Protein conformation sampling using conditional random fields
Speaker: Jinbo Xu , Toyota Technological Institute at Chicago
Date: February 20 2008
Time: 11:30AM to 1:30AM
Location: 32-G575
Host: Bonnie Berger & Peter Clote, MIT - BC
Contact: Patrice Macaluso, macaluso@csail.mit.edu
Protein structure prediction without using templates (i.e., ab initio
folding) is one of the most challenging
problems in structural biology. In particular, conformation sampling
poses as a major bottleneck
of ab initio folding. This talk presents CRFSampler, an extensible
protein conformation sampler, built
upon a probabilistic graphical model Conditional Random Fields (CRFs).
Using a discriminative learning
method, CRFSampler can automatically learn thousands of parameters
quantifying the
relationship among primary sequence, secondary structure and (pseudo)
backbone angles. Using only
compactness and self-avoiding constraints, CRFSampler can efficiently
generate protein-like conformations
from primary sequence and predicted secondary structure. CRF Sampler is
also very flexible in that
a variety of model topologies and feature sets can be defined to model
the sequence-structure relationship
without worrying about parameter estimation. Our experimental results
demonstrate that using a simple
set of features, CRFSampler can generate decoys with much higher
quality than the most recent HMM
model and Levitt's lattice model.
See other events that are part of Bioinformatics Seminar Series 2008
See other events happening in February 2008
