Machine Learning Models for Human In Vivo Pharmacokinetic Parameters with In-House Validation

Clinical trials in-a-dish for cardiovascular medicine

Cardiovascular diseases persist as a global health challenge that requires methodological innovation for effective drug development. Conventional pipelines relying on animal models suffer from high failure rates due to significant interspecies variation between humans and animal models. In response, the recently enacted Food and Drug Administration Modernization Act 2.0 encourages alternative approaches including induced pluripotent stem cells (iPSCs). Human iPSCs provide a patient-specific, precise, and screenable platform for drug testing, paving the way for cardiovascular precision medicine. This review discusses milestones in iPSC differentiation and their applications from disease modelling to drug discovery in cardiovascular medicine. It then explores challenges and emerging opportunities for the implementation of 'clinical trials in-a-dish'. Concluding, this review proposes a framework for future clinical trial design with strategic incorporations of iPSC technology, microphysiological systems, clinical pan-omics, and artificial intelligence to improve success rates and advance cardiovascular healthcare.

Can Machine Learning Overcome the 95% Failure Rate and Reality that Only 30% of Approved Cancer Drugs Meaningfully Extend Patient Survival?

Despite implementing hundreds of strategies, cancer drug development suffers from a 95% failure rate over 30 years, with only 30% of approved cancer drugs extending patient survival beyond 2.5 months. Adding more criteria without eliminating nonessential ones is impractical and may fall into the "survivorship bias" trap. Machine learning (ML) models may enhance efficiency by saving time and cost. Yet, they may not improve success rate without identifying the root causes of failure. We propose a "STAR-guided ML system" (structure-tissue/cell selectivity-activity relationship) to enhance success rate and efficiency by addressing three overlooked interdependent factors: potency/specificity to the on/off-targets determining efficacy in tumors at clinical doses, on/off-target-driven tissue/cell selectivity influencing adverse effects in the normal organs at clinical doses, and optimal clinical doses balancing efficacy/safety as determined by potency/specificity and tissue/cell selectivity. STAR-guided ML models can directly predict clinical dose/efficacy/safety from five features to design/select the best drugs, enhancing success and efficiency of cancer drug development.

Actionable Predictions of Human Pharmacokinetics at the Drug Design Stage

We present a novel computational approach for predicting human pharmacokinetics (PK) that addresses the challenges of early stage drug design. Our study introduces and describes a large-scale data set of 11 clinical PK end points, encompassing over 2700 unique chemical structures to train machine learning models. To that end multiple advanced training strategies are compared, including the integration of in vitro data and a novel self-supervised pretraining task. In addition to the predictions, our final model provides meaningful epistemic uncertainties for every data point. This allows us to successfully identify regions of exceptional predictive performance, with an absolute average fold error (AAFE/geometric mean fold error) of less than 2.5 across multiple end points. Together, these advancements represent a significant leap toward actionable PK predictions, which can be utilized early on in the drug design process to expedite development and reduce reliance on nonclinical studies.

Ulgen K. Advances in Physiologically Based Pharmacokinetic (PBPK) Modeling of Nanomaterials

Nanoparticles (NPs) have been widely used to improve the pharmacokinetic properties and tissue distribution of small molecules such as targeting to a specific tissue of interest, enhancing their systemic circulation, and enlarging their therapeutic properties. NPs have unique and complicated in vivo disposition properties compared to small molecule drugs due to their complex multifunctionality. Physiologically based pharmacokinetic (PBPK) modeling has been a powerful tool in the simulation of the absorption, distribution, metabolism, and elimination (ADME) characteristics of the materials, and it can be used in the characterization and prediction of the systemic disposition, toxicity, efficacy, and target exposure of various types of nanoparticles. In this review, recent advances in PBPK model applications related to the nanoparticles with unique properties, and dispositional features in the biological systems, ADME characteristics, the description of transport processes of nanoparticles in the PBPK model, and the challenges in PBPK model development of nanoparticles are delineated and juxtaposed with those encountered in small molecule models. Nanoparticle related, non-nanoparticle-related, and interspecies-scaling methods applied in PBPK modeling are reviewed. In vitro to in vivo extrapolation (IVIVE) methods being a promising computational tool to provide in vivo predictions from the results of in vitro and in silico studies are discussed. Finally, as a recent advancement ML/AI-based approaches and challenges in PBPK modeling in the estimation of ADME parameters and pharmacokinetic (PK) analysis results are introduced.

