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: Jul 4, 2025

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

5.3K

Inactive-enriched machine-learning models exploiting patent data improve structure-based virtual screening for PDL1

Pablo Gómez-Sacristán1, Saw Simeon1, Viet-Khoa Tran-Nguyen1

  • 1Centre de Recherche en Cancérologie de Marseille, Marseille 13009, France.

Journal of Advanced Research
|January 27, 2024
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

Evaluation of Serum Adipocytokines and Cystatin C As Early Biomarkers in Chronic Kidney Disease Patients and Their Relation to Endothelial Dysfunction.

Cureus·2026
Same author

Decoding carbon, water, and energy exchange driven by agricultural and horticultural intensification in semi-arid ecosystem of India.

Environmental monitoring and assessment·2026
Same author

Successful Outcome of Rhino-Orbital-Cerebral Mucormycosis With Extensive Intracranial Disease in a Patient With Poorly Controlled Diabetes.

The Permanente journal·2026
Same author

Incidence and Outcomes of Metastatic Patterns of Pancreatic Ductal Adenocarcinoma.

The American surgeon·2025
Same author

Management of Hypertension and Associated Comorbidities: An Expert Consensus Statement from India.

The Journal of the Association of Physicians of India·2025
Same author

Computational modeling of protein-ligand interactions: From binding site identification to pose prediction and beyond.

Current opinion in structural biology·2025
This summary is machine-generated.

Machine learning scoring functions (SFs) targeting PDL1 dimerization show promise for developing new cancer drugs. These PDL1-specific SFs outperform generic methods, aiding the discovery of novel inhibitors.

Area of Science:

  • Computational drug discovery
  • Machine learning in pharmacology
  • Protein-ligand interactions

Background:

  • Targeting Programmed Cell Death Protein 1/Programmed Death-Ligand 1 (PD1/PDL1) through PDL1 dimerization offers a path to cost-effective cancer therapies with improved patient outcomes and reduced side effects.
  • Developing PDL1 dimerizers has been challenging, with limited clinical progression, highlighting the need for efficient drug discovery methods.

Purpose of the Study:

  • To demonstrate the utility of structure-based virtual screening (SBVS) employing PDL1-specific machine learning scoring functions (MLSFs) for identifying PD1/PDL1 inhibitors via PDL1 dimerization.
  • To establish MLSFs as a potent tool in drug design for this therapeutic target.

Main Methods:

  • Generation and evaluation of numerous PDL1-specific MLSFs, including both classifiers and inactive-enriched regressors.
Keywords:
Artificial intelligenceDockingImmunotherapyMachine learningPD1PDL1Virtual screening

More Related Videos

Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors
10:29

Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors

Published on: May 9, 2025

1.1K
Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

2.5K

Related Experiment Videos

Last Updated: Jul 4, 2025

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

5.3K
Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors
10:29

Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors

Published on: May 9, 2025

1.1K
Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA
10:21

Author Spotlight: Streamlining Protein Target Prediction and Validation via Molecular Docking and CETSA

Published on: February 23, 2024

2.5K
  • Incorporation of recent advancements in MLSF development.
  • Validation using two rigorous test datasets to assess predictive performance.

    • Main Results:

    • Successfully generated 60 PDL1-specific MLSFs (30 classifiers, 30 regressors).
    • Demonstrated that large-scale training datasets incorporating numerous docked inactives significantly enhance MLSF performance.
    • Achieved highly predictive capabilities for the developed PDL1-specific MLSFs.

    Conclusions:

    • PDL1-specific MLSFs significantly outperformed generic scoring functions across various types for the PDL1 target.
    • The developed PDL1-specific MLSFs are made publicly available without restrictions to facilitate further research and drug development.