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

Development of machine learning-based quantitative structure-activity relationship models for predicting plasma half-lives of drugs in six common food animal species

Plasma half-life is a crucial pharmacokinetic parameter for estimating extralabel withdrawal intervals of drugs to ensure the safety of food products derived from animals. This study focuses on developing a quantitative structure-activity relationship (QSAR) model incorporating multiple machine learning and artificial intelligence algorithms, and aims to predict the plasma half-lives of drugs in 6 food animals, including cattle, chickens, goats, sheep, swine, and turkeys. By integrating 4 machine learning algorithms with 5 molecular descriptor types, 20 QSAR models were developed using data from the Food Animal Residue Avoidance Databank (FARAD) Comparative Pharmacokinetic Database. The deep neural network (DNN) algorithm demonstrated the best prediction ability of plasma half-lives. The DNN model with all descriptors achieved superior performance with a high coefficient of determination (R2) of 0.82 ± 0.19 in 5-fold cross-validation on the training sets and an R2 of 0.67 on the independent test set, indicating accurate predictions and good generalizability. The final model was converted to a user-friendly web dashboard to facilitate its wide application by the scientific community. This machine learning-based QSAR model serves as a valuable tool for predicting drug plasma half-lives and extralabel withdrawal intervals in 6 common food animals based on physicochemical properties. It also provides a foundation to develop more advanced models to predict the tissue half-life of drugs in food animals.

Prediction of Multi-Pharmacokinetics Property in Multi-Species: Bayesian Neural Network Stacking Model with Uncertainty

Pharmacokinetic (PK) properties of a drug are vital attributes influencing its therapeutic effectiveness, playing an important role in the drug development process. Focusing on the difficult task of predicting PK parameters, we compiled an extensive data set comprising parameters across multiple species. Building upon this groundwork, we introduced the PKStack ensemble model to predict PK parameters across diverse species. PKStack integrates a variety of base models and includes uncertainty in its predictions. We also manually collected PK data from animals as an external test set. We predicted a total of 45 tasks for nine PK parameters in five species, and in general, the prediction accuracy was better for intravenous injections, including parameters such as human Vd (R2 = 0.72, RMSE = 0.31), human CL (R2 = 0.52, RMSE = 0.32), and others. In addition to predictive accuracy, we also considered the interpretability of the results and the definition of the model's application domain. Based on the findings, our model has great potential for practical applications in drug discovery.

Development of Predictive Statistical Model for Gaining Valuable Insights in Pharmaceutical Product Recalls

The rapid progress in artificial intelligence (AI) has revolutionized problem-solving across various domains. The global challenge of pharmaceutical product recalls imposes the development of effective tools to control and reduce shortage of pharmaceutical products and help avoid such recalls. This study employs AI, specifically machine learning (MI), to analyze critical factors influencing formulation, manufacturing, and formulation complexity which could offer promising avenue for optimizing drug development processes. Utilizing FDAZilla and SafeRX tools, an open database model was constructed, and predictive statistical models were developed using Multivariate Analysis and the Least Absolute Shrinkage and Selection Operator (LASSO) Approach. The study focuses on key descriptors such as delivery route, dosage form, dose, BCS classification, solid-state and physicochemical properties, release type, half-life, and manufacturing complexity. Through statistical analysis, a data simplification process identifies critical descriptors, assigning risk numbers and computing a cumulative risk number to assess product complexity and recall likelihood. Partial Least Square Regression and the LASSO approach established quantitative relationships between key descriptors and cumulative risk numbers. Results have identified key descriptors; BCS Class I, dose number, release profile, and drug half-life influencing product recall risk. The LASSO model further confirms these identified descriptors with 71% accuracy. In conclusion, the study presents a holistic AI and machine learning approach for evaluating and forecasting pharmaceutical product recalls, underscoring the importance of descriptors, formulation complexity, and manufacturing processes in mitigating risks associated with product quality.

