Artykuł w czasopiśmie
Brak miniatury
Licencja
CC-BYCC-BY - Uznanie autorstwa
 

Discovering highly potent antimicrobial peptides with deep generative model HydrAMP

Uproszczony widok
cris.lastimport.scopus2024-02-12T20:16:25Z
dc.abstract.enAntimicrobial peptides emerge as compounds that can alleviate the global health hazard of antimicrobial resistance, prompting a need for novel computational approaches to peptide generation. Here, we propose HydrAMP, a conditional variational autoencoder that learns lower-dimensional, continuous representation of peptides and captures their antimicrobial properties. The model disentangles the learnt representation of a peptide from its antimicrobial conditions and leverages parameter-controlled creativity. HydrAMP is the first model that is directly optimized for diverse tasks, including unconstrained and analogue generation and outperforms other approaches in these tasks. An additional preselection procedure based on ranking of generated peptides and molecular dynamics simulations increases experimental validation rate. Wet-lab experiments on five bacterial strains confirm high activity of nine peptides generated as analogues of clinically relevant prototypes, as well as six analogues of an inactive peptide. HydrAMP enables generation of diverse and potent peptides, making a step towards resolving the antimicrobial resistance crisis.
dc.affiliationUniwersytet Warszawski
dc.contributor.authorSzczurek, Ewa
dc.contributor.authorKamysz, Wojciech
dc.contributor.authorSetny, Piotr
dc.contributor.authorSroka, Jacek
dc.contributor.authorMichalski, Michał
dc.contributor.authorSikora, Karol
dc.contributor.authorNeubauer, Damian
dc.contributor.authorBauer, Marta
dc.contributor.authorJurczak, Radosław
dc.contributor.authorGrzegorzek, Tomasz
dc.contributor.authorMożejko, Marcin
dc.contributor.authorSzymczak, Paulina
dc.date.accessioned2024-01-24T21:54:31Z
dc.date.available2024-01-24T21:54:31Z
dc.date.copyright2023-03-15
dc.date.issued2023
dc.description.accesstimeAT_PUBLICATION
dc.description.financeŚrodki finansowe przyznane na realizację projektu w zakresie badań naukowych lub prac rozwojowych
dc.description.number1
dc.description.versionFINAL_PUBLISHED
dc.description.volume14
dc.identifier.doi10.1038/S41467-023-36994-Z
dc.identifier.issn2041-1723
dc.identifier.urihttps://repozytorium.uw.edu.pl//handle/item/104968
dc.identifier.weblinkhttps://www.nature.com/articles/s41467-023-36994-z.pdf
dc.languageeng
dc.pbn.affiliationbiological sciences
dc.relation.ispartofNature Communications
dc.relation.pages1453: 1-23
dc.rightsCC-BY
dc.sciencecloudnosend
dc.subject.enComputational models
dc.subject.enMachine learning
dc.subject.enProtein design
dc.titleDiscovering highly potent antimicrobial peptides with deep generative model HydrAMP
dc.typeJournalArticle
dspace.entity.typePublication