Predicting Volume of Distribution in Humans: Performance of In Silico Methods for a Large Set of Structurally Diverse Clinical Compounds

A Combination of Machine Learning and PBPK Modeling Approach for Pharmacokinetics Prediction of Small Molecules in Humans

PURPOSE

Recently, there has been rapid development in model-informed drug development, which has the potential to reduce animal experiments and accelerate drug discovery. Physiologically based pharmacokinetic (PBPK) and machine learning (ML) models are commonly used in early drug discovery to predict drug properties. However, basic PBPK models require a large number of molecule-specific inputs from in vitro experiments, which hinders the efficiency and accuracy of these models. To address this issue, this paper introduces a new computational platform that combines ML and PBPK models. The platform predicts molecule PK profiles with high accuracy and without the need for experimental data.

METHODS

This study developed a whole-body PBPK model and ML models of plasma protein fraction unbound ( f up ), Caco-2 cell permeability, and total plasma clearance to predict the PK of small molecules after intravenous administration. Pharmacokinetic profiles were simulated using a "bottom-up" PBPK modeling approach with ML inputs. Additionally, 40 compounds were used to evaluate the platform's accuracy.

RESULTS

Results showed that the ML-PBPK model predicted the area under the concentration-time curve (AUC) with 65.0 % accuracy within a 2-fold range, which was higher than using in vitro inputs with 47.5 % accuracy.

CONCLUSION

The ML-PBPK model platform provides high accuracy in prediction and reduces the number of experiments and time required compared to traditional PBPK approaches. The platform successfully predicts human PK parameters without in vitro and in vivo experiments and can potentially guide early drug discovery and development.

Another string to your bow: machine learning prediction of the pharmacokinetic properties of small molecules

INTRODUCTION

Prediction of pharmacokinetic (PK) properties is crucial for drug discovery and development. Machine-learning (ML) models, which use statistical pattern recognition to learn correlations between input features (such as chemical structures) and target variables (such as PK parameters), are being increasingly used for this purpose. To embed ML models for PK prediction into workflows and to guide future development, a solid understanding of their applicability, advantages, limitations, and synergies with other approaches is necessary.

AREAS COVERED

This narrative review discusses the design and application of ML models to predict PK parameters of small molecules, especially in light of established approaches including in vitro-in vivo extrapolation (IVIVE) and physiologically based pharmacokinetic (PBPK) models. The authors illustrate scenarios in which the three approaches are used and emphasize how they enhance and complement each other. In particular, they highlight achievements, the state of the art and potentials of applying machine learning for PK prediction through a comphrehensive literature review.

EXPERT OPINION

ML models, when carefully crafted, regularly updated, and appropriately used, empower users to prioritize molecules with favorable PK properties. Informed practitioners can leverage these models to improve the efficiency of drug discovery and development process.

Translational modeling-based evidence for enhanced efficacy of standard-of-care drugs in combination with anti-microRNA-155 in non-small-cell lung cancer

Elevated microRNA-155 (miR-155) expression in non-small-cell lung cancer (NSCLC) promotes cisplatin resistance and negatively impacts treatment outcomes. However, miR-155 can also boost anti-tumor immunity by suppressing PD-L1 expression. We developed a multiscale mechanistic model, calibrated with in vivo data and then extrapolated to humans, to investigate the therapeutic effects of nanoparticle-delivered anti-miR-155 in NSCLC, alone or in combination with standard-of-care drugs. Model simulations and analyses of the clinical scenario revealed that monotherapy with anti-miR-155 at a dose of 2.5 mg/kg administered once every three weeks has substantial anti-cancer activity. It led to a median progression-free survival (PFS) of 6.7 months, which compared favorably to cisplatin and immune checkpoint inhibitors. Further, we explored the combinations of anti-miR-155 with standard-of-care drugs, and found strongly synergistic two- and three-drug combinations. A three-drug combination of anti-miR-155, cisplatin, and pembrolizumab resulted in a median PFS of 13.1 months, while a two-drug combination of anti-miR-155 and cisplatin resulted in a median PFS of 11.3 months, which emerged as a more practical option due to its simple design and cost-effectiveness. Our analyses also provided valuable insights into unfavorable dose ratios for drug combinations, highlighting the need for optimizing dose regimen to prevent antagonistic effects. Thus, this work bridges the gap between preclinical development and clinical translation of anti-miR-155 and unravels the potential of anti-miR-155 combination therapies in NSCLC.

