Prediction of Oral Pharmacokinetics Using a Combination of In Silico Descriptors and In Vitro ADME Properties

GraphEGFR: Multi-task and transfer learning based on molecular graph attention mechanism and fingerprints improving inhibitor bioactivity prediction for EGFR family proteins on data scarcity

The proteins within the human epidermal growth factor receptor (EGFR) family, members of the tyrosine kinase receptor family, play a pivotal role in the molecular mechanisms driving the development of various tumors. Tyrosine kinase inhibitors, key compounds in targeted therapy, encounter challenges in cancer treatment due to emerging drug resistance mutations. Consequently, machine learning has undergone significant evolution to address the challenges of cancer drug discovery related to EGFR family proteins. However, the application of deep learning in this area is hindered by inherent difficulties associated with small-scale data, particularly the risk of overfitting. Moreover, the design of a model architecture that facilitates learning through multi-task and transfer learning, coupled with appropriate molecular representation, poses substantial challenges. In this study, we introduce GraphEGFR, a deep learning regression model designed to enhance molecular representation and model architecture for predicting the bioactivity of inhibitors against both wild-type and mutant EGFR family proteins. GraphEGFR integrates a graph attention mechanism for molecular graphs with deep and convolutional neural networks for molecular fingerprints. We observed that GraphEGFR models employing multi-task and transfer learning strategies generally achieve predictive performance comparable to existing competitive methods. The integration of molecular graphs and fingerprints adeptly captures relationships between atoms and enables both global and local pattern recognition. We further validated potential multi-targeted inhibitors for wild-type and mutant HER1 kinases, exploring key amino acid residues through molecular dynamics simulations to understand molecular interactions. This predictive model offers a robust strategy that could significantly contribute to overcoming the challenges of developing deep learning models for drug discovery with limited data and exploring new frontiers in multi-targeted kinase drug discovery for EGFR family proteins.

Predicting human half-life for insulin analogs: An inter-drug approach

An inter-drug approach, applying pharmacokinetic information for insulin analogs in different animal species, rat, dog and pig, performed better compared to allometric scaling for human translation of intra-venous half-life and only required data from a single animal species for reliable predictions. Average fold error (AFE) between 1.2-1.7 were determined for all species and for multispecies allometric scaling AFE was 1.9. A slightly larger prediction error for human half-life was determined from in vitro human insulin receptor affinity data (AFE on 2.3-2.6). The requirements for the inter-drug approach were shown to be a span of at least 2 orders of magnitude in half-life for the included drugs and a shared clearance mechanism. The insulin analogs in this study were the five fatty acid protracted analogs: Insulin degludec, insulin icodec, insulin 320, insulin 338 and insulin 362, as well as the non-acylated analog insulin aspart.

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.

The Comparison of Machine Learning and Mechanistic In Vitro-In Vivo Extrapolation Models for the Prediction of Human Intrinsic Clearance

Accurate prediction of human pharmacokinetics (PK) remains one of the key objectives of drug metabolism and PK (DMPK) scientists in drug discovery projects. This is typically performed by using in vitro-in vivo extrapolation (IVIVE) based on mechanistic PK models. In recent years, machine learning (ML), with its ability to harness patterns from previous outcomes to predict future events, has gained increased popularity in application to absorption, distribution, metabolism, and excretion (ADME) sciences. This study compares the performance of various ML and mechanistic models for the prediction of human IV clearance for a large (645) set of diverse compounds with literature human IV PK data, as well as measured relevant in vitro end points. ML models were built using multiple approaches for the descriptors: (1) calculated physical properties and structural descriptors based on chemical structure alone (classical QSAR/QSPR); (2) in vitro measured inputs only with no structure-based descriptors (ML IVIVE); and (3) in silico ML IVIVE using in silico model predictions for the in vitro inputs. For the mechanistic models, well-stirred and parallel-tube liver models were considered with and without the use of empirical scaling factors and with and without renal clearance. The best ML model for the prediction of in vivo human intrinsic clearance (CLint) was an in vitro ML IVIVE model using only six in vitro inputs with an average absolute fold error (AAFE) of 2.5. The best mechanistic model used the parallel-tube liver model, with empirical scaling factors resulting in an AAFE of 2.8. The corresponding mechanistic model with full in silico inputs achieved an AAFE of 3.3. These relative performances of the models were confirmed with the prediction of 16 Pfizer drug candidates that were not part of the original data set. Results show that ML IVIVE models are comparable to or superior to their best mechanistic counterparts. We also show that ML IVIVE models can be used to derive insights into factors for the improvement of mechanistic PK prediction.

