Towards best practices in low-dimensional semi-supervised latent Bayesian optimization for the design of antimicrobial peptides
Abstract
Searching through a low-dimensional projection rather than the full latent space associated with a generative model can improve performance and interpretability for biomolecular design.
Fields of Study & Subjects
Antimicrobial Peptides and Activities
Machine Learning in Bioinformatics
Microbial Natural Products and Biosynthesis
Publication details
- Journal / source
- Molecular Systems Design & Engineering
- Volume
- 11
- Issue
- 7
- Pages
- 616–637
- Publication date
- 1 January 2026
- Language
- EN