Development of quantitative structure-metabolism (QSMR) relationships for substituted anilines based on computational chemistry

Machine learning and artificial intelligence in physiologically based pharmacokinetic modeling

Physiologically based pharmacokinetic (PBPK) models are useful tools in drug development and risk assessment of environmental chemicals. PBPK model development requires the collection of species-specific physiological, and chemical-specific absorption, distribution, metabolism, and excretion (ADME) parameters, which can be a time-consuming and expensive process. This raises a need to create computational models capable of predicting input parameter values for PBPK models, especially for new compounds. In this review, we summarize an emerging paradigm for integrating PBPK modeling with machine learning (ML) or artificial intelligence (AI)-based computational methods. This paradigm includes 3 steps (1) obtain time-concentration PK data and/or ADME parameters from publicly available databases, (2) develop ML/AI-based approaches to predict ADME parameters, and (3) incorporate the ML/AI models into PBPK models to predict PK summary statistics (eg, area under the curve and maximum plasma concentration). We also discuss a neural network architecture "neural ordinary differential equation (Neural-ODE)" that is capable of providing better predictive capabilities than other ML methods when used to directly predict time-series PK profiles. In order to support applications of ML/AI methods for PBPK model development, several challenges should be addressed (1) as more data become available, it is important to expand the training set by including the structural diversity of compounds to improve the prediction accuracy of ML/AI models; (2) due to the black box nature of many ML models, lack of sufficient interpretability is a limitation; (3) Neural-ODE has great potential to be used to generate time-series PK profiles for new compounds with limited ADME information, but its application remains to be explored. Despite existing challenges, ML/AI approaches will continue to facilitate the efficient development of robust PBPK models for a large number of chemicals.

Metabolism of cyclic phenones in rainbow trout in vitro assays

1. Cyclic phenones are chemicals of interest to the USEPA due to their potential for endocrine disruption to aquatic and terrestrial species.2. Prior to this report, there was very limited information addressing metabolism of cyclic phenones by fish species and the potential for estrogen receptor (ER) binding and vitellogenin (Vtg) gene activation by their metabolites.3. The main objectives of the current research were to characterize rainbow trout (rt) liver slice-mediated in vitro metabolism of model parent cyclic phenones exhibiting disparity between ER binding and ER-mediated Vtg gene induction, and to assess the metabolic competency of fish liver in vitro tests to help determine the chemical form (parent and/or metabolite) associated with the observed biological response.4. GC-MS, HPLC and LC-MS/MS technologies were applied to investigate the in vitro biotransformation of cyclobutyl phenyl ketone (CBP), benzophenone (DPK), cyclohexyl phenyl ketone (CPK) mostly in the absence of standards for metabolite characterization.5. It was concluded that estrogenic effects of the studied cyclic phenones are mediated by the parent chemical structure for DPK, but by active metabolites for CPK. A definitive interpretation was not possible for CBP and CBPOH (alcohol), although a contribution of both structures to gene induction is suspected.

Structure-Oxidative Metabolism Relationships of Substituted Flavones by Aspergillus niger

Aspergillus niger is a rich source of oxidative enzymes, which are important for many industrial applications. However, systematic evaluation of their metabolic characteristics is limited. In this study, structure-dependent metabolism of flavones by Aspergillus niger were investigated with synthetic substrates. Metabolic inhibitor studies suggested that cytochrome P450s are the major enzymes in oxidative metabolism. The reactions include ring hydroxylation, O-demethylation, sulfone/sulfoxide formation, and oxidation of alkyls to carboxy groups. Initial oxidative metabolism occurred almost exclusively at 4'-substituents. 4'-Halogenated- and 3',5'-dihalogenated analogues were stable against biodegradation. Hydrophilic flavones were more rapidly metabolized than lipophilic analogues. Molecular widths of the A and B ring were important determinants of the position of metabolic oxidation and biotransformation rate. The structure-metabolism relationship analysis indicates that the shape of the B ring was the most important parameter of biotransformation. The electrostatic environment of the same ring also affected the transformation. Additionally, the results showed that the B ring may preferentially be oriented toward the catalytic center.

The metabolism of 4-bromoaniline in the bile-cannulated rat: application of ICPMS ((79/81)Br), HPLC-ICPMS & HPLC-oaTOFMS

1. An excretion balance study was performed following i.p. administration of 4-bromoaniline (50 mg kg⁻¹) to bile-cannulated rats, using bromine-detected (^79/81Br) ICPMS for quantification. Approximately 90% of the dose was recovered in urine (68.9 ± 3.6%) and bile (21.4 ± 1.4%) by 48 h post-administration.

2. HPLC-ICPMS (^79/81Br) was used to selectively detect and profile the major urinary and biliary-excreted metabolites and determined that the 0–12 h urine contained at least 21 brominated metabolites with 19 bromine-containing peaks observed in the 6–12 h bile samples.

3. The urinary and biliary metabolites were subsequently profiled using HPLC-oaTOFMS. By exploiting the distinctive bromine isotope pattern ca. 60 brominated metabolites were detected in the urine in negative electrospray ionisation (ESI) mode while bile contained ca. 21.

4. While a large number of bromine-containing metabolites were detected, the profiles were dominated by a few major components with the bulk of the 4-bromoaniline-related material in urine accounted for by 4-bromoanaline O-sulfate (∼75% of the total by ICPMS, 84% by TOFMS). In bile a hydroxylated N-acetyl compound was the major metabolite detected, forming some ∼65% of the 4-bromoaniline-related material by ICPMS (37% by TOFMS).

Applying machine learning techniques for ADME-Tox prediction: a review

INTRODUCTION

Pharmacokinetics involves the study of absorption, distribution, metabolism, excretion and toxicity of xenobiotics (ADME-Tox). In this sense, the ADME-Tox profile of a bioactive compound can impact its efficacy and safety. Moreover, efficacy and safety were considered some of the major causes of clinical failures in the development of new chemical entities. In this context, machine learning (ML) techniques have been often used in ADME-Tox studies due to the existence of compounds with known pharmacokinetic properties available for generating predictive models.

AREAS COVERED

This review examines the growth in the use of some ML techniques in ADME-Tox studies, in particular supervised and unsupervised techniques. Also, some critical points (e.g., size of the data set and type of output variable) must be considered during the generation of models that relate ADME-Tox properties and biological activity.

EXPERT OPINION

ML techniques have been successfully employed in pharmacokinetic studies, helping the complex process of designing new drug candidates from the use of reliable ML models. An application of this procedure would be the prediction of ADME-Tox properties from studies of quantitative structure-activity relationships or the discovery of new compounds from a virtual screening using filters based on results obtained from ML techniques.