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.

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

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 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.

Machine Learning Approach in Dosage Individualization of Isoniazid for Tuberculosis

INTRODUCTION

Isoniazid is a first-line antituberculosis agent with high variability, which would profit from individualized dosing. Concentrations of isoniazid at 2 h (C2h), as an indicator of safety and efficacy, are important for optimizing therapy.

OBJECTIVE

The objective of this study was to establish machine learning (ML) models to predict the C2h, that can be used for establishing an individualized dosing regimen in clinical practice.

METHODS

Published population pharmacokinetic (PopPK) models for adults were searched based on PubMed and ultimately four reliable models were selected for simulating individual C2h datasets under different conditions (demographics, genotype, ethnicity, etc.). Machine learning models were trained on simulated C2h obtained from the four PopPK models. Five different algorithms were used for ML model building to predict C2h. Real-world data were used for predictive performance evaluations. Virtual trials were used to compare ML-optimized doses with PopPK model-optimized doses.

RESULTS

Categorical boosting (CatBoost) exhibited the highest prediction ability. Target C2h can be predicted using the ML model combined with the dosing regimen and three covariates (N-acetyltransferase 2 [NAT2] genotypes, weight and race [Asians and Africans]). Real-world data validation results showed that the ML model can achieve an overall prediction accuracy of 93.4%. Using the final ML model, the mean absolute prediction error value decreased by 45.7% relative to the average of PopPK models. Using the ML-optimized dosing regimen, the probability of target attainment increased by 43.7% relative to the PopPK model-optimized dosing regimens.

CONCLUSION

Machine learning models were developed with great predictive performance, which can be used to determine the individualized initial dose of isoniazid in adult patients.

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.

Deus Ex Machina? The Rise of Artificial Intelligence in Toxicology

Artificial intelligence (AI) is rising rapidly, driven by big data, complex algorithms, and computing resources. Current research presented at the American Chemical Society Fall 2023 Meeting demonstrates AI to be a valuable predictive and supporting tool across all facets of toxicology.

Artificial Intelligence for Quantitative Modeling in Drug Discovery and Development: An Innovation and Quality Consortium Perspective on Use Cases and Best Practices

Recent breakthroughs in artificial intelligence (AI) and machine learning (ML) have ushered in a new era of possibilities across various scientific domains. One area where these advancements hold significant promise is model-informed drug discovery and development (MID3). To foster a wider adoption and acceptance of these advanced algorithms, the Innovation and Quality (IQ) Consortium initiated the AI/ML working group in 2021 with the aim of promoting their acceptance among the broader scientific community as well as by regulatory agencies. By drawing insights from workshops organized by the working group and attended by key stakeholders across the biopharma industry, academia, and regulatory agencies, this white paper provides a perspective from the IQ Consortium. The range of applications covered in this white paper encompass the following thematic topics: (i) AI/ML-enabled Analytics for Pharmacometrics and Quantitative Systems Pharmacology (QSP) Workflows; (ii) Explainable Artificial Intelligence and its Applications in Disease Progression Modeling; (iii) Natural Language Processing (NLP) in Quantitative Pharmacology Modeling; and (iv) AI/ML Utilization in Drug Discovery. Additionally, the paper offers a set of best practices to ensure an effective and responsible use of AI, including considering the context of use, explainability and generalizability of models, and having human-in-the-loop. We believe that embracing the transformative power of AI in quantitative modeling while adopting a set of good practices can unlock new opportunities for innovation, increase efficiency, and ultimately bring benefits to patients.