Ensemble Machine Learning Approaches Based on Molecular Descriptors and Graph Convolutional Networks for Predicting the Efflux Activities of MDR1 and BCRP Transporters

Multidrug resistance (MDR1) and breast cancer resistance protein (BCRP) play important roles in drug absorption and distribution. Computational prediction of substrates for both transporters can help reduce time in drug discovery. This study aimed to predict the efflux activity of MDR1 and BCRP using multiple machine learning approaches with molecular descriptors and graph convolutional networks (GCNs). In vitro efflux activity was determined using MDR1- and BCRP-expressing cells. Predictive performance was assessed using an in-house dataset with a chronological split and an external dataset. CatBoost and support vector regression showed the best predictive performance for MDR1 and BCRP efflux activities, respectively, of the 25 descriptor-based machine learning methods based on the coefficient of determination (R2). The single-task GCN showed a slightly lower performance than descriptor-based prediction in the in-house dataset. In both approaches, the percentage of compounds predicted within twofold of the observed values in the external dataset was lower than that in the in-house dataset. Multi-task GCN did not show any improvements, whereas multimodal GCN increased the predictive performance of BCRP efflux activity compared with single-task GCN. Furthermore, the ensemble approach of descriptor-based machine learning and GCN achieved the highest predictive performance with R2 values of 0.706 and 0.587 in MDR1 and BCRP, respectively, in time-split test sets. This result suggests that two different approaches to represent molecular structures complement each other in terms of molecular characteristics. Our study demonstrated that predictive models using advanced machine learning approaches are beneficial for identifying potential substrate liability of both MDR1 and BCRP.

Human Brain Penetration Prediction Using Scaling Approach from Animal Machine Learning Models

Machine learning (ML) approaches have been applied to predicting drug pharmacokinetic properties. Previously, we predicted rat unbound brain-to-plasma ratio (Kpuu,brain) by ML models. In this study, we aimed to predict human Kpuu,brain through animal ML models. First, we re-evaluated ML models for rat Kpuu,brain prediction by using trendy open-source packages. We then developed ML models for monkey Kpuu,brain prediction. Leave-one-out cross validation was utilized to rationally build models using a relatively small dataset. After establishing the monkey and rat ML models, human Kpuu,brain prediction was achieved by implementing the animal models considering appropriate scaling methods. Mechanistic NeuroPK models for the identical monkey and human dataset were treated as the criteria for comparison. Results showed that rat Kpuu,brain predictivity was successfully replicated. The optimal ML model for monkey Kpuu,brain prediction was superior to the NeuroPK model, where accuracy within 2-fold error was 78% (R2 = 0.76). For human Kpuu,brain prediction, rat model using relative expression factor (REF), scaled transporter efflux ratios (ERs), and monkey model using in vitro ERs can provide comparable predictivity to the NeuroPK model, where accuracy within 2-fold error was 71% and 64% (R2 = 0.30 and 0.52), respectively. We demonstrated that ML models can deliver promising Kpuu,brain prediction with several advantages: (1) predict reasonable animal Kpuu,brain; (2) prospectively predict human Kpuu,brain from animal models; and (3) can skip expensive monkey studies for human prediction by using the rat model. As a result, ML models can be a powerful tool for drug Kpuu,brain prediction in the discovery stage.

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.

