Development of a decision tree to classify the most accurate tissue-specific tissue to plasma partition coefficient algorithm for a given compound

Systematic evaluation of high-throughput PBK modelling strategies for the prediction of intravenous and oral pharmacokinetics in humans

Physiologically based kinetic (PBK) modelling offers a mechanistic basis for predicting the pharmaco-/toxicokinetics of compounds and thereby provides critical information for integrating toxicity and exposure data to replace animal testing with in vitro or in silico methods. However, traditional PBK modelling depends on animal and human data, which limits its usefulness for non-animal methods. To address this limitation, high-throughput PBK modelling aims to rely exclusively on in vitro and in silico data for model generation. Here, we evaluate a variety of in silico tools and different strategies to parameterise PBK models with input values from various sources in a high-throughput manner. We gather 2000 + publicly available human in vivo concentration-time profiles of 200 + compounds (IV and oral administration), as well as in silico, in vitro and in vivo determined compound-specific parameters required for the PBK modelling of these compounds. Then, we systematically evaluate all possible PBK model parametrisation strategies in PK-Sim and quantify their prediction accuracy against the collected in vivo concentration-time profiles. Our results show that even simple, generic high-throughput PBK modelling can provide accurate predictions of the pharmacokinetics of most compounds (87% of Cmax and 84% of AUC within tenfold). Nevertheless, we also observe major differences in prediction accuracies between the different parameterisation strategies, as well as between different compounds. Finally, we outline a strategy for high-throughput PBK modelling that relies exclusively on freely available tools. Our findings contribute to a more robust understanding of the reliability of high-throughput PBK modelling, which is essential to establish the confidence necessary for its utilisation in Next-Generation Risk Assessment.

Development of Novel Methods for QSAR Modeling by Machine Learning Repeatedly: A Case Study on Drug Distribution to Each Tissue

Artificial intelligence is expected to help identify excellent candidates in drug discovery. However, we face a lack of data, as it is time-consuming and expensive to acquire raw data perfectly for many compounds. Hence, we tried to develop a novel quantitative structure-activity relationship (QSAR) method to predict a parameter more precisely from an incomplete data set via optimizing data handling by making use of predicted explanatory variables. As a case study we focused on the tissue-to-plasma partition coefficient (Kp), which is an important parameter for understanding drug distribution in tissues and building the physiologically based pharmacokinetic model and is a representative of small and sparse data sets. In this study, we predicted the Kp values of 119 compounds in nine tissues (adipose, brain, gut, heart, kidney, liver, lung, muscle, and skin), although some of these were not available. To fill the missing values in Kp for each tissue, first we predicted those Kp values by the nonmissing data set using a random forest (RF) model with in vitro parameters (log P, fu, Drug Class, and fi) like a classical prediction by a QSAR model. Next, to predict the tissue-specific Kp values in a test data set, we constructed a second RF model with not only in vitro parameters but also the Kp values of other tissues (i.e., other than target tissues) predicted by the first RF model as explanatory variables. Furthermore, we tested all possible combinations of explanatory variables and selected the model with the highest predictability from the test data set as the final model. The evaluation of Kp prediction accuracy based on the root-mean-square error and R2 value revealed that the proposed models outperformed other machine learning methods such as the conventional RF and message-passing neural networks. Significant improvements were observed in the Kp values of adipose tissue, brain, kidney, liver, and skin. These improvements indicated that the Kp information on other tissues can be used to predict the same for a specific tissue. Additionally, we found a novel relationship between each tissue by evaluating all combinations of explanatory variables. In conclusion, we developed a novel RF model to predict Kp values. We hope that this method will be applied to various problems in the field of experimental biology which often contains missing values in the near future.

Development of a 2D-QSAR Model for Tissue-to-Plasma Partition Coefficient Value with High Accuracy Using Machine Learning Method, Minimum Required Experimental Values, and Physicochemical Descriptors

BACKGROUND

The demand for physiologically based pharmacokinetic (PBPK) model is increasing currently. New drug application (NDA) of many compounds is submitted with PBPK models for efficient drug development. Tissue-to-plasma partition coefficient (K_p) is a key parameter for the PBPK model to describe differential equations. However, it is difficult to obtain the K_p value experimentally because the measurement of drug concentration in the tissue is much harder than that in plasma.

