AbstractAripiprazole and ziprasidone are atypical antipsychotic drugs with the effect on positive and negative symptoms of schizophrenia, mania, and mixed states of bipolar disorder. Hansen's solubility parameters, δd, δp, and δh, which account for dispersive, polarizable, and hydrogen bonding contributions to the overall cohesive energy of a compound, are often used to assess pharmacokinetic properties of drugs. However, no data exist of solubility parameters for the drugs of interest in this study. Therefore, in the present study, partial least square regression (PLS), artificial neural networks (ANNs), regression trees (RT), boosted trees (BT), and random forests (RF) were applied to estimate Hansen's solubility parameters of ziprasidone, aripiprazole, and their impurities/metabolic derivatives, targeting their biopharmaceutical classes and absorption routes. A training set of 47 structurally diverse and pharmacologically active compounds and 290 molecular descriptors and pharmaceutically important properties were used to build the prediction models. The modeling approaches were compared by the sum of ranking differences, using the consensus values as a reference for the unknowns and the experimentally determined values as a gold standard for the calibration set. In both instances, the PLS models, together with ANNs, demonstrated better performance than RT, BT and especially RF. Based on the best scored models, we were able to pinpoint the most probable absorption sites for each drug and the corresponding metabolite, i.e., the upper parts of the gastrointestinal tract, small intestine, or absorption along entire length of gastrointestinal tract.
Read full abstract