Modeling of Hansen's solubility parameters of aripiprazole, ziprasidone, and their impurities: A nonparametric comparison of models for prediction of drug absorption sites

Abstract

Aripiprazole 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, δ d , δ p , and δ h , 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. KEYWORDS artificial neural network (ANN), drug absorption, Hansen's solubility parameters, partial least square regression (PLS), sum of ranking difference (SRD)

A Bayesian Approach to Predict Solubility Parameters

“…Although HSPiP contains around 8000 drug‐like molecules according to Lipinski's rule of five, we examined drug molecules of interest from recent work. For example, HSP have been utilized to assess pharmacokinetic properties of drugs, determining the most probable absorption sites for each drug and the corresponding metabolite by looking at miscibilities between these two. Hossin et al.…”

“…The chains are capped at a molecular weight of 1500. 3) The Hansen Solubility Parameters in Practice (HSPiP) set contains around 8000 organic chemicals common to a wide array of contexts, 4) which is augmented with a drug‐like set contains 64 drug‐like molecules . Section S1, Supporting Information outlines the format in which we provide these datasets and their source for experimentally determined data.…”

A Bayesian Approach to Predict Solubility Parameters

“…Although HSPiP contains around 8,000 drug-like molecules according to Lipinski's rule of five [57], we examined drug molecules of interest from recent work. For example, HSP have been utilized to assess pharmacokinetic properties of drugs [26], determining the most probable absorption sites for each drug and the corresponding metabolite by looking at miscibilities between these two. Hossin et al looked at predicting nail-drug interactions by comparing drug and nail HSPs [58].…”

A Bayesian Approach to Predict Solubility Parameters

“…The chains are capped at a molecular weight of 1500. (3) The Hansen Solubility Parameters in Practice (HSPiP) set [24] contains around 8,000 organic chemicals common to a wide array of contexts, (4) which is augmented with a drug-like set contains 64 drug-like molecules [25,26]. Section S1 in the Supporting Information outlines the format in which we provide these datasets and their source for experimentally determined data.…”