Artificial Intelligence (AI) Applications in Drug Discovery and Drug Delivery: Revolutionizing Personalized Medicine

Artificial intelligence (AI) encompasses a broad spectrum of techniques that have been utilized by pharmaceutical companies for decades, including machine learning, deep learning, and other advanced computational methods. These innovations have unlocked unprecedented opportunities for the acceleration of drug discovery and delivery, the optimization of treatment regimens, and the improvement of patient outcomes. AI is swiftly transforming the pharmaceutical industry, revolutionizing everything from drug development and discovery to personalized medicine, including target identification and validation, selection of excipients, prediction of the synthetic route, supply chain optimization, monitoring during continuous manufacturing processes, or predictive maintenance, among others. While the integration of AI promises to enhance efficiency, reduce costs, and improve both medicines and patient health, it also raises important questions from a regulatory point of view. In this review article, we will present a comprehensive overview of AI's applications in the pharmaceutical industry, covering areas such as drug discovery, target optimization, personalized medicine, drug safety, and more. By analyzing current research trends and case studies, we aim to shed light on AI's transformative impact on the pharmaceutical industry and its broader implications for healthcare.

Multi-Task ADME/PK prediction at industrial scale: leveraging large and diverse experimental datasets

ADME (Absorption, Distribution, Metabolism, Excretion) properties are key parameters to judge whether a drug candidate exhibits a desired pharmacokinetic (PK) profile. In this study, we tested multi-task machine learning (ML) models to predict ADME and animal PK endpoints trained on in-house data generated at Boehringer Ingelheim. Models were evaluated both at the design stage of a compound (i. e., no experimental data of test compounds available) and at testing stage when a particular assay would be conducted (i. e., experimental data of earlier conducted assays may be available). Using realistic time-splits, we found a clear benefit in performance of multi-task graph-based neural network models over single-task model, which was even stronger when experimental data of earlier assays is available. In an attempt to explain the success of multi-task models, we found that especially endpoints with the largest numbers of data points (physicochemical endpoints, clearance in microsomes) are responsible for increased predictivity in more complex ADME and PK endpoints. In summary, our study provides insight into how data for multiple ADME/PK endpoints in a pharmaceutical company can be best leveraged to optimize predictivity of ML models.

A comprehensive review of artificial intelligence for pharmacology research

With the innovation and advancement of artificial intelligence, more and more artificial intelligence techniques are employed in drug research, biomedical frontier research, and clinical medicine practice, especially, in the field of pharmacology research. Thus, this review focuses on the applications of artificial intelligence in drug discovery, compound pharmacokinetic prediction, and clinical pharmacology. We briefly introduced the basic knowledge and development of artificial intelligence, presented a comprehensive review, and then summarized the latest studies and discussed the strengths and limitations of artificial intelligence models. Additionally, we highlighted several important studies and pointed out possible research directions.

Understanding predictions of drug profiles using explainable machine learning models

PURPOSE

The analysis of absorption, distribution, metabolism, and excretion (ADME) molecular properties is of relevance to drug design, as they directly influence the drug's effectiveness at its target location. This study concerns their prediction, using explainable Machine Learning (ML) models. The aim of the study is to find which molecular features are relevant to the prediction of the different ADME properties and measure their impact on the predictive model.

METHODS

The relative relevance of individual features for ADME activity is gauged by estimating feature importance in ML models' predictions. Feature importance is calculated using feature permutation and the individual impact of features is measured by SHAP additive explanations.

RESULTS

The study reveals the relevance of specific molecular descriptors for each ADME property and quantifies their impact on the ADME property prediction.

CONCLUSION

The reported research illustrates how explainable ML models can provide detailed insights about the individual contributions of molecular features to the final prediction of an ADME property, as an effort to support experts in the process of drug candidate selection through a better understanding of the impact of molecular features.

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.

