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 ensembles to classify compounds for drug discovery.

J Kevin Lanctot1, Santosh Putta, Christian Lemmen

  • 1Deltagen Research Laboratories, Inc, 740 Bay Road, Redwood City, California 94063, USA. klanctot@bioinformatics.uwaterloo.ca

Journal of Chemical Information and Computer Sciences
|November 25, 2003
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

Genomic epidemiology of the 2025 mpox epidemic in Sierra Leone.

Nature medicine·2026
Same author

Correction: SAVI Space-combinatorial encoding of the billion-size synthetically accessible virtual inventory.

Scientific data·2025
Same author

SAVI Space-combinatorial encoding of the billion-size synthetically accessible virtual inventory.

Scientific data·2025
Same author

Combining crystallographic and binding affinity data towards a novel dataset of small molecule overlays.

Journal of computer-aided molecular design·2024
Same author

Verification of the Prediction Accuracy of a Biomarker-Based Prognostic for Veno-Occlusive Disease/Sinusoidal Obstruction Syndrome (VOD/SOS) After Hematopoietic Cell Transplantation (HCT).

Transplantation and cellular therapy·2024
Same author

B-cell receptor signaling activity identifies patients with mantle cell lymphoma at higher risk of progression.

Scientific reports·2024
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
Same journal

Future Papers.

Journal of chemical information and computer sciences·2016
See all related articles

Signal, a new computational method, enhances drug discovery by creating predictive models from compound properties. It effectively classifies compound activity against targets, aiding high-throughput screening.

Area of Science:

  • Computational Chemistry
  • Drug Discovery
  • Bioinformatics

Background:

  • Drug discovery relies on predicting compound activity against biological targets.
  • High-throughput screening (HTS) generates large datasets requiring efficient analysis.
  • Existing methods may not fully leverage diverse chemical descriptor information.

Purpose of the Study:

  • Introduce Signal, a novel ensemble method for classifying small molecule drug target activity.
  • Develop a robust computational approach for analyzing HTS data.
  • Improve the accuracy of predictive models in drug discovery.

Main Methods:

  • Signal employs a two-step process: descriptor evaluation and ensemble model creation.
  • Descriptors are ranked based on their correlation with compound activity (mutual information, chi-square).

Related Experiment Videos

  • Ensemble models are built using high-ranking descriptors (high ranking, high ranking set cover).

    • Main Results:

    • The Signal method effectively creates ensembles of meaningful descriptors from a large property space.
    • It utilizes information from both active and inactive compounds.
    • The combination of chi-square ranking and high ranking set cover ensemble yielded optimal performance on a Thrombin dataset.

    Conclusions:

    • Signal provides a versatile and effective approach for classifying compound activity against drug targets.
    • The method is suitable for analyzing high-throughput screening data.
    • Signal enhances predictive modeling for drug discovery by integrating diverse chemical information.