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

Boosting classifier for predicting protein domain structural class.

Kai-Yan Feng1, Yu-Dong Cai, Kuo-Chen Chou

  • 1Imaging Science and Biomedical Engineering, Medical School, The University of Manchester, Manchester, M13 9PT, UK.

Biochemical and Biophysical Research Communications
|July 5, 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

Identification of Gene Markers Associated with COVID-19 Severity and Recovery in Different Immune Cell Subtypes.

Biology·2023
Same author

Machine Learning Classification of Time since BNT162b2 COVID-19 Vaccination Based on Array-Measured Antibody Activity.

Life (Basel, Switzerland)·2023
Same author

DNAPred_Prot: Identification of DNA-Binding Proteins Using Composition- and Position-Based Features.

Applied bionics and biomechanics·2022
Same author

iHyd-LysSite (EPSV): Identifying Hydroxylysine Sites in Protein Using Statistical Formulation by Extracting Enhanced Position and Sequence Variant Feature Technique.

Current genomics·2020
Same author

Two Latest Hot Researches in Medicinal Chemistry.

Current topics in medicinal chemistry·2020
Same author

RETRACTED ARTICLE: An insightful 20-year recollection since the birth of pseudo amino acid components.

Amino acids·2020
Same journal

NAT10-mediated RNA N4-acetylation promotes intestinal fibroblast senescence via DHRS2.

Biochemical and biophysical research communications·2026
Same journal

Deciphering potent MPL activation by the fucose-binding lectin thrombocorticin.

Biochemical and biophysical research communications·2026
Same journal

Mitochondrial genome alterations in cancer: From mutations and epigenetics to targeted therapiesack.

Biochemical and biophysical research communications·2026
Same journal

GPC3 chimeric antigen receptor (CAR)-NK cells combined with Enoblituzumab enhance the anti-tumor efficacy against hepatocellular carcinoma.

Biochemical and biophysical research communications·2026
Same journal

A miR-382-5p-PORCN axis modulates endogenous Wnt signaling during palatal development.

Biochemical and biophysical research communications·2026
Same journal

Development of a vitamin-related gene signature to predict the immune characteristics and prognosis of glioma.

Biochemical and biophysical research communications·2026
See all related articles

A new LogitBoost classifier accurately predicts protein structural class from amino acid sequences. This robust method outperforms existing classifiers and shows promise for other protein attribute predictions.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning in Biology

Background:

  • Predicting protein structural class from amino acid sequences is crucial for understanding protein function.
  • Existing classification methods may be sensitive to noise and outliers.

Purpose of the Study:

  • To introduce and evaluate a novel classifier, LogitBoost, for predicting protein domain structural class based on amino acid sequences.

Main Methods:

  • Developed the LogitBoost classifier utilizing a log-likelihood loss function.
  • Employed a strategy of combining multiple weak classifiers into a strong, robust classifier.
  • Validated performance using jackknife cross-validation tests.

Main Results:

Related Experiment Videos

  • LogitBoost demonstrated superior performance compared to other classifiers, including support vector machines.
  • The classifier showed reduced sensitivity to noise and outliers due to its loss function.

    • Conclusions:

    • LogitBoost is an effective and robust classifier for predicting protein structural class from amino acid sequences.
    • The method holds potential for classifying other protein attributes, such as subcellular localization and enzyme family.