Looking for new antibiotic families.

Researchers used explainable deep learning to identify a structural class of antibiotic candidates.

Experimental · source published 2023-12-20

The human problem

Drug resistance creates demand for new classes of antibiotics.

Laboratory screening cannot easily cover huge chemical libraries.

Models predicted activity and highlighted chemical substructures.

Candidate compounds showed antibacterial activity, including tests in mouse models.

The results offer starting points for drug development.

Preclinical findings do not demonstrate human safety or effectiveness.

Optimize candidates and establish safety.

Source history & evidence assessment

Legacy source check; no named human reviewer is recorded in this projection.

Maturity describes the tested or operational setting. Confidence describes support for the particular claim; one does not determine the other.

Institutions: MIT & collaborators

Editorial connections between distinct settings and results; these links do not imply replication.

No corrections recorded.