3.4 A Deep Learning Approach to Antibiotic Discovery

A trained deep neural network predicts antibiotic activity in molecules that are structurally different from known antibiotics, among which Halicin exhibits efficacy against broad-spectrum bacterial infections in mice. More details can be found at (Stokes et al. 2020)

Figure from (Stokes et al. 2020)

• A deep learning model is trained to predict antibiotics based on structure
• Halicin is predicted as an antibacterial molecule from the Drug Repurposing Hub
• Halicin shows broad-spectrum antibiotic activities in mice
• More antibiotics with distinct structures are predicted from the ZINC15 database

References

Stokes, Jonathan M, Kevin Yang, Kyle Swanson, Wengong Jin, Andres Cubillos-Ruiz, Nina M Donghia, Craig R MacNair, et al. 2020. “A Deep Learning Approach to Antibiotic Discovery.” Cell 180 (4): 688–702.