Enzymes with working catalytic machinery designed from scratch
Enzymes with working catalytic machinery designed from scratch is graded peer reviewed on whataifound.org, with the AI's role graded search scaffold.
Diffusion-based protein design produced serine hydrolases with catalytic efficiencies up to 2.2 × 10⁵ M⁻¹s⁻¹ on five folds unlike any natural serine hydrolase, with crystal structures matching the design models to under 1 Å.
- Verification
- Peer reviewed
- Autonomy
- Search scaffold
- Lab
- Institute for Protein Design, University of Washington
- Model
- RFdiffusion with PLACER ensemble scoring
- Field
- Chemistry
- Date
- 2025-02-13
- Human collaborators
- Anna Lauko, David Baker
What was found
An enzyme needs more than the right shape: its active site has to stay organised at every step of the reaction, which is where designed enzymes have historically failed. The team generated backbones with RFdiffusion from a minimal active-site description, then used an ensemble-generation network to check that the catalytic geometry held along the whole reaction coordinate, keeping only designs that passed. The resulting hydrolases approach natural catalytic efficiency on folds not found among natural serine hydrolases, and the crystal structures match the designs closely. Published in Science.
Novelty check
De novo enzyme design dates to the 2000s — Kemp eliminases, retro-aldolases — but designed enzymes were typically orders of magnitude slower than natural ones and needed directed evolution to become useful. The advance is reaching this efficiency with multi-step catalytic machinery by design rather than by evolution.
Caveats
Serine hydrolases are a comparatively tractable target with a well-understood catalytic triad; the result does not generalise automatically to harder chemistry. Efficiencies remain below the best natural hydrolases. The per-round success rate is low and the paper reports the screening funnel. The reaction, the active-site description and the assays were human-specified, which is why autonomy is search-scaffold.
Sources
How this is graded
whataifound.org grades every entry on two axes: verification (how solid the result is, from a machine-checked proof down to refuted) and autonomy (how much the AI did versus its human collaborators). This finding is peer reviewed and search scaffold. Full definitions are in the methodology.
Cite this entry
whataifound.org (2025). Enzymes with working catalytic machinery designed from scratch. whataifound.org: A Registry of AI Scientific and Mathematical Discoveries. https://whataifound.org/finding/2025-02-13-designed-serine-hydrolases