Gaussian Processes for Classification: QSAR Modeling of ADMET and Target Activity

Advances in Modeling Approaches for Oral Drug Delivery: Artificial Intelligence, Physiologically-Based Pharmacokinetics, and First-Principles Models

Oral drug absorption is the primary route for drug administration. However, this process hinges on multiple factors, including the drug's physicochemical properties, formulation characteristics, and gastrointestinal physiology. Given its intricacy and the exorbitant costs associated with experimentation, the trial-and-error method proves prohibitively expensive. Theoretical models have emerged as a cost-effective alternative by assimilating data from diverse experiments and theoretical considerations. These models fall into three categories: (i) data-driven models, encompassing classical pharmacokinetics, quantitative-structure models (QSAR), and machine/deep learning; (ii) mechanism-based models, which include quasi-equilibrium, steady-state, and physiologically-based pharmacokinetics models; and (iii) first principles models, including molecular dynamics and continuum models. This review provides an overview of recent modeling endeavors across these categories while evaluating their respective advantages and limitations. Additionally, a primer on partial differential equations and their numerical solutions is included in the appendix, recognizing their utility in modeling physiological systems despite their mathematical complexity limiting widespread application in this field.

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.

Machine Learning in Chemoinformatics and Medicinal Chemistry

In chemoinformatics and medicinal chemistry, machine learning has evolved into an important approach. In recent years, increasing computational resources and new deep learning algorithms have put machine learning onto a new level, addressing previously unmet challenges in pharmaceutical research. In silico approaches for compound activity predictions, de novo design, and reaction modeling have been further advanced by new algorithmic developments and the emergence of big data in the field. Herein, novel applications of machine learning and deep learning in chemoinformatics and medicinal chemistry are reviewed. Opportunities and challenges for new methods and applications are discussed, placing emphasis on proper baseline comparisons, robust validation methodologies, and new applicability domains. Expected final online publication date for the Annual Review of Biomedical Data Science, Volume 5 is August 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

The effect of noise on the predictive limit of QSAR models

A key challenge in the field of Quantitative Structure Activity Relationships (QSAR) is how to effectively treat experimental error in the training and evaluation of computational models. It is often assumed in the field of QSAR that models cannot produce predictions which are more accurate than their training data. Additionally, it is implicitly assumed, by necessity, that data points in test sets or validation sets do not contain error, and that each data point is a population mean. This work proposes the hypothesis that QSAR models can make predictions which are more accurate than their training data and that the error-free test set assumption leads to a significant misevaluation of model performance. This work used 8 datasets with six different common QSAR endpoints, because different endpoints should have different amounts of experimental error associated with varying complexity of the measurements. Up to 15 levels of simulated Gaussian distributed random error was added to the datasets, and models were built on the error laden datasets using five different algorithms. The models were trained on the error laden data, evaluated on error-laden test sets, and evaluated on error-free test sets. The results show that for each level of added error, the RMSE for evaluation on the error free test sets was always better. The results support the hypothesis that, at least under the conditions of Gaussian distributed random error, QSAR models can make predictions which are more accurate than their training data, and that the evaluation of models on error laden test and validation sets may give a flawed measure of model performance. These results have implications for how QSAR models are evaluated, especially for disciplines where experimental error is very large, such as in computational toxicology.

Artificial intelligence to deep learning: machine intelligence approach for drug discovery