Prediction of Human Clearance Using In Silico Models with Reduced Bias

Predicting human clearance with high accuracy from in silico-derived parameters alone is highly desirable, as it is fast, saves in vitro resources, and is animal-sparing. We derived random forest (RF) models from 1340 compounds with human intravenous pharmacokinetic (PK) data, the largest data set publicly available today. To assess the general applicability of the RF models, we systematically removed structural-therapeutic class analogues and other compounds with structural similarity from the training sets. For a quasi-prospective test set of 343 compounds, we show that RF models devoid of structurally similar compounds in the training set predict human clearance with a geometric mean fold error (GMFE) of 3.3. While the observed GMFE illustrates how difficult it is to generate a useful model that is broadly applicable, we posit that our RF models yield a more realistic assessment of how well human clearance can be predicted prospectively. We deployed the conformal prediction formalism to assess the model applicability and to determine the prediction confidence intervals for each prediction. We observed that clearance can be predicted better for renally cleared compounds than for other clearance mechanisms. We show that applying a classification model for predicting renal clearance identifies a subset of compounds for which clearance can be predicted with higher accuracy, yielding a GMFE of 2.3. In addition, our in silico RF human clearance models compared well to models derived from scaling human hepatocytes or preclinical in vivo data.

Artificial Intelligence-Powered Electronic Skin

Skin-interfaced electronics is gradually changing medical practices by enabling continuous and noninvasive tracking of physiological and biochemical information. With the rise of big data and digital medicine, next-generation electronic skin (e-skin) will be able to use artificial intelligence (AI) to optimize its design as well as uncover user-personalized health profiles. Recent multimodal e-skin platforms have already employed machine learning (ML) algorithms for autonomous data analytics. Unfortunately, there is a lack of appropriate AI protocols and guidelines for e-skin devices, resulting in overly complex models and non-reproducible conclusions for simple applications. This review aims to present AI technologies in e-skin hardware and assess their potential for new inspired integrated platform solutions. We outline recent breakthroughs in AI strategies and their applications in engineering e-skins as well as understanding health information collected by e-skins, highlighting the transformative deployment of AI in robotics, prosthetics, virtual reality, and personalized healthcare. We also discuss the challenges and prospects of AI-powered e-skins as well as predictions for the future trajectory of smart e-skins.

The Trends and Future Prospective of In Silico Models from the Viewpoint of ADME Evaluation in Drug Discovery

Drug discovery and development are aimed at identifying new chemical molecular entities (NCEs) with desirable pharmacokinetic profiles for high therapeutic efficacy. The plasma concentrations of NCEs are a biomarker of their efficacy and are governed by pharmacokinetic processes such as absorption, distribution, metabolism, and excretion (ADME). Poor ADME properties of NCEs are a major cause of attrition in drug development. ADME screening is used to identify and optimize lead compounds in the drug discovery process. Computational models predicting ADME properties have been developed with evolving model-building technologies from a simplified relationship between ADME endpoints and physicochemical properties to machine learning, including support vector machines, random forests, and convolution neural networks. Recently, in the field of in silico ADME research, there has been a shift toward evaluating the in vivo parameters or plasma concentrations of NCEs instead of using predictive results to guide chemical structure design. Another research hotspot is the establishment of a computational prediction platform to strengthen academic drug discovery. Bioinformatics projects have produced a series of in silico ADME models using free software and open-access databases. In this review, we introduce prediction models for various ADME parameters and discuss the currently available academic drug discovery platforms.

Physiological Dynamics in the Upper Gastrointestinal Tract and the Development of Gastrointestinal Absorption Models for the Immediate-Release Oral Dosage Forms in Healthy Adult Human

This review is a revisit of various oral drug absorption models developed in the past decades, focusing on how to incorporate the physiological dynamics in the upper gastrointestinal (GI) tract. For immediate-release oral drugs, GI absorption is a critical input of drug exposure and subsequent human body response, yet difficult to model largely due to the complex GI environment. One of the biggest hurdles lies at capturing the high within-subject variability (WSV) of bioavailability measures, which can be mechanistically explained by the GI physiological dynamics. A thorough summary of how GI dynamics is handled in the absorption models would promote the development of mechanism-based oral drug absorption models, aid in the design of clinical studies regarding dosing regimens and bioequivalence studies based on WSV, and advance the decision-making on formulation selection.

