Collective recognition strategy for estimating hepatoprotector activity of various chemical compounds in increasing liver repair potential

The relationship between molecular characteristics and hepatoprotector activity (increasing liver repair potential) was investigated for a diverse series of chemical compounds. Application of the nearest-neighbor method using geometric descriptors to a training set including 44 compounds (23 active...

Full description

Saved in:
Bibliographic Details
Published inPharmaceutical chemistry journal Vol. 47; no. 4; pp. 181 - 186
Main Authors Kabankin, A. S., Radkevich, L. A.
Format Journal Article
LanguageEnglish
Published Boston Springer US 01.07.2013
Springer
Subjects
Liver
Medicine
Molecular-Biological Problems of Drug Design and Mechanism of Drug Action
Organic Chemistry
Pharmacology/Toxicology
Pharmacy
liver repair potential
hepatoprotector activity
geometric descriptors
activity prognosis
Online AccessGet full text

Cover

More Information
Summary:The relationship between molecular characteristics and hepatoprotector activity (increasing liver repair potential) was investigated for a diverse series of chemical compounds. Application of the nearest-neighbor method using geometric descriptors to a training set including 44 compounds (23 active and 21 inactive) gave combinations of the descriptors that classified correctly 79 – 91% of the training-set compounds. It was shown that a classifier that classified correctly all training-set compounds could be constructed by applying a simple voting procedure to results obtained for various combinations of descriptors. The effectiveness of the proposed approach for predicting the activity of untested compounds was proved by cross-validation with groups of compounds removed from the training set.
ISSN:0091-150X
1573-9031
DOI:10.1007/s11094-013-0922-5