Evaluation of Quantitative Structure Property Relationship Algorithms for Predicting Plasma Protein Binding in Humans

Investigation of the Binding Fraction of PFAS in Human Plasma and Underlying Mechanisms Based on Machine Learning and Molecular Dynamics Simulation

More than 7000 per- and polyfluorinated alkyl substances (PFAS) have been documented in the U.S. Environmental Protection Agency's CompTox Chemicals database. These PFAS can be used in a broad range of industrial and consumer applications but may pose potential environmental issues and health risks. However, little is known about emerging PFAS bioaccumulation to assess their chemical safety. This study focuses specifically on the large and high-quality data set of fluorochemicals from the related environmental and pharmaceutical chemicals databases, and machine learning (ML) models were developed for the classification prediction of the unbound fraction of compounds in plasma. A comprehensive evaluation of the ML models shows that the best blending model yields an accuracy of 0.901 for the test set. The predictions suggest that most PFAS (∼92%) have a high binding fraction in plasma. Introduction of alkaline amino groups is likely to reduce the binding affinities of PFAS with plasma proteins. Molecular dynamics simulations indicate a clear distinction between the high and low binding fractions of PFAS. These computational workflows can be used to predict the bioaccumulation of emerging PFAS and are also helpful for the molecular design of PFAS to prevent the release of high-bioaccumulation compounds into the environment.

Prediction model for milk transfer of drugs by primarily evaluating the area under the curve using QSAR/QSPR

PURPOSE

Information on milk transferability of drugs is important for patients who wish to breastfeed. The purpose of this study is to develop a prediction model for milk-to-plasma drug concentration ratio based on area under the curve (M/P_AUC). The quantitative structure-activity/property relationship (QSAR/QSPR) approach was used to predict compounds involved in active transport during milk transfer.

METHODS

We collected M/P ratio data from literature, which were curated and divided into M/P_AUC ≥ 1 and M/P_AUC < 1. Using the ADMET Predictor® and ADMET Modeler™, we constructed two types of binary classification models: an artificial neural network (ANN) and a support vector machine (SVM).

RESULTS

M/P ratios of 403 compounds were collected, M/P_AUC data were obtained for 173 compounds, while 230 compounds only had M/P_non-AUC values reported. The models were constructed using 129 of the 173 compounds, excluding colostrum data. The sensitivity of the ANN model was 0.969 for the training set and 0.833 for the test set, while the sensitivity of the SVM model was 0.971 for the training set and 0.667 for the test set. The contribution of the charge-based descriptor was high in both models.

CONCLUSIONS

We built a M/P_AUC prediction model using QSAR/QSPR. These predictive models can play an auxiliary role in evaluating the milk transferability of drugs.

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.

A Machine Learning Model to Estimate Toxicokinetic Half-Lives of Per- and Polyfluoro-Alkyl Substances (PFAS) in Multiple Species

Per- and polyfluoroalkyl substances (PFAS) are a diverse group of man-made chemicals that are commonly found in body tissues. The toxicokinetics of most PFAS are currently uncharacterized, but long half-lives (t_½) have been observed in some cases. Knowledge of chemical-specific t_½ is necessary for exposure reconstruction and extrapolation from toxicological studies. We used an ensemble machine learning method, random forest, to model the existing in vivo measured t_½ across four species (human, monkey, rat, mouse) and eleven PFAS. Mechanistically motivated descriptors were examined, including two types of surrogates for renal transporters: (1) physiological descriptors, including kidney geometry, for renal transporter expression and (2) structural similarity of defluorinated PFAS to endogenous chemicals for transporter affinity. We developed a classification model for t_½ (Bin 1: <12 h; Bin 2: <1 week; Bin 3: <2 months; Bin 4: >2 months). The model had an accuracy of 86.1% in contrast to 32.2% for a y-randomized null model. A total of 3890 compounds were within domain of the model, and t_½ was predicted using the bin medians: 4.9 h, 2.2 days, 33 days, and 3.3 years. For human t_½, 56% of PFAS were classified in Bin 4, 7% were classified in Bin 3, and 37% were classified in Bin 2. This model synthesizes the limited available data to allow tentative extrapolation and prioritization.

