Computational Prediction of Drug Solubility in Fasted Simulated and Aspirated Human Intestinal Fluid

Abstract

PurposeTo develop predictive models of apparent solubility (Sapp) of lipophilic drugs in fasted state simulated intestinal fluid (FaSSIF) and aspirated human intestinal fluid (HIF).MethodsMeasured Sapp values in FaSSIF, HIF and phosphate buffer pH 6.5 (PhBpH6.5) for 86 lipophilic drugs were compiled and divided into training (Tr) and test (Te) sets. Projection to latent structure (PLS) models were developed through variable selection of calculated molecular descriptors. Experimentally determined properties were included to investigate their contribution to the predictions.ResultsModest relationships between Sapp in PhBpH6.5 and FaSSIF (R2 = 0.61) or HIF (R2 = 0.62) were found. As expected, there was a stronger correlation obtained between FaSSIF and HIF (R2 = 0.78). Computational models were developed using calculated descriptors alone (FaSSIF, R2 = 0.69 and RMSEte of 0.77; HIF, R2 = 0.84 and RMSEte of 0.81). Accuracy improved when solubility in PhBpH6.5 was added as a descriptor (FaSSIF, R2 = 0.76 and RMSETe of 0.65; HIF, R2 = 0.86 and RMSETe of 0.69), whereas no improvement was seen when melting point (Tm) or logDpH 6.5 were included in the models.ConclusionComputational models were developed, that reliably predicted Sapp of lipophilic compounds in intestinal fluid, from molecular structures alone. If experimentally determined pH-dependent solubility values were available, this further improved the accuracy of the predictions.

Computational methods in drug discovery

“…Therefore, in silico prediction of solubility and membrane permeability of drugs is an important part of lead optimization [222]. If an orally administrated drug has poor solubility or a high dissolution rate, the drug tends to be excreted by the body without entering the blood stream.…”

Biopharmaceutic IVIVE—Mechanistic Modeling of Single- and Two-Phase In Vitro Experiments to Obtain Drug-Specific Parameters for Incorporation Into PBPK Models

“…These aqueous solubility measurements are devoid of bile micelle-mediated solubility effect and hence are used only to assess consistency with pKa and S o and, at low pH, for the estimation of the salt limiting SF. In addition, the solubility measurements of dipyridamole at pH 4.1, pH 6.0, and pH 7.0, 27 pH 5.0 23 and 6.5 28 were used for the external validation of the solubility model (Table 1). 29 Bile-micelle partition coefficients for neutral and ionized species ( (2)…”

The Next Era: Deep Learning in Pharmaceutical Research

“…Based on a non-exhaustive assessment of several different end points relevant to pharmaceutical research, while it appears that most have seen utilization of Bayesian or SVM approaches to develop predictive models, few have so far utilized DL (Table 2). Recent examples of computational models appearing in this journal alone over the past 18 months include: modeling thermodynamic proxies (35), predicting mouse liver microsomal stability (36), predicting autooxidation (37), drug solubility in human intestinal fluid (38), site of metabolism prediction in CYP2C9 (39), human skin permeability prediction (40, 41), blood brain barrier penetration modeling (42), predicting clearance mechanism (41) and skin concentration due to dermal exposure (43). Many of these datasets could likely utilize and benefit from DL and it would be of interest to see for how many an improvement in predictions could be obtained.…”