Screening of phytochemicals from Clerodendrum inerme (L.) Gaertn as potential anti-breast cancer compounds targeting EGFR: an in-silico approach

Breast cancer (BC) is the most prevalent malignancy among women around the world. The epidermal growth factor receptor (EGFR) is a tyrosine kinase receptor (RTK) of the ErbB/HER family. It is essential for triggering the cellular signaling cascades that control cell growth and survival. However, perturbations in EGFR signaling lead to cancer development and progression. Hence, EGFR is regarded as a prominent therapeutic target for breast cancer. Therefore, in the current investigation, EGFR was targeted with phytochemicals from Clerodendrum inerme (L.) Gaertn (C. inerme). A total of 121 phytochemicals identified by gas chromatography-mass spectrometry (GC-MS) analysis were screened against EGFR through molecular docking, ADMET analyses (Absorption, Distribution, Metabolism, Excretion, and Toxicity), PASS predictions, and molecular dynamics simulation, which revealed three potential hit compounds with CIDs 10586 [i.e. alpha-bisabolol (-6.4 kcal/mol)], 550281 [i.e. 2,(4,4-Trimethyl-3-hydroxymethyl-5a-(3-methyl-but-2-enyl)-cyclohexene) (-6.5 kcal/mol)], and 161271 [i.e. salvigenin (-7.4 kcal/mol)]. The FDA-approved drug gefitinib was used to compare the inhibitory effects of the phytochemicals. The top selected compounds exhibited good ADMET properties and obeyed Lipinski's rule of five (ROF). The molecular docking analysis showed that salvigenin was the best among the three compounds and formed bonds with the key residue Met 793. Furthermore, the molecular mechanics generalized born surface area (MMGBSA) calculations, molecular dynamics simulation, and normal mode analysis validated the binding affinity of the compounds and also revealed the strong stability and compactness of phytochemicals at the docked site. Additionally, DFT and DOS analyses were done to study the reactivity of the compounds and to further validate the selected phytochemicals. These results suggest that the identified phytochemicals possess high inhibitory potential against the target EGFR and can treat breast cancer. However, further in vitro and in vivo investigations are warranted towards the development of these constituents into novel anti-cancer drugs.Communicated by Ramaswamy H. Sarma.

A review on potential approach for in silico toxicity analysis of respirable fraction of ambient particulate matter

Epidemiological and toxicological studies have shown the adverse effect of ambient particulate matter (PM) on respiratory and cardiovascular systems inside the human body. Various cellular and acellular assays in literature use indicators like ROS generation, cell inflammation, mutagenicity, etc., to assess PM toxicity and associated health effects. The presence of toxic compounds in respirable PM needs detailed studies for proper understanding of absorption, distribution, metabolism, and excretion mechanisms inside the body as it is difficult to accurately imitate or simulate these mechanisms in lab or animal models. The leaching kinetics of the lung fluid, PM composition, retention time, body temperature, etc., are hard to mimic in an artificial experimental setup. Moreover, the PM size fraction also plays an important role. For example, the ultrafine particles may directly enter systemic circulations while coarser PM10 may be trapped and deposited in the tracheo-bronchial region. Hence, interpretation of these results in toxicity models should be done judiciously. Computational models predicting PM toxicity are rare in the literature. The variable composition of PM and lack of proper understanding for their synergistic role inside the body are prime reasons behind it. This review explores different possibilities of in silico modeling and suggests possible approaches for the risk assessment of PM particles. The toxicity testing approach for engineered nanomaterials, drugs, food industries, etc., have also been investigated for application in computing PM toxicity.

