How AI Company Isomorphic Labs Is Working to Solve All Disease | Bloomberg Tech: Europe 9/12/2025

Isomorphic Labs: Revolutionizing Drug Discovery with AI

Key Concepts:

• AI-driven drug discovery
• Protein folding prediction (AlphaFold)
• Drug design engine
• Generative models
• Multi-modal approach
• Preclinical and clinical stages
• Target identification
• Molecular interactions
• Toxicity prediction
• Clinical trial optimization
• Personalized medicine

Isomorphic Labs' Mission and Progress

Isomorphic Labs, founded by Demis Hassabis (also head of Google DeepMind), aims to "solve all disease" by building a general AI platform to understand biology and chemistry for drug discovery. Their initial focus is on oncology and immunology due to favorable clinical aspects for new drugs and the platform's capabilities.

• Mission Statement: "To solve all disease."
• Current Stage: Preclinical, building the core platform and extending AlphaFold's capabilities.
• Internal Pipeline Focus: Oncology and immunology.
• Partnerships: Novartis and Eli Lilly.

The AI Drug Discovery Platform

Isomorphic Labs is developing a "drug design engine" capable of generating new molecule designs for various disease areas and modalities. This engine relies on multiple AI models, including advancements beyond AlphaFold.

• Drug Design Engine: A system for generating novel molecule designs for different diseases and modalities.
• AI Models: A suite of models, including those that go beyond AlphaFold, to understand molecular interactions and design new compounds.
• Generative Models: Used to efficiently search the vast molecular space (10 to the power of 60) and identify promising candidates.

AlphaFold and Beyond

AlphaFold, Google DeepMind's Nobel-Prize winning AI system, solved the protein folding problem. Isomorphic Labs is building upon this foundation with more advanced models that consider:

• Molecular Interactions: Understanding how molecules interact with different parts of the body.
• Toxicity Prediction: Predicting potential toxicity by analyzing interactions with all proteins in the body.
• Chemical Properties: Designing compounds with desired properties, including ADME (absorption, distribution, metabolism, and excretion) characteristics.

Speed and Efficiency

The AI platform aims to significantly reduce the time required for preclinical drug discovery, potentially from 3-6 years to a matter of months.

• Time Reduction Goal: Reduce preclinical drug discovery time from years to months.
• Focus: Initially on the drug discovery phase, with potential for AI to assist in clinical stages later.

Partnerships and Future Plans

Isomorphic Labs is collaborating with Novartis and Eli Lilly to validate its platform and identify new drug targets. The company is exploring various options for its future, including partnerships, licensing, and becoming a fully stacked biotech.

• Partnership Goals: Validate the platform and identify new drug targets.
• Partnership Expansion: Increased collaboration with Novartis and Eli Lilly from three to six targets.
• Future Options: Partnerships, licensing, or becoming a fully stacked biotech.

Multi-Modal Approach

Isomorphic Labs is taking a general approach, focusing on building a platform that can revolutionize drug discovery rather than focusing on a single disease or therapy.

• General Approach: Building a platform for revolutionizing drug discovery.
• Platform Capabilities: Aiming to discover hundreds of cures in the future.

The Role of Data

High-quality data is crucial for training effective AI models. While clinical and medical data can be messy and biased, AI can also be used to harmonize and improve data quality.

• Data Importance: Essential for training effective AI models.
• Data Challenges: Messy, biased, and containing missing information.
• AI's Role: Harmonizing and improving data quality.

Impact on the Pharmaceutical Industry

AI-driven drug discovery has the potential to change the balance of power in the pharmaceutical industry, with new startups emerging and challenging established players.

• Industry Transformation: New startups are challenging established pharmaceutical companies.
• Competition: Energizing the industry and leading to the development of new drugs.

Curing Cancer and Extending Lifespan

While curing cancer is a complex challenge due to its many forms, AI-driven drug discovery could lead to significant improvements in cancer treatment, potentially transforming it into a manageable chronic disease.

• Cancer Treatment Goals: Transform cancer into a manageable chronic disease with a normal lifespan.
• Lifespan Extension: Potential for elongated lifespans if the technology progresses as hoped.

Key Quotes

• Demis Hassabis: "The mission statement of Isomorphic Labs is to solve all disease."
• Demis Hassabis: "I do think A.I. will be one of the biggest technology that humanity will ever invent."
• Max Jaderburg: "We want to be building this machine that we can apply again and again on any target in any disease area even against, you know, any different modality."
• Mihaela van der Schaar: "I hope that this competition is going to energize everybody and provide exciting new drugs that will be solving a lot of current diseases that for which we can’t have a solution."

Technical Terms

• AlphaFold: An AI system developed by Google DeepMind that predicts the 3D structure of proteins from their amino acid sequence.
• Preclinical Stage: The stage of drug development before clinical trials in humans.
• Clinical Trials: Research studies that evaluate the safety and effectiveness of new drugs or treatments in humans.
• Modalities: Different types of therapeutic interventions, such as small molecules, antibodies, or gene therapies.
• Generative Models: AI models that can generate new data, such as novel molecule designs.
• ADME Properties: Absorption, distribution, metabolism, and excretion properties of a drug.
• AGI (Artificial General Intelligence): A hypothetical type of AI that possesses human-level cognitive abilities.

Conclusion

Isomorphic Labs is at the forefront of AI-driven drug discovery, aiming to revolutionize the process and develop new treatments for a wide range of diseases. By building a general AI platform and leveraging advancements in protein folding prediction and generative models, the company hopes to significantly reduce the time and cost of drug development and ultimately improve human health. While challenges remain, the potential impact of this technology is significant, with the possibility of transforming cancer treatment and extending lifespan.