# An enzyme for a plastic problem.

Scientists used machine learning to help engineer an enzyme that breaks down PET plastic.

Canonical: https://brightaifuture.com/discoveries/petase
Format: discovery
Source publication: 2022-04-27
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

PET waste is difficult to return to reusable chemical building blocks.

## The prior constraint

Enzymatic recycling is constrained by activity and operating conditions.

## AI’s actual role

A model guided protein mutations for improved performance.

## The documented result

Engineered enzymes demonstrated PET depolymerization in laboratory experiments.

## Why it may matter

A possible component of improved recycling processes.

## Limitations

Laboratory success does not establish industrial economics or a solution for all plastics.

## Unresolved questions

Evaluate scale, energy use, and realistic waste streams.

## Provenance and history

{
  "dates": {
    "eventDate": null,
    "publicationDate": "2022-04-27",
    "captureDate": null,
    "lastReviewedDate": "2026-09-05"
  },
  "provenance": {
    "origin": "legacy-projection",
    "externalId": "petase"
  },
  "revisions": [],
  "corrections": []
}

## Original sources

- [Machine learning-aided engineering of hydrolases for PET depolymerization](https://www.nature.com/articles/s41586-022-04599-z)

## Continue exploring

- [Frontier](https://brightaifuture.com/worlds/frontier)
- [Where can human judgment go with a new instrument?](https://brightaifuture.com/threads/discovery)
- [Extended story and historical record](https://brightaifuture.com/stories/an-enzyme-for-a-plastic-problem)
- [Open this record in the interactive world](https://brightaifuture.com/?event=petase)