Elham Azizi, Department of Biomedical Engineering, Columbia University
Machine Learning for Modeling the Complex Tumor Microenvironment
Current cancer therapies succeed only in a subset of patients partly due to the heterogeneity of cells across and within tumors. Recent genomic technologies that measure cell features at the resolution of single cells, present exciting opportunities to study heterogeneity of cells and characterize unknown cell types in the complex tumor microenvironment. However, analyzing single-cell data involves significant statistical and computational challenges. I will present a set of statistical machine learning methods developed to address challenges such as handling sparsity and noise, distinguishing technical variation from biological heterogeneity and integration of different data modalities. I will also present novel biological insights obtained from applying these methods to multiple cancer systems. These results include identifying pre-cancerous cells that diverge from normal developmental trajectories, as well as immune cell subsets that are associated with response to immunotherapy.