Novel methods for data integration in computational medicine

Abstract:  How can we combine multiple types of measurements to create a comprehensive view of a given disease? In this talk I will introduce a novel paradigm for data integration - patient networks. I will present our recently developed Similarity Network Fusion (SNF) to integrate genomic and other types of data for the same set of patients. Combining three biological data types, SNF substantially outperformed single data type analysis and other integrative approaches to identify cancer subtypes in five cancers. Patient networks made us think deeper about the problem of feature (e.g. gene) selection, diagnosis and prognosis for each individual patient.  I will thus present an alternative test for differential gene analysis and a novel patient-network based regularization of the Cox survival model. Finally, if the time permits, I will show how to use patient networks to integrate data in a non-negative matrix factorization (NMF) setting, efficiently extending the popular single-data type NMF approach for cancer subtyping.

Bio: Dr Goldenberg is a Scientist at the SickKids Research Institute in the Genetics and Genome Biology program and an Assistant Professor in the Department of Computer Science at the University of Toronto. Dr Goldenberg received her PhD in Machine Learning from Carnegie Mellon University focusing on structural learning in large graphical models. Her lab develops machine learning methods for problems in computational medicine. Her specific interests include methods for data integration and models that capture heterogeneity in complex human diseases.