cswHMM: A Novel Context Switching Hidden Markov Model for Biological Sequence Analysis

In this work we created a sequence model that goes beyond simple linear patterns and models a specific type of higher-order relationship possible in biological sequences. Particularly, we seek models that can account for partially overlaid and intermixed patterns in biological sequences. Our proposed context-switching model (cswHMM) is designed as a variable-order hidden Markov model with a specific structure that allows switching control between two or more submodels. An important feature of our model is the ability of its submodels to remember their last active state, so when each submodel resumes control it can continue uninterrupted. This is a fundamental variation on the closely related jumping HMMs. Combining as few as two simple linear HMMs can describe sequences with complicated mixed dependencies. Tests of this approach suggest that a combination of HMMs for protein sequence analysis, such as pattern mining based HMMs or profile HMMs can improve the descriptive ability and performance of the model.