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

Discovery of a New Scaffold RSK2 Inhibitor With Virtual and Phenotypical Screening.

ChemMedChem·2026

Same author

Deviations from recommended use of liposomal bupivacaine: a real-world pharmacovigilance study using the FAERS database.

Frontiers in medicine·2026

Same author

Design, synthesis, and evaluation of 4-(aminomethyl)-2-(phenylamino)pyridine derivatives as novel lysyl oxidase-like 2 inhibitors against metastatic melanoma.

Bioorganic & medicinal chemistry·2026

Same author

DeepCYP: an integrated deep learning web server for the holistic "pathway-site product" prediction of CYP450 metabolism.

Nucleic acids research·2026

Same author

Computational insights into drug hygroscopicity by coupling machine learning and molecular simulation.

Drug delivery and translational research·2026

Same author

A Prospective, Multicenter, Randomized, Assessor-Blinded Study Assessing the Efficacy and Safety of Injectable Non-Cross-Linked Hyaluronic Acid for Improving Facial Skin Rejuvenation.

Clinical, cosmetic and investigational dermatology·2026

Search research articles

Related Experiment Video

Updated: Aug 19, 2025

A Droplet-Based Microfluidic Approach and Microsphere-PCR Amplification for Single-Stranded DNA Amplicons

A Droplet-Based Microfluidic Approach and Microsphere-PCR Amplification for Single-Stranded DNA Amplicons

Published on: November 14, 2018

Machine learning in accelerating microsphere formulation development.

Jiayin Deng¹, Zhuyifan Ye¹, Wenwen Zheng²

¹State Key Laboratory of Quality Research in Chinese Medicine, Institute of Chinese Medical Sciences (ICMS), University of Macau, Macau, China.

Drug Delivery and Translational Research

|December 1, 2022

Summary

This study developed a machine learning model to predict microsphere drug release, accelerating development for small-molecule drugs. The accurate consensus model offers insights into formulation factors and improves quality control in the pharmaceutical industry.

Keywords:

Drug release Machine learning Microspheres Molecular dynamics simulation

More Related Videos

High Throughput Single-cell and Multiple-cell Micro-encapsulation

High Throughput Single-cell and Multiple-cell Micro-encapsulation

Published on: June 15, 2012

Author Spotlight: Advancing Therapeutics with Biocompatible Sodium Alginate Hydrogel Microspheres

Author Spotlight: Advancing Therapeutics with Biocompatible Sodium Alginate Hydrogel Microspheres

Published on: June 7, 2024

Related Experiment Videos

Last Updated: Aug 19, 2025

A Droplet-Based Microfluidic Approach and Microsphere-PCR Amplification for Single-Stranded DNA Amplicons

A Droplet-Based Microfluidic Approach and Microsphere-PCR Amplification for Single-Stranded DNA Amplicons

Published on: November 14, 2018

High Throughput Single-cell and Multiple-cell Micro-encapsulation

High Throughput Single-cell and Multiple-cell Micro-encapsulation

Published on: June 15, 2012

Author Spotlight: Advancing Therapeutics with Biocompatible Sodium Alginate Hydrogel Microspheres

Author Spotlight: Advancing Therapeutics with Biocompatible Sodium Alginate Hydrogel Microspheres

Published on: June 7, 2024

Area of Science:

Pharmaceutical Sciences
Materials Science
Computational Chemistry

Background:

Microspheres offer biodegradable and controlled-release drug delivery benefits.
Traditional microsphere formulation is inefficient and relies on trial-and-error.
Predicting drug release is complex due to formulation and manufacturing variables.

Purpose of the Study:

To develop a machine learning (ML) based prediction model for accelerating microsphere formulation development.
To predict in vitro drug release profiles for small-molecule drugs at 37°C and 45°C.
To gain insights into critical formulation factors influencing microsphere performance.

Main Methods:

Collected data from 286 microsphere formulations (small-molecule drugs) from publications and industry.
Compared fourteen ML approaches, selecting a consensus model for prediction.
Validated model predictions with experimental microsphere formulations and molecular dynamics (MD) simulations.

Main Results:

The consensus ML model accurately predicted in vitro drug release profiles at 37°C (R²=0.880) and 45°C (R²=0.958).
The model identified key formulation features influencing drug release, providing valuable development insights.
Experimental validation confirmed the high accuracy of the developed prediction model.

Conclusions:

A highly accurate ML prediction model for small-molecule drug microsphere formulations was successfully established.
The model accelerates microsphere product development and enhances quality control in the pharmaceutical industry.
Integration of ML and MD simulations offers a powerful approach for microsphere design and optimization.