Send to

Choose Destination
Pharm Res. 2009 Sep;26(9):2216-24. doi: 10.1007/s11095-009-9937-8. Epub 2009 Jul 15.

Predicting inhibitors of acetylcholinesterase by regression and classification machine learning approaches with combinations of molecular descriptors.

Author information

Department of Pharmacology and Environmental Bioinformatics & Computational Toxicology Center (ebCTC), University of Medicine & Dentistry of New Jersey, Robert Wood Johnson Medical School, Piscataway, NJ 08854, USA.



Acetylcholinesterase (AChE) is both a therapeutic target for Alzheimer's disease and a target for organophosphorus, carbamates and chemical warfare agents. Prediction of the likelihood of compounds interacting with this enzyme is therefore important from both therapeutic and toxicological perspectives.


Support vector machine classification and regression models with molecular descriptors derived from Shape Signatures and the Molecular Operating Environment (MOE) application software were built and tested using a set of piperidine AChE inhibitors (N = 110).


The combination of the alignment free Shape Signatures and 2D MOE descriptors with the Support Vector Regression method outperforms the models based solely on 2D and internal 3D (i3D) MOE descriptors, and is comparable with the best previously reported PLS model based on CoMFA molecular descriptors (r(2)(test,SVR) = 0.48 vs. r(2)(test,PLS) = 0.47 from Sutherland et al. J Med Chem 47:5541-5554, 2004). Support Vector Classification algorithms proved superior to a classifier based on scores from the molecular docking program GOLD, with the overall prediction accuracies being Q(SVC(10CV)) = 74% and Q(SVC(LNO)) = 67% vs. Q(GOLD) = 56%.


These new machine learning models with combined descriptor schemes may find utility for predicting novel AChE inhibitors.

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center