# Looking for new antibiotic families.

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

Canonical: https://brightaifuture.com/discoveries/mrsa
Format: story
Source publication: 2023-12-20
Bright publication: 2026-09-05
Substantive update: None recorded
Evidence and review: Experimental; confidence: unassessed; source-checked; legacy source check. Legacy source check; no named human reviewer is recorded in this projection.

## The human problem

Drug resistance creates demand for new classes of antibiotics.

## The prior constraint

Laboratory screening cannot easily cover huge chemical libraries.

## AI’s actual role

Models predicted activity and highlighted chemical substructures.

## The documented result

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

## Why it may matter

The results offer starting points for drug development.

## Limitations

Preclinical findings do not demonstrate human safety or effectiveness.

## Unresolved questions

Optimize candidates and establish safety.

## Provenance and history

{
  "dates": {
    "eventDate": null,
    "publicationDate": "2023-12-20",
    "captureDate": null,
    "lastReviewedDate": "2026-09-05"
  },
  "provenance": {
    "origin": "legacy-projection",
    "externalId": "mrsa"
  },
  "revisions": [],
  "corrections": []
}

## Original sources

- [Discovery of a structural class of antibiotics with explainable deep learning](https://www.nature.com/articles/s41586-023-06887-8)

## Continue exploring

- [Concise evidence record](https://brightaifuture.com/discoveries/mrsa)