BibTeX
@MISC{Singh_profilehidden,
author = {Lecturer Mona Singh},
title = {Profile Hidden Markov Models},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In the previous lecture, we began our discussion of profiles, and today we will talk about how to use hidden Markov models to build profiles. One of the advantages of using hidden Markov models for profile analysis is that they provide a better method for dealing with gaps found in protein families. We will begin by an introduction of hidden Markov models. HMMs have also been used in many other areas of computational biology, including for gene finding as well as construction of genetic linkage maps and of physical maps. 1 Introduction to Hidden Markov Models A hidden Markov model is defined by specifying five things: Q = the set of states = {q1, q2,..., qn} V = the output alphabet = {v1, v2,..., vm} π(i) = probability of being in state qi at time t = 0 (i.e., in initial states)
