BioInformatics--> HMM

[karthik3k]

What is the use of HMM (Hidden Markov Models) ?? in sequence analysis ??

[Monique]

This is a statistical tool that allows you to model a system that is assumed to be a Markov process with unknow parameters. A Markov process basically means something random, stochastic, where future states do not depend on past states. It is hidden because you cannot directly measure the effect, so you are metaphorically using the shadow or acoustics to measure the real parameter.

This would apply to sequence analysis, since the order of basis is assumed to be random, if you measure Adenine.. you cannot say whether the next base is going to be A, C, G or T. So I guess that would mean it is a Markov chain..

Now I'm not all too familiar with the statistic, but think for instance that it can be used for the recognition of genes in DNA.