Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Finding the biologically optimal alignment of multiple sequences.

Hiroshi Mamitsuka1

  • 1Institute for Chemical Research, Kyoto University, Gokasho, Uji 611-0011, Japan. mami@kuicr.kyoto-u.ac.jp

Artificial Intelligence in Medicine
|July 30, 2005
PubMed
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

Clinical Key Features Uncovered by Blood Eosinophilia-Based Machine Learning Classification of Chronic Rhinosinusitis.

International forum of allergy & rhinology·2025
Same author

Re: Letter to the Editor Regarding "Uncovering Key Features for Predicting Comorbid Chronic Eosinophilic Pneumonia in Chronic Rhinosinusitis Via Machine Learning".

International forum of allergy & rhinology·2025
Same author

Beyond rigid docking: deep learning approaches for fully flexible protein-ligand interactions.

Briefings in bioinformatics·2025
Same author

Uncovering Key Features for Predicting Comorbid Chronic Eosinophilic Pneumonia in Chronic Rhinosinusitis via Machine Learning.

International forum of allergy & rhinology·2025
Same author

The interictal transcriptomic map of migraine without aura.

The journal of headache and pain·2025
Same author

GORetriever: reranking protein-description-based GO candidates by literature-driven deep information retrieval for protein function annotation.

Bioinformatics (Oxford, England)·2024
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

Deterministic annealing, a method from statistical physics, efficiently finds optimal multiple sequence alignments. This novel approach significantly outperforms existing methods in accuracy and computation time.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Statistical Physics

Background:

  • Multiple sequence alignment is crucial for understanding protein function and evolution.
  • Existing stochastic methods for sequence alignment can be computationally intensive.
  • Deterministic annealing offers a computationally efficient approach to find global optima.

Purpose of the Study:

  • To apply deterministic annealing for efficient, biologically optimal multiple sequence alignment.
  • To introduce a novel stochastic model suitable for sequence alignment that incorporates symbol similarity scores.
  • To develop a learning algorithm combining deterministic annealing with expectation-maximization (EM).

Main Methods:

  • Developed a new probabilistic model for multiple sequence alignment.

Related Experiment Videos

  • Integrated deterministic annealing with the expectation-maximization (EM) algorithm for model training.
  • Utilized similarity scores between symbols and gaps within the probabilistic model.

    • Main Results:

    • The proposed method achieved superior performance compared to existing approaches in aligning protein sequences.
    • The alignment accuracy was validated against alignments based on known 3D protein structures.
    • The approach demonstrated a tenfold increase in computational efficiency over a competing method.

    Conclusions:

    • Deterministic annealing provides a time-efficient and accurate solution for multiple sequence alignment.
    • The novel stochastic model and learning algorithm advance the field of computational bioinformatics.
    • This method holds promise for accelerating biological sequence analysis and discovery.