General Multimodal Protein Design Enables DNA-Encoding of Chemistry

TL;DR

DISCO is a multimodal deep generative model that co-designs protein sequences and structures to create novel enzymes capable of catalyzing new-to-nature reactions, with high activity and evolvability.

Contribution

Introduces DISCO, a scalable multimodal model for protein design that enables creation of enzymes with novel active sites and catalytic functions from reactive intermediates.

Findings

Designed heme enzymes catalyzing new-to-nature reactions with high activity.

DISCO's enzyme designs outperform engineered enzymes in activity.

Directed mutagenesis further improved enzyme activity.

Abstract

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.