OBJECTIVE

Instead of experiments, many researchers have sought in silico methods. Today, most of the models for K_p prediction are using in vitro and in vivo parameters as explanatory variables. We thought of physicochemical descriptors that could improve the predictability. Therefore, we aimed to develop the two-dimensional quantitative structure-activity relationship (2D-QSAR) model for K_p using physicochemical descriptors instead of in vivo experimental data as explanatory variables.

METHODS

We compared our model with the conventional models using 20-fold cross-validation according to the published method (Yun et al. J Pharmacokinet Pharmacodyn 41:1-14, 2014). We used random forest algorithm, which is known to be one of the best predictors for the 2D-QSAR model. Finally, we combined minimum in vitro experimental values and physiochemical descriptors. Thus, the prediction method for K_p value using a few in vitro parameters and physicochemical descriptors was developed; this is a multimodal model.

RESULTS

Its accuracy was found to be superior to that of the conventional models. Results of this research suggest that multimodality is useful for the 2D-QSAR model [RMSE and % of two-fold error: 0.66 and 42.2% (Berezohkovsky), 0.52 and 52.2% (Rodgers), 0.65 and 34.6% (Schmitt), 0.44 and 61.1% (published model), 0.41 and 62.1% (traditional model), 0.39 and 64.5% (multimodal model)].

CONCLUSION

We could develop a 2D-QSAR model for K_p value with the highest accuracy using a few in vitro experimental data and physicochemical descriptors.

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.

Beyond the Michaelis-Menten: Accurate Prediction of Drug Interactions through Cytochrome P450 3A4 Induction

The US Food and Drug Administration (FDA) guidance has recommended several model-based predictions to determine potential drug-drug interactions (DDIs) mediated by cytochrome P450 (CYP) induction. In particular, the ratio of substrate area under the plasma concentration-time curve (AUCR) under and not under the effect of inducers is predicted by the Michaelis-Menten (MM) model, where the MM constant ( K m $$ {K}_{\mathrm{m}} $$ ) of a drug is implicitly assumed to be sufficiently higher than the concentration of CYP enzymes that metabolize the drug ( E T $$ {E}_{\mathrm{T}} $$ ) in both the liver and small intestine. Furthermore, the fraction absorbed from gut lumen ( F a $$ {F}_{\mathrm{a}} $$ ) is also assumed to be one because F a $$ {F}_{\mathrm{a}} $$ is usually unknown. Here, we found that such assumptions lead to serious errors in predictions of AUCR. To resolve this, we propose a new framework to predict AUCR. Specifically, F a $$ {F}_{\mathrm{a}} $$ was re-estimated from experimental permeability values rather than assuming it to be one. Importantly, we used the total quasi-steady-state approximation to derive a new equation, which is valid regardless of the relationship between K m $$ {K}_{\mathrm{m}} $$ and E T $$ {E}_{\mathrm{T}} $$ , unlike the MM model. Thus, our framework becomes much more accurate than the original FDA equation, especially for drugs with high affinities, such as midazolam or strong inducers, such as rifampicin, so that the ratio between K m $$ {K}_{\mathrm{m}} $$ and E T $$ {E}_{\mathrm{T}} $$ becomes low (i.e., the MM model is invalid). Our work greatly improves the prediction of clinical DDIs, which is critical to preventing drug toxicity and failure.

IVIVE: Facilitating the Use of In Vitro Toxicity Data in Risk Assessment and Decision Making

During the past few decades, the science of toxicology has been undergoing a transformation from observational to predictive science. New approach methodologies (NAMs), including in vitro assays, in silico models, read-across, and in vitro to in vivo extrapolation (IVIVE), are being developed to reduce, refine, or replace whole animal testing, encouraging the judicious use of time and resources. Some of these methods have advanced past the exploratory research stage and are beginning to gain acceptance for the risk assessment of chemicals. A review of the recent literature reveals a burst of IVIVE publications over the past decade. In this review, we propose operational definitions for IVIVE, present literature examples for several common toxicity endpoints, and highlight their implications in decision-making processes across various federal agencies, as well as international organizations, including those in the European Union (EU). The current challenges and future needs are also summarized for IVIVE. In addition to refining and reducing the number of animals in traditional toxicity testing protocols and being used for prioritizing chemical testing, the goal to use IVIVE to facilitate the replacement of animal models can be achieved through their continued evolution and development, including a strategic plan to qualify IVIVE methods for regulatory acceptance.

