PepGlider: Property Regularized VAE for interpretable and controllable peptide design

Abstract Computational peptide design requires precise control over peptide properties that often exhibit complex correlations. Existing generative models for peptide design rely on simplistic discrete conditioning mechanisms rather than precise targeting of specific property values. We present PepGlider, a continuous property regularization framework that enables direct control over their specific values. The method achieves structured latent space with superior disentanglement quality and displays smooth property gradients along regularized dimension. In silico experimental results demonstrate that PepGlider enables independent control of naturally correlated properties, and supports both de novo generation and targeted optimization of existing peptides. PepGlider applied to antimicrobial peptide design allows generation of candidates with desired antibacterial activity profile and maintained low toxicity profile. Unlike existing approaches, PepGlider provides precise control over continuous property distributions while maintaining generation quality, thus offering a generalizable solution for therapeutic and materials applications requiring exact property specifications. Competing Interest Statement The authors have declared no competing interest.