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

HSEpred: predict half-sphere exposure from protein sequences.

Jiangning Song1, Hao Tan, Kazuhiro Takemoto

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

Bioinformatics (Oxford, England)
|May 10, 2008
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

Double Zernike polynomial-based desensitization design method for off-axis optical systems.

Optics express·2026
Same author

CRISPR-based next-generation molecular diagnostics for bone infection.

Frontiers in cell and developmental biology·2026
Same author

White cell - platelet ratio: A strong indicator for early mortality in liver cirrhosis patients with esophagogastric varices.

Scientific reports·2026
Same author

Fast-Scan Voltammetry-Driven Nanoprobes for the Intracellular PTP1B Activity Assay and Invasiveness Evaluation of Single Tumor Cells.

Analytical chemistry·2026
Same author

Evaluation of DeepSeek-Generated Biochemistry Clinical Cases for Teaching Purpose.

Biochemistry and molecular biology education : a bimonthly publication of the International Union of Biochemistry and Molecular Biology·2026
Same author

Exploring the causal relationship between inflammatory cytokines and diabetic foot ulcer: A bidirectional Mendelian randomization and clinical validation study.

Canadian journal of physiology and pharmacology·2026
Same journal

3DICE: Interpretable 3D Cross-Modal Learning for Drug-Target Interaction Prediction and Large-Scale Drug Discovery.

Bioinformatics (Oxford, England)·2026
Same journal

KASSPer: Kinase Active Site Structure Prediction using Protein and Ligand Language Models and Its Application to Virtual Screening.

Bioinformatics (Oxford, England)·2026
Same journal

IDR searcher: a search engine solution for public image resources.

Bioinformatics (Oxford, England)·2026
Same journal

KCFtools: Rapid alignment-free method for introgression screening and GWAS using k-mer profiles.

Bioinformatics (Oxford, England)·2026
Same journal

Meta2DB: Curated shotgun metagenomic feature sets and metadata for health state prediction.

Bioinformatics (Oxford, England)·2026
Same journal

conMItion: an R package adjusting confounding factors for associations in multi-omics.

Bioinformatics (Oxford, England)·2026
See all related articles

We developed a new method to predict half-sphere exposure (HSE) measures from protein sequences using support vector regression. This approach accurately predicts HSE and residue contact numbers, advancing protein structure analysis.

Area of Science:

  • Computational Biology
  • Structural Bioinformatics
  • Protein Science

Background:

  • Half-sphere exposure (HSE) is a novel 2D solvent exposure measure, outperforming existing metrics like accessible surface area.
  • HSE quantifies distinct spatial neighborhoods (upward and downward) for amino acids within protein structures.
  • No existing methods predict HSE measures directly from protein sequence data.

Purpose of the Study:

  • To develop a novel computational method for predicting HSE measures from protein sequences.
  • To infer residue contact numbers utilizing predicted HSE values.
  • To explore sequence-encoding schemes for optimizing prediction performance.

Main Methods:

  • Employed support vector regression (SVR) to model the relationship between protein sequences and HSE measures.

Related Experiment Videos

  • Utilized a curated dataset of non-homologous protein structures for training and validation.
  • Evaluated prediction performance across five different sequence-encoding schemes.

    • Main Results:

    • Achieved high correlation coefficients of 0.72 for HSE-up and 0.68 for HSE-down predictions.
    • Successfully predicted residue contact numbers by summing predicted HSE-up and HSE-down values.
    • Demonstrated the efficacy of the SVR approach in quantifying protein sequence-structure relationships.

    Conclusions:

    • The proposed SVR-based method enables accurate prediction of HSE measures from protein sequences.
    • This approach extends the utility of HSE measures for inferring structural properties and contact numbers.
    • The findings highlight the potential of SVR for predicting structural profiles directly from sequence data.