DeepMirror

DeepMirror is a UK-based company that has developed an AI-powered platform to accelerate the drug discovery process. Spun out from the University of Cambridge in 2019, the company was founded by Dr Max Jakobs, Dr Andrea Dimitracopoulos, and Dr Ryan Greenhalgh. The founders identified that a significant barrier to AI adoption in drug discovery was not the lack of advanced models but their accessibility to chemists.

The founding team combines expertise in physics, biology, and AI. Dr Max Jakobs, the CEO, has a Ph.D. in Neuroscience and Machine Learning from Cambridge University. Co-founder Dr Andrea Dimitracopoulos trained as a Biomedical Engineer and holds a Ph.D. in Theoretical Physics and Cell Biology from University College London. Dr Ryan Greenhalgh, the CTO, met his co-founders through the EnterpriseTECH STAR program at Cambridge in 2020 and has a background in Material Science and Engineering from the University of Manchester.

DeepMirror’s core product is a user-friendly, secure software platform that allows medicinal chemists at biotech and pharmaceutical companies to design and optimize drug molecules. The platform uses a combination of generative and predictive AI, including meta-learning and protein-ligand co-folding, to identify promising drug candidates, predict molecular properties like toxicity and activity, and overcome challenges in potency. This enables research and development teams to generate ideas for molecules with a higher probability of pre-clinical success, potentially reducing the time to get drugs into clinical trials. The business model is centered on providing access to the platform, allowing client companies to use the AI tools without needing to build their own infrastructure or relinquish intellectual property. Security is a key feature, with ISO 27001-certified infrastructure ensuring client data and discoveries remain private and protected.

Keywords: drug discovery, AI platform, medicinal chemistry, molecule design, generative AI, predictive AI, small molecules, biotech, pharmaceutical, lead optimization, ADMET prediction, pre-clinical research, University of Cambridge spin-out, computational chemistry, drug development, molecular property prediction, protein-ligand co-folding, hit-to-lead, life sciences AI