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

Linear regression models for solvent accessibility prediction in proteins.

Michael Wagner1, Rafał Adamczak, Aleksey Porollo

  • 1Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, 3333 Burnet Avenue, Cincinnati, OH 45229, USA.

Journal of Computational Biology : a Journal of Computational Molecular Cell Biology
|April 29, 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

SPPIDER-seq: sequence-based partner-aware predictor of protein-protein interaction sites.

Bioinformatics (Oxford, England)·2026
Same author

BPabZIP, a new bZIP protein motif that promotes binding near, and displacement of, nucleosomes.

bioRxiv : the preprint server for biology·2026
Same author

Single-cell RNA sequencing defines developmental progression and reproductive transitions of <i>Pneumocystis carinii</i>.

Microbiology spectrum·2025
Same author

Catalytic region mimetics in Na+/H+ exchanger regulatory factor 4 suppress guanylate cyclase 2C activity to regulate enterotoxin triggered diarrhea.

The Journal of biological chemistry·2025
Same author

Case Report: Association of Ocular Colobomas With a Novel Missense Variant in CDC42, a Member of the Rho Family of Small GTPases.

Clinical genetics·2025
Same author

Role of Forkhead box F1 in the Pathobiology of Pulmonary Arterial Hypertension.

bioRxiv : the preprint server for biology·2024
Same journal

Mosquito Species and Gender Identification System Based on Artificial Intelligence and Image Processing Methods.

Journal of computational biology : a journal of computational molecular cell biology·2026
Same journal

GMSA: A Graph Matching and Point Cloud Registration-Based Method for Spatial Transcriptomics Data Alignment.

Journal of computational biology : a journal of computational molecular cell biology·2026
Same journal

Investigations on Multiple Protein Scaffold Filling.

Journal of computational biology : a journal of computational molecular cell biology·2026
Same journal

Cell Type Prediction for Single-Cell RNA Sequencing Utilizing Unsupervised Domain Adaptation and Semi-Supervised Learning.

Journal of computational biology : a journal of computational molecular cell biology·2026
Same journal

PPIGAN: Prediction of Protein-Protein Interactions Using Generative Adversarial Networks.

Journal of computational biology : a journal of computational molecular cell biology·2026
Same journal

Deep Structure-Enhanced Cell Clustering Model for Single-Cell RNA Sequencing Data.

Journal of computational biology : a journal of computational molecular cell biology·2026
See all related articles

Predicting relative solvent accessibility (RSA) in proteins is now more efficient. Linear Support Vector Regression (SVR) models offer competitive accuracy with significantly reduced computational cost compared to complex neural networks.

Area of Science:

  • Computational biology
  • Bioinformatics
  • Machine learning

Background:

  • Relative solvent accessibility (RSA) prediction is crucial for understanding protein structure and function.
  • Traditionally, RSA prediction has been approached as a classification problem, limiting accuracy.
  • Nonlinear regression methods offer improved RSA prediction but are computationally intensive.

Purpose of the Study:

  • To develop computationally efficient regression models for accurate RSA prediction.
  • To compare the performance of linear Support Vector Regression (SVR) and least squares (LS) regression against existing nonlinear methods.
  • To identify cost-effective alternatives for RSA prediction in bioinformatics.

Main Methods:

  • Investigated linear L1-Support Vector Regression (SVR) and linear least squares (LS) regression for RSA prediction.

Related Experiment Videos

  • Utilized rigorously derived protein structure validation sets and extensive cross-validation.
  • Compared performance against established nonlinear Neural Network (NN)-based methods.

    • Main Results:

    • Linear SVR models demonstrated competitive prediction quality compared to computationally expensive nonlinear NN methods.
    • SVR's flexibility, through metaparameters, proved beneficial for optimizing accuracy, particularly for buried residues.
    • Linear SVR models require orders-of-magnitude fewer parameters and are significantly less computationally expensive to train.

    Conclusions:

    • Linear SVR provides a computationally efficient and accurate alternative for RSA prediction.
    • This approach facilitates further development of more precise RSA prediction tools.
    • Applications include enhancing protein fold recognition and de novo protein structure prediction.