Discovery of novel multi-functional peptides by using protein language models and graph-based deep learning

Abstract

Functional peptides are one kind of short protein fragments that have a wide range of beneficial functions for living organisms. The majority of previous research focused on mono-functional peptides, but a growing number of multi-functional peptides have been discovered. Although enormous experimental efforts endeavor to assay multi-functional peptides, only a small fraction of millions of known peptides have been explored. Effective and precise techniques for identifying multi-functional peptides can facilitate their discovery and mechanistic understanding. In this article, we presented a novel method, called iMFP-LG, for identifying multi-functional peptides based on protein language models (pLMs) and graph attention networks (GATs). iMFP-LG converts multi-function identification into graph node classification, where graph node representations are extracted from peptide sequences by pLMs and their relationships are captured by GATs. Comparison results showed iMFP-LG significantly outperforms state-of-the-art methods on both multi-functional bioactive peptides and multi-functional therapeutic peptides datasets. The interpretability of iMFP-LG was also illustrated by visualizing patterns learned by attention mechanism. More importantly, we employed iMFP-LG to discover 13 candidate peptides with both anticancer and antimicrobial functions from UniRef90. We anticipate iMFP-LG can assist in the discovery of multi-functional peptides and contribute to the advancement of peptide drug design.