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

Prediction and evolutionary information analysis of protein solvent accessibility using multiple linear regression.

Jung-Ying Wang1, Hahn-Ming Lee, Shandar Ahmad

  • 1Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan.

Proteins
|September 20, 2005
PubMed
Summary

Predicting protein solvent accessibility using multiple linear regression improves accuracy. This method leverages sequence and evolutionary data, outperforming existing approaches for residue accessibility prediction.

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

Identification of Moonlighting Proteins from Published Literature Using Natural Language Processing and AI.

The protein journal·2026
Same author

Protein-DNA interactions in disease and drug discovery.

Chemical communications (Cambridge, England)·2026
Same author

Editorial overview: Protein-nucleic acid interactions: From origins to design.

Current opinion in structural biology·2025
Same author

Dictionary based approaches for studying intrinsic DNA shape in transcription factor recognition.

Current opinion in structural biology·2025
Same author

A pan-cancer, pan-treatment model for predicting drug responses from patient-derived xenografts.

NAR genomics and bioinformatics·2025
Same author

A Survey of Current Status in AI-Based Topology Prediction of Transmembrane Proteins.

Methods in molecular biology (Clifton, N.J.)·2025

Area of Science:

  • Computational biology
  • Structural bioinformatics
  • Protein science

Background:

  • Solvent accessibility is a crucial protein structural feature.
  • Accurate prediction of solvent accessibility aids in understanding protein function and interactions.
  • Existing prediction methods have limitations in accuracy and scope.

Purpose of the Study:

  • To develop and evaluate a multiple linear regression model for predicting protein residue solvent accessibility.
  • To assess the contribution of sequence and evolutionary information to solvent accessibility prediction.
  • To compare the model's performance against state-of-the-art methods.

Main Methods:

  • Applied multiple linear regression using sequence and evolutionary information.
  • Calculated regression coefficients and correlation matrices.

Related Experiment Videos

  • Analyzed the relationship between residue properties (hydrophobic, charged, polar) and solvent accessibility.
  • Evaluated model performance using mean absolute error (MAE).

    • Main Results:

    • The model achieved MAE of 18.9% (sequence info) and 16.2% (evolutionary info).
    • Performance is comparable or superior to existing methods.
    • Hydrophobic residues negatively correlate with accessibility; charged/polar residues show positive correlation.
    • Predictive accuracy increases with protein chain length.

    Conclusions:

    • Multiple linear regression effectively predicts solvent accessibility using sequence and evolutionary data.
    • Evolutionary information significantly enhances prediction accuracy.
    • The model provides insights into residue-environment interactions within proteins.