Photo by diana_pole from unsplash
Discovering new antibiotics capable of tackling resistant bacteria is increasingly difficult. Stokes et al. train a deep neural network model to predict molecules with antibacterial activity. Applying the model to… Click to show full abstract
Discovering new antibiotics capable of tackling resistant bacteria is increasingly difficult. Stokes et al. train a deep neural network model to predict molecules with antibacterial activity. Applying the model to the Drug Repurposing Hub identified the JNK inhibitor, halicin, which is structurally distinct from conventional antibiotics. Halicin inhibited growth of a wide spectrum of pathogens in vitro and was highly effective against Clostridium difficile and pan-resistant Acinetobacter baumannii infections in mice. Applying the model to the much larger ZINC15 database rapidly identified two structurally novel antibacterials with powerful broad-spectrum activity.
Journal Title: Nature Reviews Drug Discovery
Year Published: 2020
Link to full text (if available)
Share on Social Media: Sign Up to like & get
recommendations!