Search research articles

Search research articles

Related Experiment Videos

Improved Hidden Markov Model training for multiple sequence alignment by a particle swarm optimization-evolutionary

Thomas Kiel Rasmussen¹, Thiemo Krink

¹EVALife Group, Department of Computer Science, University of Aarhus, Ny Munkegade B540, DK-8000 C Aarhus, Denmark. kiel@daimi.au.dk

|December 4, 2003

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Spider webs inspiring soft robotics.

Journal of the Royal Society, Interface·2020

Same journal

Spatiotemporal bursting in simulated cultures of cortical neurons.

Bio Systems·2026

Same journal

A brief discussion on recent models shedding light on how life emerged.

Bio Systems·2026

Same journal

Memory-based strategy reputation and adaptive learning in spatial evolutionary games: A robust agent-based model for cooperation dynamics.

Bio Systems·2026

Same journal

Coherent Photonic Biofields: Revisiting Fritz-Albert Popp's Hypothesis.

Bio Systems·2026

Same journal

Ruliological Resilience: Pattern Restoration and Robustness in Wolfram Patterns. A Basis for Regeneration, Not Just in Cone Shells?

Bio Systems·2026

Same journal

The quantum-to-classical transducer: A thermodynamic and quantum mechanical framework for the emergence of bioenergetics.

Bio Systems·2026

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

This study introduces a hybrid algorithm combining particle swarm optimization and evolutionary algorithms for training Hidden Markov Models (HMMs). This novel approach improves protein sequence alignment accuracy compared to traditional HMM training methods.

Area of Science:

Computational Biology
Bioinformatics
Machine Learning

Background:

Multiple Sequence Alignment (MSA) is a fundamental computational biology problem.
Exact algorithms for realistic MSA instances are computationally intractable.
Hidden Markov Models (HMMs) are powerful tools for MSA but challenging to train optimally.

Purpose of the Study:

To develop an improved method for training Hidden Markov Models (HMMs) for protein sequence alignment.
To overcome the limitations of existing HMM training algorithms, such as Baum-Welch's local optima problem.

Main Methods:

A hybrid algorithm combining particle swarm optimization (PSO) with evolutionary algorithms (EAs) was developed.
This hybrid approach was used to train HMMs specifically for protein sequence alignment tasks.

Related Experiment Videos

Main Results:

The proposed hybrid PSO-EA algorithm achieved superior protein sequence alignments on benchmark datasets.
Results demonstrated better performance compared to standard HMM training methods like Baum-Welch and Simulated Annealing.

Conclusions:

Hybrid optimization algorithms offer a promising solution for training HMMs in computational biology.
This method enhances the accuracy of protein sequence alignment, advancing the field of bioinformatics.