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

Drug Discovery: Overview01:26

Drug Discovery: Overview

11.1K
Drug discovery is a multifaceted process involving extensive screening, testing, and optimization of lead compounds to identify potential new drugs for therapeutic use. It combines several approaches, including screening large numbers of natural products, chemical modification of known active molecules, identification of new drug targets, and rational design based on biological mechanisms and drug-receptor structure. These approaches are carried out in both academic research laboratories and...
11.1K
Structure-Activity Relationships and Drug Design01:28

Structure-Activity Relationships and Drug Design

1.7K
Drug design is a dynamic field that involves discovering and developing new medications based on specific biological targets. This process heavily relies on structure-activity relationships (SAR) and quantitative structure-activity relationships (QSAR) to guide the design and optimization of efficient drugs.
SAR studies the intricate relationship between a drug's chemical structure and biological activity. It focuses on understanding how modifications to a drug's structure can influence...
1.7K
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

242
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
242

You might also read

Related Articles

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

Sort by
Same author

QM/MM Free Energy Calculations of IRE1 Reveal a Unique Protonation State of the Catalytic Lys599.

Journal of computational chemistry·2025
Same author

Correction to "Computational Characterization of the Interaction of CARD Domains in the Apoptosome".

Biochemistry·2025
Same author

iScore: A ML-Based Scoring Function for De Novo Drug Discovery.

Journal of chemical information and modeling·2025
Same author

Unraveling the Binding Mode of TSC2-Rheb through Protein Docking and Simulations.

Biochemistry·2025
Same author

Design and Synthesis of Topoisomerases-Histone Deacetylase Dual Targeted Quinoline-Bridged Hydroxamates as Anticancer Agents.

Journal of medicinal chemistry·2025
Same author

Computational Characterization of the Interaction of CARD Domains in the Apoptosome.

Biochemistry·2025

Related Experiment Video

Updated: Jan 17, 2026

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.4K

MolAI: A Deep Learning Framework for Data-Driven Molecular Descriptor Generation and Advanced Drug Discovery

Sayyed Jalil Mahdizadeh1, Leif A Eriksson1

  • 1Department of Chemistry and Molecular Biology, University of Gothenburg, Göteborg 405 30, Sweden.

Journal of Chemical Information and Modeling
|September 15, 2025
PubMed
Summary

MolAI, a deep learning model, generates molecular descriptors from 221 million compounds. Its latent space representations enable accurate prediction of molecular properties and enhance drug discovery processes.

More Related Videos

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
08:49

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Published on: June 20, 2025

1.1K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.7K

Related Experiment Videos

Last Updated: Jan 17, 2026

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

4.4K
Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis
08:49

Incorporating Target Protein Structure Flexibility and Dynamics in Computational Drug Discovery Using Ensemble-Based Docking Analysis

Published on: June 20, 2025

1.1K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.7K

Area of Science:

  • Computational chemistry
  • Machine learning
  • Drug discovery

Background:

  • Molecular descriptors are crucial for predicting chemical properties.
  • Existing methods for descriptor generation can be limited in scope and accuracy.
  • Deep learning offers potential for novel descriptor generation.

Purpose of the Study:

  • Introduce MolAI, a deep learning model for data-driven molecular descriptor generation.
  • Demonstrate the utility of MolAI-generated descriptors in various cheminformatics applications.
  • Explore the potential of MolAI for advancing drug discovery.

Main Methods:

  • Utilized a large dataset of 221 million unique compounds for training.
  • Employed an autoencoder neural machine translation model to create latent space representations.
  • Validated the model's performance through molecule regeneration accuracy (>99.8%).

Main Results:

  • MolAI achieved high accuracy in regenerating molecules from latent space.
  • Developed an ML-based model (iLP) for predicting protonation states using MolAI descriptors.
  • Enhanced ligand-based virtual screening and accurately predicted ADMET features (iADMET).

Conclusions:

  • MolAI provides robust, data-driven molecular descriptors.
  • MolAI-generated descriptors significantly improve predictive modeling for chemical and biological properties.
  • The encoding/decoding capability of MolAI offers new avenues in drug discovery and molecular generation.