
Vivian S. Hir
Eric and Wendy Schmidt Center Funded Research and Innovation Scholar
Using Deep Learning to Construct a Pan-Cancer Blueprint of Tumor Spatial Organization
2024–2025
Electrical Engineering and Computer Science
- AI for Healthcare and Life Sciences
Caroline Uhler
Salil Bhate
The objective of the project is to construct a pan-cancer atlas of cellular neighborhoods and their spatial assembly. We aim to analyze the impact of two adjacent cellular neighborhoods on patient survival, as well as the relevant genes correlated with these significant neighborhoods. Furthermore, we plan to do an analysis of shared clusters across different gastrointestinal (GI) cancers. We will apply a foundation model to extract image features from whole-slide imaging data of GI cancers in the Cancer Genome Atlas (TCGA), and apply the tissue schematics framework to find cellular neighborhoods and map their spatial assembly. By leveraging the clinical, gene expression and mutation data in TCGA, we can decipher the functional mechanisms and impact of this assembly.
I am participating in this SuperUROP because I am interested in computational biology research, specifically in the field of cancer. This project excites me because of its medical and clinical applications. Taking on this project will not only help me better understand computational histopathology, but also further develop my research and communication skills.