Drug discovery is costly, time consuming, model systems have poor translation rates to patients and do not significantly reduce the risk of failure in the clinic. Before running any wet lab experiments, Turbine computationally simulates tumor cell behavior in patients to understand the complex mechanisms driving the disease. Observing these in silico experiments, our biologists and translational experts gain insight into the molecular context by which therapies can potentially lead to patient benefit. Our benchmarks show that augmenting R&D with simulations could prevent 2 out of 3 failed experiments in vitro (controlled cell cultures) and every 2nd failure in vivo (tissues in living organisms).
With the world’s first cell simulation platform augmented by interpretable machine learning, we map and model how thousands of signaling proteins interact characterizing cellular level cancer behavior and response or resistance to treatment. This approach will potentially allow us to predict not only what works in cells, mice and people but more importantly, why and how. Hundreds of millions of iterated simulations are filtered, translated, then validated by our proprietary experimental assays to confirm predictions while improving the underlying Simulated Cell™ through a continuous learning loop.
During my talk, I will cover what kind and quality of input data is needed to construct an in silico experiment representative of real life biology and how machine learning can be used to build an interpretable model.
Robert is a Machine Learning Engineering Lead at Turbine.ai working on unlocking biology by applying engineering disciplines to decrease cost, provide reproducibility, and answer "why?" in drug discovery.He holds a Ph.D., summa cum laude, in Engineering and Technology from the Budapest University of Technology and Economics. In his dissertation, he broadened the set of mathematical tools used for ...