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

Using functional domain composition to predict enzyme family classes.

Yu-Dong Cai1, Kuo-Chen Chou

  • 1Biomolecular Sciences Department, University of Manchester Institute of Science & Technology, Manchester, M60 1QD, United Kingdom. y.cai@umist.ac.uk

Journal of Proteome Research
|February 15, 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

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RETRACTED ARTICLE: An insightful 20-year recollection since the birth of pseudo amino acid components.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

iMethylK_pseAAC: Improving Accuracy of Lysine Methylation Sites Identification by Incorporating Statistical Moments and Position Relative Features into General PseAAC <i>via</i> Chou's 5-steps Rule.

Current genomics·2020
Same author

iSulfoTyr-PseAAC: Identify Tyrosine Sulfation Sites by Incorporating Statistical Moments <i>via</i> Chou's 5-steps Rule and Pseudo Components.

Current genomics·2020
Same journal

From Method-Defined Signals to Reference Measurement Procedures: Two Decades of Mass Spectrometry-Based ProGRP Quantification.

Journal of proteome research·2026
Same journal

Proteomic Profiling of Extracellular Vesicle-Enriched Plasma Using Mag-Net for Biomarker Discovery in Pancreatic Ductal Adenocarcinoma.

Journal of proteome research·2026
Same journal

Computationally Efficient Bayesian Estimation of Graphical Networks for Omics Data.

Journal of proteome research·2026
Same journal

Hierarchy of MS-Based Evidence.

Journal of proteome research·2026
Same journal

Proteomic Profiling of Exosomes from HPV-Positive and HPV-Negative Head and Neck Squamous Cell Carcinoma: Selective Cargo Packaging.

Journal of proteome research·2026
Same journal

Proteomic Analysis Identifies ATE1-Dependent Arginylation Dysregulation across Meningioma Grades.

Journal of proteome research·2026
See all related articles

A new method uses functional domain composition to predict enzyme classes in proteins. This approach achieves 85% accuracy, outperforming other methods on stringent datasets for bioinformatics and proteomics.

Area of Science:

  • Bioinformatics
  • Proteomics
  • Enzymology

Background:

  • Enzymes are classified into six main classes based on EC numbers.
  • Predicting enzyme function from protein sequences is crucial in bioinformatics.
  • Existing methods may not fully capture sequence and function relationships.

Purpose of the Study:

  • To develop a novel method for predicting enzyme attributes.
  • To incorporate functional domain composition for enhanced protein sequence representation.
  • To evaluate the method's performance on a challenging, non-homologous dataset.

Main Methods:

  • Utilized functional domain composition to represent protein sequences.
  • Developed a predictor incorporating sequence-order and function-related features.

Related Experiment Videos

  • Performed jackknife cross-validation on a dataset with <20% sequence identity.

    • Main Results:

    • Achieved an overall success rate of 85% in identifying enzyme family classes.
    • Successfully identified non-enzyme protein sequences.
    • Demonstrated significantly higher accuracy compared to other methods on the stringent dataset.

    Conclusions:

    • Functional domain composition is a promising approach for protein statistical prediction.
    • The developed method offers a powerful new tool for bioinformatics and proteomics.
    • This approach effectively integrates sequence and functional information for enzyme classification.