In Silico Prediction of Human Clinical Pharmacokinetics with ANDROMEDA by Prosilico: Predictions for an Established Benchmarking Data Set, a Modern Small Drug Data Set, and a Comparison with Laboratory Methods

There is an ongoing aim to replace animal and in vitro laboratory models with in silico methods. Such replacement requires the successful validation and comparably good performance of the alternative methods. We have developed an in silico prediction system for human clinical pharmacokinetics, based on machine learning, conformal prediction and a new physiologically-based pharmacokinetic model, i.e. ANDROMEDA. The objectives of this study were: a) to evaluate how well ANDROMEDA predicts the human clinical pharmacokinetics of a previously proposed benchmarking data set comprising 24 physicochemically diverse drugs and 28 small drug molecules new to the market in 2021; b) to compare its predictive performance with that of laboratory methods; and c) to investigate and describe the pharmacokinetic characteristics of the modern drugs. Median and maximum prediction errors for the selected major parameters were ca 1.2 to 2.5-fold and 16-fold for both data sets, respectively. Prediction accuracy was on par with, or better than, the best laboratory-based prediction methods (superior performance for a vast majority of the comparisons), and the prediction range was considerably broader. The modern drugs have higher average molecular weight than those in the benchmarking set from 15 years earlier (ca 200 g/mol higher), and were predicted to (generally) have relatively complex pharmacokinetics, including permeability and dissolution limitations and significant renal, biliary and/or gut-wall elimination. In conclusion, the results were overall better than those obtained with laboratory methods, and thus serve to further validate the ANDROMEDA in silico system for the prediction of human clinical pharmacokinetics of modern and physicochemically diverse drugs.

Exposure forecasting - ExpoCast - for data-poor chemicals in commerce and the environment

Estimates of exposure are critical to prioritize and assess chemicals based on risk posed to public health and the environment. The U.S. Environmental Protection Agency (EPA) is responsible for regulating thousands of chemicals in commerce and the environment for which exposure data are limited. Since 2009 the EPA's ExpoCast ("Exposure Forecasting") project has sought to develop the data, tools, and evaluation approaches required to generate rapid and scientifically defensible exposure predictions for the full universe of existing and proposed commercial chemicals. This review article aims to summarize issues in exposure science that have been addressed through initiatives affiliated with ExpoCast. ExpoCast research has generally focused on chemical exposure as a statistical systems problem intended to inform thousands of chemicals. The project exists as a companion to EPA's ToxCast ("Toxicity Forecasting") project which has used in vitro high-throughput screening technologies to characterize potential hazard posed by thousands of chemicals for which there are limited toxicity data. Rapid prediction of chemical exposures and in vitro-in vivo extrapolation (IVIVE) of ToxCast data allow for prioritization based upon risk of adverse outcomes due to environmental chemical exposure. ExpoCast has developed (1) integrated modeling approaches to reliably predict exposure and IVIVE dose, (2) highly efficient screening tools for chemical prioritization, (3) efficient and affordable tools for generating new exposure and dose data, and (4) easily accessible exposure databases. The development of new exposure models and databases along with the application of technologies like non-targeted analysis and machine learning have transformed exposure science for data-poor chemicals. By developing high-throughput tools for chemical exposure analytics and translating those tools into public health decisions ExpoCast research has served as a crucible for identifying and addressing exposure science knowledge gaps.

Plasma Protein Binding Rate and Pharmacokinetics of Lekethromycin in Rats

Lekethromycin (LKMS), a novel macrolide lactone, is still unclear regarding its absorption. Thus, we conducted this study to investigate the characteristics of LKMS in rats. We chose the ultrafiltration method to measure the plasma protein binding rate of LKMS. As a result, LKMS was characterized by quick absorption, delayed elimination, and extensive distribution in rats following intramuscular (im) and subcutaneous (sc) administration. Moreover, LKMS has a high protein binding rate (78–91%) in rats at a concentration range of 10–800 ng/mL. LKMS bioavailability was found to be approximately 84–139% and 52–77% after im and sc administration, respectively; however, LKMS was found to have extremely poor bioavailability after oral administration (po) in rats. The pharmacokinetic parameters cannot be considered linearly correlated with the administered dose. Additionally, LKMS and its corresponding metabolites were shown to be metabolically stable in the liver microsomes of rats, dogs, pigs, and humans. Notably, only one phase I metabolite was identified during in vitro study, suggesting most of drug was not converted. Collectively, LKMS had quick absorption but poor absorption after oral administration, extensive tissue distribution, metabolic stability, and slow elimination in rats.

