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

Analysis of a large structure/biological activity data set using recursive partitioning.

A Rusinko1, M W Farmen, C G Lambert

  • 1Glaxo Wellcome Inc., North Carolina 27709, USA.

Journal of Chemical Information and Computer Sciences
|December 30, 1999
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

The rostromedial tegmental nucleus modulates the development of stress-induced helpless behavior.

Behavioural brain research·2018
Same author

The rectus abdominis muscle advancement flap as a salvage option for chest wall reconstruction.

Annals of the Royal College of Surgeons of England·2017
Same author

Estimating deep molecular responses in chronic myelogenous leukemia: a Bayesian approach.

Leukemia·2016
Same author

Relationship of thyroid transcription factor 1 to EGFR status in non-small-cell lung cancer.

Current oncology (Toronto, Ont.)·2014
Same author

Chronic illness and return to work: a social cognitive perspective.

Work (Reading, Mass.)·2014
Same author

Computer simulation of within family selection in finite populations.

TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik·2014

Recursive partitioning, implemented in the SCAM program, efficiently analyzes large datasets to classify molecules by potency. This method reveals substructural rules and classifies inhibitors, even with complex binding mechanisms.

Area of Science:

  • Drug discovery and development
  • Computational chemistry
  • Medicinal chemistry

Background:

  • Combinatorial chemistry and high-throughput screening generate vast amounts of data, overwhelming traditional structure-activity relationship (SAR) analysis.
  • Existing quantitative structure-activity relationship (QSAR) methods often require compounds to follow a single binding mechanism, limiting their applicability to complex datasets.

Purpose of the Study:

  • To introduce and exemplify a novel computational method for analyzing large-scale SAR data.
  • To demonstrate the capability of recursive partitioning for classifying molecules based on biological potency.
  • To address the limitations of traditional SAR analysis in handling complex datasets and diverse binding mechanisms.

Main Methods:

  • Utilized recursive partitioning, a statistical method for classifying objects into similar categories.

Related Experiment Videos

  • Implemented the SCAM (Structure-Classification Analysis of Molecules) computer program for efficient application of recursive partitioning.
  • Applied the method to a dataset of 1650 monoamine oxidase inhibitors to derive substructural rules.

    • Main Results:

    • The SCAM program efficiently determined classification rules from large biological assay datasets.
    • The method successfully yielded substructural rules and general classifications for monoamine oxidase inhibitors.
    • The approach demonstrated linear scalability with the number of molecular descriptors, enabling analysis of hundreds of thousands of structures.

    Conclusions:

    • Recursive partitioning, as implemented in SCAM, offers a scalable and effective solution for SAR analysis of large and complex datasets.
    • The method's ability to handle mixtures and identify SAR rules for compounds with different binding mechanisms is a significant advantage over traditional QSAR approaches.
    • This methodology has the potential to revolutionize lead discovery by enabling the analysis of unprecedented volumes of chemical and biological data.