Search papers, labs, and topics across Lattice.
DISCO, a novel multimodal diffusion model, co-designs protein sequence and 3D structure conditioned on reactive intermediates to generate enzymes. The model uses inference-time scaling methods to optimize objectives across sequence and structure modalities. DISCO successfully designed heme enzymes that catalyze new-to-nature carbene-transfer reactions, demonstrating activities exceeding those of engineered enzymes and confirming evolvability via random mutagenesis.
DNA can now encode entirely new-to-nature enzymatic reactions, thanks to a generative model that designs proteins around user-specified chemistries.
Evolution is an extraordinary engine for enzymatic diversity, yet the chemistry it has explored remains a narrow slice of what DNA can encode. Deep generative models can design new proteins that bind ligands, but none have created enzymes without pre-specifying catalytic residues. We introduce DISCO (DIffusion for Sequence-structure CO-design), a multimodal model that co-designs protein sequence and 3D structure around arbitrary biomolecules, as well as inference-time scaling methods that optimize objectives across both modalities. Conditioned solely on reactive intermediates, DISCO designs diverse heme enzymes with novel active-site geometries. These enzymes catalyze new-to-nature carbene-transfer reactions, including alkene cyclopropanation, spirocyclopropanation, B-H, and C(sp$^3$)-H insertions, with high activities exceeding those of engineered enzymes. Random mutagenesis of a selected design further confirmed that enzyme activity can be improved through directed evolution. By providing a scalable route to evolvable enzymes, DISCO broadens the potential scope of genetically encodable transformations. Code is available at https://github.com/DISCO-design/DISCO.
Mila