The development of therapeutics for diseases is contingent upon a thorough understanding of the disease’s root causes. Diseases like Alzheimer’s and cancer are intricately linked to physical changes in affected cells, as well as genetic and transcriptomic alterations. While researchers have made strides in integrating these aspects to identify potential therapeutic targets, they encounter limitations due to the diversity and limited nature of biological datasets.

To address this challenge, a promising approach involves adapting successful methodologies for a given disease dataset and applying them to analogous datasets with similar structures. This approach can yield new insights and discoveries.

Drawing inspiration from the success of STACI, a computational framework used to analyze Alzheimer’s Disease, my research focuses on creating and applying similar methods to a dataset (with both imaging and transcriptomic details) related to cardiometabolic diseases. My work will aim to provide valuable and potentially therapeutic-inspiring diagnostic information for a range of such cardiometabolic health conditions, ranging from heart attacks to obesity.

I am pursing this project because I am passionate about using computational tools (especially AI) to solve biological problems. I also want to learn more about the process of research so I can learn what kind of work I want to commit to in graduate school. I am excited to apply my knowledge from cancer research in industry, biology classes, and 6.036 to this project. I hope that by the end of this SuperUROP, I can publish a paper on my findings.