English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

New antibiotics are needed to battle growing antibiotic resistance, but thedevelopment process from hit, to lead, and ultimately to a useful drug, takesdecades. Although progress in molecular property prediction usingmachine-learning methods has opened up new pathways for aiding the antibioticsdevelopment process, many existing solutions rely on large datasets and findingstructural similarities to existing antibiotics. Challenges remain in modellingof unconventional antibiotics classes that are drawing increasing researchattention. In response, we developed an antimicrobial activity prediction modelfor conjugated oligoelectrolyte molecules, a new class of antibiotics thatlacks extensive prior structure-activity relationship studies. Our approachenables us to predict minimum inhibitory concentration for E. coli K12, with 21molecular descriptors selected by recursive elimination from a set of 5,305descriptors. This predictive model achieves an R2 of 0.65 with no priorknowledge of the underlying mechanism. We find the molecular representationoptimum for the domain is the key to good predictions of antimicrobialactivity. In the case of conjugated oligoelectrolytes, a representationreflecting the 3-dimensional shape of the molecules is most critical. Althoughit is demonstrated with a specific example of conjugated oligoelectrolytes, ourproposed approach for creating the predictive model can be readily adapted toother novel antibiotic candidate domains.

Predicting antimicrobial activity of conjugated oligoelectrolyte molecules via machine learning