Estimation of linezolid exposure in patients with hepatic impairment using machine learning based on a population pharmacokinetic model

PURPOSE

To investigate the pharmacokinetic changes of linezolid in patients with hepatic impairment and to explore a method to predict linezolid exposure.

METHODS

Patients with hepatic impairment who received linezolid were recruited. A population pharmacokinetic model (PPK) was then built using NONMEM software. And based on the final model, virtual patients with rich concentration values was constructed through Monte Carlo simulations (MCS), which were used to build machine learning (ML) models to predict linezolid exposure levels. Finally, we investigated the risk factors for thrombocytopenia in patients included.

RESULTS

A PPK model with population typical values of 3.83 L/h and 34.1 L for clearance and volume of distribution was established, and the severe hepatic impairment was identified as a significant covariate of clearance. Then, we built a series of ML models to predict the area under 0 -24 h concentration-time curve (AUC0-24) of linezolid based on virtual patients from MCS. The results showed that the Xgboost models showed the best predictive performance and were superior to the methods for estimating linezolid AUC0-24 based on though concentration or daily dose. Finally, we found that baseline platelet count, linezolid AUC0-24, and combination with fluoroquinolones were independent risk factors for thrombocytopenia, and based on this, we proposed a method for calculating the toxicity threshold of linezolid.

CONCLUSION

In this study, we successfully constructed a PPK model for patients with hepatic impairment and used ML algorithm to estimate linezolid AUC0-24 based on limited data. Finally, we provided a method to determine the toxicity threshold of linezolid.

Computational insights into allosteric inhibition of focal adhesion kinase: A combined pharmacophore modeling and molecular dynamics approach

Focal adhesion kinase (FAK) is a non-receptor tyrosine kinase that modulates integrin and growth factor signaling pathways and is implicated in cancer cell migration, proliferation, and survival. Over the past decade various, FAK kinase, FERM, and FAT domain inhibitors have been reported and a few kinase domain inhibitors are under clinical consideration. However, few of them were identified as multikinase inhibitors. In kinase drug design selectivity is always a point of concern, to improve selectivity allosteric inhibitor development is the best choice. The current research utilized a pharmacophore modeling (PM) approach to identify novel allosteric inhibitors of FAK. The all-available allosteric inhibitor bound 3D structures with PDB ids 4EBV, 4EBW, and 4I4F were utilized for the pharmacophore modeling. The validated PM models were utilized to map a database of 770,550 compounds prepared from ZINC, EXIMED, SPECS, ASINEX, and InterBioScreen, aiming to identify potential allosteric inhibitors. The obtained compounds from screening step were forwarded to molecular docking (MD) for the prediction of binding orientation inside the allosteric site and the results were evaluated with the known FAK allosteric inhibitor (REF). Finally, 14 FAK-inhibitor complexes were selected from the docking study and were studied under molecular dynamics simulations (MDS) for 500 ns. The complexes were ranked according to binding free energy (BFE) and those demonstrated higher affinity for allosteric site of FAK than REF inhibitors were selected. The selected complexes were further analyzed for intermolecular interactions and finally, three potential allosteric inhibitor candidates for the inhibition of FAK protein were identified. We believe that identified scaffolds may help in drug development against FAK as an anticancer agent.

Advancing Drug Safety in Drug Development: Bridging Computational Predictions for Enhanced Toxicity Prediction

The attrition rate of drugs in clinical trials is generally quite high, with estimates suggesting that approximately 90% of drugs fail to make it through the process. The identification of unexpected toxicity issues during preclinical stages is a significant factor contributing to this high rate of failure. These issues can have a major impact on the success of a drug and must be carefully considered throughout the development process. These late-stage rejections or withdrawals of drug candidates significantly increase the costs associated with drug development, particularly when toxicity is detected during clinical trials or after market release. Understanding drug-biological target interactions is essential for evaluating compound toxicity and safety, as well as predicting therapeutic effects and potential off-target effects that could lead to toxicity. This will enable scientists to predict and assess the safety profiles of drug candidates more accurately. Evaluation of toxicity and safety is a critical aspect of drug development, and biomolecules, particularly proteins, play vital roles in complex biological networks and often serve as targets for various chemicals. Therefore, a better understanding of these interactions is crucial for the advancement of drug development. The development of computational methods for evaluating protein-ligand interactions and predicting toxicity is emerging as a promising approach that adheres to the 3Rs principles (replace, reduce, and refine) and has garnered significant attention in recent years. In this review, we present a thorough examination of the latest breakthroughs in drug toxicity prediction, highlighting the significance of drug-target binding affinity in anticipating and mitigating possible adverse effects. In doing so, we aim to contribute to the development of more effective and secure drugs.

