In the past decade, there has been a rapid development of technologies for profiling various biological phenomena (data modalities) at the cell and tissue level. These modalities include: retrieving the sequence of DNA in the cell, assessing the abundance of RNA and protein, the accessibility of the DNA, among others.
Cancer is among the leading causes of death worldwide, and a plethora of such data modalities have been collected from patient cohorts for many types of cancer with the specific goal of understanding its causes and developing novel therapies. In this talk, I will overview the fundamentals of cancer as a disease, the nature of the large-scale data collected for cancer, and the main objectives when analyzing such data. Furthermore, I will describe some open questions in cancer data analysis, and how machine learning and generative modeling techniques can help address them.
Post Talk Link: Click Here
Passcode: #p8W5+70
Petar Stojanov is a postdoctoral fellow at the Eric and Wendy Schmidt Center, Broad Institute of MIT and Harvard, where he is supervised by Dr. Gad Getz. He received his PhD in Computer Science at Carnegie Mellon University with focus on machine learning and transfer learning, where he was fortunate to be advised by Dr. Jaime Carbonell and Dr. Kun Zhang. Prior to that, he was an associate computational biologist at the Getz Lab, where he performed high-impact work on analyzing data from cancer genomes. His research interests span machine learning and computational biology. He is currently very interested in applying machine learning methodology to improve genomic analysis of cancer mutation and single-cell RNA sequencing data with the goal of understanding relevant causal relationships in cancer progression. His doctoral research was in transfer learning and domain adaptation from the causal perspective, a field which he is still interested and active in.
Read More
Read More