Atom-level enzyme active site scaffolding using RFdiffusion2

Designing new enzymes typically begins with idealized arrangements of catalytic functional groups around a reaction transition state, then attempts to generate protein structures that precisely position these groups. Current AI-based methods can create active enzymes but require predefined residue positions and rely on reverse-building residue backbones from side-chain placements, which limits design flexibility. Here we show that a new deep generative model, RoseTTAFold diffusion 2 (RFdiffusion2), overcomes these constraints by designing enzymes directly from functional group geometries without specifying residue order or performing inverse rotamer generation. RFdiffusion2 successfully generates scaffolds for all 41 active sites in a diverse benchmark, compared to 16 using previous methods. We further design enzymes for three distinct catalytic mechanisms and identify active candidates after experimentally testing fewer than 96 sequences in each case. These results highlight the potential of atomic-level generative modeling to create de novo enzymes directly from reaction mechanisms.

Authors

Institutions

Publication Details

Journal
Nature Methods
Published
2025-12-03
DOI
https://doi.org/10.1038/s41592-025-02975-x
Citations
17
Primary Topic
Protein Structure and Dynamics
Type
article
Field-Weighted Citation Impact
13.70

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Atom-level enzyme active site scaffolding using RFdiffusion2

Indrek Kalvet, Brian Coventry, Woody Ahern, Regina Barzilay et al.
17 citations
Nature Methods
Protein Structure and Dynamics
13.70
article

Atom-level enzyme active site scaffolding using RFdiffusion2

Indrek Kalvet, Brian Coventry, Woody Ahern, Regina Barzilay, Yakov Kipnis, Donghyo Kim, Han Altae-Tran, Doug Tischer, Rohith Krishna, Magnus S. Bauer, Tommi Jaakkola, David A. Baker, Jason Yim, Seth M. Woodbury, Saman Salike
article en
17 citations

Abstract

Designing new enzymes typically begins with idealized arrangements of catalytic functional groups around a reaction transition state, then attempts to generate protein structures that precisely position these groups. Current AI-based methods can create active enzymes but require predefined residue positions and rely on reverse-building residue backbones from side-chain placements, which limits design flexibility. Here we show that a new deep generative model, RoseTTAFold diffusion 2 (RFdiffusion2), overcomes these constraints by designing enzymes directly from functional group geometries without specifying residue order or performing inverse rotamer generation. RFdiffusion2 successfully generates scaffolds for all 41 active sites in a diverse benchmark, compared to 16 using previous methods. We further design enzymes for three distinct catalytic mechanisms and identify active candidates after experimentally testing fewer than 96 sequences in each case. These results highlight the potential of atomic-level generative modeling to create de novo enzymes directly from reaction mechanisms.

Nature MethodsVol. 23(1)
Howard Hughes Medical Institute (US), University of Washington (US), PDL BioPharma (United States) (US), Massachusetts Institute of Technology (US)
National Science Foundation, Bill and Melinda Gates Foundation, Sanofi, Open Philanthropy Project, Defense Advanced Research Projects Agency, Defense Threat Reduction Agency
Openalex Percentile: Top 1%
Protein Structure and Dynamics
13.70
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.