(58a) Identification of Highly Selective Antifungal Peptides Containing Non-Canonical Amino Acids with Iterative Machine Learning

Antimicrobial peptides (AMPs) – a component of the innate immune system of organisms – are promising compounds for the treatment and prevention of multidrug-resistant infections because of their ability to directly disrupt microbial membranes. Although this mechanism is less likely to lead to resistance compared to antibiotics,¹ natural AMPs are unfortunately prone to proteolytic cleavage in vivo and have relatively low selectivity for microbial versus human cells, motivating the development of synthetic peptidomimetics of AMPs with improved stability, activity, and selectivity. One promising class of synthetic peptides is α/β-peptides, where α denotes traditional amino acids while β denotes modified amino acids with an additional backbone carbon. α/β-peptides exhibit enhanced proteolytic resistance while maintaining side chain presentations similar to those of α-peptides, enabling the templating of sequences on naturally occurring AMPs.^{2, 3} However, a lack of understanding of structure–activity relationships for peptidomimetics constrains development to rational design or experimental predictors, both of which are cost and time prohibitive, especially when the design space of possible sequences scales exponentially with the number of amino acids.

To address these challenges, we developed an iterative Gaussian process regression (GPR) model to explore a large design space of 336,000 synthetic α/β-peptide analogues of a natural AMP, aurein 1.2, based on an initial training set of 147 sequences and their biological activities against microbial vs. mammalian red blood cells.⁴ We show that the quantification of prediction uncertainty provided by GPR can guide the exploration of this design space via iterative experimental measurements to efficiently discover novel sequences with up to a 52-fold increase in antifungal selectivity compared to aurein 1.2. Using this approach, the highest selectivity peptide discovered features an unconventional substitution of cationic amino acids in the hydrophobic face and would be unlikely to be explored by conventional rational design. Overall, this work demonstrates a generalizable approach that integrates computation and experiment to accurately predict the selectivity of AMPs containing synthetic amino acids, which circumvents the need for large sets of low-throughput and costly experimental physicochemical data while maintaining good prediction accuracy.

(1) Muttenthaler, M.; King, G. F.; Adams, D. J.; Alewood, P. F. Trends in peptide drug discovery. Nature Reviews Drug Discovery 2021, 20 (4), 309-325. DOI: 10.1038/s41573-020-00135-8.

(2) Lee, M. R.; Raman, N.; Gellman, S. H.; Lynn, D. M.; Palecek, S. P. Incorporation of β-Amino Acids Enhances the Antifungal Activity and Selectivity of the Helical Antimicrobial Peptide Aurein 1.2. ACS Chem Biol 2017, 12 (12), 2975-2980. DOI: 10.1021/acschembio.7b00843 From NLM.

(3) Chang, D. H.; Lee, M.-R.; Wang, N.; Lynn, D. M.; Palecek, S. P. Establishing Quantifiable Guidelines for Antimicrobial α/β-Peptide Design: A Partial Least-Squares Approach to Improve Antimicrobial Activity and Reduce Mammalian Cell Toxicity. ACS Infectious Diseases 2023, 9 (12), 2632-2651. DOI: 10.1021/acsinfecdis.3c00468.

(4) Chang, D. H.; Richardson, J. D.; Lee, M.-R.; Lynn, D. M.; Palecek, S. P.; Van Lehn, R. C. Machine learning-driven discovery of highly selective antifungal peptides containing non-canonical β-amino acids. Chemical Science 2025, 10.1039/D4SC06689H. DOI: 10.1039/D4SC06689H.