A dataset of Nickel-Schiff base complexes displaying potent activity against Candida albicans has been investigated utilizing 0D,1D,2D, and 3D Quantitative Structure-Activity Relationship (QSAR) techniques. Genetic Function Approximation method was used to produce QSAR models that correlated the Minimum Inhibitory Concentration (MIC) values against Candida albicans with the molecular structures of the active complexes. A training set of 21 active complexes was used to develop the models; the optimum model was then evaluated by a series of internal and external cross-validation techniques. A test set of 10 complexes was used for the external validation. The optimum model has squared correlation coefficient R2 value of 0.934, adjusted squared correlation coefficient R2adj value of 0.918, Leave one out (LOO) cross validation coefficient (Q2) value of 0.9059, F value of 56.70, Friedman’s Lack of Fit (LOF) of 0.124. The external set used for confirming the predictive power of the model has its R2pred = 0.830. Our work may offer a pathway to the design of novel and biologically active Nickel-Schiff base complexes that will arrest the growing trend of C. albicans resistance.
