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 Video

Updated: Jun 16, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Sparse support vector machines with Lp penalty for biomarker identification.

Zhenqiu Liu1, Shili Lin, Ming T Tan

  • 1Division of Biostatistics and Bioinformatics, Department of Epidemiology and Preventive Medicine, Greenebaum Cancer Center, School of Medicine, University of Maryland, Baltimore, MD 21201, USA. zliu@umm.edu

IEEE/ACM Transactions on Computational Biology and Bioinformatics
|February 13, 2010
PubMed
Summary

This study introduces LpSVM, a novel sparse support vector machine algorithm for high-dimensional discrete and continuous data. LpSVM enhances feature selection and overfitting control, demonstrating accuracy and efficiency in biological data analysis.

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

Ultra-processed food consumption and the trajectory of cardio-renal-metabolic multimorbidity: insights from multi-state modelling.

Food & function·2026
Same author

Age-related metabolomic signatures and stroke susceptibility in a population-based cohort.

GeroScience·2026
Same author

In vivo CRISPR knockout screen identifies Polr1a as a key driver and a potential therapeutic target for melanoma metastasis.

Oncogene·2026
Same author

Oncofetal RNA-binding proteins of IGF2BP family suppress IRF-3 and NF-kB dependent transcription downstream of cytosolic RNA sensors.

bioRxiv : the preprint server for biology·2026
Same author

Causal Associations of Red Cell Distribution Width with Rheumatoid Arthritis and Congestive Heart Failure: A Phenome-Wide Mendelian Randomization Study.

Phenomics (Cham, Switzerland)·2026
Same author

Refining the Definition for "Low Risk" in Pulmonary Arterial Hypertension: Time to Reduce Morbidity and Mortality.

JACC. Heart failure·2026

Area of Science:

  • Computational Biology
  • Machine Learning
  • Bioinformatics

Background:

  • High-throughput technologies generate vast amounts of high-dimensional data, often of discrete types.
  • Existing feature selection algorithms, like LASSO, are primarily designed for continuous data, limiting their application.
  • There is a need for robust algorithms capable of handling mixed data types in high-dimensional biological datasets.

Purpose of the Study:

  • To propose a novel sparse support vector machine (SVM) method using L_(p) (p < 1) regularization for high-dimensional data.
  • To develop efficient algorithms (LpSVM) applicable to datasets containing both discrete and continuous variables.
  • To improve feature selection and overfitting control in the analysis of complex biological data.

Main Methods:

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

Related Experiment Videos

Last Updated: Jun 16, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

  • Developed a novel sparse support vector machine (SVM) classifier incorporating L_(p) (p < 1) regularization.
  • Created efficient algorithms (LpSVM) to handle high-dimensional datasets with mixed discrete and continuous data types.
  • Estimated regularization parameters by maximizing the area under the ROC curve (AUC) using cross-validation data.

    • Main Results:

    • The proposed LpSVM algorithm demonstrated accuracy, sparsity, and efficiency on protein sequence and SNP datasets.
    • Biomarkers identified using LpSVM were compared favorably with existing methods.
    • The algorithm effectively performs feature selection and overfitting control for mixed-type high-dimensional data.

    Conclusions:

    • LpSVM is an effective and efficient method for feature selection and classification in high-dimensional biological data.
    • The algorithm's ability to handle both discrete and continuous data types makes it broadly applicable.
    • The developed method offers improved performance and biomarker identification compared to existing approaches.