PepLand: a large-scale pre-trained peptide representation model for a comprehensive landscape of both canonical and non-canonical amino acids

TL;DR

PepLand is a novel pre-trained model utilizing a multi-view heterogeneous graph neural network to effectively represent and analyze both canonical and non-canonical peptides, advancing peptide research.

Contribution

Introduces PepLand, a comprehensive pre-training architecture specifically designed for complex peptide sequences with canonical and non-canonical amino acids.

Findings

Effective in predicting peptide properties such as interactions, permeability, and solubility.

Outperforms existing models in capturing structural features of peptides.

Provides publicly available code for reproducibility.

Abstract

In recent years, the scientific community has become increasingly interested on peptides with non-canonical amino acids due to their superior stability and resistance to proteolytic degradation. These peptides present promising modifications to biological, pharmacological, and physiochemical attributes in both endogenous and engineered peptides. Notwithstanding their considerable advantages, the scientific community exhibits a conspicuous absence of an effective pre-trained model adept at distilling feature representations from such complex peptide sequences. We herein propose PepLand, a novel pre-training architecture for representation and property analysis of peptides spanning both canonical and non-canonical amino acids. In essence, PepLand leverages a comprehensive multi-view heterogeneous graph neural network tailored to unveil the subtle structural representations of peptides. Empirical validations underscore PepLand's effectiveness across an array of peptide property predictions, encompassing protein-protein interactions, permeability, solubility, and synthesizability. The rigorous evaluation confirms PepLand's unparalleled capability in capturing salient synthetic peptide features, thereby laying a robust foundation for transformative advances in peptide-centric research domains. We have made all the source code utilized in this study publicly accessible via GitHub at https://github.com/zhangruochi/pepland