Abstract: The field of genomics over the past decade has been driven by technological advances as the throughput and diversity of genomics assays has increased dramatically. We have developed a series of machine learning methods to help biologists make sense of the resulting big, heterogeneous data sets. I will describe an unsupervised learning strategy that uses a dynamic Bayesian network to annotate the genome, including our recent efforts to improve the utility and interpretability of the resulting annotation. I will also discuss an optimization procedure to select a "most informative" genomics assays to carry out on a given cell type, as well as a tensor factorization method to impute missing genomics data.
Bio: William Stafford Noble (formerly William Noble Grundy) was raised in Naperville, IL, and graduated from Stanford University in 1991 with a degree in Symbolic Systems. Between undergraduate and graduate school, he worked in the speech group at SRI International in Menlo Park, CA, and at Entropic Research Laboratory in Palo Alto, CA. He also spent two years teaching high school math, physics and English literature with the US Peace Corps in Lesotho, Africa. In 1994, he entered graduate school at the University of California, San Diego, where he studied with Charles Elkan. He received the Ph.D. in computer science and cognitive science in 1998. He then spent one year as a Sloan/DOE Postdoctoral Fellow with David Haussler at the University of California, Santa Cruz. From 1999 until 2002, Noble was an Assistant Professor in the Department of Computer Science at Columbia University, with a joint appointment at the Columbia Genome Center. In 2002, he joined the faculty of the Department of Genome Sciences at the University of Washington, where he has adjunct appointments in the Department of Computer Science and Engineering, the Department of Medicine, and the Department of Biomedical Informatics and Medical Education. His research group develops and applies statistical and machine learning techniques for modeling and understanding biological processes at the molecular level. Noble is the recipient of an NSF CAREER award and is a Sloan Research Fellow, and is a former member of the Board of Directors of the International Society for Computational Biology. He is currently the Director of the UW Computational Molecular Biology Program and Co-Director of the UW Center for Nuclear Organization and Function.