Not all benzimidazole derivatives are microtubule destabilizing agents

In recent years, microtubule-targeting agents (MTAs) have gained considerable interest in developing novel small-molecule anticancer drugs. MTAs demonstrate anticancer activity either as microtubule-stabilizing agents (paclitaxel) or microtubule-destabilizing agents (nocodazole). FDA-approved drugs containing a benzimidazole ring (nocodazole, albendazole, mebendazole, etc.) are well-known microtubule-destabilizing agents. Thus, most recent research on benzimidazole scaffold-based MTAs focuses on developing microtubule-destabilizing agents. However, there is no report on the benzimidazole scaffold-based microtubule-stabilizing agent. Here, we present the benzimidazole derivatives NI-11 and NI-18 that showed a profound anticancer activity as microtubule-stabilization agents. About twenty benzimidazole analogues were synthesized with excellent yield (80.0% ∼ 98.0%) and tested for their anticancer activity using two cancer cell lines (A549, MCF-7) and one normal cell line (MRC-5). NI-11 showed IC₅₀ values of 2.90, 7.17, and 16.9 µM in A549, MCF-7, and MRC-5 cell lines. NI-18 showed IC₅₀ values of 2.33, 6.10, and 12.1 µM in A549, MCF-7, and MRC-5 cell lines. Thus, NI-11 and NI-18 demonstrated selectivity indexes of 5.81 and 5.20, respectively, which are much higher than the currently available anticancer agents. NI-11 and NI-18 inhibited the cancer cell motility and migration, induced the early phase apoptosis. Both of these comounds were found to show an upregulation of DeY-α-tubulin and downregulation of Ac-α-tubulin expressions in cancer cells. Eventhough the reported benzimidazole scaffold-based commercially available drugs are known to be microtubule-destabilizing agents, the analogues NI-11 and NI-18 were found to have microtubule-stabilizing activity. The in vitro tubulin polymerization assay and the immunofluorescence assay results indicate that the NI-11 and NI-18 exhibit anticancer activity by stabilizing the microtubule network.

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

BACKGROUND

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

OBJECTIVE

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

METHODS

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

RESULTS

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

CONCLUSION

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

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.

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.

In silico and in vitro studies of GENT-EDTA encapsulated niosomes: A novel approach to enhance the antibacterial activity and biofilm inhibition in drug-resistant Klebsiella pneumoniae

Klebsiella pneumoniae (Kp) is a common pathogen inducing catheter-related biofilm infections. Developing effective therapy to overcome antimicrobial resistance (AMR) in Kp is a severe therapeutic challenge that must be solved. This study aimed to prepare niosome-encapsulated GENT (Gentamicin) and EDTA (Ethylenediaminetetraacetic acid) (GENT-EDTA/Nio) to evaluate its efficacy toward Kp strains. The thin-film hydration method was used to prepare various formulations of GENT-EDTA/Nio. Formulations were characterized for their physicochemical characteristics. GENT-EDTA/Nio properties were used for optimization with Design-Expert Software. Molecular docking was utilized to determine the antibacterial activity of GENT. The niosomes displayed a controlled drug release and storage stability of at least 60 days at 4 and 25 °C. GENT-EDTA/Nio performance as antimicrobial agents has been evaluated by employing agar well diffusion method, minimum bactericidal concentration (MBC), and minimum inhibitory concentration (MIC) against the Kp bacteria strains. Biofilm formation was investigated after GENT-EDTA/Nio administration through different detection methods, which showed that this formulation reduces biofilm formation. The effect of GENT-EDTA/Nio on the expression of biofilm-related genes (mrkA, ompA, and vzm) was estimated using QRT-PCR. MTT assay was used to evaluate the toxicity effect of niosomal formulations on HFF cells. The present study results indicate that GENT-EDTA/Nio decreases Kp's resistance to antibiotics and increases its antibiotic and anti-biofilm activity and could be helpful as a new approach for drug delivery.

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.

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.

Studying and mitigating the effects of data drifts on ML model performance at the example of chemical toxicity data

Machine learning models are widely applied to predict molecular properties or the biological activity of small molecules on a specific protein. Models can be integrated in a conformal prediction (CP) framework which adds a calibration step to estimate the confidence of the predictions. CP models present the advantage of ensuring a predefined error rate under the assumption that test and calibration set are exchangeable. In cases where the test data have drifted away from the descriptor space of the training data, or where assay setups have changed, this assumption might not be fulfilled and the models are not guaranteed to be valid. In this study, the performance of internally valid CP models when applied to either newer time-split data or to external data was evaluated. In detail, temporal data drifts were analysed based on twelve datasets from the ChEMBL database. In addition, discrepancies between models trained on publicly-available data and applied to proprietary data for the liver toxicity and MNT in vivo endpoints were investigated. In most cases, a drastic decrease in the validity of the models was observed when applied to the time-split or external (holdout) test sets. To overcome the decrease in model validity, a strategy for updating the calibration set with data more similar to the holdout set was investigated. Updating the calibration set generally improved the validity, restoring it completely to its expected value in many cases. The restored validity is the first requisite for applying the CP models with confidence. However, the increased validity comes at the cost of a decrease in model efficiency, as more predictions are identified as inconclusive. This study presents a strategy to recalibrate CP models to mitigate the effects of data drifts. Updating the calibration sets without having to retrain the model has proven to be a useful approach to restore the validity of most models.

