Related Experiment Video
Updated: Jul 9, 2026
11:26
Sequencing of mRNA from Whole Blood using Nanopore Sequencing
Published on: June 3, 2019
A novel, fast, HMM-with-Duration implementation - for application with a new, pattern recognition informed, nanopore
Stephen Winters-Hilt1, Carl Baribault
1Dept. of Computer Science, University of New Orleans, New Orleans, LA 70148, USA. winters@cs.uno.edu
BMC Bioinformatics
|December 6, 2007
Summary
A new Hidden Markov Model with Duration (HMMwD) offers improved accuracy for analyzing sequential data, matching ideal models in many cases. This faster HMMwD implementation enhances structure identification and feature extraction for applications like Nanopore detector analysis.
Area of Science:
- Computational Biology
- Bioinformatics
- Signal Processing
Background:
- Hidden Markov Models (HMMs) are effective for structure identification and feature extraction in sequential data.
- Standard HMMs approximate hidden-label length distributions with a geometric distribution.
- HMMs with Duration (HMMwD) can precisely model these hidden-label length distributions.
Purpose of the Study:
- To present a novel, fast implementation of HMMwD.
- To evaluate its performance against ideal models and conventional HMMs.
- To demonstrate its application in pattern recognition-informed (PRI) sampling control for Nanopore detector data.
Main Methods:
- Developed a novel, fast HMMwD implementation.
- Tested the HMMwD on synthetic two-state data modeling Nanopore detector signals.
- Compared HMMwD performance against ideal models and standard HMMs.
- Utilized HMM feature extraction for PRI sampling control of a Nanopore detector device.
Main Results:
- The HMMwD implementation demonstrated improved accuracy over the standard HMM.
- HMMwD accuracy matched the ideal solution in many instances.
- The computational cost of HMMwD is comparable to the standard HMM.
- Achieved 99.9% accuracy in PRI sampling control using DNA hairpin blockades as test probes.
Conclusions:
- The enhanced accuracy and comparable computational cost of HMMwD make it valuable for gene structure identification and channel current analysis.
- HMMwD is particularly beneficial for applications requiring speed, such as PRI sampling control.
- The study successfully established the first PRI sampling control for a Nanopore detector device using HMM feature extraction.
