Deep Learning Empowers the Discovery of Self-Assembling Peptides with Over 10 Trillion Sequences

Self-assembling of peptides is essential for a variety of biological and medical applications. However, it is challenging to investigate the self-assembling properties of peptides within the complete sequence space due to the enormous sequence quantities. Here, it is demonstrated that a transformer-based deep learning model is effective in predicting the aggregation propensity (AP) of peptide systems, even for decapeptide and mixed-pentapeptide systems with over 10 trillion sequence quantities. Based on the predicted AP values, not only the aggregation laws for designing self-assembling peptides are derived, but the transferability relation among the APs of pentapeptides, decapeptides, and mixed pentapeptides is also revealed, leading to discoveries of self-assembling peptides by concatenating or mixing, as consolidated by experiments. This deep learning approach enables speedy, accurate, and thorough search and design of self-assembling peptides within the complete sequence space of oligopeptides, advancing peptide science by inspiring new biological and medical applications.