We will jointly present how a personal cancer diagnosis drove development of machine learning and analysis methods to apply to tumor gene expression data. We will discuss the motivating problems and how we addressed them in our recent work. In addition to highlighting important features of the resultant tools, we will narrate the timeline of our collaboration and how the techniques ultimately came together to have a real-life impact.
Shirley Pepke is a computational biologist who has worked to push the boundaries in terms of translating big data to clinical cancer applications. After Shirley was diagnosed with ovarian cancer, she engaged with oncology, genomics, and machine learning researchers to sequence her tumor and develop novel analyses of cancer data in public databases in order to select her treatment regimen. She has a Ph.D. in physics from the University of California, Santa Barbara. Her prior work included research in neurobiology and high throughput genomics at the California Institute of Technology.
Greg Ver Steeg is a research professor in computer science at USC’s Information Sciences Institute. He received his Ph. D. in physics from Caltech in 2009 and since then has focused on using ideas from information theory to understand complex systems like human behavior, biology, and language. His work has been recognized with an AFOSR Young Investigator Award.