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

Mining SARS-CoV protease cleavage data using non-orthogonal decision trees: a novel method for decisive template

Zheng Rong Yang1

  • 1Department of Computer Science, Exeter University, United Kingdom. z.r.yang@exeter.ac.uk

Bioinformatics (Oxford, England)
|March 31, 2005
PubMed
Summary

Scientists developed a new method to analyze protease data by constructing non-orthogonal decision trees. This approach significantly improves prediction accuracy for identifying cleavage sites in SARS-related coronaviruses.

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

In silico prediction of Severe Acute Respiratory Syndrome Coronavirus 2 main protease cleavage sites.

Proteins·2021
Same author

Global Analysis of Genes Essential for Francisella tularensis Schu S4 Growth <i>In Vitro</i> and for Fitness during Competitive Infection of Fischer 344 Rats.

Journal of bacteriology·2019
Same author

A Noise Trimming and Positional Significance of Transposon Insertion System to Identify Essential Genes in Yersinia pestis.

Scientific reports·2017
Same author

Multi-omic measurement of mutually exclusive loss-of-function enriches for candidate synthetic lethal gene pairs.

BMC genomics·2016
Same author

Improved prediction of RNA secondary structure by integrating the free energy model with restraints derived from experimental probing data.

Nucleic acids research·2015
Same author

An ultra-fast metabolite prediction algorithm.

PloS one·2012

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Virology

Background:

  • The severe acute respiratory syndrome (SARS) may re-emerge, necessitating effective inhibitor design.
  • Understanding SARS-related coronavirus (SARS-CoV) cleavage site specificity is crucial for drug development.
  • Conventional inductive programming methods struggle with non-orthogonal data patterns.

Purpose of the Study:

  • To develop a novel method for constructing non-orthogonal decision trees for mining protease data.
  • To improve the prediction accuracy of cleavage sites in SARS-CoV.
  • To identify decisive templates for inhibitor design.

Main Methods:

  • Downloaded 18 SARS-related coronavirus polyprotein sequences from NCBI.
  • Generated approximately 50,000 k-mer subsequences using a sliding window approach (k=4-12).

Related Experiment Videos

  • Applied a bio-mapping transform using a bio-basis function to a high-dimensional numerical space for inductive programming.

    • Main Results:

    • Constructed non-orthogonal decision trees by selecting about 10 decisive k-mer templates from 50,000.
    • Significantly improved prediction accuracy for cleavage sites.
    • Identified a small set of critical k-mers for decision-making.

    Conclusions:

    • The novel non-orthogonal decision tree method effectively mines protease data.
    • This approach enhances the identification of SARS-CoV cleavage sites.
    • The findings support the design of targeted inhibitors against SARS-CoV.