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.

Investigation of potential descriptors of chemical compounds on prevention of nephrotoxicity via QSAR approach

Drug-induced nephrotoxicity remains a common problem after exposure to medications and diagnostic agents, which may be heightened in the kidney microenvironment and deteriorate kidney function. In this study, the toxic effects of fourteen marked drugs with the individual chemical structure were evaluated in kidney cells. The quantitative structure–activity relationship (QSAR) approach was employed to investigate the potential structural descriptors of each drug-related to their toxic effects. The most reasonable equation of the QSAR model displayed that the estimated regression coefficients such as the number of ring assemblies, three-membered rings, and six-membered rings were strongly related to toxic effects on renal cells. Meanwhile, the chemical properties of the tested compounds including carbon atoms, bridge bonds, H-bond donors, negative atoms, and rotatable bonds were favored properties and promote the toxic effects on renal cells. Particularly, more numbers of rotatable bonds were positively correlated with strong toxic effects that displayed on the most toxic compound. The useful information discovered from our regression QSAR models may help to identify potential hazardous moiety to avoid nephrotoxicity in renal preventive medicine.

Machine learning predicts the effect of food on orally administered medicines

Food-mediated changes to drug absorption, termed the food effect, are hard to predict and can have significant implications for the safety and efficacy of oral drug products in patients. Mimicking the prandial states of the human gastrointestinal tract in preclinical studies is challenging, poorly predictive and can produce difficult to interpret datasets. Machine learning (ML) has emerged from the computer science field and shows promise in interpreting complex datasets present in the pharmaceutical field. A ML-based approach aimed to predict the food effect based on an extensive dataset of over 311 drugs with more than 20 drug physicochemical properties, referred to as features. Machine learning techniques were tested; including logistic regression, support vector machine, k-Nearest neighbours and random forest. First a standard ML pipeline using a 80:20 split for training and testing was tried to predict no food effect, negative food effect and positive food effect, however this lead to specificities of less than 40%. To overcome this, a strategic ML pipeline was devised and three tasks were developed. Random forest achieved the strongest performance overall. High accuracies and sensitivities of 70%, 80% and 70% and specificities of 71%, 76% and 71% were achieved for classifying; (i) no food effect vs food effect, (ii) negative food vs positive food effect and (iii) no food effect vs negative food effect vs positive food effect, respectively. Feature importance using random forest ranked the features by importance for building the predictive tasks. The calculated dose number was the most important feature. Here, ML has provided an effective screening tool for predicting the food effect, with the potential to select lead compounds with no food effect, reduce the number of animal studies, and accelerate oral drug development studies.

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

Prior to clinical development, a comprehensive pharmacokinetic characterization of a novel drug is required to understand its exposure at the site of action and elimination. Accordingly, in vitro assays and animal pharmacokinetic studies are regularly employed to predict drug exposure in humans, which is often costly and time-consuming. For this reason, the prediction of human pharmacokinetics at the point of design would be of high value for drug discovery. Therefore, we have established a comprehensive data curation protocol that enables machine learning evaluation of 12 human in vivo pharmacokinetic parameters using only chemical structure information and available doses for 1001 unique compounds. These machine learning models were thoroughly investigated and validated using both an independent hold-out test set and AstraZeneca clinical data. In addition, the availability of preclinical predictions for a subset of internal clinical candidates allowed us to compare our in silico approach with state-of-the-art pharmacokinetic predictions. Based on this evaluation, three fit-for-purpose models for AUC PO (R_test² = 0.63; RMSE_test = 0.76), C_max PO (R_test² = 0.68; RMSE_test = 0.62), and Vd_ss IV (R_test² = 0.47; RMSE_test = 0.50) were identified. Based on the findings, our machine learning models have considerable potential for practical applications in drug discovery, such as influencing decision-making in drug discovery projects and progression of drug candidates toward the clinic.

