Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Author Correction: Comprehensive genomics in androgen receptor-dependent castration-resistant prostate cancer identifies an adaptation pathway mediated by opioid receptor kappa 1.

Communications biology·2022

Same author

Utility of Homologous Recombination Deficiency Biomarkers Across Cancer Types.

JCO precision oncology·2022

Same author

Comprehensive genomics in androgen receptor-dependent castration-resistant prostate cancer identifies an adaptation pathway mediated by opioid receptor kappa 1.

Communications biology·2022

Same author

Utility of Homologous Recombination Deficiency Biomarkers Across Cancer Types.

JCO precision oncology·2021

Same author

Large scale relative protein ligand binding affinities using non-equilibrium alchemy.

Chemical science·2021

Same author

Active learning effectively identifies a minimal set of maximally informative and asymptotically performant cytotoxic structure-activity patterns in NCI-60 cell lines.

RSC medicinal chemistry·2021

Search research articles

Related Experiment Video

Updated: Jun 20, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

ADMET Predictability at Boehringer Ingelheim: State-of-the-Art, and Do Bigger Datasets or Algorithms Make a

Stevan Aleksić¹, Daniel Seeliger¹, J B Brown¹

¹Medicinal Chemistry, Boehringer Ingelheim Pharma GmbH & Co. KG, 88397, Biberach, Germany.

Molecular Informatics

|September 2, 2021

Summary

Computational models for drug discovery show limited gains from larger datasets or advanced algorithms. Performance improvements in ADMET prediction are assay-specific, guiding realistic expectations for computational drug design.

Keywords:

ADMET modelling algorithm comparison chemical representation congeneric series machine learning

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jun 20, 2026

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

DeepOmicsAE: Representing Signaling Modules in Alzheimer's Disease with Deep Learning Analysis of Proteomics, Metabolomics, and Clinical Data

Published on: December 15, 2023

Area of Science:

Computational chemistry and cheminformatics
Drug discovery and development
Pharmacology and toxicology

Background:

Computational methods are integral to modern pharmaceutical research for drug discovery.
Digital ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) assay data fuels predictive model development.
The actual utility of these predictive models in ADMET research remains unclear despite data and algorithm advancements.

Purpose of the Study:

To critically evaluate the impact of data volume, modeling algorithms, chemical representation, and assay timing on ADMET prediction.
To identify which ADMET assays are most and least amenable to computational prediction.
To establish realistic expectations for the application of computational models in guiding molecular design.

Main Methods:

Analysis of an in-house ADMET database.
Systematic evaluation of relationships between prediction performance and factors like dataset size, algorithm choice, chemical features, and assay chronology.
Identification of assay-specific prediction suitability.

Main Results:

No significant performance differences were observed between various prediction algorithms.
Increasing dataset size did not yield substantial or systemic improvements in prediction accuracy.
Temporal data expansion improved performance in only a subset of assays, with minimal gains.

Conclusions:

The predictive power of computational models in ADMET research is highly assay-dependent.
Current data volumes and algorithms offer limited, non-systemic improvements for many ADMET predictions.
This study provides a framework for understanding the limitations and potential of computational approaches in drug development.