Assessing the impacts on fetal dosimetry of the modelling of the placental transfers of xenobiotics in a pregnancy physiologically based pharmacokinetic model

The developmental origin of health and diseases theory supports the critical role of the fetal exposure to children's health. We developed a physiologically based pharmacokinetic model for human pregnancy (pPBPK) to simulate the maternal and fetal dosimetry throughout pregnancy. Four models of the placental exchanges of chemicals were assessed on ten chemicals for which maternal and fetal data were available. These models were calibrated using non-animal methods: in vitro (InV) or ex vivo (ExV) data, a semi-empirical relationship (SE), or the limitation by the placental perfusion (PL). They did not impact the maternal pharmacokinetics but provided different profiles in the fetus. The PL and InV models performed well even if the PL model overpredicted the fetal exposure for some substances. The SE and ExV models showed the lowest global performance and the SE model a tendency to underprediction. The comparison of the profiles showed that the PL model predicted an increase in the fetal exposure with the pregnancy age, whereas the ExV model predicted a decrease. For the SE and InV models, a small decrease was predicted during the second trimester. All models but the ExV one, presented the highest fetal exposure at the end of the third trimester. Global sensitivity analyses highlighted the predominant influence of the placental transfers on the fetal exposure, as well as the metabolic clearance and the fraction unbound. Finally, the four transfer models could be considered depending on the framework of the use of the pPBPK model and the availability of data or resources to inform their parametrization.

Prediction of the Partition Coefficient between Adipose Tissue and Blood for Environmental Chemicals: From Single QSAR Models to an Integrated Approach

The adipose tissue:blood partition coefficient is a key-endpoint to predict the pharmacokinetics of chemicals in humans and animals, since other organ:blood affinities can be estimated as a function of this parameter. We performed a search in the literature to select all the available rat in vivo data. This approach resulted into two improvements to existing models: a homogeneous definition of the endpoint and an expanded data collection. The resulting dataset was used to develop QSAR models as a function of linear and non-linear algorithms. Several applicability domain definitions were assessed and the definition corresponding to a good balance between performance and coverage was retained. We assessed the pertinence of combining single models into integrated approaches to increase the accuracy in predictions. The best integrated model outperformed the single models and it was characterized by an external mean absolute error (MAE) equal to 0.26, while preserving an adequate coverage (84 %). This performance is comparable to experimental variability and it highlights the pertinence of the integrated model.

Methods to Predict Volume of Distribution

PURPOSE OF REVIEW

Prior to human studies, knowledge of drug disposition in the body is useful to inform decisions on drug safety and efficacy, first in human dosing, and dosing regimen design. It is therefore of interest to develop predictive models for primary pharmacokinetic parameters, clearance, and volume of distribution. The volume of distribution of a drug is determined by the physiological properties of the body and physiochemical properties of the drug, and is used to determine secondary parameters, including the half-life. The purpose of this review is to provide an overview of current methods for the prediction of volume of distribution of drugs, discuss a comparison between the methods, and identify deficiencies in current predictive methods for future improvement.

RECENT FINDINGS

Several volumes of distribution prediction methods are discussed, including preclinical extrapolation, physiological methods, tissue composition-based models to predict tissue:plasma partition coefficients, and quantitative structure-activity relationships. Key factors that impact the prediction of volume of distribution, such as permeability, transport, and accuracy of experimental inputs, are discussed. A comparison of current methods indicates that in general, all methods predict drug volume of distribution with an absolute average fold error of 2-fold. Currently, the use of composition-based PBPK models is preferred to models requiring in vivo input.

SUMMARY

Composition-based models perfusion-limited PBPK models are commonly used at present for prediction of tissue:plasma partition coefficients and volume of distribution, respectively. A better mechanistic understanding of important drug distribution processes will result in improvements in all modeling approaches.

