Machine Learning for Modeling Dynamics of Immune Cell States
In the upcoming NIAID Data Science Seminar, Columbia University’s Dr. Elham Azizi will present a set of machine learning (ML) methods appropriate not only for studying immune cell states in clinical cohorts but also cancer systems.
Despite the opportunities presented by genomic and imaging technologies (including their roles in driving response to therapies), analyzing and integrating single-cell data across patients, time points, and data modalities has its statistical and computational challenges. As a result, these ML methods have been developed to address such challenges (e.g., distinguishing technical variation from biological heterogeneity, inferring temporal dynamics of immune states in clinical cohorts, etc.). Moreover, when applied to cancer systems, they’ve yielded novel biological insights. Such results include continuous expansion of immune cells when (1) interfacing with breast tumors, and (2) detecting key exhausted T cell subsets with divergent temporal dynamics that define response to immunotherapy in leukemia.
This seminar is open to the public, but registration is required. If you need interpreting services and/or other reasonable accommodations to participate in this event, contact NIAIDODSET@niaid.nih.gov.
Dr. Elham Azizi is a Herbert and Florence Irving Assistant Professor of Cancer Data Research at the Irving Institute for Cancer Dynamics of Columbia University. She is also an assistant professor of biomedical engineering.
Upcoming Events
-
Predicting Patients’ Response to Immunotherapy from Tumor Histopathology and Blood: Computational Science in Immuno-oncologyJuly 08, 2025Data Jamboree: Enhancing Childhood Cancer Data Sharing and UtilitySeptember 29, 2025 - September 30, 2025NCI Office of Data Sharing’s Annual Data Sharing Symposium 2025: How Data Advances the Impact of Cancer ResearchSeptember 30, 2025 - October 01, 2025Childhood Cancer Data Initiative (CCDI) Symposium 2025October 06, 2025 - October 07, 2025