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

Prediction of protein structural classes by modified mahalanobis discriminant algorithm

W M Liu1, K C Chou

  • 1Department of Computer and Information Science, Indiana University Purdue University Indianapolis, 46202-5132, USA.

Journal of Protein Chemistry
|May 20, 1998
PubMed
Summary

This study introduces a modified least Mahalanobis distance method for predicting protein structural classes using secondary structure information. The new method improves accuracy when class sample sizes or covariance matrices differ significantly.

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

Test of CP Symmetry in the Neutral Decays of Λ via J/ψ→ΛΛ[over ¯].

Physical review letters·2026
Same author

Precise Measurement of the Chromoelectric Dipole Moment of the Charm Quark.

Physical review letters·2026
Same author

Precise Measurement of Matter-Antimatter Asymmetry with Entangled Hyperon-Antihyperon Pairs.

Physical review letters·2026
Same author

Observation of Λ[over ¯]p→K^{+}π^{+}π^{-}π^{0} and Λ[over ¯]p→K^{+}π^{+}π^{-}2π^{0}.

Physical review letters·2026
Same author

First Measurement of the D_{s}^{+}→K^{0}μ^{+}ν_{μ} Decay.

Physical review letters·2026
Same author

Observation of the Electromagnetic Radiative Decays of the Λ(1520) and Λ(1690) to γΣ^{0}.

Physical review letters·2026

Area of Science:

  • Computational Biology
  • Structural Bioinformatics
  • Machine Learning in Biochemistry

Background:

  • Accurate prediction of protein structural classes is crucial for understanding protein function and evolution.
  • Existing methods for protein class prediction often struggle with imbalanced datasets or heterogeneous class covariance matrices.

Purpose of the Study:

  • To develop and evaluate a modified least Mahalanobis distance method for enhanced protein structural class prediction.
  • To provide quantitative rules for determining protein structural classes based on secondary structure elements.

Main Methods:

  • Quantitative analysis of protein secondary structures to establish classification rules.
  • Generalization of the quadratic discriminant function to handle degenerate covariance matrices.

Related Experiment Videos

  • Comparative analysis using resubstitution and leave-one-out cross-validation tests.

    • Main Results:

    • The modified least Mahalanobis distance method demonstrates superior performance compared to standard methods under specific conditions.
    • The proposed method effectively addresses challenges posed by unequal class sample sizes and differing covariance matrices.
    • Validation confirms the robustness and accuracy of the new prediction algorithm.

    Conclusions:

    • The modified least Mahalanobis distance method is recommended for protein class prediction when dealing with significant variations in class sample sizes or covariance matrices.
    • This advancement offers a more reliable approach to classifying protein structures based on secondary structure data.
    • The study provides a valuable tool for computational biologists and bioinformaticians.