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 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

Related Experiment Video

Updated: Jun 14, 2026

Profiling of Methyltransferases and Other S-adenosyl-L-homocysteine-binding Proteins by Capture Compound Mass Spectrometry (CCMS)
17:12

Profiling of Methyltransferases and Other S-adenosyl-L-homocysteine-binding Proteins by Capture Compound Mass Spectrometry (CCMS)

Published on: December 20, 2010

Large scale study of multiple-molecule queries.

Ramzi J Nasr1, S Joshua Swamidass, Pierre F Baldi

  • 1The Bren School of Information and Computer Science, Institute for Genomics and Bioinformatics, University of California, Irvine, CA 92697-3435, USA. pfbaldi@uci.edu.

Journal of Cheminformatics
|March 20, 2010
PubMed
Summary
This summary is machine-generated.

This study introduces and compares fourteen multiple-molecule query methods for searching chemical databases. Novel methods like Exponential Tanimoto Discriminant (ETD) and Tanimoto Power Discriminant (TPD) show superior performance in retrieving similar molecules.

More Related Videos

Quaternary Structure Modeling Through Chemical Cross-Linking Mass Spectrometry: Extending TX-MS Jupyter Reports
05:18

Quaternary Structure Modeling Through Chemical Cross-Linking Mass Spectrometry: Extending TX-MS Jupyter Reports

Published on: October 20, 2021

Combining Chemical Cross-linking and Mass Spectrometry of Intact Protein Complexes to Study the Architecture of Multi-subunit Protein Assemblies
10:01

Combining Chemical Cross-linking and Mass Spectrometry of Intact Protein Complexes to Study the Architecture of Multi-subunit Protein Assemblies

Published on: November 28, 2017

Related Experiment Videos

Last Updated: Jun 14, 2026

Profiling of Methyltransferases and Other S-adenosyl-L-homocysteine-binding Proteins by Capture Compound Mass Spectrometry (CCMS)
17:12

Profiling of Methyltransferases and Other S-adenosyl-L-homocysteine-binding Proteins by Capture Compound Mass Spectrometry (CCMS)

Published on: December 20, 2010

Quaternary Structure Modeling Through Chemical Cross-Linking Mass Spectrometry: Extending TX-MS Jupyter Reports
05:18

Quaternary Structure Modeling Through Chemical Cross-Linking Mass Spectrometry: Extending TX-MS Jupyter Reports

Published on: October 20, 2021

Combining Chemical Cross-linking and Mass Spectrometry of Intact Protein Complexes to Study the Architecture of Multi-subunit Protein Assemblies
10:01

Combining Chemical Cross-linking and Mass Spectrometry of Intact Protein Complexes to Study the Architecture of Multi-subunit Protein Assemblies

Published on: November 28, 2017

Area of Science:

  • Chemoinformatics
  • Computational Chemistry
  • Drug Discovery

Background:

  • Ligand-based screening typically uses a single molecule lead for database searches.
  • Multiple-molecule query methods are less studied and previous research often used proprietary data and lacked rigorous validation.
  • This study addresses the need for robust, publicly validated multiple-molecule query methods.

Purpose of the Study:

  • To develop and compare multiple-molecule query methods for searching chemical databases.
  • To establish a framework for unbiased benchmarking using strict cross-validation protocols.
  • To identify effective methods for retrieving molecules similar to a query set.

Main Methods:

  • Defined and benchmarked fourteen different multiple-molecule query methods.
  • Utilized 41 publicly available data sets of related molecules and large background data sets from ChemDB.
  • Employed a strict cross-validation protocol to assess performance using metrics like AUAC, AUC, F1-measure, and BEDROC.

Main Results:

  • Parameter-free methods MAX-SIM and MIN-RANK performed well, consistent with prior literature.
  • Novel parameterized methods Exponential Tanimoto Discriminant (ETD) and Tanimoto Power Discriminant (TPD), along with Binary Kernel Discriminant (BKD), outperformed most other methods.
  • ETD, TPD, and BKD require one or two parameters for optimal performance.

Conclusions:

  • Validated fourteen multiple-molecule querying methods, including novel ETD and TPD, using public data and standard protocols.
  • ETD, TPD, BKD, MAX-SIM, and MIN-RANK demonstrated the best performance.
  • The study provides a replicable framework and downloadable data for future research in chemical database searching.