Machine learning for multiomics analysis of biological systems in translational settings.

About this Class

Recent technological advances in science provide novel opportunities to unravel the complex biology of diseases. Immunological changes in translational settings are often highly dynamic and involve multiple interconnected biological systems. We will discuss a series of machine learning innovations which enable objective analysis of single-cell immunologic data robust to small variations in patient cohort, as well as integration with prior knowledge to increase predictive power without increasing cohort size. Next, we will discuss integration of single cell data into a multiomics setting using a customized machine learning algorithm. This computational pipeline increases predictive power and reveals new biology, by combining datasets of various sizes and modularities in a balanced manner. Finally, we will discuss the use of machine learning algorithms for integration of biological profiling with social determinants of health and electronic health records for identification of non-biological modifiable factors. Bio: Nima Aghaeepour is an Assistant Professor at Stanford University. His laboratory develops machine learning and artificial intelligence methods to study clinical and biological modalities in translational settings.  He is primarily interested in leveraging multiomics studies, wearable devices, and electronic health records to address global health challenges. His work is recognized by awards from numerous national and international organizations including the Bill and Melinda Gates Foundation, the March of Dimes Foundation, the Burroughs Wellcome Fund, the National Institute of General Medical Sciences, and the National Center for Advancing Translational Sciences.