Comparison of Pinoresinol and its Diglucoside on their ADME Properties and Vasorelaxant Effects on Phenylephrine-Induced Model

Pinoresinol (PINL) and pinoresinol diglucoside (PDG), two natural lignans found in Eucommia ulmoides Oliv. (Duzhong), have several pharmacological activities. However, there is no report available on their absorption, distribution, metabolism, and elimination (ADME) properties. Given the possible wide spectrum of their application in therapeutic areas, this area should be investigated. This work studied the in vitro ADME properties of PDG and PINL, including their kinetic solubility, permeability across monolayer cells (PAMPA), protein binding, and metabolic stabilities in liver microsomes. The in vivo pharmacokinetic study and in vitro vasorelaxant effects on isolated phenylephrine-induced aortic rings of PINL and PDG were also investigated. It was found that both of their kinetic solubility in PBS (pH 7.4) was greater than 100 μM, indicating that they are both soluble compounds. The permeability investigations (P_eff) by PAMPA indicated that PINL had higher permeability than PDG (p < 0.05). Both components represented moderate plasma protein binding activities (average binding rate in human plasma: PINL 89.03%, PDG 45.21%) and low metabolic rate (t_1/2 in human liver microsome: PINL 1509.5 min, PDG 1004.8 min). Furthermore, the results of pharmacokinetic studies indicated that PINL might be eliminated less quickly than PDG from the rat plasma, and its cumulative urinary excretion was much lower than that of PDG. The phenylephrine-induced aortic rings demonstrated concentration-dependent vasorelaxation in PDG, PINL, or their combination group. The vasorelaxant effects of PINL were more obvious than those of PDG, whereas the vasorelaxant effect of the combinations was significantly better than that of the single component (p < 0.05). The similarity or difference between PINL and its diglucoside in these pharmaceutical aspects may offer valuable insights into the further exploration of lignans and might contribute to relevant studies involving natural products with similar molecular structure and their glucosides.

Harnessing artificial intelligence for the next generation of 3D printed medicines

Artificial intelligence (AI) is redefining how we exist in the world. In almost every sector of society, AI is performing tasks with super-human speed and intellect; from the prediction of stock market trends to driverless vehicles, diagnosis of disease, and robotic surgery. Despite this growing success, the pharmaceutical field is yet to truly harness AI. Development and manufacture of medicines remains largely in a 'one size fits all' paradigm, in which mass-produced, identical formulations are expected to meet individual patient needs. Recently, 3D printing (3DP) has illuminated a path for on-demand production of fully customisable medicines. Due to its flexibility, pharmaceutical 3DP presents innumerable options during formulation development that generally require expert navigation. Leveraging AI within pharmaceutical 3DP removes the need for human expertise, as optimal process parameters can be accurately predicted by machine learning. AI can also be incorporated into a pharmaceutical 3DP 'Internet of Things', moving the personalised production of medicines into an intelligent, streamlined, and autonomous pipeline. Supportive infrastructure, such as The Cloud and blockchain, will also play a vital role. Crucially, these technologies will expedite the use of pharmaceutical 3DP in clinical settings and drive the global movement towards personalised medicine and Industry 4.0.

Direct Comparison of the Prediction of the Unbound Brain-to-Plasma Partitioning Utilizing Machine Learning Approach and Mechanistic Neuropharmacokinetic Model

The mechanistic neuropharmacokinetic (neuroPK) model was established to predict unbound brain-to-plasma partitioning (K_p,uu,brain) by considering in vitro efflux activities of multiple drug resistance 1 (MDR1) and breast cancer resistance protein (BCRP). Herein, we directly compare this model to a computational machine learning approach utilizing physicochemical descriptors and efflux ratios of MDR1 and BCRP-expressing cells for predicting K_p,uu,brain in rats. Two different types of machine learning techniques, Gaussian processes (GP) and random forest regression (RF), were assessed by the time and cluster-split validation methods using 640 internal compounds. The predictivity of machine learning models based on only molecular descriptors in the time-split dataset performed worse than the cluster-split dataset, whereas the models incorporating MDR1 and BCRP efflux ratios showed similar predictivity between time and cluster-split datasets. The GP incorporating MDR1 and BCRP in the time-split dataset achieved the highest correlation (R² = 0.602). These results suggested that incorporation of MDR1 and BCRP in machine learning is beneficial for robust and accurate prediction. K_p,uu,brain prediction utilizing the neuroPK model was significantly worse compared to machine learning approaches for the same dataset. We also investigated the predictivity of K_p,uu,brain using an external independent test set of 34 marketed drugs. Compared to machine learning models, the neuroPK model showed better predictive performance with R² of 0.577. This work demonstrates that the machine learning model for K_p,uu,brain achieves maximum predictive performance within the chemical applicability domain, whereas the neuroPK model is applicable more widely beyond the chemical space covered in the training dataset.

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

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