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

Searching for discrimination rules in protease proteolytic cleavage activity using genetic programming with a min-max

Zheng Rong Yang1, Rebecca Thomson, T Charles Hodgman

  • 1School of Engineering and Computer Science, Exeter University, Northcote House The Queen's Drive, Exeter EX4 4QJ, UK. z.r.yang@ex.ac.uk

Bio Systems
|December 4, 2003
PubMed
Summary

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

Longitudinal, Multi-Cycle Evaluation of Passive Function Improvement in People with Arm Spasticity Treated with Botulinum Toxin A.

Toxins·2026
Same author

A symptom network approach to schizophrenia in the CATIE study: processing speed as the central cognitive impairment.

BJPsych open·2026
Same author

Global risk of selection and spread of Plasmodium falciparum histidine-rich protein 2 and 3 gene deletions.

Nature medicine·2025
Same author

The NEuroCOUGH Chronic Cough Registry: a protocol for a pan-European observational study.

ERJ open research·2025
Same author

The Protective Effect of Omeprazole on Vancomycin Cytotoxicity in HK-2 Cells and Renal Injury in Rats.

BioMed research international·2025
Same author

A Proof-of-Concept Development on Speech Analysis for Concussion Detection.

Studies in health technology and informatics·2025

This study introduces a novel algorithm using genetic programming to predict protease cleavage sites in oligopeptides. The method outperforms traditional decision tree approaches for accurate cleavage activity prediction.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning

Background:

  • Protease activity is crucial in biological processes and disease.
  • Accurate prediction of proteolytic cleavage sites is essential for drug discovery and understanding enzyme function.
  • Existing methods for cleavage site prediction often lack accuracy and efficiency.

Purpose of the Study:

  • To develop a novel algorithm for extracting discriminant rules from oligopeptides for protease cleavage activity prediction.
  • To improve the accuracy and efficiency of predicting protease cleavage sites.
  • To compare the algorithm's performance against conventional methods.

Main Methods:

  • Genetic programming was employed to develop the algorithm.
  • Key components include a min-max scoring function utilizing amino acid similarity matrices, reverse Polish notation (RPN) for simplified evolutionary operations, and minimum description length (MDL) to prevent overfitting.

Related Experiment Videos

  • A fitness function combining the Fisher ratio and MDL was used for an efficient evolutionary process.

    • Main Results:

    • The algorithm successfully extracts discriminant rules from oligopeptides for protease cleavage activity prediction.
    • The use of RPN reduced computational cost.
    • Application to four protease datasets (Trypsin, Factor Xa, Hepatitis C Virus, and HIV protease) demonstrated superior performance compared to the C5 algorithm.
    • The min-max scoring function effectively measures similarity between oligopeptides and rules, which are complex algebraic expressions of amino acids.

    Conclusions:

    • The developed genetic programming algorithm offers a superior approach for protease cleavage site prediction.
    • The integration of min-max scoring, RPN, and MDL provides an efficient and accurate method.
    • This algorithm has significant potential for applications in drug discovery and bioinformatics.