In silico ADME/tox comes of age: twenty years later

In the early 2000s pharmaceutical drug discovery was beginning to use computational approaches for absorption, distribution, metabolism, excretion and toxicity (ADME/Tox, also known as ADMET) prediction. This emphasis on prediction was an effort to reduce the risk of later stage failures from ADME/Tox.Much has been written in the intervening twenty plus years and significant expenditure has occurred in companies developing these in silico capabilities which can be gleaned from publications. It is therefore an appropriate time to briefly reflect on what was proposed then and what the reality is today.20 years ago, we tended to optimise bioactivity and perhaps one ADME/Tox property at a time. Previously pharmaceutical companies needed a whole infrastructure for models - in silico and in vitro experts, IT, champions on a project team, educators and management support. Now we are in the age of generative de novo design where bioactivity and many ADME/Tox properties can be optimised and large language model technologies are available.There are also some challenges such as the focus on very large molecules which may be outside of current ADME/Tox models.We provide an opportunity to look forward with the increasing public data for ADME/Tox as well as expanded types of algorithms available.

Using In Silico Approach for Metabolomic and Toxicity Prediction of Alternariol

Alternariol is a metabolite produced by Alternaria fungus that can contaminate a variety of food and feed materials. The objective of the present paper was to provide a prediction of Phase I and II metabolites of alternariol and a detailed ADME/Tox profile for alternariol and its metabolites using an in silico working model based on the MetaTox, SwissADME, pKCMS, and PASS online computational programs. A number of 12 metabolites were identified as corresponding to the metabolomic profile of alternariol. ADME profile for AOH and predicted metabolites indicated a moderate or high intestinal absorption probability but a low probability to penetrate the blood-brain barrier. In addition to cytotoxic, mutagenic, carcinogenic, and endocrine disruptor effects, the computational model has predicted other toxicological endpoints for the analyzed compounds, such as vascular toxicity, haemato-toxicity, diarrhea, and nephrotoxicity. AOH and its metabolites have been predicted to act as a substrate for different isoforms of phase I and II drug-metabolizing enzymes and to interact with the response to oxidative stress. In conclusion, in silico methods can represent a viable alternative to in vitro and in vivo tests for the prediction of mycotoxins metabolism and toxicity.

Artificial intelligence for compound pharmacokinetics prediction

Optimisation of compound pharmacokinetics (PK) is an integral part of drug discovery and development. Animal in vivo PK data as well as human and animal in vitro systems are routinely utilised to evaluate PK in humans. In recent years machine learning and artificial intelligence (AI) emerged as a major tool for modelling of in vivo animal and human PK, enabling prediction from chemical structure early in drug discovery, and therefore offering opportunities to guide the design and prioritisation of molecules based on relevant in vivo properties and, ultimately, predicting human PK at the point of design. This review presents recent advances in machine learning and AI models for in vivo animal and human PK for small-molecule compounds as well as some examples for antibody therapeutics.

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.

Computational Predictions of Nonclinical Pharmacokinetics at the Drug Design Stage

Although computational predictions of pharmacokinetics (PK) are desirable at the drug design stage, existing approaches are often limited by prediction accuracy and human interpretability. Using a discovery data set of mouse and rat PK studies at Roche (9,685 unique compounds), we performed a proof-of-concept study to predict key PK properties from chemical structure alone, including plasma clearance (CLp), volume of distribution at steady-state (Vss), and oral bioavailability (F). Ten machine learning (ML) models were evaluated, including Single-Task, Multitask, and transfer learning approaches (i.e., pretraining with in vitro data). In addition to prediction accuracy, we emphasized human interpretability of outcomes, especially the quantification of uncertainty, applicability domains, and explanations of predictions in terms of molecular features. Results show that intravenous (IV) PK properties (CLp and Vss) can be predicted with good precision (average absolute fold error, AAFE of 1.96-2.84 depending on data split) and low bias (average fold error, AFE of 0.98-1.36), with AutoGluon, Gaussian Process Regressor (GP), and ChemProp displaying the best performance. Driven by higher complexity of oral PK studies, predictions of F were more challenging, with the best AAFE values of 2.35-2.60 and higher overprediction bias (AFE of 1.45-1.62). Multi-Task approaches and pretraining of ChemProp neural networks with in vitro data showed similar precision to Single-Task models but helped reduce the bias and increase correlations between observations and predictions. A combination of GP-computed prediction variance, molecular clustering, and dimensionality-reduction provided valuable quantitative insights into prediction uncertainty and applicability domains. SHAPley Additive exPlanations (SHAPs) highlighted molecular features contributing to prediction outcomes of Vss, providing explanations that could aid drug design. Combined results show that computational predictions of PK are feasible at the drug design stage, with several ML technologies converging to successfully leverage historical PK data sets. Further studies are needed to unlock the full potential of this approach, especially with respect to data set sizes and quality, transfer learning between in vitro and in vivo data sets, model-independent quantification of uncertainty, and explainability of predictions.

