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

Classification and knowledge discovery in protein databases.

Predrag Radivojac1, Nitesh V Chawla, A Keith Dunker

  • 1Center for Information Science and Technology, Temple University, USA.

Journal of Biomedical Informatics
|October 7, 2004
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

Saturation Genome Editing reveals the functional impact of RAD51D <i>and</i> XRCC2 variants.

bioRxiv : the preprint server for biology·2026
Same author

Improving splice site usage prediction with SPLAIRE.

bioRxiv : the preprint server for biology·2026
Same author

Organic Chemistry as a Catalyst for AI Innovation: Challenges, Methods, and Emerging Paradigms.

Chemical reviews·2026
Same author

On the state of protein function prediction: a report on the fourth CAFA challenge.

bioRxiv : the preprint server for biology·2026
Same author

Gene- and domain-aware calibration increases the clinical utility of variant effect predictors.

Research square·2026
Same author

Advances in Protein Function Prediction from the Fifth CAFA Challenge.

bioRxiv : the preprint server for biology·2026
Same journal

Evaluation of temporal preservation in synthetic longitudinal patient data.

Journal of biomedical informatics·2026
Same journal

ARKE: An ontology-driven framework for automated mapping of local radiology procedure terms to the LOINC-RadLex playbook using large language model.

Journal of biomedical informatics·2026
Same journal

A validation-driven training controller for cross-lingual biomedical NER via reinforcement learning-based adaptive loss weighting.

Journal of biomedical informatics·2026
Same journal

ASP-HR: An Adaptive Spatial Perception and Hierarchical Reasoning mechanism for document-level biomedical relation extraction.

Journal of biomedical informatics·2026
Same journal

Beyond Accuracy: Safety-Centered guidelines for the evaluation of LLM-based therapy recommendation systems for chronic multimorbidity patients.

Journal of biomedical informatics·2026
Same journal

DeepEN: A deep reinforcement learning framework for personalized enteral nutrition in critical care.

Journal of biomedical informatics·2026
See all related articles

This study introduces a three-stage machine learning framework for classifying noisy, high-dimensional, and imbalanced protein data. Ensemble logistic regression models show robustness, while neural networks excel on large datasets, improving classification accuracy.

Area of Science:

  • Bioinformatics
  • Machine Learning
  • Computational Biology

Background:

  • Protein datasets often present challenges such as high dimensionality, noise, and class imbalance.
  • Accurate classification of protein data is crucial for various biological and biomedical applications.

Purpose of the Study:

  • To develop a robust machine learning framework for protein dataset classification.
  • To address noise and class imbalance issues in high-dimensional protein data.
  • To integrate prior biological knowledge for improved classification performance.

Main Methods:

  • A three-stage framework: feature selection, noise/imbalance handling, and prior-knowledge based clustering.
  • Fisher's permutation test for feature selection.
  • Ensemble learning with over-sampling and under-sampling techniques for class imbalance.

Related Experiment Videos

  • Prior-knowledge based clustering to partition unlabeled data.

    • Main Results:

    • Fisher's permutation test demonstrated effectiveness as a feature selection filter for protein datasets.
    • Ensemble logistic regression models often outperformed other models due to robustness to noise and low sample density.
    • Ensemble neural networks proved effective for large datasets.
    • Specialized classifiers trained on clusters derived from prior knowledge further reduced classification error.

    Conclusions:

    • The proposed three-stage framework effectively handles noisy, high-dimensional, and imbalanced protein data.
    • Ensemble methods, particularly logistic regression and neural networks, offer robust solutions for protein classification.
    • Incorporating prior biological knowledge through clustering enhances classification accuracy.