Drug designing and development is an important area of research for pharmaceutical companies and chemical scientists. However, low efficacy, off-target delivery, time consumption, and high cost impose a hurdle and challenges that impact drug design and discovery. Further, complex and big data from genomics, proteomics, microarray data, and clinical trials also impose an obstacle in the drug discovery pipeline. Artificial intelligence and machine learning technology play a crucial role in drug discovery and development. In other words, artificial neural networks and deep learning algorithms have modernized the area. Machine learning and deep learning algorithms have been implemented in several drug discovery processes such as peptide synthesis, structure-based virtual screening, ligand-based virtual screening, toxicity prediction, drug monitoring and release, pharmacophore modeling, quantitative structure-activity relationship, drug repositioning, polypharmacology, and physiochemical activity. Evidence from the past strengthens the implementation of artificial intelligence and deep learning in this field. Moreover, novel data mining, curation, and management techniques provided critical support to recently developed modeling algorithms. In summary, artificial intelligence and deep learning advancements provide an excellent opportunity for rational drug design and discovery process, which will eventually impact mankind. The primary concern associated with drug design and development is time consumption and production cost. Further, inefficiency, inaccurate target delivery, and inappropriate dosage are other hurdles that inhibit the process of drug delivery and development. With advancements in technology, computer-aided drug design integrating artificial intelligence algorithms can eliminate the challenges and hurdles of traditional drug design and development. Artificial intelligence is referred to as superset comprising machine learning, whereas machine learning comprises supervised learning, unsupervised learning, and reinforcement learning. Further, deep learning, a subset of machine learning, has been extensively implemented in drug design and development. The artificial neural network, deep neural network, support vector machines, classification and regression, generative adversarial networks, symbolic learning, and meta-learning are examples of the algorithms applied to the drug design and discovery process. Artificial intelligence has been applied to different areas of drug design and development process, such as from peptide synthesis to molecule design, virtual screening to molecular docking, quantitative structure-activity relationship to drug repositioning, protein misfolding to protein-protein interactions, and molecular pathway identification to polypharmacology. Artificial intelligence principles have been applied to the classification of active and inactive, monitoring drug release, pre-clinical and clinical development, primary and secondary drug screening, biomarker development, pharmaceutical manufacturing, bioactivity identification and physiochemical properties, prediction of toxicity, and identification of mode of action.

Recent developments in predicting CYP-independent metabolism

As lead optimization efforts have successfully reduced metabolic liabilities due to cytochrome P450 (CYP)-mediated metabolism, there has been an increase in the frequency of involvement of non-CYP enzymes in the metabolism of investigational compounds. Although there have been numerous notable advancements in the characterization of non-CYP enzymes with respect to their localization, reaction mechanisms, species differences and identification of typical substrates, accurate prediction of non-CYP-mediated clearance, with a particular emphasis with the difficulties in accounting for any extrahepatic contributions, remains a challenge. The current manuscript comprehensively summarizes the recent advancements in the prediction of drug metabolism and the in vitro to in vitro extrapolation of clearance for substrates of non-CYP drug metabolizing enzymes.

Improving drug safety predictions by reducing poor analytical practices

Predicting the safety of a drug from preclinical data is a major challenge in drug discovery, and progressing an unsafe compound into the clinic puts patients at risk and wastes resources. In drug safety pharmacology and related fields, methods and analytical decisions known to provide poor predictions are common and include creating arbitrary thresholds, binning continuous values, giving all assays equal weight, and multiple reuse of information. In addition, the metrics used to evaluate models often omit important criteria and models’ performance on new data are often not assessed rigorously. Prediction models with these problems are unlikely to perform well, and published models suffer from many of these issues. We describe these problems in detail, demonstrate their negative consequences, and propose simple solutions that are standard in other disciplines where predictive modelling is used.

In Silico ADMET Evaluation of Natural DPP-IV Inhibitors for Rational Drug Design against Diabetes

BACKGROUND

As a metabolic and lifestyle disorder, diabetes mellitus poses a prodigious health risk. Out of the many key targets, DPP-IV is one of the very imperative therapeutic targets for the treatment of diabetic patients.

METHODS

In our current study, we have done the in silico simulations of ADME-T properties for naturally originated potent DPP-IV inhibitors like quinovic acid, stigmasterol, quinovic acid-3-beta-D-glycopyranoside, zygophyloside E, and lupeol. Structural topographies associated with different pharmacokinetic properties have been systematically assessed.

RESULTS

Glycosylation on quinovic acid is found to be noteworthy for the improvement of pharmacokinetic and toxicological properties, which leads to the prediction that zygophyloside E can be further tailored down to get the lead DPP-IV inhibitor.

CONCLUSION

This assessment provides useful insight into the future development of novel drugs for the treatment of diabetes mellitus.

Practical Applications of Deep Learning To Impute Heterogeneous Drug Discovery Data

Contemporary deep learning approaches still struggle to bring a useful improvement in the field of drug discovery because of the challenges of sparse, noisy, and heterogeneous data that are typically encountered in this context. We use a state-of-the-art deep learning method, Alchemite, to impute data from drug discovery projects, including multitarget biochemical activities, phenotypic activities in cell-based assays, and a variety of absorption, distribution, metabolism, and excretion (ADME) endpoints. The resulting model gives excellent predictions for activity and ADME endpoints, offering an average increase in R² of 0.22 versus quantitative structure-activity relationship methods. The model accuracy is robust to combining data across uncorrelated endpoints and projects with different chemical spaces, enabling a single model to be trained for all compounds and endpoints. We demonstrate improvements in accuracy on the latest chemistry and data when updating models with new data as an ongoing medicinal chemistry project progresses.

