Prediction of Oral Bioavailability in Rats: Transferring Insights from in Vitro Correlations to (Deep) Machine Learning Models Using in Silico Model Outputs and Chemical Structure Parameters.

Oral administration of drug products is a strict requirement in many medical indications. Therefore, bioavailability prediction models are of high importance for prioritization of compound candidates in the drug discovery process. However, oral exposure and bioavailability are difficult to predict, as they are the result of various highly complex factors and/or processes influenced by the physicochemical properties of a compound, such as solubility, lipophilicity, or charge state, as well as by interactions with the organism, for instance, metabolism or membrane permeation. In this study, we assess whether it is possible to predict intravenous (iv) or oral drug exposure and oral bioavailability in rats. As input parameters, we use (i) six experimentally determined in vitro and physicochemical endpoints, namely, membrane permeation, free fraction, metabolic stability, solubility, pKa value, and lipophilicity; (ii) the outputs of six in silico absorption, distribution, metabolism, and excretion models trained on the same endpoints, or (iii) the chemical structure encoded as fingerprints or simplified molecular input line entry system strings. The underlying data set for the models is an unprecedented collection of almost 1900 data points with high-quality in vivo experiments performed in rats. We find that drug exposure after iv administration can be predicted similarly well using hybrid models with in vitro- or in silico-predicted endpoints as inputs, with fold change errors (FCE) of 2.28 and 2.08, respectively. The FCEs for exposure after oral administration are higher, and here, the prediction from in vitro inputs performs significantly better in comparison to in silico-based models with FCEs of 3.49 and 2.40, respectively, most probably reflecting the higher complexity of oral bioavailability. Simplifying the prediction task to a binary alert for low oral bioavailability, based only on chemical structure, we achieve accuracy and precision close to 70%.

Pharmacokinetics and in vitro efficacy of salicylic acid after oral administration of acetylsalicylic acid in horses.

BACKGROUND: Although acetylsalicylic acid (ASA) is not frequently used as a therapeutic agent in horses, its metabolite SA is of special interest in equestrianism since it is a natural component of many plants used as horse feed. This led to the establishment of thresholds by horse sport organizations for SA in urine and plasma. The aim of this study was to investigate plasma and urine concentrations of salicylic acid (SA) after oral administration of three different single dosages (12.5 mg/kg, 25 mg/kg and 50 mg/kg) of acetylsalicylic acid (ASA) to eight horses in a cross-over designed study. RESULTS: In the 12.5 mg/kg group, SA concentrations in urine peaked 2 h after oral administration (2675 µg/mL); plasma concentrations peaked at 1.5 h (17 µg/mL). In the 25 mg/kg group, maximum concentrations were detected after 2 h (urine, 2785 µg/mL) and 1.5 h (plasma, 23 µg/mL). In the 50 mg/kg group, maximum concentrations were observed after 5 h (urine, 3915 µg/mL) and 1.5 h (plasma, 45 µg/mL). The plasma half-life calculated for SA varied between 5.0 and 5.7 h. The urine concentration of SA fell below the threshold of 750 µg/mL (set by the International Equestrian Federation FEI and most of the horseracing authorities) between 7 and 26 h after administration of 12.5 and 25 mg/kg ASA and between 24 and 36 h after administration of 50 mg/kg ASA. For ASA, IC50 were 0.50 µg/mL (COX-1) and 5.14 µg/mL (COX-2). For salicylic acid, it was not possible to calculate an IC50 for either COX due to insufficient inhibition of both cyclooxygenases. CONCLUSION: The established SA thresholds of 750 µg//mL urine and 6.5 µg/mL plasma appear too generous and are leaving space for misuse of the anti-inflammatory and analgetic compound ASA in horses.