Machine learning designs non-hemolytic antimicrobial peptides

The research article "Machine Learning Designs Non-Hemolytic Antimicrobial Peptides" just got published in Chemical Science!

Antimicrobial peptides (AMPs) offer a unique opportunity to address antibiotic resistance, which is one of the major global public health threats. Most AMPs are membrane disruptive amphiphiles, and unfortunately, this activity is often associated with toxicity to human red blood cells. We have trained a combination of supervised and unsupervised recurrent neural networks (RNN) with hemolysis and activity data from DBAASP (Database of Antimicrobial Activity and Structure of Peptides) to design short non-hemolytic AMPs. Synthesis and testing of 28 generated peptides allowed us to identify eight new non-hemolytic AMPs against Pseudomonas aeruginosa, Acinetobacter baumannii, and methicillin-resistant Staphylococcus aureus.

Author(s): Alice Capecchi, Xingguang Cai, Hippolyte Personne, Thilo Köhler, Christian van Delden and Jean-Louis Reymond