Solubilization of drugs using beta-cyclodextrin: Experimental data and modeling

Many drug candidates fail to complete the entire drug development process because of poor physicochemical properties. Solubility is an important physicochemical property which plays a vital role in various stages of drug discovery and development. Several methods have been proposed to enhance the solubility of drugs, and complex formation with cyclodextrins is among them. Beta-cyclodextrin (βCD) is a common excipient for solubilization of drugs. The aim of this study is to develop the mechanistic QSPR models to predict the solubility enhancement of a drug in the presence of βCD. In this study, the solubility enhancement of some drugs in the presence of 10mM βCD at 25°C was experimentally determined or collected from the literature. Two different models to predict the solubilization by βCD were developed by binary logistic regression using structural properties of drugs with more than 80% accuracy. Polar surface area and excess molar refraction are the main parameters for estimating solubilization by βCD. Moreover, other descriptors related to hydrophobicity and the capability of hydrogen bonding formation of molecules could improve the accuracy of the established models.

Image-based molecular representation learning for drug development: a survey

Artificial intelligence (AI) powered drug development has received remarkable attention in recent years. It addresses the limitations of traditional experimental methods that are costly and time-consuming. While there have been many surveys attempting to summarize related research, they only focus on general AI or specific aspects such as natural language processing and graph neural network. Considering the rapid advance on computer vision, using the molecular image to enable AI appears to be a more intuitive and effective approach since each chemical substance has a unique visual representation. In this paper, we provide the first survey on image-based molecular representation for drug development. The survey proposes a taxonomy based on the learning paradigms in computer vision and reviews a large number of corresponding papers, highlighting the contributions of molecular visual representation in drug development. Besides, we discuss the applications, limitations and future directions in the field. We hope this survey could offer valuable insight into the use of image-based molecular representation learning in the context of drug development.

Predicting Pharmacokinetics of Drugs Using Artificial Intelligence Tools: A Systematic Review

BACKGROUND AND OBJECTIVE

Pharmacokinetic studies encompass the examination of the absorption, distribution, metabolism, and excretion of bioactive compounds. The pharmacokinetics of drugs exert a substantial influence on their efficacy and safety. Consequently, the investigation of pharmacokinetics holds great importance. However, laboratory-based assessment necessitates the use of numerous animals, various materials, and significant time. To mitigate these challenges, alternative methods such as artificial intelligence have emerged as a promising approach. This systematic review aims to review existing studies, focusing on the application of artificial intelligence tools in predicting the pharmacokinetics of drugs.

METHODS

A pre-prepared search strategy based on related keywords was used to search different databases (PubMed, Scopus, Web of Science). The process involved combining articles, eliminating duplicates, and screening articles based on their titles, abstracts, and full text. Articles were selected based on inclusion and exclusion criteria. Then, the quality of the included articles was assessed using an appraisal tool.

RESULTS

Ultimately, 23 relevant articles were included in this study. The clearance parameter received the highest level of investigation, followed by the  area under the concentration-time curve (AUC) parameter, in pharmacokinetic studies. Among the various models employed in the articles, Random Forest and eXtreme Gradient Boosting (XGBoost) emerged as the most commonly utilized ones. Generalized Linear Models and Elastic Nets (GLMnet) and Random Forest models showed the most performance in predicting clearance.

