Pharmacokinetic parameter prediction from drug structure using artificial neural networks

A Quantitative Structure-Activity Relationship for Human Plasma Protein Binding: Prediction, Validation and Applicability Domain

Purpose

The purpose of this study was to develop a robust and externally predictive in silico QSAR-neural network model for predicting plasma protein binding of drugs. This model aims to enhance drug discovery processes by reducing the need for chemical synthesis and extensive laboratory testing.

Methods

A dataset of 277 drugs was used to develop the QSAR-neural network model. The model was constructed using a Filter method to select 55 molecular descriptors. The validation set's external accuracy was assessed through the predictive squared correlation coefficient Q2 and the root mean squared error (RMSE).

Results

The developed QSAR-neural network model demonstrated robustness and good applicability domain. The external accuracy of the validation set was high, with a predictive squared correlation coefficient Q2 of 0.966 and a root mean squared error (RMSE) of 0.063. Comparatively, this model outperformed previously published models in the literature.

Conclusion

The study successfully developed an advanced QSAR-neural network model capable of predicting plasma protein binding in human plasma for a diverse set of 277 drugs. This model's accuracy and robustness make it a valuable tool in drug discovery, potentially reducing the need for resource-intensive chemical synthesis and laboratory testing.

Quantitative Structure-Property Relationship Approach in Formulation Development: an Overview

Chemoinformatics is emerging as a new trend to set drug discovery which correlates the relationship between structure and biological functions. The main aim of chemoinformatics refers to analyzing the similarity among molecules, searching the molecules in the structural database, finding potential drug molecule and their property. One of the key fields in chemoinformatics is quantitative structure-property relationship (QSPR), which is an alternative process to predict the various physicochemical and biopharmaceutical properties. This methodology expresses molecules via various numerical values or properties (descriptors), which encodes the structural characteristics of molecules and further used to calculate physicochemical properties of the molecule. The established QSPR model could be used to predict the properties of compounds that have been measured or even have been unknown, which ultimately accelerates the development process of a new molecule or the product. The formulation characteristics (drug release, transportability, bioavailability) can be predicted with the integration of QSPR approach. Therefore, QSPR modeling is an emerging trend to skip conventional drug as well as formulation development process. The current review highlights the overall process involved in the application of the QSPR approach in formulation development.

Evaluating the influence of half-life, milk:plasma partition coefficient, and volume of distribution on lactational exposure to chemicals in children

Women are exposed to multiple environmental chemicals, many of which are known to transfer to breast milk during lactation. However, little is known about the influence of the different chemical-specific pharmacokinetic parameters on children's lactational dose. Our objective was to develop a generic pharmacokinetic model and subsequently quantify the influence of three chemical-specific parameters (biological half-life, milk:plasma partition coefficient, and volume of distribution) on lactational exposure to chemicals and resulting plasma levels in children. We developed a two-compartment pharmacokinetic model to simulate lifetime maternal exposure, placental transfer, and lactational exposure to the child. We performed 10,000 Monte Carlo simulations where half-life, milk:plasma partition coefficient, and volume of distribution were varied. Children's dose and plasma levels were compared to their mother's by calculating child:mother dose ratios and plasma level ratios. We then evaluated the association between the three chemical-specific pharmacokinetic parameters and child:mother dose and level ratios through linear regression and decision trees. Our analyses revealed that half-life was the most influential parameter on children's lactational dose and plasma concentrations, followed by milk:plasma partition coefficient and volume of distribution. In bivariate regression analyses, half-life explained 72% of child:mother dose ratios and 53% of child:mother level ratios. Decision trees aiming to identify chemicals with high potential for lactational exposure (ratio>1) had an accuracy of 89% for child:mother dose ratios and 84% for child:mother level ratios. Our study showed the relative importance of half-life, milk:plasma partition coefficient, and volume of distribution on children's lactational exposure. Developed equations and decision trees will enable the rapid identification of chemicals with a high potential for lactational exposure.

