Dr. Schadt provides an overview of how his team organizes very large scale data across many different types, and then integrates these data using sophisticated mathematical algorithms to construct predictive network models of disease. This approach well complements the type of natural artificial intelligence/machine learning approaches that have become nearly standard in the life and biomedical sciences for building classifiers for a whole range of problems (disease classification, subtype classification, drug response classification, and so on). By building a causal network model that spans multiple scales (from the molecular to the cellular, to the tissue/organ, to the organism and community) we can understand the flow of information and how best to modulate that flow to improve human wellbeing, whether better diagnosing and treating disease or improving overall health. Examples of building these predictive network models across a range of diseases are given, covering areas such as Alzheimer’s disease, inflammatory bowel disease, and diabetes.
Dr. Schadt also discusses the application of this type of modeling in the cancer arena where interpreting any given cancer case in the context of the digital universe of information relating to the cancer of interest is carried out using predictive network models to inform on personalized treatment options for a given patient, including personalized vaccines or novel drug combinations.