Quantitative structure-retention relationships (QSRRs) are used to correlate paper chromatographic retention factors of disperse dyes with theoretical molecular descriptors. A data set of 23 compounds with known RF values was used. The genetic algorithm-multiple linear regression analysis (GA-MLR) with three selected theoretical descriptors was obtained. The stability and predictability of the model was validated by use of leave-one-out (LOO), leave-many-out (LMO) cross-validation, external validation, Y-randomization and applicability domain (AD) analysis. The GA-MLR revealed a statistically meaningful model showing the dependence of the RF value on sum of topological distances between N and Br atoms (T(N..Br)), global topological charge index (JGT) and R autocorrelation of lag 5 / unweighted (R5u_A) of the compounds. Prog. Color Colorants Coat. 9 (2016), 195-206© Institute for Color Science and Technology. 1. Introduction The rapid increase in the manufacture and consumption of synthetic dyes during the past century has been quite phenomenal. There are more than 10,000 commercially available dyes and it is estimated that more than 7 × 105 tonnes of dyestuffs are produced per year [1]. At the present time nearly all industrial fields such as textiles, paper, rubber, plastics, dyestuffs, leather, ink, cosmetics, food, biomedicine, paint and varnishes are users of synthetic dyes [2-4]. They are also often added to a product to influence purchasing behaviors, but do not improve the product itself. The disposal of these dyes is an environmental concern because they are toxic to living organisms, they last for a long time in the ecosystem, cause allergies and skin or eye irritation, and are suspected human carcinogens [5-7]. On the other hand they are resistant against light and microbial attach. Therefore, as persistent organic compounds, synthetic dyes are not readily degradable and are typically not easily removable from water by conventional treatment methods. Dispe
