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

Learning to translate sequence and structure to function: identifying DNA binding and membrane binding proteins.

Robert E Langlois1, Matthew B Carson, Nitin Bhardwaj

  • 1Department of Bioengineering, University of Illinois at Chicago, Chicago, IL 60607-7052, USA.

Annals of Biomedical Engineering
|April 17, 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

Primary age-related tauopathy in a Chinese cohort.

Journal of Zhejiang University. Science. B·2020
Same author

The metabolic effect of gut microbiota on drugs.

Drug metabolism reviews·2020
Same author

Population-based preference weights for the Adult Social Care Outcomes Toolkit (ASCOT) for service users for Austria: Findings from a best-worst experiment.

Social science & medicine (1982)·2020
Same author

Dissymmetric On-Surface Dehalogenation Reaction Steered by Preformed Self-Assembled Structure.

The journal of physical chemistry letters·2020
Same author

Exosomes mediate intercellular transfer of non-autonomous tolerance to proteasome inhibitors in mixed-lineage leukemia.

Cancer science·2020
Same author

Neuroprotective Effects of Selective Inhibition of Histone Deacetylase 3 in Experimental Stroke.

Translational stroke research·2020
Same journal

Patient-Specific Adaptation of a Mechano-Regulatory Bone-Healing Model Using Longitudinal Loading Data.

Annals of biomedical engineering·2026
Same journal

Effects of Simulated Body-Mass Reduction on Peak Knee Joint Loads During Daily Functional Activities.

Annals of biomedical engineering·2026
Same journal

Evaluating Different Optimization Criteria for Estimating Spine Loads and Muscle Activity During Manual Lifting With and Without Assistance from Back-Support Exoskeletons.

Annals of biomedical engineering·2026
Same journal

A Physiologic Left Ventricle Flow Phantom for 4D Flow MRI Applications and CFD Verification.

Annals of biomedical engineering·2026
Same journal

Pulsatile Hemodynamics of Prehypertension and Hypertension: Associations with Pressure and Sex.

Annals of biomedical engineering·2026
Same journal

A Pressure Difference-Based Strategy for Blood Oxygen Control in Membrane Oxygenators: Reduced Modeling, Computational Simulation, and Exploratory In Vivo Evaluation.

Annals of biomedical engineering·2026
See all related articles

This study introduces a machine learning protocol to identify DNA- and membrane-binding proteins. Boosted tree classifiers achieved high accuracy, outperforming previous methods by focusing on physical features over sequence similarity.

Area of Science:

  • Bioinformatics
  • Structural Biology
  • Machine Learning

Background:

  • Protein function is largely determined by molecular interactions.
  • The growing availability of protein structures necessitates efficient interaction identification methods.
  • Machine learning offers robust annotation of genes and proteins independent of sequence homology.

Purpose of the Study:

  • To develop a general machine learning protocol for identifying DNA- and membrane-binding proteins.
  • To systematically compare classification algorithms for this task.
  • To identify key physical features driving DNA and membrane binding.

Main Methods:

  • Developed a general machine learning protocol.
  • Systematically compared several well-performing classification algorithms.

Related Experiment Videos

  • Applied a boosted tree classifier for performance evaluation and feature importance analysis.

    • Main Results:

    • The boosted tree classifier achieved 93% accuracy for membrane-binding proteins and 88% for DNA-binding proteins.
    • This performance significantly outperformed previously published methods.
    • Identified key physical features important for DNA and membrane binding.

    Conclusions:

    • The developed machine learning protocol effectively identifies DNA- and membrane-binding proteins.
    • Boosted tree classifiers provide a robust and accurate method for this task.
    • The approach prioritizes physical features for functional annotation, bypassing sequence similarity limitations.