Related Experiment Video
Updated: May 21, 2026
07:41
A Neurite Outgrowth Assay and Neurotoxicity Assessment with Human Neural Progenitor Cell-Derived Neurons
Published on: August 6, 2020
Using artificial neural networks to predict cell-penetrating compounds.
Mati Karelson1, Dimitar Dobchev
1University of Tartu, Institute of Chemistry , Ravila 14a, Tartu 50411 , Estonia +372 7 371 536 ; +372 7 371 535 ; mati.karelson@ttu.ee.
Expert Opinion on Drug Discovery
|June 2, 2012
Summary
Artificial neural networks (ANNs) can accurately predict drug candidates
Area of Science:
- Computational chemistry
- Pharmacology
- Drug discovery
Background:
- Membrane-cell penetration is crucial for drug candidates targeting CNS and gastrointestinal diseases.
- Predicting this property early saves pharmaceutical companies significant time and resources.
- Artificial neural networks (ANNs) offer a robust and rapid solution for predicting cell penetration.
Purpose of the Study:
- To review the application of artificial neural networks (ANNs) in predicting cell-penetrating drugs.
- To explore ANN methods for modeling cell penetration across various biological systems.
- To highlight new approaches in cell-penetrating peptide discovery.
Main Methods:
- Review of artificial neural network (ANN) applications in drug discovery.
- Analysis of ANN models for blood-brain barrier (BBB) penetration.
- Examination of ANN models for gastrointestinal absorption and permeation.
Main Results:
- ANNs demonstrate successful application in predicting cell-penetrating drugs.
- Quantitative structure-activity relationship (QSAR) neural networks offer broad applicability.
- ANNs provide a valuable tool for enhancing drug discovery and development pipelines.
Conclusions:
- Artificial neural networks (ANNs) are effective for predicting drug cell penetration.
- The field offers extensive opportunities for QSAR neural network applications in pharmaceuticals.
- Further research into ANNs can significantly advance drug discovery and development.
