A. Geronikaki et al., Computer aided predicting the biological activity spectra and experimentaltesting of new thiazole derivatives, QSAR, 18(1), 1999, pp. 16-25
Computer aided prediction of biological activity spectra has been carried o
ut for 50 new thiazolyl and benzothiazolyl derivatives. Predicted activity
spectra for different compounds from the set include 1-8 activities with es
timated probability to be found more than 50%, which cover both possible th
erapeutic and adverse/side effects. Experimental data coincide with the pre
diction for 25 of 39 compounds tested as NSAIDs (64.1%); for 4 of 6 compoun
ds tested as local anaesthetics (66.7%); for 1 compound tested as antioxida
nts (100%). The concordance that describes the overall percentage of correc
t predictions equals to 65.2% that is sufficient to use this approach for o
ptimization of biological testing. In particular, the compounds from studie
d data set will be further tested according to the additional predicted act
ivities. Description of the current version of computer system PASS and fea
sibility for free testing is available via Internet on http://www.ibmh.msk.
su/PASS.