A four-compartment PBPK heart model accounting for cardiac metabolism - model development and application

In the field of cardiac drug efficacy and safety assessment, information on drug concentration in heart tissue is desirable. Because measuring drug concentrations in human cardiac tissue is challenging in healthy volunteers, mathematical models are used to cope with such limitations. With a goal of predicting drug concentration in cardiac tissue, we have developed a whole-body PBPK model consisting of seventeen perfusion-limited compartments. The proposed PBPK heart model consisted of four compartments: the epicardium, midmyocardium, endocardium, and pericardial fluid, and accounted for cardiac metabolism using CYP450. The model was written in R. The plasma:tissues partition coefficients (Kp) were calculated in Simcyp Simulator. The model was fitted to the concentrations of amitriptyline in plasma and the heart. The estimated parameters were as follows: 0.80 for the absorption rate [h-1], 52.6 for Kprest, 0.01 for the blood flow through the pericardial fluid [L/h], and 0.78 for the P-parameter describing the diffusion between the pericardial fluid and epicardium [L/h]. The total cardiac clearance of amitriptyline was calculated as 0.316 L/h. Although the model needs further improvement, the results support its feasibility, and it is a first attempt to provide an active drug concentration in various locations within heart tissue using a PBPK approach.

In silico optimization of pharmacokinetic properties and receptor binding affinity simultaneously: a 'parallel progression approach to drug design' applied to β-blockers

The present work exploits the potential of in silico approaches for minimizing attrition of leads in the later stages of drug development. We propose a theoretical approach, wherein 'parallel' information is generated to simultaneously optimize the pharmacokinetics (PK) and pharmacodynamics (PD) of lead candidates. β-blockers, though in use for many years, have suboptimal PKs; hence are an ideal test series for the 'parallel progression approach'. This approach utilizes molecular modeling tools viz. hologram quantitative structure activity relationships, homology modeling, docking, predictive metabolism, and toxicity models. Validated models have been developed for PK parameters such as volume of distribution (log Vd) and clearance (log Cl), which together influence the half-life (t1/2) of a drug. Simultaneously, models for PD in terms of inhibition constant pKi have been developed. Thus, PK and PD properties of β-blockers were concurrently analyzed and after iterative cycling, modifications were proposed that lead to compounds with optimized PK and PD. We report some of the resultant re-engineered β-blockers with improved half-lives and pKi values comparable with marketed β-blockers. These were further analyzed by the docking studies to evaluate their binding poses. Finally, metabolic and toxicological assessment of these molecules was done through in silico methods. The strategy proposed herein has potential universal applicability, and can be used in any drug discovery scenario; provided that the data used is consistent in terms of experimental conditions, endpoints, and methods employed. Thus the 'parallel progression approach' helps to simultaneously fine-tune various properties of the drug and would be an invaluable tool during the drug development process.

Applying linear and non-linear methods for parallel prediction of volume of distribution and fraction of unbound drug

Volume of distribution and fraction unbound are two key parameters in pharmacokinetics. The fraction unbound describes the portion of free drug in plasma that may extravasate, while volume of distribution describes the tissue access and binding of a drug. Reliable in silico predictions of these pharmacokinetic parameters would benefit the early stages of drug discovery, as experimental measuring is not feasible for screening purposes. We have applied linear and nonlinear multivariate approaches to predict these parameters: linear partial least square regression and non-linear recursive partitioning classification. The volume of distribution and fraction of unbound drug in plasma are predicted in parallel within the model, since the two are expected to be affected by similar physicochemical drug properties. Predictive models for both parameters were built and the performance of the linear models compared to models included in the commercial software Volsurf+. Our models performed better in predicting the unbound fraction (Q² 0.54 for test set compared to 0.38 with Volsurf+ model), but prediction accuracy of the volume of distribution was comparable to the Volsurf+ model (Q² of 0.70 for test set compared to 0.71 with Volsurf+ model). The nonlinear classification models were able to identify compounds with a high or low volume of distribution (sensitivity 0.81 and 0.71, respectively, for test set), while classification of fraction unbound was less successful. The interrelationship between the volume of distribution and fraction unbound is investigated and described in terms of physicochemical descriptors. Lipophilicity and solubility descriptors were found to have a high influence on both volume of distribution and fraction unbound, but with an inverse relationship.

Dexamethasone-releasing cochlear implant coatings: application of artificial neural networks for modelling of formulation parameters and drug release profile

Objectives

Over the past few decades, mathematical modelling and simulation of drug delivery systems has been steadily gained interest as a focus for academic and industrial attention. Here, simulation of dexamethasone (DEX, a corticosteroid anti-inflammatory agent) release profile from drug-eluting cochlear implant coatings is reported using artificial neural networks.