A Machine Learning Framework to Improve Rat Clearance Predictions and Inform Physiologically Based Pharmacokinetic Modeling

During drug discovery and development, achieving appropriate pharmacokinetics is key to establishment of the efficacy and safety of new drugs. Physiologically based pharmacokinetic (PBPK) models integrating in vitro-to-in vivo extrapolation have become an essential in silico tool to achieve this goal. In this context, the most important and probably most challenging pharmacokinetic parameter to estimate is the clearance. Recent work on high-throughput PBPK modeling during drug discovery has shown that a good estimate of the unbound intrinsic clearance (CLint,u,) is the key factor for useful PBPK application. In this work, three different machine learning-based strategies were explored to predict the rat CLint,u as the input into PBPK. Therefore, in vivo and in vitro data was collected for a total of 2639 proprietary compounds. The strategies were compared to the standard in vitro bottom-up approach. Using the well-stirred liver model to back-calculate in vivo CLint,u from in vivo rat clearance and then training a machine learning model on this CLint,u led to more accurate clearance predictions (absolute average fold error (AAFE) 3.1 in temporal cross-validation) than the bottom-up approach (AAFE 3.6-16, depending on the scaling method) and has the advantage that no experimental in vitro data is needed. However, building a machine learning model on the bias between the back-calculated in vivo CLint,u and the bottom-up scaled in vitro CLint,u also performed well. For example, using unbound hepatocyte scaling, adding the bias prediction improved the AAFE in the temporal cross-validation from 16 for bottom-up to 2.9 together with the bias prediction. Similarly, the log Pearson r2 improved from 0.1 to 0.29. Although it would still require in vitro measurement of CLint,u., using unbound scaling for the bottom-up approach, the need for correction of the fu,inc by fu,p data is circumvented. While the above-described ML models were built on all data points available per approach, it is discussed that evaluation comparison across all approaches could only be performed on a subset because ca. 75% of the molecules had missing or unquantifiable measurements of the fraction unbound in plasma or in vitro unbound intrinsic clearance, or they dropped out due to the blood-flow limitation assumed by the well-stirred model. Advantageously, by predicting CLint,u as the input into PBPK, existing workflows can be reused and the prediction of the in vivo clearance and other PK parameters can be improved.

Can machine learning 'transform' peptides/peptidomimetics into small molecules? A case study with ghrelin receptor ligands

There has been considerable interest in transforming peptides into small molecules as peptide-based molecules often present poorer bioavailability and lower metabolic stability. Our studies looked into building machine learning (ML) models to investigate if ML is able to identify the 'bioactive' features of peptides and use the features to accurately discriminate between binding and non-binding small molecules. The ghrelin receptor (GR), a receptor that is implicated in various diseases, was used as an example to demonstrate whether ML models derived from a peptide library can be used to predict small molecule binders. ML models based on three different algorithms, namely random forest, support vector machine, and extreme gradient boosting, were built based on a carefully curated dataset of peptide/peptidomimetic and small molecule GR ligands. The results indicated that ML models trained with a dataset exclusively composed of peptides/peptidomimetics provide limited predictive power for small molecules, but that ML models trained with a diverse dataset composed of an array of both peptides/peptidomimetics and small molecules displayed exceptional results in terms of accuracy and false rates. The diversified models can accurately differentiate the binding small molecules from non-binding small molecules using an external validation set with new small molecules that we synthesized previously. Structural features that are the most critical contributors to binding activity were extracted and are remarkably consistent with the crystallography and mutagenesis studies.

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.

An artificial intelligence-assisted physiologically-based pharmacokinetic model to predict nanoparticle delivery to tumors in mice

The critical barrier for clinical translation of cancer nanomedicine stems from the inefficient delivery of nanoparticles (NPs) to target solid tumors. Rapid growth of computational power, new machine learning and artificial intelligence (AI) approaches provide new tools to address this challenge. In this study, we established an AI-assisted physiologically based pharmacokinetic (PBPK) model by integrating an AI-based quantitative structure-activity relationship (QSAR) model with a PBPK model to simulate tumor-targeted delivery efficiency (DE) and biodistribution of various NPs. The AI-based QSAR model was developed using machine learning and deep neural network algorithms that were trained with datasets from a published "Nano-Tumor Database" to predict critical input parameters of the PBPK model. The PBPK model with optimized NP cellular uptake kinetic parameters was used to predict the maximum delivery efficiency (DEmax) and DE at 24 (DE24) and 168 h (DE168) of different NPs in the tumor after intravenous injection and achieved a determination coefficient of R2 = 0.83 [root mean squared error (RMSE) = 3.01] for DE24, R2 = 0.56 (RMSE = 2.27) for DE168, and R2 = 0.82 (RMSE = 3.51) for DEmax. The AI-PBPK model predictions correlated well with available experimentally-measured pharmacokinetic profiles of different NPs in tumors after intravenous injection (R2 ≥ 0.70 for 133 out of 288 datasets). This AI-based PBPK model provides an efficient screening tool to rapidly predict delivery efficiency of a NP based on its physicochemical properties without relying on an animal training dataset.

