(please see the main page for schedule information)
A central challenge in computational biology is to uncover the complete gene-regulatory 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. In this talk, I will discuss my group's work on applying machine learning methods to the task of elucidating transcription-regulation networks in bacterial genomes. In particular, I will focus on several algorithmic contributions we have made, including methods for (i) refining the structure of stochastic context free grammars, (ii) modeling and predicting arbitrarily overlapping elements in sequence data, (iii) training sequence models with "weakly" labeled data, and (iv) learning to represent the hidden states and roles of key variables in regulatory networks.
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. His current research is focused on developing and applying machine learning methods to the problems of elucidating, modeling and annotating biological networks. This research involves algorithms that operate on the scientific literature as well as methods that analyze primary data sources, such as genomic sequences and gene-expression data.