Swarthmore College Department of Computer Science

Talk by Ameet Soni, Swarthmore College CS

Techniques for Improved Probabilistic Inference in Protein-Structure Determination
Wed, February 1, 2012
SCI 240, 4:30 pm (refreshments at 4:15)


Abstract

Over the past decade, the field of computer science has seen a large increase in the use and study of probabilistic graphical models due to their ability to provide a compact representation of complex, multidimensional problems. Graphical models have applications in many areas, including natural language processing, computer vision, social-network modeling, and medical diagnosis. Recently, the complexity of problems posed in many domains has stressed the ability of algorithms to reason in graphical models. New techniques for inference are essential to meet the demands of these problems in an efficient and accurate manner.

One such area of application is in the area of structural genomics. The task of determining protein structures has been a central one to the biological community as they are essential to almost all cellular functions in an organism. In this talk, I will discuss my research on ACMI - a state-of-the-art, automated technique for determining protein structures given low-quality images of a protein. I will discuss my contributions to this problem, and in particular to the topic of probabilistic inference - drawing conclusions from incomplete information. In addition, I will discuss my current research interests, which include applying these new inference techniques to problems in both the medical and biological fields where data is relational and incomplete.