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 Video

Updated: May 12, 2026

NMR-Based Fragment Screening in a Minimum Sample but Maximum Automation Mode
09:19

NMR-Based Fragment Screening in a Minimum Sample but Maximum Automation Mode

Published on: June 4, 2021

Managing missing measurements in small-molecule screens.

Michael R Browning1, Bradley T Calhoun, S Joshua Swamidass

  • 1Division of Laboratory and Genomic Medicine, Department of Pathology and Immunology, Washington University School of Medicine, St. Louis, MO, USA.

Journal of Computer-Aided Molecular Design
|April 16, 2013
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

Superior transplant recipient outcome prediction and pathology assessment using rapid deep learning applied to procurement kidney biopsies.

Scientific reports·2025
Same author

Domain Knowledge Inclusive Monotonic Neural Network Guides Patient-Specific Induction of General Anesthesia Dosing.

A&A practice·2025
Same author

Development of a deep learning algorithm for Paneth cell density quantification for inflammatory bowel disease.

EBioMedicine·2024
Same author

Understanding and mitigating the impact of race with adversarial autoencoders.

Communications medicine·2024
Same author

Role of Artificial Intelligence in Kidney Pathology: Promises and Pitfalls.

Kidney360·2024
Same author

GAiN: An integrative tool utilizing generative adversarial neural networks for augmented gene expression analysis.

Patterns (New York, N.Y.)·2024

High-throughput screening (HTS) often misses active molecules due to unmeasured data. This study uses machine learning imputation to accurately predict missing measurements, significantly improving the identification of active compounds for drug discovery.

Area of Science:

  • Medicinal Chemistry
  • Computational Biology
  • Drug Discovery

Background:

  • High-throughput screening (HTS) campaigns typically measure less than 1% of small-molecule libraries.
  • The vast majority of molecules are excluded from downstream analysis, potentially missing active compounds.
  • Missing experimental data is a significant barrier to identifying all active molecules in HTS.

Purpose of the Study:

  • To address the challenge of missing measurements in HTS.
  • To improve the identification of active small molecules by leveraging imputation techniques.
  • To develop a novel visualization method for HTS results that incorporates imputed data.

Main Methods:

  • Utilized imputation, a machine learning technique, to predict missing experimental measurements.

More Related Videos

Nano-Differential Scanning Fluorimetry for Screening in Fragment-based Lead Discovery
06:26

Nano-Differential Scanning Fluorimetry for Screening in Fragment-based Lead Discovery

Published on: May 16, 2021

Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source
08:35

Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source

Published on: May 29, 2021

Related Experiment Videos

Last Updated: May 12, 2026

NMR-Based Fragment Screening in a Minimum Sample but Maximum Automation Mode
09:19

NMR-Based Fragment Screening in a Minimum Sample but Maximum Automation Mode

Published on: June 4, 2021

Nano-Differential Scanning Fluorimetry for Screening in Fragment-based Lead Discovery
06:26

Nano-Differential Scanning Fluorimetry for Screening in Fragment-based Lead Discovery

Published on: May 16, 2021

Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source
08:35

Achieving Efficient Fragment Screening at XChem Facility at Diamond Light Source

Published on: May 29, 2021

  • Constructed an imputed scaffold tree visualization based on existing methods.
  • Validated the imputation methodology through simulations on eight quantitative HTS datasets.

    • Main Results:

    • The imputed visualization successfully identified nearly all active molecule groups in simulated HTS experiments.
    • The method effectively recovered active molecules that would have been missed with traditional analysis.
    • Simulations demonstrated the robustness of the imputation approach across diverse datasets.

    Conclusions:

    • Imputation is a powerful tool for managing missing data in HTS campaigns.
    • This approach significantly enhances the ability to identify novel active molecules.
    • The method offers a rapid and cost-effective strategy for drug discovery, potentially uncovering new intellectual property.