Methods

The devices were fabricated as monolithic dispersions of the pharmaceutically active ingredient in a silicone rubber matrix. A two-phase exponential model was fitted on the experimentally obtained DEX release profiles. An artificial neural network (ANN) was trained to determine formulation parameters (i.e. DEX loading percentage, the devices surface area and their geometry) for a specific experimentally obtained drug release profile. In a reverse strategy, an ANN was trained for determining expected drug release profiles for the same set of formulation parameters.

Key findings

An algorithm was developed by combining the two previously developed ANNs in a serial manner, and this was successfully used for simulating the developed drug-eluting cochlear implant coatings. The models were validated by a leave-one-out method and performing new experiments.

Conclusions

The developed ANN algorithms were capable to bilaterally predict drug release profile for a known set of formulation parameters or find out the levels for input formulation parameters to obtain a desired DEX release profile.

Predicting biological activity: computational approach using novel distance based molecular descriptors

Four novel distance based molecular descriptors termed as superpendentic eccentric distance sum indices 1-4 (denoted by:∫P-1EDS, ∫P-2EDS, ∫P-3EDS and ∫P-4EDS) as well as their topochemical counterparts (denoted by:∫cP-1EDS, ∫cP-2EDS, ∫cP-3EDS and ∫cP-4EDS) have been conceptualized and developed in the present study. The sensitivity towards branching, discriminating power, and degeneracy of the proposed novel descriptors were investigated. Utility of these indices was investigated for development of models through decision tree and moving average analysis for the prediction of human corticotropin releasing factor-1 receptor binding affinity of substituted pyrazines. A wide variety of 46 2D and 3D molecular descriptors including proposed indices was employed for development of models through decision tree and moving average analysis. The calculation of most of these descriptors for each compound of the dataset was performed using online E-Dragon software (version 1.0). An in-house computer programme was also employed to calculate additional topological descriptors which did not figure in E-Dragon software. The decision tree classified and correctly predicted the input data with an impressive accuracy of 92% in the training set and 71% during cross-validation. A total of three descriptors, identified by decision tree, were subsequently utilized for development of suitable models using moving average analysis. These models predicted human corticotropin releasing factor-1 receptor binding affinity with an accuracy of ≥85%. The statistical significance of models was assessed through sensitivity, specificity and Matthew's correlation coefficient. High discriminating power, high sensitivity towards branching amalgamated with negligible degeneracy offer proposed descriptors a vast potential for use in the quantitative structure-activity/property/toxicity relationships so as to facilitate drug design.

Prediction of pharmacokinetic parameters

In silico tools specifically developed for prediction of pharmacokinetic parameters are of particular interest to pharmaceutical industry because of the high potential of discarding inappropriate molecules during an early stage of drug development itself with consequent saving of vital resources and valuable time. The ultimate goal of the in silico models of absorption, distribution, metabolism, and excretion (ADME) properties is the accurate prediction of the in vivo pharmacokinetics of a potential drug molecule in man, whilst it exists only as a virtual structure. Various types of in silico models developed for successful prediction of the ADME parameters like oral absorption, bioavailability, plasma protein binding, tissue distribution, clearance, half-life, etc. have been briefly described in this chapter.

Drug-drug relationship based on target information: application to drug target identification

Background

Drugs that bind to common targets likely exert similar activities. In this target-centric view, the inclusion of richer target information may better represent the relationships between drugs and their activities. Under this assumption, we expanded the “common binding rule” assumption of QSAR to create a new drug-drug relationship score (DRS).

Method

Our method uses various chemical features to encode drug target information into the drug-drug relationship information. Specifically, drug pairs were transformed into numerical vectors containing the basal drug properties and their differences. After that, machine learning techniques such as data cleaning, dimension reduction, and ensemble classifier were used to prioritize drug pairs bound to a common target. In other words, the estimation of the drug-drug relationship is restated as a large-scale classification problem, which provides the framework for using state-of-the-art machine learning techniques with thousands of chemical features for newly defining drug-drug relationships.

