Hidden Markov Model HMM

Algorithms based on HMMs are able to identify localization motifs by modeling sequence alignments. A test sequence is compared against all the HMM models produced for the various subcellular compartments, and it is assigned to the one with the highest probability score. The success of HMMs is highly dependent upon accurate alignment of the training sequences. Also, HMMs can only cope with linear sequences, and, for this reason, any localization motifs created as a result of the secondary or the tertiary structure cannot be modeled by HMMs. Modeling such 2D or 3D motifs may require alternative probabilistic methodologies such as stochastic context-free grammars (SCFGs). SCFGs have been successfully deployed to assist with the RNA secondary structure prediction [31] but have found limited application in predicting protein localization.

Was this article helpful?

0 0
How To Win Your War Against Allergies

How To Win Your War Against Allergies

Not Able To Lead A Happy Life Because Of Excessive Allergies? Want To Badly Get Rid Of Your Allergy Problems, But Are Super Confused And Not Sure Where To Even Start? Don't Worry, Help Is Just Around The Corner Revealed The All-In-One Power Packed Manual Containing Ample Strategies And Little-Known Tips To Get Rid Of Any Allergy Problems That Are Ruining Your Life Learn How You Can Eliminate Allergies Completely Reclaim Your Life Once Again

Get My Free Ebook


Post a comment