Machine Learning Guides the Design of Non-Hemolytic Antimicrobial Peptides
Antimicrobial peptides (AMPs) offer an opportunity to address antibiotic resistance, which represents one of the major global public health threats [1]. Most AMPs are membrane disruptive amphiphiles, and unfortunately this activity is often associated with toxicity to human red blood cells [2]. Here, we have trained a combination of supervised and unsupervised recurrent neural networks (RNN) using hemolysis and activity data from DBAASP (Database of Antimicrobial Activity and Structure of Peptides) [3] to design non-hemolytic AMPs. The synthesis and test of 28 generated peptides led to the identification of eight novel non-hemolytic AMPs against Pseudomonas aeruginosa, Acinetobacter baumannii, and methicillin-resistant Staphylococcus aureus (MRSA).
[1] Magana, M.; Pushpanathan, M.; Santos, A. L.; Leanse, L.; Fernandez, M.; Ioannidis, A.; Giulianotti, M. A.; Apidianakis, Y.; Bradfute, S.; Ferguson, A. L.; Cherkasov, A.; Seleem, M. N.; Pinilla, C.; de la Fuente-Nunez, C.; Lazaridis, T.; Dai, T.; Houghten, R. A.; Hancock, R. E. W.; Tegos, G. P. The Value of Antimicrobial Peptides in the Age of Resistance. Lancet Infect. Dis. 2020, 20 (9), e216–e230.
[2] Greco, I.; Molchanova, N.; Holmedal, E.; Jenssen, H.; Hummel, B. D.; Watts, J. L.; Håkansson, J.; Hansen, P. R.; Svenson, J. Correlation between Hemolytic Activity, Cytotoxicity and Systemic in Vivo Toxicity of Synthetic Antimicrobial Peptides. Sci. Rep. 2020, 10 (1), 13206.
[3] Gogoladze, G.; Grigolava, M.; Vishnepolsky, B.; Chubinidze, M.; Duroux, P.; Lefranc, M.-P.; Pirtskhalava, M. DBAASP: Database of Antimicrobial Activity and Structure of Peptides. FEMS Microbiol. Lett. 2014, 357 (1), 63–68.