PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences

TL;DR

PepCVAE is a semi-supervised generative model that creates diverse, controllable antimicrobial peptides by learning disentangled representations from both labeled and unlabeled data, addressing antimicrobial resistance.

Contribution

The paper introduces PepCVAE, a novel semi-supervised VAE framework that disentangles antimicrobial attributes for targeted peptide design, improving diversity and biological relevance.

Findings

PepCVAE outperforms plain VAE in generating diverse AMP sequences.

Generated sequences are closer to natural peptides, enhancing biological plausibility.

The model enables controllable design of antimicrobial properties.

Abstract

Given the emerging global threat of antimicrobial resistance, new methods for next-generation antimicrobial design are urgently needed. We report a peptide generation framework PepCVAE, based on a semi-supervised variational autoencoder (VAE) model, for designing novel antimicrobial peptide (AMP) sequences. Our model learns a rich latent space of the biological peptide context by taking advantage of abundant, unlabeled peptide sequences. The model further learns a disentangled antimicrobial attribute space by using the feedback from a jointly trained AMP classifier that uses limited labeled instances. The disentangled representation allows for controllable generation of AMPs. Extensive analysis of the PepCVAE-generated sequences reveals superior performance of our model in comparison to a plain VAE, as PepCVAE generates novel AMP sequences with higher long-range diversity, while being closer to the training distribution of biological peptides. These features are highly desired in next-generation antimicrobial design.