Artificial neural networks in drug design II: Influence of learning rate and momentum factor on the predictive ability

Author(s)
Dominik Kaiser, Claudia Tmej, Peter Chiba, Klaus-Jürgen Schaper, Gerhard Ecker
Abstract

A data set of 48 propafenone-type modulators of multidrug resistance was used to investigate the influence of learning rate and momentum factor on the predictive power of artificial neural networks of different architecture. Generally, small learning rates and medium sized momentum factors are preferred. Some of the networks showed higher cross validated Q2 values than the corresponding linear model (0.87 vs. 0.83). Screening of a 158 compound virtual library identified several new lead compounds with activities in the nanomolar range.

Organisation(s)
External organisation(s)
Research Center Borstel - Leibniz Lung Center
Journal
Scientia Pharmaceutica
Volume
68
Pages
57-64
No. of pages
8
ISSN
0036-8709
Publication date
2000
Peer reviewed
Yes
Austrian Fields of Science 2012
3012 Pharmacy, Pharmacology, Toxicology
Portal url
https://ucrisportal.univie.ac.at/en/publications/b7fc7bc7-b139-428a-abc2-cb1066321428