CONCLUSION

Overall, artificial intelligence tools offer a robust, rapid, and precise means of predicting various pharmacokinetic parameters based on a dataset containing information of patients or drugs.

Transfer learning empowers accurate pharmacokinetics prediction of small samples

Accurate assessment of pharmacokinetic (PK) properties is crucial for selecting optimal candidates and avoiding downstream failures. Transfer learning is an innovative machine learning approach enabling high-throughput prediction with limited data. Recently, transfer learning methods showed promise in predicting ADME/PK parameters. Given the prolific growth of research on transfer learning for PK prediction, a comprehensive review of its advantages and challenges is imperative. This study explores the fundamentals, classifications, toolkits and applications of various transfer learning techniques for PK prediction, demonstrating their utility through three practical case studies. This work will serve as a reference for drug design researchers.

Difficulty in chirality recognition for Transformer architectures learning chemical structures from string representations

Recent years have seen rapid development of descriptor generation based on representation learning of extremely diverse molecules, especially those that apply natural language processing (NLP) models to SMILES, a literal representation of molecular structure. However, little research has been done on how these models understand chemical structure. To address this black box, we investigated the relationship between the learning progress of SMILES and chemical structure using a representative NLP model, the Transformer. We show that while the Transformer learns partial structures of molecules quickly, it requires extended training to understand overall structures. Consistently, the accuracy of molecular property predictions using descriptors generated from models at different learning steps was similar from the beginning to the end of training. Furthermore, we found that the Transformer requires particularly long training to learn chirality and sometimes stagnates with low performance due to misunderstanding of enantiomers. These findings are expected to deepen the understanding of NLP models in chemistry.

Modeling of small molecule's affinity to phospholipids using IAM-HPLC and QSRR approach enhanced by similarity-based machine algorithms

Immobilized artificial membrane chromatography (IAM) has been proposed as a more biosimilar alternative to classical lipophilicity measurement. Determination of small molecule's affinity to phospholipids can be supported for predicting their behavior in the human body. Therefore, a better understanding of the molecular interaction mechanism between small xenobiotics and phospholipids can accelerate drug discovery. Here, the quantitative structure-retention relationships (QSRR) approach was integrated with mechanistic descriptors calculated using Chemicalize software to propose an easy-to-interpretation QSRR model. Considering the heterogeneous character of the data set, locally weighted least squares kernel regression belonging to similarity-based machine learning methods have been applied. The results showed that lipophilicity, charge, and maximum projection area determine molecule binding to phospholipids. Full validation of the obtained model based on OECD recommendations has been performed and the applicability domain was defined using the probability-oriented distance-based approach. The high values of predictive squared correlation coefficient (Q2), and small root mean square error of prediction (RMSEP), 0.812 and 6.739, respectively, confirmed that the obtained QSRR model is not well-fitted to the training data but also showed prediction power. Additionally, only 1.5% of molecules from the training set and 2.8% from the validation test are outside the applicability domain, confirming great predictive abilities.

Recent Studies of Artificial Intelligence on In Silico Drug Absorption

Absorption is an important area of research in pharmacochemistry and drug development, because the drug has to be absorbed before any drug effects can occur. Furthermore, the ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) profile of drugs can be directly and considerably altered by modulating factors affecting absorption. Many drugs in development fail because of poor absorption. The research and continuous efforts of researchers in recent years have brought many successes and promises in drug absorption property prediction, especially in silico, which helps to reduce the time and cost significantly for screening undesirable drug candidates. In this report, we explicitly provide an overview of recent in silico studies on predicting absorption properties, especially from 2019 to the present, using artificial intelligence. Additionally, we have collected and investigated public databases that support absorption prediction research. On those grounds, we also proposed the challenges and development directions of absorption prediction in the future. We hope this review can provide researchers with valuable guidelines on absorption prediction to facilitate the development of newer approaches in drug discovery.