Pharmacophore-Oriented Identification of Potential Leads as CCR5 Inhibitors to Block HIV Cellular Entry

Cysteine-cysteine chemokine receptor 5 (CCR5) has been discovered as a co-receptor for cellular entry of human immunodeficiency virus (HIV). Moreover, the role of CCR5 in a variety of cancers and various inflammatory responses was also discovered. Despite the fact that several CCR5 antagonists have been investigated in clinical trials, only Maraviroc has been licensed for use in the treatment of HIV patients. This indicates that there is a need for novel CCR5 antagonists. Keeping this in mind, the present study was designed. The active CCR5 inhibitors with known IC₅₀ value were selected from the literature and utilized to develop a ligand-based common feature pharmacophore model. The validated pharmacophore model was further used for virtual screening of drug-like databases obtained from the Asinex, Specs, InterBioScreen, and Eximed chemical libraries. Utilizing computational methods such as molecular docking studies, molecular dynamics simulations, and binding free energy calculation, the binding mechanism of selected inhibitors was established. The identified Hits not only showed better binding energy when compared to Maraviroc, but also formed stable interactions with the key residues and showed stable behavior throughout the 100 ns MD simulation. Our findings suggest that Hit1 and Hit2 may be potential candidates for CCR5 inhibition, and, therefore, can be considered for further CCR5 inhibition programs.

Application of machine learning techniques to the analysis and prediction of drug pharmacokinetics

In this review, we describe the current status and challenges in applying machine-learning techniques to the analysis and prediction of pharmacokinetic data. The theory of pharmacokinetics has been developed over decades on the basis of physiology and reaction kinetics. Mathematical models allow the reduction of pharmacokinetic data to parameter values, giving insight and understanding into ADME processes and predicting the outcome of different dosing scenarios. However, much information hidden in the data is lost through conceptual simplification with models. It is difficult to use mechanistic models alone to predict diverse pharmacokinetic time profiles, including inter-drug and inter-individual differences, in a cross-sectional manner. Machine learning is a prediction platform that can handle complex phenomena through data-driven analysis. As a resule, machine learning has been successfully adopted in various fields, including image recognition and language processing, and has been used for over two decades in pharmacokinetic research, primarily in the area of quantitative structure-activity relationships for pharmacokinetic parameters. Machine-learning models are generally known to provide better predictive performance than conventional linear models. Owing to the recent success in deep learning, models with new structures are being consistently proposed. These models include transfer learning and generative adversarial networks, which contribute to the effective use of a limited amount of data by diverting existing similar models or generating pseudo-data. How to make such newly emerging machine learning technologies applicable to meet challenges in the pharmacokinetics/pharmacodynamics field is now the key issue.

Translational pharmacokinetics of a novel bispecific antibody against Ebola virus (MBS77E) from animal to human by PBPK modeling & simulation

The goal of this study was to construct a PBPK model to accelerate the translation of MBS77E, a humanized bispecific antibody against the Ebola virus. In-depth nonclinical pharmacokinetic studies in rats, monkeys, wild-type mice and transgenic mice were conducted. The pH-dependent affinities (K_D) of MBS77E to recombinant FcRn of different species were determined by surface plasmon resonance analysis. A mechanistic whole-body PBPK model of MBS77E was developed and validated in the assessment of PK profiles and tissue distributions in preclinical models. This PBPK model was finally used to predict human PK behaviors of MBS77E. Simulations from the PBPK model with measured and fitted parameters were able to yield good predictions of the serum and tissue pharmacokinetic parameters of MBS77E within 2-fold errors. The predicted serum concentration in humans was able to maintain a sufficiently high level for more than 14 days after 50 mg/kg i.v. administrating. This achievement unlocks that PBPK modeling is a powerful tool to gain insights into the properties of antibody drugs. It guided experimental efforts to obtain necessary information before entry into humans.

