DISCO — Teaching AI to Invent Enzymes Nature Never Imagined

DISCO is a multimodal generative model that co-designs protein sequence and 3D structure to create entirely new enzymes for reactions never seen in biology.

DISCO — Teaching AI to Invent Enzymes Nature Never Imagined Your browser does not support the video tag. Figure 1. DISCO simultaneously generates protein sequence and 3D structure around a molecular target. The sequence is progressively unmasked with self-correction while the backbone co-folds with the conditioning molecule. 01 — The Challenge Nature's Chemistry — and Beyond Evolution is the greatest chemist the world has ever known. Over billions of years, it has crafted enzymes of breathtaking precision, molecular machines that accelerate reactions by factors of millions, under the gentlest

saved by

• Brooke Joseph

related reading

• Highly accurate protein structure prediction with AlphaFoldnature.com
• Engineering Plastic-Degrading Enzymes and PCSK9 Binders with Protein AI Toolsblog.latch.bio
• Protein World Model | Biohubbiohub.ai
• One-shot design of functional protein binders with BindCraftnature.com
• AlphaProteo generates novel proteins for biology and health researchdeepmind.google
• Language models of protein sequences at the scale of evolution enable accurate structure predictionbiorxiv.org
• Google DeepMind and Isomorphic Labs introduce AlphaFold 3 AI modelblog.google
• AlphaFolddeepmind.google
• [2502.06914] UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site Knowledgearxiv.org
• Anthrogenanthrogen.com
• Fast and Ultra-Capable Protein Design: Advancing the Frontier Through Atomistic SE(3)-Equivariance with Genie 3biorxiv.org
• AlphaFold: a solution to a 50-year-old grand challenge in biologydeepmind.com