Conclusions

Various aspects of the presented score were examined to determine its reliability and usefulness: the abundance of common domains for the predicted drug pairs, c.a. 80% coverage for known targets, successful identifications of unknown targets, and a meaningful correlation with another cutting-edge method for analyzing drug similarities. The most significant strength of our method is that the DRS can be used to describe phenotypic similarities, such as pharmacological effects.

Prediction of steady-state volume of distribution of acidic drugs by quantitative structure-pharmacokinetics relationships

The volume of distribution (VD) is one of the most important pharmacokinetic parameters of drugs. The present study employs quantitative structure-pharmacokinetics relationships (QSPkR) to derive models for VD prediction of acidic drugs. The steady-state volume of distribution (VD(ss)) values of 132 acidic drugs were collected, the chemical structures were described by 178 molecular descriptors, and QSPkR models were derived after variable selection by genetic algorithm and stepwise regression. Models were validated by cross-validation procedures and external test set. According to the molecular descriptors selected as the most predictive for VD(ss), the presence of seven- and nine-member cycles, atom type P(5+), SH groups, and large nonionized substituents increase the VD(ss), whereas atom types S(2+) and S(4+) and polar ionized substituents decrease it. Cross-validation and external validation studies on the QSPkR models derived in the present study showed good predictive ability with mean fold error values ranging from 1.58 (cross-validation) to 2.25 (external validation). The model performance is comparable to more complicated methods requiring in vitro or in vivo experiments and superior to the existing QSPkR models concerning acidic drugs. Apart from the prediction of VD in human, present models are also useful as a curator of available pharmacokinetic databases.

Models for prediction of (V)600(E)BRAF and melanoma cells growth inhibitory activities of pyridoimidazolones

Targeted inhibition of activated BRAF mutation has emerged as a most promising and putative therapeutic approach for the anticancer drug development. In the present study, an in-silico approach using decision tree and moving average analysis has been applied to a data set comprising of 43 analogues of pyridoimidazolones for development of models for prediction of both (V)600(E)BRAF and melanoma cells (BRAF WM266.4) growth inhibitory activities. A decision tree was mainly employed for determining the importance of molecular descriptors (n=46). The value of majority of these descriptors for each analogue in the dataset was computed using E-Dragon software (version 1.0). The decision tree learned the information from the input data with an accuracy of 98% and correctly predicted the cross-validated (10-fold) data with accuracy up to 79%. A total of three non-correlating descriptors, identified best by the decision tree analysis, were subsequently utilized for development of suitable models using moving average analysis. These proposed models resulted in the prediction of (V)600(E)BRAF inhibitory activity (IC50) and melanoma cells growth (SRB GI50) inhibitory activity with an overall accuracy of ≥90%. The statistical significance of models/descriptors was assessed through intercorrelation analysis, sensitivity, specificity and Matthew's correlation coefficient.

Toxicokinetic Considerations in Predicting Toxicity

The ability of a compound to elicit a toxic effect within an organism is dependent upon three factors (i) the external exposure of the organism to the toxicant in the environment or via the food chain (ii) the internal uptake of the compound into the organism and its transport to the site of action in sufficient concentration and (iii) the inherent toxicity of the compound. The in silico prediction of toxicity and the role of external exposure have been dealt with in other chapters of this book. This chapter focuses on the importance of ‘internal exposure’ i.e. the absorption, distribution, metabolism and elimination (ADME) properties of compounds which determine their toxicokinetic profile. An introduction to key concepts in toxicokinetics will be provided, along with examples of modelling approaches and software available to predict these properties. A brief introduction will also be given into the theory of physiologically-based toxicokinetic modelling.

Machine learning approaches for predicting compounds that interact with therapeutic and ADMET related proteins

Computational methods for predicting compounds of specific pharmacodynamic and ADMET (absorption, distribution, metabolism, excretion and toxicity) property are useful for facilitating drug discovery and evaluation. Recently, machine learning methods such as neural networks and support vector machines have been explored for predicting inhibitors, antagonists, blockers, agonists, activators and substrates of proteins related to specific therapeutic and ADMET property. These methods are particularly useful for compounds of diverse structures to complement QSAR methods, and for cases of unavailable receptor 3D structure to complement structure-based methods. A number of studies have demonstrated the potential of these methods for predicting such compounds as substrates of P-glycoprotein and cytochrome P450 CYP isoenzymes, inhibitors of protein kinases and CYP isoenzymes, and agonists of serotonin receptor and estrogen receptor. This article is intended to review the strategies, current progresses and underlying difficulties in using machine learning methods for predicting these protein binders and as potential virtual screening tools. Algorithms for proper representation of the structural and physicochemical properties of compounds are also evaluated.

