Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.05181 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914450739560448 |
|---|---|
| author | Rector-Brooks, Jarrid Lambert, Théophile Skreta, Marta Roth, Daniel Long, Yueming Li, Zi-Qi Zhang, Xi Cretu, Miruna Li, Francesca-Zhoufan Ganapathy, Tanvi Jin, Emily Bose, Avishek Joey Yang, Jason Neklyudov, Kirill Bengio, Yoshua Tong, Alexander Arnold, Frances H. Liu, Cheng-Hao |
| author_facet | Rector-Brooks, Jarrid Lambert, Théophile Skreta, Marta Roth, Daniel Long, Yueming Li, Zi-Qi Zhang, Xi Cretu, Miruna Li, Francesca-Zhoufan Ganapathy, Tanvi Jin, Emily Bose, Avishek Joey Yang, Jason Neklyudov, Kirill Bengio, Yoshua Tong, Alexander Arnold, Frances H. Liu, Cheng-Hao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_05181 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | General Multimodal Protein Design Enables DNA-Encoding of Chemistry Rector-Brooks, Jarrid Lambert, Théophile Skreta, Marta Roth, Daniel Long, Yueming Li, Zi-Qi Zhang, Xi Cretu, Miruna Li, Francesca-Zhoufan Ganapathy, Tanvi Jin, Emily Bose, Avishek Joey Yang, Jason Neklyudov, Kirill Bengio, Yoshua Tong, Alexander Arnold, Frances H. Liu, Cheng-Hao Machine Learning 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. |
| title | General Multimodal Protein Design Enables DNA-Encoding of Chemistry |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2604.05181 |