3D QSAR Markov model for drug-induced eosinophilia--theoretical prediction and preliminary experimental assay of the antimicrobial drug G1.

The application of 3D-MEDNEs as a novel alternative technique to reduce the use of animal experimentation in toxicology in the early stages of medicinal chemistry research has been extended from agranulocytosis to chemically induced eosinophilia. Firstly, a heterogeneous series of organic compounds, which are classified either as eosinophilia inductors or noninductors, was collected. A linear discriminant analysis was subsequently used to obtain a QSTR that gave rise to a very good classification of 91.82% (110 chemicals within training series). Eosinophilia inductors (88.89%) composed the first group while the other one contained only harmless compounds (97.37%). The total predictability (88.1%) was tested by means of an external validation series (42 compounds). The model correctly classifies 88.89% of harmless compounds and 87.5% of toxic ones. Finally, comparison of predicted versus experimental results for G1 [2-bromo-5-(2-bromo-2-nitroethenyl)furan, which is a promising antibacterial-antifungal compound] illustrates the practical application of the method. A dose-dependent study of G1 (9.8-185.6 mg/Kg) at 48, 72 and 96 h after oral administration in rats is reported here for the first time. The study has shown that G1 does not affect the murine eosinophils count under these conditions--a situation in total agreement with the model prediction.