Nonsteroidal anti-inflammatory drugs (NSAIDs) are a group of agents important for their analgesic,
anti-inflammatory, and antipyretic properties. This study presents several approaches to predict and elucidate new molecular
structures of NSAIDs based on 36 known and proven anti-inflammatory compounds. Based on 36 known NSAIDs
the mean value of Log P is found to be 3.338 (standard deviation= 1.237), mean value of polar surface area is
63.176 Angstroms2 (standard deviation = 20.951 A2), and the mean value of molecular weight is 292.665 (standard deviation
= 55.627). Nine molecular properties are determined for these 36 NSAID agents, including Log P, number of -OH
and -NHn, violations of Rule of 5, number of rotatable bonds, and number of oxygens and nitrogens. Statistical analysis of
these nine molecular properties provides numerical parameters to conform to in the design of novel NSAID drug candidates.
Multiple regression analysis is accomplished using these properties of 36 agents followed with examples of predicted
molecular weight based on minimum and maximum property values. Hierarchical cluster analysis indicated that
licofelone, tolfenamic acid, meclofenamic acid, droxicam, and aspirin are substantially distinct from all remaining
NSAIDs. Analysis of similarity (ANOSIM) produced R = 0.4947, which indicates low to moderate level of dissimilarity
between these 36 NSAIDs. Non-hierarchical K-means cluster analysis separated the 36 NSAIDs into four groups having
members of greatest similarity. Likewise, discriminant analysis divided the 36 agents into two groups indicating the greatest
level of distinction (discrimination) based on nine properties. These two multivariate methods together provide investigators
a means to compare and elucidate novel drug designs to 36 proven compounds and ascertain to which of those are
most analogous in pharmacodynamics. In addition, artificial neural network modeling is demonstrated as an approach to
predict numerous molecular properties of new drug designs that is based on neural training from 36 proven NSAIDs.
Comprehensive and effective approaches are presented in this study for the design of new NSAID type agents which are
so very important for inhibition of COX-2 and COX-1 isoenzymes.