PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences
This work addresses the need for new antimicrobial design methods for public health, though it is incremental as it builds on existing VAE approaches with semi-supervised enhancements.
The authors tackled the problem of designing novel antimicrobial peptides to combat antimicrobial resistance by developing PepCVAE, a semi-supervised variational autoencoder framework that generates sequences with higher long-range diversity and closer alignment to biological peptide distributions compared to a plain VAE.
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.