Google DeepMind, Isomorphic Labs Predicts Over 200 Million Protein Structures

Google DeepMind, in collaboration with Isomorphic Labs, has predicted over 200 million protein structures using AlphaFold by training the model with nearly 100,000 known proteins, driving significant breakthroughs in drug discovery by targeting previously intractable biomedical challenges.

The protein prediction model can predict the 3D structure of proteins with incredible accuracy, aiming to design drugs that target specific proteins, unlocking treatments for diseases that were previously untreatable.

Recently, Google DeepMind also launched AlphaProteo, an AI system that generates novel proteins designed to bind to specific target molecules poised to significantly advance research in drug design, disease understanding and other health applications.

DeepMind is not the only active player in the market, ESMFold, Meta’s protein-folding model has also predicted about 772 Million protein structure.

Unfolding AlphaFold 3 

All of these developments come in the backdrop of Google DeepMind launching its AlphaFold 3 in May, 2024. The model has achieved a 50% improvement in predicting protein-molecule interactions, surpassing existing methods. This breakthrough, as highlighted by DeepMind CEO Demis Hassabis, marks a significant step towards designing drug compounds that bind to specific protein surfaces.

Hassabis envisions a future where AI-designed drugs can address hundreds of debilitating diseases, and Isomorphic Labs has the potential to become a multi-billion dollar business. The company’s recent partnerships with Eli Lilly & Co. and Novartis AG, valued at nearly $3 billion, underscore the commercial potential of AI in drug discovery.

Hassabise also emphasised the potential of AI in addressing global challenges. “The benefits of the generative AI models that we build, such as drug discovery and other areas, are going to far outweigh these costs,” he said. “It will increase the efficiency of power grids, invent new materials and technologies—including clean technologies, things like helping with fusion.”

Hassabis further highlighted the versatility of AI in various fields. “It can be applied to many of these areas and be extraordinarily productive,” he stated. “And far outweigh the costs and efforts involved in building these so it can be sustainable.”