An enzyme for a plastic problem.
Scientists used machine learning to help engineer an enzyme that breaks down PET plastic.
Original sources ↓ · Revision history ↓
Experimental · source published 2022-04-27
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.
Source history & evidence assessment
- Maturity
- Experimental
- Claim confidence
- unassessed
- Event date
- Not recorded
- Source published
- 2022-04-27
- Captured
- Not recorded
- Last source review
- 2026-09-05
- Editorial method
- Original source check
- Place / relevance
- Austin, United States · institution-location
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.
Original sources
Machine learning-aided engineering of hydrolases for PET depolymerization ↗ · paper
Institutions: University of Texas at Austin
Explore the underlying question
Related developments
Editorial connections between distinct settings and results; these links do not imply replication.
Revision & correction history
No corrections recorded.