Abstract:
A central challenge in biology is to uncover the complete gene-regulation network of an organism. This challenge can now be profitably attacked given the availability of complete genomes and high-throughput technologies for interrogating the states of cells.A key step in addressing the challenge is to assemble a "parts list" of the regulatory elements for a given genome. We have been developing an approach, based on probabilistic language models, that uses DNA-sequence and gene-_expression data to predict a variety of regulatory elements in bacterial genomes. Given experimentally verified instances of certain regulatory elements, our approach learns models that can be used to predict other instances in a genome. We have applied this approach to the task of predicting a nearly complete map of promoters, terminators and operons in the genome of E. coli.

Speaker:
Dr. Mark Craven is an Assistant Professor in the Department of Biostatistics and Medical Informatics and in the Department of Computer Sciences at the University of Wisconsin. He received his Ph.D. in Computer Sciences from the University of Wisconsin in 1996,spent several years as a Postdoctoral Fellow in the School of Computer Science at Carnegie Mellon University, and joined the University of Wisconsin faculty in 1999. His research interests are centered in machine learning and bioinformatics. He has more> than 30 publications in these areas. He served as co-chair of KDD Cup in 2002, is on the editorial board of the Machine Learning journal, and was awarded an NSF CAREER award in 2001. His current research projects involve developing computational methods for automatically mining the biomedical literature, and for uncovering gene-regulatory networks in bacterial genomes.