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

Multicompartment Models: Overview

Multicompartment Models: Overview

Multicompartment models are mathematical constructs that depict how drugs are distributed and eliminated within the body. They segment the body into several compartments, symbolizing various physiological or anatomical areas connected through drug transfer processes such as absorption, metabolism, distribution, and elimination.
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...

Cardiovascular Drugs: Classification based on Therapeutic Indications

Cardiovascular Drugs: Classification based on Therapeutic Indications

Cardiovascular diseases, encompassing a range of conditions, can significantly affect the heart's operations and the overall circulatory system. These conditions impair the heart's ability to pump blood, leading to a deficit in oxygen supply to crucial organs. Anomalies in the heart's electrical system, known as arrhythmias, can cause heartbeats to accelerate or slow down. Usually, heart rates increase during physical activity and decrease while resting or sleeping. However,...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Optima: a GUI-based toolkit for developing and validating interpretable machine learning based supervised classification QSAR models.

SAR and QSAR in environmental research·2026

Same author

Managing Blood Pressure in Dialysis Patients: A Summary of UK Clinical Practice Guideline.

Kidney international reports·2026

Same author

Effectiveness of Intensity Modulate Proton Therapy in Managing Complex Multiple Meningiomas: A Dosimetric and Radiobiological Comparative Study with Helical Tomotherapy on Neurological Risk.

Clinical oncology (Royal College of Radiologists (Great Britain))·2025

Same author

Fabry disease in the haemodialysis population: outcome of a UK screening study (SoFAH).

BMC nephrology·2025

Same author

Modelling of intrinsic membrane permeability of drug molecules by explainable ML-based q-RASPR approach towards better pharmacokinetics and toxicokinetics properties.

SAR and QSAR in environmental research·2025

Same author

Geometric and Dosimetric Evaluation of a RayStation Deep Learning Model for Auto-Segmentation of Organs at Risk in a Real-World Head and Neck Cancer Dataset.

Clinical oncology (Royal College of Radiologists (Great Britain))·2025

Search research articles

Related Experiment Video

Updated: Jan 18, 2026

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

First report on machine learning based multiclass classification of Caco-2 permeability using different balancing

I Dasgupta¹, S Gayen¹

¹Laboratory of Drug Design and Discovery, Department of Pharmaceutical Technology, Jadavpur University, Kolkata, India.

SAR and QSAR in Environmental Research

|September 8, 2025

Summary

This summary is machine-generated.

Machine learning models predict molecule permeability across Caco-2 cells. Data balancing strategies significantly improved multiclass classification accuracy, aiding drug discovery.

Keywords:

Permeability prediction classification models descriptors machine learning sampling methods

More Related Videos

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

Canine Intestinal Organoids in a Dual-Chamber Permeable Support System

Canine Intestinal Organoids in a Dual-Chamber Permeable Support System

Published on: March 2, 2022

Related Experiment Videos

Last Updated: Jan 18, 2026

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

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

Canine Intestinal Organoids in a Dual-Chamber Permeable Support System

Canine Intestinal Organoids in a Dual-Chamber Permeable Support System

Published on: March 2, 2022

Area of Science:

Computational chemistry
Pharmacokinetics
Machine learning in drug discovery

Background:

Caco-2 cell permeability is vital for assessing drug absorption and efficacy.
Predicting molecular permeability is challenging due to complex biological factors and data limitations.
Class imbalance in permeability datasets hinders the development of accurate multiclass predictive models.

Purpose of the Study:

To develop and evaluate machine learning-based multiclass classification models for predicting Caco-2 cell permeability.
To investigate the impact of various data balancing strategies on model performance for imbalanced permeability datasets.
To enhance model interpretability using SHAP analysis for descriptor importance.

Main Methods:

Development of multiclass classification models using machine learning algorithms.
Application of oversampling (e.g., ADASYN), undersampling, and hybrid balancing techniques to address class imbalance.
Hyperparameter optimization using five-fold cross-validation.
Evaluation of model performance on a test set using accuracy and Matthews Correlation Coefficient (MCC).
SHAP (SHapley Additive exPlanations) analysis for model interpretability.

Main Results:

The XGBoost multiclass classifier, trained with ADASYN oversampling, achieved the highest performance (accuracy: 0.717, MCC: 0.512) on the test set.
Separate classification of extreme permeability classes yielded strong predictive performance (accuracy: 0.853, MCC: 0.703).
SHAP analysis provided insights into descriptor importance, enhancing model explainability.

Conclusions:

Data balancing strategies are crucial for improving the predictive performance of machine learning models in multiclass permeability classification.
The developed models offer a valuable framework for drug permeability assessment in drug discovery and development.
Machine learning approaches, combined with appropriate data handling techniques, can effectively predict molecular permeability across Caco-2 cells.