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

Protein fold recognition using the gradient boost algorithm.

Feng Jiao1, Jinbo Xu, Libo Yu

  • 1Alberta Ingenuity Centre for Machine Learning, University of Alberta, Alberta, Canada. fjiao@cs.uwaterloo.ca

Computational Systems Bioinformatics. Computational Systems Bioinformatics Conference
|March 21, 2007
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

Genome-Wide Identification and Expression of the Mulberry PLA Family Under Drought and Salinity.

Biology·2026
Same author

The tRNA landscape in cancer: from pathogenesis to therapeutic interventions.

Acta biochimica et biophysica Sinica·2026
Same author

Multi-omics profiling of the diabetic human heart reveals coupled dysregulation in lipid metabolism, mitophagy, and extracellular matrix remodeling.

Genome medicine·2026
Same author

Awareness, Attitudes, and Help-Seeking Intention Towards Perinatal Depression Among Women from Different Ethnic Groups in Western Rural China.

International journal of women's health·2026
Same author

Engineering Symbiotic Nitrogen Fixation for Agriculture: Predominant Role of Host Plants and Fine-Tuning Regulation.

Plants (Basel, Switzerland)·2026
Same author

Inferring cell-specific gene regulatory networks based on causal graph embedding.

Cell reports methods·2026
Same journal

Novel Gene Discovery in the Human Malaria Parasite using Nucleosome Positioning Data.

Computational systems bioinformatics. Computational Systems Bioinformatics Conference·2014
Same journal

Proceedings of Computational Systems Bioinformatics 2008. August 26-29, 2008. Palo Alto, California, USA.

Computational systems bioinformatics. Computational Systems Bioinformatics Conference·2009
Same journal

Graph wavelet alignment kernels for drug virtual screening.

Computational systems bioinformatics. Computational Systems Bioinformatics Conference·2009
Same journal

Fast multisegment alignments for temporal expression profiles.

Computational systems bioinformatics. Computational Systems Bioinformatics Conference·2009
Same journal

Knowledge representation and data mining for biological imaging.

Computational systems bioinformatics. Computational Systems Bioinformatics Conference·2009
Same journal

Efficient haplotype inference from pedigrees with missing data using linear systems with disjoint-set data structures.

Computational systems bioinformatics. Computational Systems Bioinformatics Conference·2009
See all related articles

We developed a machine learning method using least-squares boosting (LS_Boost) for efficient protein fold recognition. This approach significantly speeds up protein structure prediction by avoiding time-consuming z-score calculations.

Area of Science:

  • Computational molecular biology
  • Bioinformatics
  • Machine learning

Background:

  • Protein structure prediction is a key challenge in computational biology.
  • Protein threading is a promising technique, with fold recognition being a critical step.
  • Current template selection relies on z-score calculations, which are computationally intensive and limit genome-scale predictions.

Purpose of the Study:

  • To develop an efficient machine learning approach for protein fold recognition.
  • To treat fold recognition as a regression task.
  • To improve computational efficiency and accuracy in protein structure prediction.

Main Methods:

  • Utilized a least-squares boosting (LS_Boost) algorithm.
  • Formulated the fold recognition problem as a regression task.

Related Experiment Videos

  • Tested the method on Lindahl's benchmark and compared it with other machine learning techniques like Support Vector Machines (SVMs) and neural networks.

    • Main Results:

    • Machine learning provides an effective solution for fold recognition.
    • Regression-based formulation is more effective than classification.
    • LS_Boost significantly reduces computation time by eliminating the need for z-score calculation.
    • LS_Boost achieves superior accuracy and computational efficiency compared to SVMs and neural networks.

    Conclusions:

    • Machine learning, particularly LS_Boost, offers an efficient and accurate method for protein fold recognition.
    • The regression approach and LS_Boost algorithm overcome limitations of traditional z-score based methods.
    • LS_Boost enables feature identification within the fold recognition protocol, unlike SVMs.