Global parameter optimisation and sensitivity analysis of antivenom pharmacokinetics and pharmacodynamics

In recent years it has become possible to design snakebite antivenoms with diverse pharmacokinetic properties. Owing to the pharmacokinetic variability of venoms, the choice of antivenom scaffold may influence a treatment's neutralisation coverage. Computation offers a useful medium through which to assess the pharmacokinetics and pharmacodynamics of envenomation-treatment systems, as antivenoms with identical neutralising capacities can be simulated. In this study, we simulate envenomation and treatment with a variety of antivenoms, to define the properties of effective antivenoms. Systemic envenomation and treatment were described using a two-compartment pharmacokinetic model. Treatment of Naja sumatrana and Cryptelytrops purpureomaculatus envenomation was simulated with a set of 200,000 theoretical antivenoms across 10 treatment time delays. These two venoms are well-characterised and have differing pharmacokinetic properties. The theoretical antivenom set varied across molecular weight, dose, kon, koff, and valency. The best and worst treatments were identified using an area under the curve metric, and a global sensitivity analysis was performed to quantify the influence of the input parameters on treatment outcome. The simulations show that scaffolds of diverse molecular formats can be effective. Molecular weight and valency have a negligible direct impact on treatment outcome, however low molecular weight scaffolds offer more flexibility across the other design parameters, particularly when treatment is delayed. The simulations show kon to primarily mediate treatment efficacy, with rates above 105 M-1s-1 required for the most effective treatments. koff has the greatest impact on the performance of less effective scaffolds. While the same scaffold preferences for improved treatment are seen for both model snakes, the parameter bounds for C. purpureomaculatus envenomation are more constrained. This paper establishes a computational framework for the optimisation of antivenom design.

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.

Explaining Blood-Brain Barrier Permeability of Small Molecules by Integrated Analysis of Different Transport Mechanisms

The blood-brain barrier (BBB) represents a major obstacle to delivering drugs to the central nervous system (CNS), resulting in the lack of effective treatment for many CNS diseases including brain cancer. To accelerate CNS drug development, computational prediction models could save the time and effort needed for experimental evaluation. Here, we studied BBB permeability focusing on active transport (influx and efflux) as well as passive diffusion using previously published and self-curated data sets. We created prediction models based on physicochemical properties, molecular substructures, or their combination to understand which mechanisms contribute to BBB permeability. Our results show that features that predicted passive diffusion over membranes overlap with features that explain endothelial permeation of approved CNS-active drugs. We also identified physical properties and molecular substructures that positively or negatively predicted BBB transport. These findings provide guidance toward identifying BBB-permeable compounds by optimally matching physicochemical and molecular properties to BBB transport mechanisms.

Prediction of Compound Plasma Concentration-Time Profiles in Mice Using Random Forest

Pharmacokinetic (PK) parameters such as clearance (CL) and volume of distribution (Vd) have been the subject of previous in silico predictive models. However, having information of the concentration over time profile explicitly can provide additional value like time above MIC or AUC, etc., to understand both the efficacy and safety-related aspects of a compound. In this work, we developed machine learning models for plasma concentration-time profiles after both i.v. and p.o. dosing for a series of 17 in-house projects. For explanatory variables, MACCS Keys chemical descriptors as well as in silico and experimental in vitro PK parameters were used. The predictive accuracy of random forest (RF), message passing neural network, 2-compartment models using estimated CL and Vdss, and an average model (as a control experiment) was investigated using 5-fold cross-validation (5-fold CV) and leave-one-project-out validation (LOPO-V). The predictive accuracy of RF in 5-fold CV for i.v. and p.o. plasma concentration-time profiles was the best among the models studied, with an RMSE for i.v. dosing at 0.08, 1, and 8 h of 0.245, 0.474, and 0.462, respectively, and an RMSE for p.o. dosing at 0.25, 1, and 8 h of 0.500, 0.612, and 0.509, respectively. Furthermore, by investigating the importance of the in vitro PK parameters using the Gini index, we observed that the general prior knowledge in ADME research was reflected well in the respective feature importance of in vitro parameters such as predicted human Vd (hVd) for the initial distribution, mouse intrinsic CL and unbound fraction of mouse plasma for the elimination process, and Caco2 permeability for the absorption process. Also, this model is the first model that can predict twin peaks in the concentration-time profile much better than a baseline compartment model. Because of its combination of sufficient accuracy and speed of prediction, we found the model to be fit-for-purpose for practical lead optimization.

