This course covers applications of probabilistic modeling to topics in bioinformatics, with an emphasis on literature study and novel tool development. Areas covered vary from year to year but typically include finite-state Markov models as models of point substitution processes; graphical models and dynamic programming; basic coalescent theory; grammar theory; birth-death processes and the Thorne-Kishino-Felsenstein model of indels; general PDE methods and applications to continuous-state models; the Chinese restaurant process in population genetics and ecology; data compression algorithms; general techniques including conjugate priors, MCMC, and variational methods.

Repeat Rules

Course is not repeatable for credit.