A new generation of antimicrobial peptides

The application of artificial intelligence methods for the generation of antimicrobial peptides will be the subject of research in the Deep Optimised Generation of AntiMicrobial Peptide (DOG-AMP) project.

The project will be carried out by Prof. Ewa Szczurek from the University of Warsaw Faculty of Mathematics, Informatics and Mechanics, who will join Helmholtz Munich in February 2024. For its implementation, Prof. Szczurek received the Consolidator Grant awarded by the European Research Council (ERC).

As part of the Deep Optimised Generation of Antimicrobial Peptides (DOG-AMP) project, funded at almost €2 million, Prof. Szczurek will develop artificial intelligence methods for the generation of new amino acid compounds - antimicrobial peptides (AMPs).

"AMPs are short peptides that can actively and selectively kill antibiotic-resistant pathogens and, as such, are considered the most promising strategy to combat antimicrobial resistance. However, intensive research on AMPs has not translated into their success in clinical application, mainly due to their lower activity and safety compared to existing antibiotics," Prof. Ewa Szczurek says.

The DOG-AMP project, by developing innovative methods of deep optimised generation (DOG), aims to generate new peptides that are superior to existing ones because of their higher activity and lower toxicity.

"We will be working on deep optimised generation models, which represent a new class of artificial intelligence methods. The models will be used to simultaneously generate and optimise generated samples. These methods will be applied to the design of new antimicrobial peptides, which will be synthesised and their activity and toxicity will be tested experimentally," Prof. Ewa Szczurek says.

The project will use methods of artificial intelligence, simulation, peptide synthesis and microbiology experiments. Research results will be presented in the form of publications, conference presentations and patents. "DOG-AMP has the potential to bring breakthroughs in the broad research areas of deep generative modelling, sequence optimisation and AMP discovery," Prof. Szczurek emphasises.

In February 2024 Prof. Szczurek will join Helmholtz Munich as Co-Director of the Institute of AI for Health. The project will start in May 2024 and run until May 2029. She will implement the grant partly at the University of Warsaw (co-beneficiary) and at Helmholtz Munich (host institution).

Source: Helmholtz Zentrum München