About the partner: Established in 2016 by Hungarian founders and reinforced by global industry expertise in leadership, Turbine is virtualizing biological experiments with AI to accelerate discovery and clinical decisions. We have spent the last decade building virtual disease models to outscale any lab, making complex biological experiments faster, more cost-effective, and translatable into the clinic. Our vision is that these models will ultimately become second only to the patient in predicting drug response. By simulating how cells and tissues behave under treatment, Turbine helps our partners identify the right therapeutic ideas smarter and faster, cutting years of dead-end research and reducing late-stage clinical failure caused by poor efficacy. Scientists can now run billions of virtual experiments to uncover risk, design smarter trials, and scale decisions across entire pipelines. Validated through partnerships with Bayer, AstraZeneca, MSD and others, Turbine’s platform has supported over 30 research programs. Backed by Accel, MSD Global Health Innovation Fund, we are putting predictive simulations in the hands of every scientist.
Principal investigator : Daniel Veres, MD, PhD.
Persons involved:
- Daniel Veres, MD, PhD
- Jerzy Woznicki, PhD
Role within Consortium: Turbine will execute Work Package 5 (WP5).
Task Description:
- WP5: Single cell deconvolution and in silico mechanism elucidation. Turbine’s Simulated Cell™ technology will be applied to build virtual melanoma patient avatars customizable with the refined subtyping of the Human Melanoma Proteome Atlas (HMPA) samples. These avatars will enable in silico identification & validation of drug target-biomarker pairs, while also uncovering pathway-level mechanisms of sensitivity. To address therapeutic challenges arising from disease heterogeneity, we will further explore discrete melanoma cellular states using single-cell deconvolution to predict additional vulnerabilities. Collectively, Turbine aims to accelerate target–biomarker selection by providing a robust, predictive modeling framework of melanoma patient responses.