Using Transcriptomics and Cell Morphology Data in Drug Discovery: The Long Road to Practice

Gene expression and cell morphology data are high-dimensional biological readouts of much recent interest for drug discovery. They are able to describe biological systems in different states (e.g., healthy and diseased), as well as biological systems before and after compound treatment, and they are hence useful for matching both spaces (e.g., for drug repurposing) as well as for characterizing compounds with respect to efficacy and safety endpoints. This Microperspective describes recent advances in this direction with a focus on applied drug discovery and drug repurposing, as well as outlining what else is needed to advance further, with a particular focus on better understanding the applicability domain of readouts and their relevance for decision making, which is currently often still unclear.

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.

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.

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.

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.

Evaluating the performance of machine-learning regression models for pharmacokinetic drug-drug interactions

Combination therapy or concomitant drug administration can be associated with pharmacokinetic drug-drug interactions, increasing the risk of adverse drug events and reduced drug efficacy. Thus far, machine-learning models have been developed that can classify drug-drug interactions. However, to enable quantification of the pharmacokinetic effects of a drug-drug interaction, regression-based machine learning should be explored. Therefore, this study investigated the use of regression-based machine learning to predict changes in drug exposure caused by pharmacokinetic drug-drug interactions. Fold changes in exposure relative to substrate drug monotherapy were collected from 120 clinical drug-drug interaction studies extracted from the Washington Drug Interaction Database and SimCYP compound library files. Drug characteristics (features) were collected such as structure, physicochemical properties, in vitro pharmacokinetic properties, cytochrome P450 metabolic activity, and population characteristics. Three different regression-based supervised machine-learning models were then applied to the prediction task: random forest, elastic net, and support vector regressor. Model performance was evaluated using fivefold cross-validation. Strongest performance was observed with support vector regression, with 78% of predictions within twofold of the observed exposure changes. The results show that changes in drug exposure can be predicted with reasonable accuracy using regression-based machine-learning models trained on data available early in drug discovery. This has potential applications in enabling earlier drug-drug interaction risk assessment for new drug candidates.

Predicting Total Drug Clearance and Volumes of Distribution Using the Machine Learning-Mediated Multimodal Method through the Imputation of Various Nonclinical Data

Pharmacokinetic research plays an important role in the development of new drugs. Accurate predictions of human pharmacokinetic parameters are essential for the success of clinical trials. Clearance (CL) and volume of distribution (Vd) are important factors for evaluating pharmacokinetic properties, and many previous studies have attempted to use computational methods to extrapolate these values from nonclinical laboratory animal models to human subjects. However, it is difficult to obtain sufficient, comprehensive experimental data from these animal models, and many studies are missing critical values. This means that studies using nonclinical data as explanatory variables can only apply a small number of compounds to their model training. In this study, we perform missing-value imputation and feature selection on nonclinical data to increase the number of training compounds and nonclinical datasets available for these kinds of studies. We could obtain novel models for total body clearance (CL_tot) and steady-state Vd (Vd_ss) (CL_tot: geometric mean fold error [GMFE], 1.92; percentage within 2-fold error, 66.5%; Vd_ss: GMFE, 1.64; percentage within 2-fold error, 71.1%). These accuracies were comparable to the conventional animal scale-up models. Then, this method differs from animal scale-up methods because it does not require animal experiments, which continue to become more strictly regulated as time passes.

