Transforming cancer treatment with the power
of artificial intelligence and network biology

The past decade saw the rise of systems biology. This discipline seeks to understand complex biological phenomena like cancer by describing them as networks of interconnected nodes. We are at a time when sufficient research has finally accumulated to accurately model cell signaling and other mechanisms as networks. However, static networks cannot capture the highly interlinked cascades of processes that start when introducing a therapeutic intervention.

Only network dynamics - turning networks on - can simulate the complex cellular behavior of tumors. To date, only small scale networks of a few dozen proteins ready for dynamic simulation have been published. Combining findings from thousands of published papers, we created the first, high-definition virtual cell consisting of over 1300 proteins and their interactions.

Though this complex system can temporarily assume any state from untold billions of possibilities, over time they converge on a limited number of so-called attractor states. Research indicates that these attractors closely correspond to the observed phenotype of the given cells. In cancerous cells, proliferatory behavior dominates the attractor landscape. Turbine understands the way cancer works by modeling its cells on the molecular level millions of times, then using artificial intelligence to find patterns that best explain the simulated phenotypic behaviors. This understanding can be used in discovering new molecular patterns that mark diseased behavior, finding drugs that will have the strongest therapeutic potential, and predicting cancer's reaction to treatment.

Constructing the Simulated Cell

  • Turbine’s Simulated Cell is 10x the size of the largest published signaling network usable for dynamic simulations. It currently incorporates 1300+ proteins and other second messenger molecules and their over 3300 interactions. The network incorporates 38 important signaling pathways acting in cancerous cells, including MAPK, ErbB, Notch and Hedgehog, describing all hallmarks of cancer.

Customizing the Simulated Cell to cancer type and patient

  • The genomic and transcriptomic characteristics of cancer cells vary widely not just among patients, but often inside the same tumor as well. Turbine uses available OMICS data to customize the cell model to a cell line or patient sample, enabling simulations to closely mimic the actual, in vitro or in vivo interactions.

Compiling the simulation’s drug library

  • In simulated trials where cancer cells' reaction to a drug or a combination of drugs is relevant, the available drugs and their targets, with relative affinity (if available) are mapped to the Simulated Cell’s nodes.

Modeling biological activity with the Turbine simulator

  • The customized cancer cell model is brought to life by Turbine’s dynamic network simulator. The simulator models the behavior of the cell, by biologically accurately representing how signals propagate in the cell’s protein network. In addition to signaling pathway activity, Turbine's cell comes alive through representations of detailed molecular behavior, gene expression layers and phenotypic changes all integrated in one system. Turbine’s simulator incorporates interactions resulting in both translational and post-translational modifications.

Publications from the Turbine team