Development of Neural Network QSPR Models for Hansch Substituent Constants. 2. Applications in QSAR Studies of HIV-1 Reverse Transcriptase and Dihydrofolate Reductase Inhibitors

J. Chem. Inf. Comput. Sci., 44 (1), 154 -160, 2004. 10.1021/ci030294i S0095-2338(03)00294-4
Web Release Date: December 16, 2003

Development of Neural Network QSPR Models for Hansch Substituent Constants. 2. Applications in QSAR Studies of HIV-1 Reverse Transcriptase and Dihydrofolate Reductase Inhibitors

Ting-Lan Chiu and Sung-Sau So*

Roche Research Center, Hoffmann-La Roche Inc., Nutley, New Jersey 07110

Received June 24, 2003

Abstract:

In this paper, the applications of a Hansch substituent constant predictor¹ to Quantitative Structure-Activity Relationships (QSAR) studies of E. coli dihydrofolate reductase (DHFR) inhibitors 2,4-diamino-5-(substituted-benzyl)pyrimidines as well as HIV-1 reverse transcriptase (RT) inhibitors 1-[(2-hydroxyethoxy)methyl]-6-(phenylthio)thymine (HEPT) derivatives are demonstrated. Both data sets contain functional groups for which the substituent constants (, MR, F and R) could not be found in standard substituent constant tables. The substituent constant predictor allowed us to derive predicted , MR, F and R values for all substituents in both data sets, thus enabling the generation of easily interpretable QSAR models of comparable or better predictivity than previous models.

Download the full text: PDF | HTML