efficient performance of 0.979 AUC and 0.977 ACC in the cell-penetrating peptide prediction task.