At the Longevity Summit Dublin 2024, Ivan de Weber, co-founder of Cortex Discovery, discussed how his company uses AI-driven cheminformatics to revolutionize drug discovery. Cortex Discovery leverages extensive data and machine learning to accelerate the identification of compounds that could enhance longevity. With successful projects in various therapeutic areas, including HIV and COVID-19, de Weber emphasized the importance of collaboration in advancing research on ageing and healthspan.

Key Points:

• Origin of Cortex Discovery: Ivan de Weber shared how his lifelong ambition to extend human lifespan led to the founding of Cortex Discovery. The company focuses on leveraging advanced cheminformatics and machine learning to accelerate drug discovery for longevity.
• Massive Data Aggregation: Cortex Discovery has compiled an enormous dataset of over 750 million data points on compounds and their properties. This includes measurements like drug activity and toxicity, providing a rich foundation for predictive modeling.
• Machine Learning in Drug Discovery: The company uses graph neural networks to predict the effects of compounds, analyzing multiple properties simultaneously. De Weber emphasized that these models can generate highly accurate predictions, comparable to real-world experiments.
• Success in Drug Screening: Cortex Discovery conducted successful proof-of-concept experiments, notably identifying compounds for HIV-1 inhibitors and COVID-19 treatments. They were able to predict the most active compounds with impressive accuracy.
• Cost-Effective Screening: By using virtual high-throughput screening, Cortex Discovery offers a service that is faster and up to 100 times cheaper than traditional laboratory methods. This enables more efficient identification of promising drug candidates.
• Focus on Longevity Research: De Weber’s current mission is to collaborate with researchers working on small molecules targeting longevity. He aims to advance discoveries in areas like senolytics, DNA repair, and ageing-related diseases through innovative data-driven approaches.