Thesis Defense – Rebecca Boiarsky

Abstract:

Single-cell RNA sequencing (scRNA-seq) offers an unprecedented view into the cellular and phenotypic composition of human tissues in both health and disease. While machine learning (ML) is well-suited to the high-dimensional nature of scRNA-seq data, current computational tools often fall short—especially when applied to complex datasets from clinical oncology. This thesis develops and applies ML techniques to scRNA-seq data, with the goal of addressing key computational challenges and advancing translational insights in cancer research. The talk will focus on three main areas: identifying gene signatures and biomarkers in multiple myeloma, benchmarking cell embeddings from large pre-trained scRNA-seq foundation models, and building a framework to predict clinical outcomes from patient single-cell profiles. Collectively, these studies advance ML approaches that aim to unlock actionable insights from scRNA-seq data, with an eye toward enabling personalized medicine.

Details

• Date: Wednesday, April 16
• Time: 2:00 pm - 3:00 pm
• Category: Thesis Defense
• Location: 32-D463 Star

Additional Location Details:

Location: 32-D463 (the Star room in Stata)

Host

• Rebecca Boiarsky
• Email: rboiar@mit.edu
• Phone: 6172434650