Leonardo Journal of Sciences ISSN 1583-0233 Issue 9, July-December 2006 p. 179-200 179 http://ljs.academicdirect.org Pearson versus Spearman, Kendall's Tau Correlation Analysis on Structure-Activity Relationships of Biologic Active Compounds Sorana-Daniela BOLBOACĂ 1 , Lorentz J˜NTSCHI 2 1 Iuliu Haţieganu University of Medicine and Pharmacy, 13 Emil Isac, 400023 Cluj- Napoca, Romania; 2 Technical University of Cluj-Napoca, 15 Constantin Daicoviciu, 400020 Cluj-Napoca, Romania sbolboaca@umfcluj.ro , lori@academicdirect.org , Abstract A sample of sixty-seven pyrimidine derivatives with inhibitory activity on E. coli dihydrofolate reductase (DHFR) was studied by the use of molecular descriptors family on structure-activity relationships. Starting from the results obtained by applying of MDF-SAR methodology on pyrimidine derivatives and from the assumption that the measured activity (compounds inhibitory activity) of a biologically active compounds is a semi-quantitative outcome (can be related with the type of equipment used, the researchers, the chemical used, etc.), the abilities of Pearson, Spearman, Kendalls, and Gamma correlation coefficients in analysis of estimated toxicity were studied and are presented. Keywords Multiple linear regressions, Correlation coefficients, Molecular Descriptors Family on Structure-Activity Relationships (MDF-SAR) Introduction QSAR (Quantitative Structure-Activity Relationships) is an approach which is able to indicate for a given compound or a class of compounds which feature of structure characteristics is correlated with its activity [1]. In QSAR analysis were proposed several