Adapting physiologically-based pharmacokinetic models for machine learning applications

Both machine learning and physiologically-based pharmacokinetic models are becoming essential components of the drug development process. Integrating the predictive capabilities of physiologically-based pharmacokinetic (PBPK) models within machine learning (ML) pipelines could offer significant benefits in improving the accuracy and scope of drug screening and evaluation procedures. Here, we describe the development and testing of a self-contained machine learning module capable of faithfully recapitulating summary pharmacokinetic (PK) parameters produced by a full PBPK model, given a set of input drug-specific and regimen-specific information. Because of its widespread use in characterizing the disposition of orally administered drugs, the PBPK model chosen to demonstrate the methodology was an open-source implementation of a state-of-the-art compartmental and transit model called OpenCAT. The model was tested for drug formulations spanning a large range of solubility and absorption characteristics, and was evaluated for concordance against predictions of OpenCAT and relevant experimental data. In general, the values predicted by the ML models were within 20% of those of the PBPK model across the range of drug and formulation properties. However, summary PK parameter predictions from both the ML model and full PBPK model were occasionally poor with respect to those derived from experiments, suggesting deficiencies in the underlying PBPK model.

Molecular Representations in Machine-Learning-Based Prediction of PK Parameters for Insulin Analogs

Therapeutic peptides and proteins derived from either endogenous hormones, such as insulin, or de novo design via display technologies occupy a distinct pharmaceutical space in between small molecules and large proteins such as antibodies. Optimizing the pharmacokinetic (PK) profile of drug candidates is of high importance when it comes to prioritizing lead candidates, and machine-learning models can provide a relevant tool to accelerate the drug design process. Predicting PK parameters of proteins remains difficult due to the complex factors that influence PK properties; furthermore, the data sets are small compared to the variety of compounds in the protein space. This study describes a novel combination of molecular descriptors for proteins such as insulin analogs, where many contained chemical modifications, e.g., attached small molecules for protraction of the half-life. The underlying data set consisted of 640 structural diverse insulin analogs, of which around half had attached small molecules. Other analogs were conjugated to peptides, amino acid extensions, or fragment crystallizable regions. The PK parameters clearance (CL), half-life (T1/2), and mean residence time (MRT) could be predicted by using classical machine-learning models such as Random Forest (RF) and Artificial Neural Networks (ANN) with root-mean-square errors of CL of 0.60 and 0.68 (log units) and average fold errors of 2.5 and 2.9 for RF and ANN, respectively. Both random and temporal data splittings were employed to evaluate ideal and prospective model performance with the best models, regardless of data splitting, achieving a minimum of 70% of predictions within a twofold error. The tested molecular representations include (1) global physiochemical descriptors combined with descriptors encoding the amino acid composition of the insulin analogs, (2) physiochemical descriptors of the attached small molecule, (3) protein language model (evolutionary scale modeling) embedding of the amino acid sequence of the molecules, and (4) a natural language processing inspired embedding (mol2vec) of the attached small molecule. Encoding the attached small molecule via (2) or (4) significantly improved the predictions, while the benefit of using the protein language model-based encoding (3) depended on the used machine-learning model. The most important molecular descriptors were identified as descriptors related to the molecular size of both the protein and protraction part using Shapley additive explanations values. Overall, the results show that combining representations of proteins and small molecules was key for PK predictions of insulin analogs.

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.

Recent Studies of Artificial Intelligence on In Silico Drug Distribution Prediction

Drug distribution is an important process in pharmacokinetics because it has the potential to influence both the amount of medicine reaching the active sites and the effectiveness as well as safety of the drug. The main causes of 90% of drug failures in clinical development are lack of efficacy and uncontrolled toxicity. In recent years, several advances and promising developments in drug distribution property prediction have been achieved, especially in silico, which helped to drastically reduce the time and expense of screening undesired drug candidates. In this study, we provide comprehensive knowledge of drug distribution background, influencing factors, and artificial intelligence-based distribution property prediction models from 2019 to the present. Additionally, we gathered and analyzed public databases and datasets commonly utilized by the scientific community for distribution prediction. The distribution property prediction performance of five large ADMET prediction tools is mentioned as a benchmark for future research. On this basis, we also offer future challenges in drug distribution prediction and research directions. We hope that this review will provide researchers with helpful insight into distribution prediction, thus facilitating the development of innovative approaches for drug discovery.