Multi-task convolutional neural networks for predicting in vitro clearance endpoints from molecular images

Optimization of compound metabolic stability is a highly topical issue in pharmaceutical research. Accordingly, application of predictive in silico models can potentially reduce the number of design-make-test-analyze iterations and consequently speed up the progression of novel candidate molecules. Herein, we have investigated the question if multiple in vitro clearance endpoints could be accurately predicted from image-based molecular representations. Thus, compound measurements for four commonly investigated clearance endpoints were curated from AstraZeneca internal sources, providing a sound basis for building multi-task convolutional neural network models. Application of several increasingly challenging data splitting strategies confirmed that convolutional neural network models were successful at capturing implicit chemical relationships contained in training and test data, similar to what is commonly observed for structural fingerprints. Furthermore, model benchmarking against state-of-the-art machine learning methods, including deep neural networks and graph convolutional neural networks, trained with structure- and graph-based representations, respectively, revealed on par or increased accuracy of convolutional neural networks with clear benefit of multi-task learning across all clearance endpoints. Our findings indicate that image-based molecular representations can be applied to predict multiple clearance endpoints, suggesting a potential follow-up to investigate model interpretability from molecular images.

Prediction of In Vivo Pharmacokinetic Parameters and Time-Exposure Curves in Rats Using Machine Learning from the Chemical Structure

Animal pharmacokinetic (PK) data as well as human and animal in vitro systems are utilized in drug discovery to define the rate and route of drug elimination. Accurate prediction and mechanistic understanding of drug clearance and disposition in animals provide a degree of confidence for extrapolation to humans. In addition, prediction of in vivo properties can be used to improve design during drug discovery, help select compounds with better properties, and reduce the number of in vivo experiments. In this study, we generated machine learning models able to predict rat in vivo PK parameters and concentration-time PK profiles based on the molecular chemical structure and either measured or predicted in vitro parameters. The models were trained on internal in vivo rat PK data for over 3000 diverse compounds from multiple projects and therapeutic areas, and the predicted endpoints include clearance and oral bioavailability. We compared the performance of various traditional machine learning algorithms and deep learning approaches, including graph convolutional neural networks. The best models for PK parameters achieved R² = 0.63 [root mean squared error (RMSE) = 0.26] for clearance and R² = 0.55 (RMSE = 0.46) for bioavailability. The models provide a fast and cost-efficient way to guide the design of molecules with optimal PK profiles, to enable the prediction of virtual compounds at the point of design, and to drive prioritization of compounds for in vivo assays.

Advancing pharmacy and healthcare with virtual digital technologies

Digitalisation of the healthcare sector promises to revolutionise patient healthcare globally. From the different technologies, virtual tools including artificial intelligence, blockchain, virtual, and augmented reality, to name but a few, are providing significant benefits to patients and the pharmaceutical sector alike, ranging from improving access to clinicians and medicines, as well as improving real-time diagnoses and treatments. Indeed, it is envisioned that such technologies will communicate together in real-time, as well as with their physical counterparts, to create a large-scale, cyber healthcare system. Despite the significant benefits that virtual-based digital health technologies can bring to patient care, a number of challenges still remain, ranging from data security to acceptance within the healthcare sector. This review provides a timely account of the benefits and challenges of virtual health interventions, as well an outlook on how such technologies can be transitioned from research-focused towards real-world healthcare and pharmaceutical applications to transform treatment pathways for patients worldwide.

In silico prediction of volume of distribution of drugs in man using conformal prediction performs on par with animal data-based models

Volume of distribution at steady state (V_ss) is an important pharmacokinetic endpoint. In this study we apply machine learning and conformal prediction for human V_ss prediction, and make a head-to-head comparison with rat-to-man scaling, allometric scaling and the Rodgers-Lukova method on combined in silico and in vitro data, using a test set of 105 compounds with experimentally observed V_ss.The mean prediction error and % with <2-fold prediction error for our method were 2.4-fold and 64%, respectively. 69% of test compounds had an observed V_ss within the prediction interval at a 70% confidence level. In comparison, 2.2-, 2.9- and 3.1-fold mean errors and 69, 64 and 61% of predictions with <2-fold error was reached with rat-to-man and allometric scaling and Rodgers-Lukova method, respectively.We conclude that our method has theoretically proven validity that was empirically confirmed, and showing predictive accuracy on par with animal models and superior to an alternative widely used in silico-based method. The option for the user to select the level of confidence in predictions offers better guidance on how to optimise V_ss in drug discovery applications.