Advances in the study of drug metabolism - symposium report of the 12th Meeting of the International Society for the Study of Xenobiotics (ISSX)

The 12th International Society for the Study of Xenobiotics (ISSX) meeting, held in Portland, OR, USA from July 28 to 31, 2019, was attended by diverse members of the pharmaceutical sciences community. The ISSX New Investigators Group provides learning and professional growth opportunities for student and early career members of ISSX. To share meeting content with those who were unable to attend, the ISSX New Investigators herein elected to highlight the "Advances in the Study of Drug Metabolism" symposium, as it engaged attendees with diverse backgrounds. This session covered a wide range of current topics in drug metabolism research including predicting sites and routes of metabolism, metabolite identification, ligand docking, and medicinal and natural products chemistry, and highlighted approaches complemented by computational modeling. In silico tools have been increasingly applied in both academic and industrial settings, alongside traditional and evolving in vitro techniques, to strengthen and streamline pharmaceutical research. Approaches such as quantum mechanics simulations facilitate understanding of reaction energetics toward prediction of routes and sites of drug metabolism. Furthermore, in tandem with crystallographic and orthogonal wet lab techniques for structural validation of drug metabolizing enzymes, in silico models can aid understanding of substrate recognition by particular enzymes, identify metabolic soft spots and predict toxic metabolites for improved molecular design. Of note, integration of chemical synthesis and biosynthesis using natural products remains an important approach for identifying new chemical scaffolds in drug discovery. These subjects, compiled by the symposium organizers, presenters, and the ISSX New Investigators Group, are discussed in this review.

An Analysis of QSAR Research Based on Machine Learning Concepts

Quantitative Structure-Activity Relationship (QSAR) is a popular approach developed to correlate chemical molecules with their biological activities based on their chemical structures. Machine learning techniques have proved to be promising solutions to QSAR modeling. Due to the significant role of machine learning strategies in QSAR modeling, this area of research has attracted much attention from researchers. A considerable amount of literature has been published on machine learning based QSAR modeling methodologies whilst this domain still suffers from lack of a recent and comprehensive analysis of these algorithms. This study systematically reviews the application of machine learning algorithms in QSAR, aiming to provide an analytical framework. For this purpose, we present a framework called 'ML-QSAR'. This framework has been designed for future research to: a) facilitate the selection of proper strategies among existing algorithms according to the application area requirements, b) help to develop and ameliorate current methods and c) providing a platform to study existing methodologies comparatively. In ML-QSAR, first a structured categorization is depicted which studied the QSAR modeling research based on machine models. Then several criteria are introduced in order to assess the models. Finally, inspired by aforementioned criteria the qualitative analysis is carried out.

Investigation of 3D pharmacophore of N-benzyl benzamide molecules of melanogenesis inhibitors using a new descriptor Klopman index: uncertainties in model

We used a new descriptor called the Klopman index in our software of the "molecular comparative electron topology" (MCET) method to reduce the uncertainty resulting from the descriptors used in QSAR studies. The 3D pharmacophore model (3D-PhaM), which can demonstrate three-dimensional interaction between the ligand -receptor (L-R), is only possible with local reactive descriptors (LRD). The Klopman index, containing both Coulombic and frontier orbital and interactions of atoms of the ligand, is a good LRD. Molecular conformers having the best matching atoms with the template conformer can be selected as one of the most suitable spatial structures for interaction with the receptor, and the LRD values of the atoms in this conformer serve to determine 3D-PhaM. The 3D-PhaM of the N-benzyl benzamide derivatives, such as the melanogenesis inhibitor, was determined by ligand-based MCET and confirmed by the structure-based FlexX docking method. For compounds of the training set (42) and the external cross validation test set (6), the Q² (0.862) and R² (0.913) of the statistical parameters were calculated, respectively, and were checked by r_m² (0.85) of the stringent validation.

A novel adaptive ensemble classification framework for ADME prediction

AECF is a GA based ensemble method. It includes four components which are (1) data balancing, (2) generating individual models, (3) combining individual models, and (4) optimizing the ensemble.