A Whole-Body Physiologically Based Pharmacokinetic Model for Colistin and Colistin Methanesulfonate in Rat

Colistin is a polymyxin antibiotic used to treat patients infected with multidrug-resistant Gram-negative bacteria (MDR-GNB). The objective of this work was to develop a whole-body physiologically based pharmacokinetic (WB-PBPK) model to predict tissue distribution of colistin in rat. The distribution of a drug in a tissue is commonly characterized by its tissue-to-plasma partition coefficient, K_p . Colistin and its prodrug, colistin methanesulfonate (CMS) K_p priors, were measured experimentally from rat tissue homogenates or predicted in silico. The PK parameters of both compounds were estimated fitting in vivo their plasma concentration-time profiles from six rats receiving an i.v. bolus of CMS. The variability in the data was quantified by applying a nonlinear mixed effect (NLME) modelling approach. A WB-PBPK model was developed assuming a well-stirred and perfusion-limited distribution in tissue compartments. Prior information on tissue distribution of colistin and CMS was investigated following three scenarios: K_p was estimated using in silico K_p priors (I) or K_p was estimated using experimental K_p priors (II) or K_p was fixed to the experimental values (III). The WB-PBPK model best described colistin and CMS plasma concentration-time profiles in scenario II. Colistin-predicted concentrations in kidneys in scenario II were higher than in other tissues, which was consistent with its large experimental K_p prior. This might be explained by a high affinity of colistin for renal parenchyma and active reabsorption into the proximal tubular cells. In contrast, renal accumulation of colistin was not predicted in scenario I. Colistin and CMS clearance estimates were in agreement with published values. The developed model suggests using experimental priors over in silico K_p priors for kidneys to provide a better prediction of colistin renal distribution. Such models might serve in drug development for interspecies scaling and investigate the impact of disease state on colistin disposition.

httk: R Package for High-Throughput Toxicokinetics

Thousands of chemicals have been profiled by high-throughput screening programs such as ToxCast and Tox21; these chemicals are tested in part because most of them have limited or no data on hazard, exposure, or toxicokinetics. Toxicokinetic models aid in predicting tissue concentrations resulting from chemical exposure, and a "reverse dosimetry" approach can be used to predict exposure doses sufficient to cause tissue concentrations that have been identified as bioactive by high-throughput screening. We have created four toxicokinetic models within the R software package httk. These models are designed to be parameterized using high-throughput in vitro data (plasma protein binding and hepatic clearance), as well as structure-derived physicochemical properties and species-specific physiological data. The package contains tools for Monte Carlo sampling and reverse dosimetry along with functions for the analysis of concentration vs. time simulations. The package can currently use human in vitro data to make predictions for 553 chemicals in humans, rats, mice, dogs, and rabbits, including 94 pharmaceuticals and 415 ToxCast chemicals. For 67 of these chemicals, the package includes rat-specific in vitro data. This package is structured to be augmented with additional chemical data as they become available. Package httk enables the inclusion of toxicokinetics in the statistical analysis of chemicals undergoing high-throughput screening.

European regulatory perspective on pediatric physiologically based pharmacokinetic models

Physiologically based pharmacokinetic (PBPK) models offer a mechanistic understanding of the disposition of the drug in the body. When well informed and conducted, this may lead to more efficient clinical studies in the vulnerable pediatric population. A review of pediatric submissions to European regulatory authorities has shown a limited number of recent examples. The use of PBPK models to inform pediatric drug development is encouraged. It is, however, important to consider the confidence in the predictions. A qualification of the PBPK platform for the intended purpose should be performed, and a learn-and-confirm approach is recommended. Further research in this area is encouraged to inform important parameters, and to increase availability of pediatric data for model qualification.

Physiologically based pharmacokinetic modeling and simulation in pediatric drug development

Increased regulatory demands for pediatric drug development research have fostered interest in the use of modeling and simulation among industry and academia. Physiologically based pharmacokinetic (PBPK) modeling offers a unique modality to incorporate multiple levels of information to estimate age-specific pharmacokinetics. This tutorial will serve to provide the reader with a basic understanding of the procedural steps to developing a pediatric PBPK model and facilitate a discussion of the advantages and limitations of this modeling technique.