Advances in computational methods along the exposure to toxicological response paradigm

Human health risk assessment is a function of chemical toxicity, bioavailability to reach target biological tissues, and potential environmental exposure. These factors are complicated by many physiological, biochemical, physical and lifestyle factors. Furthermore, chemical health risk assessment is challenging in view of the large, and continually increasing, number of chemicals found in the environment. These challenges highlight the need to prioritize resources for the efficient and timely assessment of those environmental chemicals that pose greatest health risks. Computational methods, either predictive or investigative, are designed to assist in this prioritization in view of the lack of cost prohibitive in vivo experimental data. Computational methods provide specific and focused toxicity information using in vitro high throughput screening (HTS) assays. Information from the HTS assays can be converted to in vivo estimates of chemical levels in blood or target tissue, which in turn are converted to in vivo dose estimates that can be compared to exposure levels of the screened chemicals. This manuscript provides a review for the landscape of computational methods developed and used at the U.S. Environmental Protection Agency (EPA) highlighting their potentials and challenges.

Applications, Challenges, and Outlook for PBPK Modeling and Simulation: A Regulatory, Industrial and Academic Perspective

Several regulatory guidances on the use of physiologically based pharmacokinetic (PBPK) analyses and physiologically based biopharmaceutics model(s) (PBBM(s)) have been issued. Workshops are routinely held, demonstrating substantial interest in applying these modeling approaches to address scientific questions in drug development. PBPK models and PBBMs have remarkably contributed to model-informed drug development (MIDD) such as anticipating clinical PK outcomes affected by extrinsic and intrinsic factors in general and specific populations. In this review, we proposed practical considerations for a "base" PBPK model construction and development, summarized current status, challenges including model validation and gaps in system models, and future perspectives in PBPK evaluation to assess a) drug metabolizing enzyme(s)- or drug transporter(s)- mediated drug-drug interactions b) dosing regimen prediction, sampling timepoint selection and dose validation in pediatric patients from newborns to adolescents, c) drug exposure in patients with renal and/or and hepatic organ impairment, d) maternal-fetal drug disposition during pregnancy, and e) pH-mediated drug-drug interactions in patients treated with proton pump inhibitors/acid-reducing agents (PPIs/ARAs) intended for gastric protection. Since PBPK can simulate outcomes in clinical studies with enrollment challenges or ethical issues, the impact of PBPK models on waivers and how to strengthen study waiver is discussed.

A PBPK Model of Ternary Cyclodextrin Complex of ST-246 Was Built to Achieve a Reasonable IV Infusion Regimen for the Treatment of Human Severe Smallpox

ST-246 is an oral drug against pathogenic orthopoxvirus infections. An intravenous formulation is required for some critical patients. A ternary complex of ST-246/meglumine/hydroxypropyl-β-cyclodextrin with well-improved solubility was successfully developed in our institute. The aim of this study was to achieve a reasonable intravenous infusion regimen of this novel formulation by a robust PBPK model based on preclinical pharmacokinetic studies. The pharmacokinetics of ST-246 after intravenous injection at different doses in rats, dogs, and monkeys were conducted to obtain clearances. The clearance of humans was generated by using the allometric scaling approach. Tissue distribution of ST-246 was conducted in rats to obtain tissue partition coefficients (K_p). The PBPK model of the rat was first built using in vivo clearance and K_p combined with in vitro physicochemical properties, unbound fraction, and cyclodextrin effect parameters of ST-246. Then the PBPK model was transferred to a dog and monkey and validated simultaneously. Finally, pharmacokinetic profiles after IV infusion at different dosages utilizing the human PBPK model were compared to the observed oral PK profile of ST-246 at therapeutic dosage (600 mg). The mechanistic PBPK model described the animal PK behaviors of ST-246 via intravenous injection and infusion with fold errors within 1.2. It appeared that 6h-IV infusion at 5 mg/kg BID produced similar C_max and AUC as oral administration at 600 mg. A PBPK model of ST-246 was built to achieve a reasonable regimen of IV infusion for the treatment of severe smallpox, which will facilitate the clinical translation of this novel formulation.

