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

Machine learning for skin permeability prediction: random forest and XG boost regression.

Journal of drug targeting·2023
Same author

Response to: Regarding the Article: Coronavirus Disease (COVID-19): Current Status and Prospects for Drug and Vaccine Development.

Archives of medical research·2021
Same author

COVID-19 Vaccines: New Developments and the Road Ahead.

Archives of medical research·2020
Same author

Coronavirus Disease (COVID-19): Current Status and Prospects for Drug and Vaccine Development.

Archives of medical research·2020
Same author

Polyplexes for gene and nucleic acid delivery: Progress and bottlenecks.

European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences·2020
Same author

Percutaneous Delivery of Antihypertensive Agents: Advances and Challenges.

AAPS PharmSciTech·2020

Related Experiment Video

Updated: Jul 5, 2025

A Method for Determination and Simulation of Permeability and Diffusion in a 3D Tissue Model in a Membrane Insert System for Multi-well Plates
10:33

A Method for Determination and Simulation of Permeability and Diffusion in a 3D Tissue Model in a Membrane Insert System for Multi-well Plates

Published on: February 23, 2018

25.3K

Artificial intelligence for skin permeability prediction: deep learning.

Kevin Ita1, Sahba Roshanaei1

  • 1College of Pharmacy, Touro University, Vallejo, CA, USA.

Journal of Drug Targeting
|January 23, 2024
PubMed
Summary
This summary is machine-generated.

Deep learning models, including convolutional neural networks, can accurately predict xenobiotic skin permeability. This offers a faster alternative to traditional laboratory measurements for drug delivery research.

Keywords:
Skin permeabilitydeep learningdescriptorsneural networktransdermal

More Related Videos

Generation of a Simplified Three-Dimensional Skin-on-a-chip Model in a Micromachined Microfluidic Platform
06:30

Generation of a Simplified Three-Dimensional Skin-on-a-chip Model in a Micromachined Microfluidic Platform

Published on: May 17, 2021

4.2K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

Related Experiment Videos

Last Updated: Jul 5, 2025

A Method for Determination and Simulation of Permeability and Diffusion in a 3D Tissue Model in a Membrane Insert System for Multi-well Plates
10:33

A Method for Determination and Simulation of Permeability and Diffusion in a 3D Tissue Model in a Membrane Insert System for Multi-well Plates

Published on: February 23, 2018

25.3K
Generation of a Simplified Three-Dimensional Skin-on-a-chip Model in a Micromachined Microfluidic Platform
06:30

Generation of a Simplified Three-Dimensional Skin-on-a-chip Model in a Micromachined Microfluidic Platform

Published on: May 17, 2021

4.2K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

Area of Science:

  • Pharmacokinetics and Drug Delivery
  • Computational Chemistry
  • Artificial Intelligence in Medicine

Background:

  • Measuring xenobiotic skin permeability (Kp) is labor-intensive.
  • Quantitative structure-permeability relationship (QSPR) models often rely on statistical analysis of experimental data.
  • Deep learning, a subset of machine learning using deep neural networks (DNNs), is gaining traction in computational drug delivery.

Purpose of the Study:

  • To explore the utility of deep learning models for predicting skin permeability coefficients.
  • To develop alternative, efficient methods for assessing xenobiotic transport across the skin.
  • To investigate the predictive performance of Convolutional Neural Networks (CNNs), Feedforward Neural Networks (FNNs), and Recurrent Neural Networks (RNNs) in this context.

Main Methods:

  • Utilized a publicly available dataset of 476 records for 145 chemicals and pharmaceuticals.
  • Applied CNN, FNN, and RNN architectures to predict skin permeability coefficients (log kp).
  • Conducted computations using Python within an Anaconda and Jupyterlab environment with Keras and TensorFlow modules.

Main Results:

  • Successfully predicted log kp values using CNN, FNN, and RNN models.
  • Demonstrated the capability of deep learning networks to model skin permeability.
  • The study validated the predictive power of the chosen deep learning architectures.

Conclusions:

  • Deep learning networks are effective tools for the digital screening and prediction of xenobiotic skin permeability.
  • This approach can significantly streamline the drug development process.
  • The findings support the broader application of AI in predicting drug transport properties.