Population pharmacokinetic and pharmacodynamic models of remifentanil in healthy volunteers using artificial neural network analysis

AIMS

An ordinary sigmoid E(max) model could not predict overshoot of electroencephalographic approximate entropy (ApEn) during recovery from remifentanil effect in our previous study. The aim of this study was to evaluate the ability of an artificial neural network (ANN) to predict ApEn overshoot and to evaluate the predictive performance of the pharmacokinetic model, and pharmacodynamic models of ANN with respect to data used.

METHODS

Using a reduced number of ApEn instances (n = 1581) to make NONMEM modelling feasible and complete ApEn data (n = 24 509), the presence of overshoot was assessed. A total of 1077 measured remifentanil concentrations and ApEn data, and a total of 24 509 predicted concentrations and ApEn data were used in the pharmacodynamic model A and B of ANN, respectively. The testing subset of model B (n = 7352) was used to evaluate the ability of ANN to predict overshoot of ApEn. Mean squared error (MSE) was calculated to evaluate the predictive performance of the ANN models.

RESULTS

With complete ApEn data, ApEn overshoot was observed in 66.7% of subjects, but only in 37% with a reduced number of ApEn instances. The ANN model B predicted 77.8% of ApEn overshoot. MSE (95% confidence interval) was 57.1 (3.22, 71.03) for the pharmacokinetic model, 0.148 (0.004, 0.007) for model A and 0.0018 (0.0017, 0.0019) for model B.

CONCLUSIONS

The reduced ApEn instances interfered with the approximation of true electroencephalographic response. ANN predicted 77.8% of ApEn overshoot. The predictive performance of model B was significantly better than that of model A.

Quantitative structure-pharmacokinetic/pharmacodynamic relationships

Quantitative structure-activity relationships have long been considered a vital component of drug discovery and development, providing insight into the role of molecular properties in the biological activity of similar and unrelated compounds. Recognition that in vitro bioassay and/or pre-clinical activity are insufficient for anticipating which compounds are suitable leads for further development has shifted the focus toward integrated pharmacokinetic (PK) and pharmacodynamic (PD) processes. Over the last decade, considerable progress has been made in constructing empirical and mechanistic quantitative structure-PK relationships (QSPKR), as well as diverse mechanism-based pharmacodynamic models of drug effects. In this review, traditional and contemporary approaches to developing QSPKR models are discussed, along with selected examples of attempts to couple QSPKR and pharmacodynamic models to anticipate the intensity and time-course of the pharmacological effects of new or related compounds, or quantitative structure-pharmacodynamic relationships modeling. Such models are in accordance with the goals of systems biology and the ideal of designing drugs and delivery systems from first principles.

Structure-based methods for the prediction of drug metabolism

There is a tantalising possibility that we may be able to predict the metabolism of a drug directly from its structure, thus obviating the requirement for animal tests in this area. There are a number of techniques that can be used to estimate a range of events associated with metabolism, and may allow us to achieve this aim. This paper considers the role of (quantitative) structure-activity relationships, and pharmacophore and homology modelling in the prediction of metabolism. Examples are also presented where such approaches have been formalised into expert systems. Clearly, many advances have been made in this area in recent years. Discussed herein is the importance of fully integrating the diverse systems and approaches available to fulfil the aspiration to predict metabolism directly from structure.

Spline functions in convolutional modeling of verapamil bioavailability and bioequivalence. I: conceptual and numerical issues

A cubic spline function for describing the verapamil concentration profile, resulting from the verapamil absorption input to be evaluated, has been used. With this method, the knots are taken to be the data points, which has the advantage of being computationally less complex. Because of its inherently low algorhythmic errors, the spline method is less distorted and more suitable for further data analysis than others. The method has been evaluated using simulated verapamil delayed release tablet concentration data containing various degrees of random noise. The accuracy of the method was determined by how well the estimates of input rate and extent represented the true values. It was found that the accuracy of the method was of the same order of magnitude as the noise level of the data. Spline functions in convolutional modeling of verapamil formulation bioavailability and bioequivalence, as shown in the numerical simulation investigation, are very powerful additional tools for assessing the quality of new verapamil formulations in order to ensure that they are of the same quality as already registered formulations of the drug. The development of such models provides the possibility to avoid additional or larger bioequivalence and/or clinical trials and to thus help shorten the investigation time and registration period.

