Virtual Screening for PPAR Modulators Using a Probabilistic Neural Network

Probabilistic Neural Networks (PNNs) were used for the retrieval of peroxisome proliferator‐activated receptor (PPAR) modulators from a large compound collection. Four out of nine compounds tested in cell‐based assays exhibited an agonistic effect toward PPARγ, one toward PPARα. The experimental bin...

Full description

Saved in:
Bibliographic Details
Published in:ChemMedChem 2006-12, Vol.1 (12), p.1346-1350
Main Authors: Derksen, Swetlana, Rau, Oliver, Schneider, Petra, Schubert-Zsilavecz, Manfred, Schneider, Gisbert
Format: Article
Language:English
Subjects:
Animals
Cercopithecus aethiops
computer chemistry
COS Cells
Drug Design
Hypoglycemic Agents - chemistry
Hypoglycemic Agents - pharmacology
Ligands
machine learning
Molecular Structure
Neural Networks (Computer)
Peroxisome Proliferator-Activated Receptors - chemistry
Peroxisome Proliferator-Activated Receptors - drug effects
PPAR agonists
Probability
Protein Conformation
Protein Structure, Secondary
reporter gene assays
Sensitivity and Specificity
Structure-Activity Relationship
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Probabilistic Neural Networks (PNNs) were used for the retrieval of peroxisome proliferator‐activated receptor (PPAR) modulators from a large compound collection. Four out of nine compounds tested in cell‐based assays exhibited an agonistic effect toward PPARγ, one toward PPARα. The experimental binding mode of a potent ligand (red) of PPARγ is compared with the predicted orientation of another ligand shown by the superposition of several high‐ranking docking solutions.
ISSN:1860-7179
1860-7187
DOI:10.1002/cmdc.200600166