These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
RNNGeneratedAMPs.pdf (6.21 MB)

Machine Learning Designs Non-Hemolytic Antimicrobial Peptides

submitted on 17.03.2021, 20:24 and posted on 18.03.2021, 13:22 by Alice Capecchi, Xingguang Cai, Hippolyte Personne, Thilo Köhler, Christian van Delden, Jean-Louis Reymond

Machine learning (ML) consists in the recognition of patterns from training data and offers the opportunity to exploit large structure-activity database sets for drug design. In the area of peptide drugs, ML is mostly being tested to design antimicrobial peptides (AMPs), a class of biomolecules potentially useful to fight multidrug resistant bacteria. ML models have successfully identified membrane disruptive amphiphilic AMPs, however without addressing the associated toxicity to human red blood cells. Here we trained recurrent neural networks (RNN) with data from DBAASP (Database of Antimicrobial Activity and Structure of Peptides) to design short non-hemolytic AMPs. Synthesis and testing of 28 generated peptides, each at least 5 mutations away from training data, allowed us to identify eight new non-hemolytic AMPs against Pseudomonas aeruginosa, Acinetobacter baumannii, and methicillin resistant Staphylococcus aureus (MRSA). These results show that machine learning (ML) can be used to design new non-hemolytic AMPs.


Swiss National Science Foundation Grant no. 200020_178998 and 407240_167048

European Research Council Grant no. 885076


Email Address of Submitting Author


University of Bern



ORCID For Submitting Author


Declaration of Conflict of Interest

no conflict of interest