Quantitative structure-pharmacokinetic relationships for drug clearance by using statistical learning methods

Quantitative structure-pharmacokinetic relationships (QSPkR) have increasingly been used for the prediction of the pharmacokinetic properties of drug leads. Several QSPkR models have been developed to predict the total clearance (CL(tot)) of a compound. These models give good prediction accuracy but they are primarily based on a limited number of related compounds which are significantly lesser in number and diversity than the 503 compounds with known CL(tot) described in the literature. It is desirable to examine whether these and other statistical learning methods can be used for predicting the CL(tot) of a more diverse set of compounds. In this work, three statistical learning methods, general regression neural network (GRNN), support vector regression (SVR) and k-nearest neighbour (KNN) were explored for modeling the CL(tot) of all of the 503 known compounds. Six different sets of molecular descriptors, DS-MIXED, DS-3DMoRSE, DS-ATS, DS-GETAWAY, DS-RDF and DS-WHIM, were evaluated for their usefulness in the prediction of CL(tot). GRNN-, SVR- and KNN-developed models have average-fold errors in the range of 1.63 to 1.96, 1.66-1.95 and 1.90-2.23, respectively. For the best GRNN-, SVR- and KNN-developed models, the percentage of compounds with predicted CL(tot) within two-fold error of actual values are in the range of 61.9-74.3% and are comparable or slightly better than those of earlier studies. QSPkR models developed by using DS-MIXED, which is a collection of constitutional, geometrical, topological and electrotopological descriptors, generally give better prediction accuracies than those developed by using other descriptor sets. These results suggest that GRNN, SVR, and their consensus model are potentially useful for predicting QSPkR properties of drug leads.

Papain entrapment in alginate beads for stability improvement and site-specific delivery: physicochemical characterization and factorial optimization using neural network modeling

This work examines the influence of various process parameters (like sodium alginate concentration, calcium chloride concentration, and hardening time) on papain entrapped in ionotropically cross-linked alginate beads for stability improvement and site-specific delivery to the small intestine using neural network modeling. A 3(3) full-factorial design and feed-forward neural network with multilayer perceptron was used to investigate the effect of process variables on percentage of entrapment, time required for 50% and 90% of the enzyme release, particle size, and angle of repose. Topographical characterization was conducted by scanning electron microscopy, and entrapment was confirmed by Fourier transform infrared spectroscopy and differential scanning calorimetry. Times required for 50% (T(50)) and 90% (T(90)) of enzyme release were increased in all 3 of the process variables. Percentage entrapment and particle size were found to be directly proportional to sodium alginate concentration and inversely proportional to calcium chloride concentration and hardening time, whereas angle of repose and degree of cross-linking showed exactly opposite proportionality. Beads with >90% entrapment and T(50) of <10 minutes could be obtained at the low levels of all 3 of the process variables. The inability of beads to dissolve in acidic environment, with complete dissolution in buffer of pH >or=6.8, showed the suitability of beads to release papain into the small intestine. The shelf-life of the capsules prepared using the papain-loaded alginate beads was found to be 3.60 years compared with 1.01 years of the marketed formulation. It can be inferred from the above results that the proposed methodology can be used to prepare papain-loaded alginate beads for stability improvement and site-specific delivery.

New Mathematical Methods in Pharmacokinetic Modeling

In recent years, several new methods for the mathematical modeling have gradually emerged in pharmacokinetics, and the development of pharmacokinetic models based on these methods has become one of the most rapidly growing and exciting application-oriented sub-disciplines of the mathematical modeling. The goals of our MiniReview are twofold: i) to briefly outline fundamental ideas of some new modeling methods that have not been widely utilized in pharmacokinetics as yet, i.e. the methods based on the following concepts: linear time-invariant dynamic system, artificial-neural-network, fuzzy-logic, and fractal; ii) to arouse the interest of pharmacological, toxicological, and pharmaceutical scientists in the given methods, by sketching some application examples which indicate the good performance and perspective of these methods in solving pharmacokinetic problems.