Accelerating Antimicrobial Peptide Discovery with Latent Structure

TL;DR

This paper introduces LSSAMP, a deep generative model that incorporates peptide structure information into antimicrobial peptide design, leading to the generation of candidates with high antimicrobial activity verified through laboratory experiments.

Contribution

LSSAMP is the first model to integrate secondary structure information via multi-scale vector quantization in latent space for AMP design.

Findings

Generated peptides show high probability of antimicrobial activity.

Two out of 21 candidates exhibit strong antimicrobial effects.

Code is publicly available for further research.

Abstract

Antimicrobial peptides (AMPs) are promising therapeutic approaches against drug-resistant pathogens. Recently, deep generative models are used to discover new AMPs. However, previous studies mainly focus on peptide sequence attributes and do not consider crucial structure information. In this paper, we propose a latent sequence-structure model for designing AMPs (LSSAMP). LSSAMP exploits multi-scale vector quantization in the latent space to represent secondary structures (e.g. alpha helix and beta sheet). By sampling in the latent space, LSSAMP can simultaneously generate peptides with ideal sequence attributes and secondary structures. Experimental results show that the peptides generated by LSSAMP have a high probability of antimicrobial activity. Our wet laboratory experiments verified that two of the 21 candidates exhibit strong antimicrobial activity. The code is released at https://github.com/dqwang122/LSSAMP.