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

Development of New Methods Needs Proper Evaluation-Benchmarking Sets for Machine Learning Experiments for Class A

Damian Leśniak1, Sabina Podlewska2,3, Stanisław Jastrzębski1

  • 1Faculty of Mathematics and Computer Science , Jagiellonian University , 6 Łojasiewicza Street , 30-348 Kraków , Poland.

Journal of Chemical Information and Modeling
|October 12, 2019
PubMed
Summary

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

Decoding Prolonged Residence Time of 5-HT<sub>2A</sub> Receptor Antagonists: Insights from Ritanserin Derivatives.

Journal of chemical information and modeling·2026
Same author

Polyfunctionalized <i>N</i>-Arylsulfonyl Indoles: Identification of (<i>E</i>)-<i>N</i>-Hydroxy-3-{3-[(5-(3-(piperidin-1-yl)propoxy]-1<i>H</i>-indol-1-yl)sulfonyl]phenyl}acrylamide (MTP150) for the Epigenetic-Based Therapy of Parkinson's Disease.

International journal of molecular sciences·2026
Same author

Novel Dual 5-HT<sub>7</sub> Antagonists and Sodium Channel Inhibitors as Potential Therapeutic Agents with Antidepressant and Anxiolytic Activities.

Pharmaceuticals (Basel, Switzerland)·2025
Same author

Identification of Orthosteric GABA<sub>B</sub> Receptor Ligands by Virtual Screening and <i>In Vitro</i> Validation.

ACS omega·2025
Same author

Residence time in drug discovery: current insights and future perspectives.

Pharmacological reports : PR·2025
Same author

Correction: Compound PZ-1262, a 4-isoquinoline-sulfonamide analog of Brexpiprazole, produces potential antidepressant, anxiolytic and procognitive effects in rodent models.

Pharmacological reports : PR·2025
Same journal

DeepDPM: A Deep Learning Method for MoRFs Prediction Based on Wavelet Transform and Dynamic Convolutional Attention Mechanism.

Journal of chemical information and modeling·2026
Same journal

Graph-Based Generation and Reduction of Complex Chemical Reaction Networks.

Journal of chemical information and modeling·2026
Same journal

Modeling the Sensitivity of Large-Scale Virtual Screening to Scoring Function Accuracy, Artifacts, and Library Composition.

Journal of chemical information and modeling·2026
Same journal

Machine Learning-Driven Discovery of Indole/Oxoindole-Piperazine Scaffolds as Dual MAO-B/Sig-1R Ligands for Neurodegenerative Disorders.

Journal of chemical information and modeling·2026
Same journal

Mapping Evolution of Molecules across Biochemistry with Assembly Theory.

Journal of chemical information and modeling·2026
Same journal

Structural Proteomics-Based Deciphering of Hydrophobic Packing Fingerprints Informing Protein Thermostability in TIM Barrels.

Journal of chemical information and modeling·2026
See all related articles
This summary is machine-generated.

This study introduces a robust protocol for preparing reliable benchmark datasets for virtual screening. It addresses data fetching, compound representation bias, and data splitting strategies to ensure accurate computational method assessment.

Area of Science:

  • Computational Chemistry
  • Cheminformatics
  • Drug Discovery

Background:

  • Virtual screening is crucial for identifying new active compounds.
  • Evaluating computational tools requires reliable benchmark datasets.
  • Existing methods for dataset preparation may introduce bias.

Purpose of the Study:

  • To develop a comprehensive protocol for creating benchmark datasets for virtual screening.
  • To analyze potential biases in data fetching, compound representation, and dataset splitting.
  • To establish reliable benchmarks for assessing computational screening methods.

Main Methods:

  • Data retrieval from the ChEMBL database.
  • Analysis of various compound representations for potential bias.

Related Experiment Videos

  • Development of a novel chemical structure similarity metric.
  • Evaluation of different training/test set division strategies.
  • Application of machine learning for cross-validation studies.

    • Main Results:

    • A standardized protocol for benchmark dataset preparation was established.
    • Identified and quantified biases associated with compound representations and data splitting.
    • A new, chemically intuitive similarity metric was developed and validated.
    • Generated benchmark datasets for virtual screening, including those for class A G protein-coupled receptors.

    Conclusions:

    • The proposed protocol enhances the reliability of virtual screening method evaluation.
    • Addressing data preparation biases is critical for accurate computational tool assessment.
    • The generated benchmarks and tools facilitate reproducible research in computational drug discovery.