At 11 AM on Tuesday, October 30, Charles (Chip) Lawrence, Professor of Applied Mathematics at Brown University, will present a seminar in the
B2 library of Building 38A.  

The title and abstract of his talk are:

Measuring Global Credibility with Application to Sequence Alignment

Computational biology is replete with high dimensional discrete prediction and inference problems, including: sequence alignment,
 RNA structure prediction, phylogenetic inference, motif finding, and prediction of pathways.  Even though prediction and inference 
in these settings are uncertain, little attention has been focused on the development of global measures of uncertainty.  Regardless 
of the procedure employed to produce a prediction, when a procedure delivers a single answer, that answer is a point estimate selected
 from the immense ensemble of possible solutions in its high dimensional space, and thus is uncertain.  We recommend the use
 of Bayesian credibility limits to describe this uncertainty, where a credibility limit is the minimum Hamming distance radius
 of a hyper-sphere containing (1-alpha %) of the posterior weighted ensemble.  We also advocate "centroid" estimators that minimize 
the mean Hamming distance from the posterior weighted ensemble, with the aim of finding alignment estimators with tight credibility limits. 
 Since, on its own merit, sequence alignment is arguably the most important high dimensional discrete prediction problem for biology, 
and because it is the cornerstone capability used by a multitude of computational biology applications, we employ sequence alignment 
to make these general concepts concrete.  Application of Bayesian credibility limits and a centroid estimator to the alignment of 
20 human/rodent orthologous sequence pairs shows that credibility limits of the alignments of promoter sequences of these two species 
vary widely, and that centroid alignments dependably have tighter credibility limits than traditional maximum similarity alignments.