Towards best use and regulatory acceptance of generic physiologically based kinetic (PBK) models for in vitro-to-in vivo extrapolation (IVIVE) in chemical risk assessment

With an increasing need to incorporate new approach methodologies (NAMs) in chemical risk assessment and the concomitant need to phase out animal testing, the interpretation of in vitro assay readouts for quantitative hazard characterisation becomes more important. Physiologically based kinetic (PBK) models, which simulate the fate of chemicals in tissues of the body, play an essential role in extrapolating in vitro effect concentrations to in vivo bioequivalent exposures. As PBK-based testing approaches evolve, it will become essential to standardise PBK modelling approaches towards a consensus approach that can be used in quantitative in vitro-to-in vivo extrapolation (QIVIVE) studies for regulatory chemical risk assessment based on in vitro assays. Based on results of an ECETOC expert workshop, steps are recommended that can improve regulatory adoption: (1) define context and implementation, taking into consideration model complexity for building fit-for-purpose PBK models, (2) harmonise physiological input parameters and their distribution and define criteria for quality chemical-specific parameters, especially in the absence of in vivo data, (3) apply Good Modelling Practices (GMP) to achieve transparency and design a stepwise approach for PBK model development for risk assessors, (4) evaluate model predictions using alternatives to in vivo PK data including read-across approaches, (5) use case studies to facilitate discussions between modellers and regulators of chemical risk assessment. Proof-of-concepts of generic PBK modelling approaches are published in the scientific literature at an increasing rate. Working on the previously proposed steps is, therefore, needed to gain confidence in PBK modelling approaches for regulatory use.

IDL-PPBopt: A Strategy for Prediction and Optimization of Human Plasma Protein Binding of Compounds via an Interpretable Deep Learning Method

The prediction and optimization of pharmacokinetic properties are essential in lead optimization. Traditional strategies mainly depend on the empirical chemical rules from medicinal chemists. However, with the rising amount of data, it is getting more difficult to manually extract useful medicinal chemistry knowledge. To this end, we introduced IDL-PPBopt, a computational strategy for predicting and optimizing the plasma protein binding (PPB) property based on an interpretable deep learning method. At first, a curated PPB data set was used to construct an interpretable deep learning model, which showed excellent predictive performance with a root mean squared error of 0.112 for the entire test set. Then, we designed a detection protocol based on the model and Wilcoxon test to identify the PPB-related substructures (named privileged substructures, PSubs) for each molecule. In total, 22 general privileged substructures (GPSubs) were identified, which shared some common features such as nitrogen-containing groups, diamines with two carbon units, and azetidine. Furthermore, a series of second-level chemical rules for each GPSub were derived through a statistical test and then summarized into substructure pairs. We demonstrated that these substructure pairs were equally applicable outside the training set and accordingly customized the structural modification schemes for each GPSub, which provided alternatives for the optimization of the PPB property. Therefore, IDL-PPBopt provides a promising scheme for the prediction and optimization of the PPB property and would be helpful for lead optimization of other pharmacokinetic properties.

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.

Designing QSARs for Parameters of High-Throughput Toxicokinetic Models Using Open-Source Descriptors

The intrinsic metabolic clearance rate (Cl_int) and the fraction of the chemical unbound in plasma (f_up) serve as important parameters for high-throughput toxicokinetic (TK) models, but experimental data are limited for many chemicals. Open-source quantitative structure-activity relationship (QSAR) models for both parameters were developed to offer reliable in silico predictions for a diverse set of chemicals regulated under the U.S. law, including pharmaceuticals, pesticides, and industrial chemicals. As a case study to demonstrate their utility, model predictions served as inputs to the TK component of a risk-based prioritization approach based on bioactivity/exposure ratios (BERs), in which a BER < 1 indicates that exposures are predicted to exceed a biological activity threshold. When applied to a subset of the Tox21 screening library (6484 chemicals), we found that the proportion of chemicals with BER <1 was similar using either in silico (1133/6484; 17.5%) or in vitro (148/848; 17.5%) parameters. Further, when considering only the chemicals in the Tox21 set with in vitro data, there was a high concordance of chemicals classified with either BER <1 or >1 using either in silico or in vitro parameters (767/848, 90.4%). Thus, the presented QSARs may be suitable for prioritizing the risk posed by many chemicals for which measured in vitro TK data are lacking.