Dichloroacetate (DCA) is a pyruvate mimetic compound that stimulates the activity of the enzyme pyruvate dehydrogenase (PDH) through inhibition of the enzyme pyruvate dehydrogenase kinases (PDK1-4). DCA works by turning on the apoptosis which is suppressed in tumor cells, hence let them to die on their own. Here, in this paper a series of DCA analogues were applied to quantitative structure–activity relationship (QSAR) analysis. A collection of chemometrics methods such as multiple linear regression (MLR), factor analysis–based multiple linear regression (FA-MLR), principal component regression (PCR), simple Free-Wilson analysis (FWA) and partial least squared combined with genetic algorithm for variable selection (GA-PLS) were conducted to make relations between structural features and cytotoxic activities of a variety of DCA derivatives. The best multiple linear regression equation obtained from genetic algorithms partial least squares which predict 91% of variances. On the basis of the produced model, an in silico-screening study was also employed and new potent lead compounds based on new structural patterns were suggested. Docking studies of these compounds were also investigated and promising results were obtained. The docking results were also conducted to protein ligand interaction fingerprints (PLIF) studies using self-organizing map (SOM) in order to evaluate the predictive ability in suggesting new potent compounds and some compounds were introduced as a good candidates for synthesis.