Quantum Annealing Designs Nonhemolytic Antimicrobial Peptides in a Discrete Latent Space

Abstract

Increasing the variety of antimicrobial peptides is crucial in meeting the global challenge of multi-drug-resistant bacterial pathogens. While several deep-learning-based peptide design pipelines are reported, they may not be optimal in data efficiency. High efficiency requires a wellcompressed latent space, where optimization is likely to fail due to numerous local minima. We present a multi-objective peptide design pipeline based on a discrete latent space and D-Wave quantum annealer with the aim of solving the local minima problem. To achieve multi-objective optimization, multiple peptide properties are encoded into a score using non-dominated sorting. Our pipeline is applied to design therapeutic peptides that are antimicrobial and non-hemolytic at the same time. From 200 000 peptides designed by our pipeline, four peptides proceeded to wet-lab validation. Three of them showed high anti-microbial activity, and two are non-hemolytic. Our results demonstrate how quantum-based optimizers can be taken advantage of in real-world medical studies.

Design of antimicrobial peptides containing non-proteinogenic amino acids using multi-objective Bayesian optimisation

“…19–21 Regarding AMP designs, several studies have been reported using Bayesian optimisation combined with machine learning (ML)-based evaluations rather than experimentation. 22,23 However, the optimisation potential of AMPs using Bayesian optimisation combined with experimental feedback has not been investigated.…”

Design of antimicrobial peptides containing non-proteinogenic amino acids using multi-objective Bayesian optimisation

“…[19][20][21] Regarding AMP designs, several studies have been reported using Bayesian optimisation combined with machine learning-based evaluations rather than experimentations. 22,23 However, the optimisation potential of AMPs using Bayesian optimisation combined with experimental feedback has not been investigated.…”