QSRR modeling of the chromatographic retention behavior for some quinolone and sulfonamide antibacterial agents using firefly algorithm coupled to support vector machine

Abstract Quinolone and sulfonamide are two classes of antibacterial agents that have an opulent history of medicinal chemistry features responsible for their improving bacterial spectrum, efficacy, pharmacokinetics, and adverse side effect profiles. The urgent need of their use and escalating rate of their resistance provokes the necessity for developing suitable analytical methods that speed up and facilitate their analysis. In this study, advanced firefly algorithm (FFA) coupled with support vector machine (SVM) were used to select the most significant descriptors and to construct two separate quantitative structure–retention relationship (QSRR) models using a series of 11 selected quinolones and 13 sulfonamide drugs, separately, in order to predict their retention factors in HPLC. Precisely, the effect of different pH range values and acetonitrile composition in the mobile phase on the retention behavior of quinolones and sulfonamides were studied, respectively. The obtained QSRR models showed high performance in both internal and external validation indicating their robustness and predictive ability. Y-randomization validation displayed that the obtained models are not obtained by chance. Besides, the obtained results shed the light on the molecular features that influence the retention behavior of these two classes under the current chromatographic conditions.