Comparison of the Predictive Performance and Interpretability of Random Forest and Linear Models on Benchmark Data Sets

The ability to interpret the predictions made by quantitative structure-activity relationships (QSARs) offers a number of advantages. While QSARs built using nonlinear modeling approaches, such as the popular Random Forest algorithm, might sometimes be more predictive than those built using linear modeling approaches, their predictions have been perceived as difficult to interpret. However, a growing number of approaches have been proposed for interpreting nonlinear QSAR models in general and Random Forest in particular. In the current work, we compare the performance of Random Forest to those of two widely used linear modeling approaches: linear Support Vector Machines (SVMs) (or Support Vector Regression (SVR)) and partial least-squares (PLS). We compare their performance in terms of their predictivity as well as the chemical interpretability of the predictions using novel scoring schemes for assessing heat map images of substructural contributions. We critically assess different approaches for interpreting Random Forest models as well as for obtaining predictions from the forest. We assess the models on a large number of widely employed public-domain benchmark data sets corresponding to regression and binary classification problems of relevance to hit identification and toxicology. We conclude that Random Forest typically yields comparable or possibly better predictive performance than the linear modeling approaches and that its predictions may also be interpreted in a chemically and biologically meaningful way. In contrast to earlier work looking at interpretation of nonlinear QSAR models, we directly compare two methodologically distinct approaches for interpreting Random Forest models. The approaches for interpreting Random Forest assessed in our article were implemented using open-source programs that we have made available to the community. These programs are the rfFC package ( https://r-forge.r-project.org/R/?group_id=1725 ) for the R statistical programming language and the Python program HeatMapWrapper [ https://doi.org/10.5281/zenodo.495163 ] for heat map generation.

Mode of Action Analyses of Neferine, a Bisbenzylisoquinoline Alkaloid of Lotus (Nelumbo nucifera) against Multidrug-Resistant Tumor Cells

Neferine, a bisbenzylisoquinoline alkaloid isolated from the green seed embryos of Lotus (Nelumbo nucifera Gaertn), has been previously shown to have various anti-cancer effects. In the present study, we evaluated the effect of neferine in terms of P-glycoprotein (P-gp) inhibition via in vitro cytotoxicity assays, R123 uptake assays in drug-resistant cancer cells, in silico molecular docking analysis on human P-gp and in silico absorption, distribution, metabolism, and excretion (ADME), quantitative structure activity relationships (QSAR) and toxicity analyses. Lipinski rule of five were mainly considered for the ADME evaluation and the preset descriptors including number of hydrogen bond donor, acceptor, hERG IC50, logp, logD were considered for the QSAR analyses. Neferine revealed higher toxicity toward paclitaxel- and doxorubicin-resistant breast, lung or colon cancer cells, implying collateral sensitivity of these cells toward neferine. Increased R123 uptake was observed in a comparable manner to the control P-gp inhibitor, verapamil. Molecular docking analyses revealed that neferine still interacts with P-gp, even if R123 was pre-bound. Bioinformatical ADME and toxicity analyses revealed that neferine possesses the druggability parameters with no predicted toxicity. In conclusion, neferine may allocate the P-gp drug-binding pocket and prevent R123 binding in agreement with P-gp inhibition experiments, where neferine increased R123 uptake.

Combined QSAR-based virtual screening and fluorescence binding assay to identify natural product mediators of Interferon Regulatory Factor 7 (IRF-7) in pulmonary infection

Interferon regulatory factor-7 (IRF-7) is involved in pulmonary infection and pneumonia. Here, a synthetic strategy that combined quantitative structure-activity relationship (QSAR)-based virtual screening and in vitro binding assay was described to identify new and potent mediator ligands of IRF-7 from natural products. In the procedure, a QSAR scoring function was developed and validated using Gaussian process (GP) regression and a structure-based set of protein-ligand affinity data. By integrating hotspot pocket prediction, pharmacokinetics profile analysis and molecular docking calculations, the scoring function was successfully applied to virtual screening against a large library of structurally diverse, drug-like natural products. With the method we were able to identify a number of potential hits, from which several compounds were found to have moderate or high affinity to IRF-7 using fluorescence binding assays, with dissociation constants K_d at micromolar level. We have also examined the structural basis and noncovalent interactions of computationally modelled IRF-7 complex with its potent ligands. It is revealed that hydrophobic forces and van der Waals contacts play a central role in stabilization of the complex architecture, while few hydrogen bonds confer additional specificity for the protein-ligand recognition.

