Interdisciplinary Genomic Data Processing: From Machine Learning to Synthetic Biology
Olgica Milenkovic Professor in the Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign
Faculty Host:Bobak Nazer
Refreshments at 1:45pm
Abstract: Recent advances in genomic data acquisition technologies have lead to the creation of large libraries of multiomics datasets that carry valuable information about cellular develompent, functionality and disease mechanisms. In order to continue a sustainable growth and efficient utilization of such datatsets, new methods need to be developed for data storage, management, computational analysis and data-specific machine learning. To illustrate this point, I will provide a sample of new results pertaining to multiomics data compression, online convex matrix factorization for single-cell RNA expression analysis, motif clustering for biological networks, and methylation pattern inference via deep learning. I will also briefly describe an ongoing line of work in coding theory and synthetic biology for the purpose of developing new storage and molecular in-memory computing platforms.
Bio:Olgica Milenkovic is a professor in the Department of Electrical and Computer Engineering at the University of Illinois, Urbana-Champaign. She received her M.S. degree in mathematics and Ph.D. in electrical engineering at the University of Michigan, Ann Arbor, in 2001 and 2002, respectively. Since 2007 she has been with the faculty of University of Illinois where she heads an interdisciplinary group working on bioinformatics, coding for synthetic biology and machine learning. She is an IEEE Fellow and has received the NSF Career Award and the DARPA Young Investigator Award.