Utilizing public and private sector data to build better machine learning models for the prediction of pharmacokinetic parameters

One solution to compensate for the shortage of publicly available data is to collect more quality-controlled data from the private sector through public-private partnerships. However, several issues must be resolved before implementing such a system. Here, we review the technical aspects of public-private partnerships using our initiative in Japan as an example. In particular, we focus on the procedure for collecting data from multiple private sector companies and building prediction models and discuss how merging public and private sector datasets will help to improve the chemical space coverage and prediction performance. Teaser: Japan's first public-private consortium in pharmacokinetics has incorporated data from multiple pharmaceutical companies to create useful predictive models.

Multi-compound and drug-combination pharmacokinetic research on Chinese herbal medicines

Traditional medicine has provided a basis for health care and disease treatment to Chinese people for millennia, and herbal medicines are regulated as drug products in China. Chinese herbal medicines have two features. They normally possess very complex chemical composition. This makes the identification of the constituents that are together responsible for the therapeutic action of an herbal medicine challenging, because how to select compounds from an herbal medicine for pharmacodynamic study has been a big hurdle in such identification efforts. To this end, a multi-compound pharmacokinetic approach was established to identify potentially important compounds (bioavailable at the action loci with significant exposure levels after dosing an herbal medicine) and to characterize their pharmacokinetics and disposition. Another feature of Chinese herbal medicines is their typical use as or in combination therapies. Coadministration of complex natural products and conventional synthetic drugs is prevalent worldwide, even though it remains very controversial. Natural product–drug interactions have raised wide concerns about reduced drug efficacy or safety. However, growing evidence shows that incorporating Chinese herbal medicines into synthetic drug-based therapies delivers benefits in the treatment of many multifactorial diseases. To address this issue, a drug-combination pharmacokinetic approach was established to assess drug–drug interaction potential of herbal medicines and degree of pharmacokinetic compatibility for multi-herb combination and herbal medicine–synthetic drug combination therapies. In this review we describe the methodology, techniques, requirements, and applications of multi-compound and drug-combination pharmacokinetic research on Chinese herbal medicines and to discuss further development for these two types of pharmacokinetic research.

Comparison of Descriptor- and Fingerprint Sets in Machine Learning Models for ADME-Tox Targets

The screening of compounds for ADME-Tox targets plays an important role in drug design. QSPR models can increase the speed of these specific tasks, although the performance of the models highly depends on several factors, such as the applied molecular descriptors. In this study, a detailed comparison of the most popular descriptor groups has been carried out for six main ADME-Tox classification targets: Ames mutagenicity, P-glycoprotein inhibition, hERG inhibition, hepatotoxicity, blood–brain-barrier permeability, and cytochrome P450 2C9 inhibition. The literature-based, medium-sized binary classification datasets (all above 1,000 molecules) were used for the model building by two common algorithms, XGBoost and the RPropMLP neural network. Five molecular representation sets were compared along with their joint applications: Morgan, Atompairs, and MACCS fingerprints, and the traditional 1D and 2D molecular descriptors, as well as 3D molecular descriptors, separately. The statistical evaluation of the model performances was based on 18 different performance parameters. Although all the developed models were close to the usual performance of QSPR models for each specific ADME-Tox target, the results clearly showed the superiority of the traditional 1D, 2D, and 3D descriptors in the case of the XGBoost algorithm. It is worth trying the classical tools in single model building because the use of 2D descriptors can produce even better models for almost every dataset than the combination of all the examined descriptor sets.