The National Cancer Institute (NCI)is collaborating with GNS Healthcare, a subsidiary of Via Science, a healthcare IT company that applies machine learning and simulation technology to optimize patient treatment, to accelerate lung cancer research with a supercomputing platform that can rapidly uncover cause-and-effect mechanisms hidden in huge data sets assembled from imaging, genetics, pathology, and other areas. The results could help predict which patients will respond to a given treatment.
As part of the collaboration, GNS Healthcare will analyze NCI data from the laboratory of Terry van Dyke, Ph.D., Director of the Center for Advanced Preclinical Research (CAPR) at NCI. The is developing a comprehensive preclinical trial framework for evaluating the anti-tumor efficacy and selectivity, biodistribution, and metabolism of early-stage candidate drugs using genetically engineered mouse (GEM) models. The collaboration will focus on genetically modified mouse models of non-small cell lung cancer (NSCLC).
This collaboration will utilize GNS’s supercomputer-driven REFS? platform which includes integrated machine learning algorithms and software that extract “causal” relationships from complex, multi-dimensional data and enable the simulation of billions of “what if?” hypotheses to explore novel unseen conditions and predictions forward in time. This model-centric discovery and simulation approach represents a paradigm shift in data analysis, leapfrogging existing approaches such as high-dimensional pattern matching.
The technology will be used to build computer models of NSCLC in a hypothesis-free, unbiased manner that will be simulated to identify key molecular mechanisms of NSCLC. The goal is to identify biomarkers and biological mechanisms that will lead to better matching of drugs to patients and new effective drugs in NSCLC.
“GNS is excited to be deploying our supercomputer-driven REFS platform to enable the maximal extraction of actionable knowledge from the rich lung cancer datasets generated by the NCI,” said GNS Executive Vice President and Co-Founder Dr. Iya Khalil. “Combined with the expertise of our NCI colleagues in lung cancer biology and in designing powerful experiments to uncover its key mechanisms, we are creating the opportunity to provide better outcomes for lung cancer patients.”
The data used in the collaboration includes the experimental assessment of transcriptomic and MRI data relating to NSCLC induction, regression and combination drug treatments. Starting from this data, GNS will use the REFS platform to reverse-engineer network models from the data that connect drug doses to transcriptional and imaging measurement networks to endpoints. The results from millions of in silico simulations of these models will provide unique insights into the fundamental mechanisms of NSCLC and its response to drug treatments, enabling the development of more effective treatments for NSCLC.
Additional computational modeling
The initial phase of this project is also intended to help GNS and NCI develop standards for the exchange of data to conduct future collaborations in other relevant mouse model systems. From this starting point, the groups envision the possibility of a combined experimental and computational work flow aimed at rapidly enabling the generation of hypotheses, testing these hypothesis in silico and in vivo, generating new confirmatory data, and rapidly cycling back to additional computational modeling, with the goal of accelerating the conversion of knowledge into new clinical options for cancer patients.
This project is being partially funded with Federal funds from the National Cancer Institute, National Institutes of Health.