Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2012 Jan 12;8(1):e1002286. doi: 10.1371/journal.pcbi.1002286

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

Seifert et al.

This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are properly credited.

PMC Copyright notice

Parsimonious state-context tree selected among the best parsimonious HMMs of order four at a fixed FPR of 2.5% in Figure 4b. Each path from the root node at the top of the tree to a leaf node at the bottom of the tree represents a set of state-contexts defined to share common transition parameters in the transition matrix of the selected model. The three nodes directly under the root node represent the possible current states of the selected parsimonious fourth-order HMM, and the subtrees under these three nodes represent the influence of predecessor states on a state-transition from one of these current states to a next state. Fusions of nodes are highlighted in different colors. White nodes represent unfused nodes characterizing important states for a state-transition. Blue, orange, and green nodes represent partially fused states of equal importance for a state-transition. Grey nodes represent completely fused nodes defining that the corresponding position in a state-context has no influence on a state-transition. The states ‘’ and ‘’ of the selected model are still representing some fourth-order transition probabilities, whereas only second-order transition probabilities remain for state ‘’. The selected parsimonious fourth-order HMM has a model complexity of 14 leaf nodes leading to 42 different transition parameters in . This is much less than for a corresponding fourth-order HMM with 81 leaf nodes in a complete state-context tree representing 243 transition parameters.

Inline graphic — Parsimonious state-context tree selected among the best parsimonious HMMs of order four at a fixed FPR of 2.5% in Figure 4b. Each path from the root node at the top of the tree to a leaf node at the bottom of the tree represents a set of state-contexts defined to share common transition parameters in the transition matrix of the selected model. The three nodes directly under the root node represent the possible current states of the selected parsimonious fourth-order HMM, and the subtrees under these three nodes represent the influence of predecessor states on a state-transition from one of these current states to a next state. Fusions of nodes are highlighted in different colors. White nodes represent unfused nodes characterizing important states for a state-transition. Blue, orange, and green nodes represent partially fused states of equal importance for a state-transition. Grey nodes represent completely fused nodes defining that the corresponding position in a state-context has no influence on a state-transition. The states ‘’ and ‘’ of the selected model are still representing some fourth-order transition probabilities, whereas only second-order transition probabilities remain for state ‘’. The selected parsimonious fourth-order HMM has a model complexity of 14 leaf nodes leading to 42 different transition parameters in . This is much less than for a corresponding fourth-order HMM with 81 leaf nodes in a complete state-context tree representing 243 transition parameters.