Turbine, a leading biological simulation company building a platform for interpreting human biology in silico, today announced it has entered into a collaboration with AstraZeneca (LSE/STO/Nasdaq: AZN), a global biopharmaceutical company.
Turbine will use its proprietary Simulated Cell™ platform to identify and understand mechanisms of resistance to therapy in hematological cancers. The collaboration will focus on understanding resistance mechanisms resulting from altered protein-protein interactions, which could enable more personalized treatment regimens based on each patient’s molecular profile. Financial terms of the collaboration are not disclosed.
“Over the past several years, Turbine has been working with researchers at AstraZeneca to evaluate our platform’s ability to identify mechanisms and potential biomarkers of response or resistance to personalized treatment combinations,” said Szabolcs Nagy, Chief Executive Officer and Co-Founder of Turbine. “The collaboration announced today builds on the promise our platform has shown and will see us apply this technology to answer new questions about molecular alterations that give rise to drug resistance and how they could be overcome. We’re excited about the opportunity to expand our collaboration with AstraZeneca with the aim of supporting the development of better, more durable therapies for the patients who need them.”
Turbine and AstraZeneca previously collaborated using an earlier version of the Simulated Cell to predict combination synergy and relevant biomarker candidates involving DNA Damage Repair mechanisms. In this study, the team evaluated hundreds of drug combinations in multiple cancers and demonstrated that the platform is capable of predicting their effect, without training on the experimental data itself. Simulations were used to identify potential mechanisms underlying the synergy between combinations of cancer treatments, revealing biomarkers of response and resistance that could be translated into clinical practice. The results of these studies, which demonstrated that Turbine’s platform matches the predictivity while adding deeper insights into the biological complexity of response mechanisms, have been posted to the bioRxiv preprint server and have been submitted for publication in a peer-reviewed journal.
Based in London with offices in Budapest, Hungary and Cambridge, UK, Turbine was founded in 2016 by Kristof Szalay Ph.D., Daniel Veres, M.D., Ph.D., Szabolcs Nagy and Ivan Fekete, M.D. The team’s vision is to overcome the limitations in developing oncology treatments with true patient benefit by building the world’s first predictive simulation of human biology through combining machine learning and molecular biology.
Turbine’s Simulated Cell™ is an interpretable cell simulation platform that captures patient biology better than currently available models, and is used for in silico experiments at scales impossible in physical assays. From billions of simulated experiments, the team uncovers novel hypotheses and the mechanisms underlying them. Simulations are validated in Turbine’s state-of-the-art laboratory facility and the resulting data is fed back to train an ever expanding and more predictive simulation of human biology. The Simulated Cells can be integrated into all steps of biopharma R&D to boost its likelihood of success, from identifying novel targets invisible to high throughput biological screening to optimally targeting existing therapies at the most responsive patients.
Simulations have already been validated from target discovery to patient stratification and life cycle management through Turbine’s proprietary pipeline and collaborations with multiple big pharma companies and research institutions, including Bayer, Ono Pharmaceutical and Cancer Research Horizons. Turbine’s latest investment round (Series A) was closed in 2022 and co-led by MSD (Merck & Co., Inc., Rahway NJ, USA) Global Health Innovation Fund, MassMutual Ventures and Mercia Asset Management, who were joined by existing investors Accel, Delin Ventures, and XTX Ventures.back