DeepMirror

deepmirror is an AI-powered drug discovery platform designed to accelerate hit-to-candidate molecule design. By combining human ingenuity with artificial intelligence, deepmirror empowers medicinal chemists and drug discovery teams to tap into broad industry data and cutting-edge AI expertise — all while keeping proprietary data and intellectual property fully secure. The platform is trusted by more than 100 organisations worldwide, spanning pharmaceutical companies, biotechs, and academic institutions.

deepmirror serves a wide range of users, from senior medicinal chemists at established drug makers to academic researchers, enabling teams of all experience levels to deploy powerful machine learning approaches in a fraction of the time traditionally required. Notable customers and collaborators include Tes Pharma, Curie.Bio, Cerevance, Morphic, the University of Manchester, and the Sanders Tri-Institutional Therapeutics Discovery Institute, as well as a partnership with Collaborative Drug Discovery for humanitarian and commercial drug discovery programs.

Core Platform Capabilities

• Generative AI: Explore chemical space at scale to generate novel molecular ideas and candidates that exist beyond standard libraries, revealing high-quality molecules that would otherwise remain hidden.
• Data-Driven Models: Build high-quality ligand-based models of potency and ADMET properties. Teams can leverage their own proprietary data to predict experimental outcomes with higher accuracy before committing to synthesis.
• Structure-Guided Design: Use advanced structure-based design and cofolding algorithms — including support for models such as AlphaFold3, OpenFold3, Boltz-2, and Chai-1 — to validate design hypotheses, understand binding modes, and refine interactions between ligands and protein targets.

Key Use Cases and Demonstrated Results

• Tes Pharma used deepmirror to screen 1 billion molecules against cancer targets in just a few hours, unlocking novel chemotypes against one of the toughest target classes in drug discovery.
• Tes Pharma also applied the deepmirror App to predict the experimental biological activity of an entire proprietary library, successfully identifying and validating novel active scaffolds.
• The platform has been used to obtain actionable solubility predictions, supporting ADMET-focused decision-making in early drug discovery.
• deepmirror enables structure enablement workflows by leveraging empirical data alongside AI structure prediction models to develop testable design hypotheses for lead compounds.
• The generative AI module has been shown to produce chemically sensible suggestions suitable for synthesis and biological testing.
• Collaboration with MMV (Medicines for Malaria Venture) demonstrates the platform's application in advancing global health research.

Security and Compliance

• Enterprise-grade encryption: All data is encrypted in transit and at rest using modern, highly secure protocols.
• Complete data privacy: User data and models remain strictly private and are never shared without explicit permission.
• ISO 27001 certified: deepmirror's infrastructure, engineering practices, and policies meet rigorous international security standards, verified by independent audits.
• The platform's Trust Center provides detailed documentation of its security posture, giving enterprise customers confidence in protecting their most valuable intellectual property.

Team and Advisors

• deepmirror was co-founded by Max Jakobs (CEO), Andrea Dimitracopoulos (COO), and Ryan Greenhalgh (CTO), with a multidisciplinary team spanning molecular AI, research engineering, and software development.
• The advisory board includes Pat Walters (ex-Chief Data Officer, Relay Therapeutics), Mark Murcko (Board Advisor), Katerina Leftheris (ex-Director of Chemistry, BMS), Maria-Jesus Blanco (Head of Drug Discovery, Atavistik Bio), Darren Green (ex-Director of Cheminformatics, GSK), and Jérémy Besnard (Co-founder, Exscientia).

deepmirror is committed to making AI an invisible but powerful partner in the drug discovery process — enhancing chemist creativity and human potential so that teams can spend less time on guesswork and more time delivering impact for patients.