Cyclodextrin-Modified Nanomaterials for Drug Delivery: Classification and Advances in Controlled Release and Bioavailability

In drug delivery, one widely used way of overcoming the biopharmaceutical problems present in several active pharmaceutical ingredients, such as poor aqueous solubility, early instability, and low bioavailability, is the formation of inclusion compounds with cyclodextrins (CD). In recent years, the use of CD derivatives in combination with nanomaterials has shown to be a promising strategy for formulating new, optimized systems. The goals of this review are to give in-depth knowledge and critical appraisal of the main CD-modified or CD-based nanomaterials for drug delivery, such as lipid-based nanocarriers, natural and synthetic polymeric nanocarriers, nanosponges, graphene derivatives, mesoporous silica nanoparticles, plasmonic and magnetic nanoparticles, quantum dots and other miscellaneous systems such as nanovalves, metal-organic frameworks, Janus nanoparticles, and nanofibers. Special attention is given to nanosystems that achieve controlled drug release and increase their bioavailability during in vivo studies.

An integrated exposure and pharmacokinetic modeling framework for assessing population-scale risks of phthalates and their substitutes

To effectively incorporate in vitro-in silico-based methods into the regulation of consumer product safety, a quantitative connection between product phthalate concentrations and in vitro bioactivity data must be established for the general population. We developed, evaluated, and demonstrated a modeling framework that integrates exposure and pharmacokinetic models to convert product phthalate concentrations into population-scale risks for phthalates and their substitutes. A probabilistic exposure model was developed to generate the distribution of multi-route exposures based on product phthalate concentrations, chemical properties, and human activities. Pharmacokinetic models were developed to simulate population toxicokinetics using Bayesian analysis via the Markov chain Monte Carlo method. Both exposure and pharmacokinetic models demonstrated good predictive capability when compared with worldwide studies. The distributions of exposures and pharmacokinetics were integrated to predict the population distributions of internal dosimetry. The predicted distributions showed reasonable agreement with the U.S. biomonitoring surveys of urinary metabolites. The "source-to-outcome" local sensitivity analysis revealed that food contact materials had the greatest impact on body burden for di(2-ethylhexyl) adipate (DEHA), di-2-ethylhexyl phthalate (DEHP), di(isononyl) cyclohexane-1,2-dicarboxylate (DINCH), and di(2-propylheptyl) phthalate (DPHP), whereas the body burden of diethyl phthalate (DEP) was most sensitive to the concentration in personal care products. The upper bounds of predicted plasma concentrations showed no overlap with ToxCast in vitro bioactivity values. Compared with the in vitro-to-in vivo extrapolation (IVIVE) approach, the integrated modeling framework has significant advantages in mapping product phthalate concentrations to multi-route risks, and thus is of great significance for regulatory use with a relatively low input requirement. Further integration with new approach methodologies will facilitate these in vitro-in silico-based risk assessments for a broad range of products containing an equally broad range of chemicals.

A decade of machine learning-based predictive models for human pharmacokinetics: Advances and challenges

Traditionally, in vitro and in vivo methods are useful for estimating human pharmacokinetics (PK) parameters; however, it is impractical to perform these complex and expensive experiments on a large number of compounds. The integration of publicly available chemical, or medical Big Data and artificial intelligence (AI)-based approaches led to qualitative and quantitative prediction of human PK of a candidate drug. However, predicting drug response with these approaches is challenging, partially because of the adaptation of algorithmic and limitations related to experimental data. In this report, we provide an overview of machine learning (ML)-based quantitative structure-activity relationship (QSAR) models used in the assessment or prediction of PK values as well as databases available for obtaining such data.