Discovery of Novel Hepatitis C Virus NS5B Polymerase Inhibitors by Combining Random Forest, Multiple e-Pharmacophore Modeling and Docking

The NS5B polymerase is one of the most attractive targets for developing new drugs to block Hepatitis C virus (HCV) infection. We describe the discovery of novel potent HCV NS5B polymerase inhibitors by employing a virtual screening (VS) approach, which is based on random forest (RB-VS), e-pharmacophore (PB-VS), and docking (DB-VS) methods. In the RB-VS stage, after feature selection, a model with 16 descriptors was used. In the PB-VS stage, six energy-based pharmacophore (e-pharmacophore) models from different crystal structures of the NS5B polymerase with ligands binding at the palm I, thumb I and thumb II regions were used. In the DB-VS stage, the Glide SP and XP docking protocols with default parameters were employed. In the virtual screening approach, the RB-VS, PB-VS and DB-VS methods were applied in increasing order of complexity to screen the InterBioScreen database. From the final hits, we selected 5 compounds for further anti-HCV activity and cellular cytotoxicity assay. All 5 compounds were found to inhibit NS5B polymerase with IC50 values of 2.01-23.84 μM and displayed anti-HCV activities with EC50 values ranging from 1.61 to 21.88 μM, and all compounds displayed no cellular cytotoxicity (CC50 > 100 μM) except compound N2, which displayed weak cytotoxicity with a CC50 value of 51.3 μM. The hit compound N2 had the best antiviral activity against HCV, with a selective index of 32.1. The 5 hit compounds with new scaffolds could potentially serve as NS5B polymerase inhibitors through further optimization and development.

Predicting human intestinal absorption of diverse chemicals using ensemble learning based QSAR modeling approaches

Human intestinal absorption (HIA) of the drugs administered through the oral route constitutes an important criterion for the candidate molecules. The computational approach for predicting the HIA of molecules may potentiate the screening of new drugs. In this study, ensemble learning (EL) based qualitative and quantitative structure-activity relationship (SAR) models (gradient boosted tree, GBT and bagged decision tree, BDT) have been established for the binary classification and HIA prediction of the chemicals, using the selected molecular descriptors. The structural diversity of the chemicals and the nonlinear structure in the considered data were tested by the similarity index and Brock-Dechert-Scheinkman statistics. The external predictive power of the developed SAR models was evaluated through the internal and external validation procedures recommended in the literature. All the statistical criteria parameters derived for the performance of the constructed SAR models were above their respective thresholds suggesting for their robustness for future applications. In complete data, the qualitative SAR models rendered classification accuracy of >99%, while the quantitative SAR models yielded correlation (R(2)) of >0.91 between the measured and predicted HIA values. The performances of the EL-based SAR models were also compared with the linear models (linear discriminant analysis, LDA and multiple linear regression, MLR). The GBT and BDT SAR models performed better than the LDA and MLR methods. A comparison of our models with the previously reported QSARs for HIA prediction suggested for their better performance. The results suggest for the appropriateness of the developed SAR models to reliably predict the HIA of structurally diverse chemicals and can serve as useful tools for the initial screening of the molecules in the drug development process.

In silico Prediction of Aqueous Solubility: a Comparative Study of Local and Global Predictive Models

32 Quantitative Structure-Property Relationship (QSPR) models were constructed for prediction of aqueous intrinsic solubility of liquid and crystalline chemicals. Data sets contained 1022 liquid and 2615 crystalline compounds. Multiple Linear Regression (MLR), Support Vector Machine (SVM) and Random Forest (RF) methods were used to construct global models, and k-nearest neighbour (kNN), Arithmetic Mean Property (AMP) and Local Regression Property (LoReP) were used to construct local models. A set of the best QSPR models was obtained: for liquid chemicals with RMSE (root mean square error) of prediction in the range 0.50-0.60 log unit; for crystalline chemicals 0.80-0.90 log unit. In the case of global models the large number of descriptors makes mechanistic interpretation difficult. The local models use only one or two descriptors, so that a medicinal chemist working with sets of structurally-related chemicals can readily estimate their solubility. However, construction of stable local models requires the presence of closely related neighbours for each chemical considered. It is probable that a consensus of global and local QSPR models will be the optimal approach for construction of stable predictive QSPR models with mechanistic interpretation.

Proteochemometric modeling in a Bayesian framework

Proteochemometrics (PCM) is an approach for bioactivity predictive modeling which models the relationship between protein and chemical information. Gaussian Processes (GP), based on Bayesian inference, provide the most objective estimation of the uncertainty of the predictions, thus permitting the evaluation of the applicability domain (AD) of the model. Furthermore, the experimental error on bioactivity measurements can be used as input for this probabilistic model.

In this study, we apply GP implemented with a panel of kernels on three various (and multispecies) PCM datasets. The first dataset consisted of information from 8 human and rat adenosine receptors with 10,999 small molecule ligands and their binding affinity. The second consisted of the catalytic activity of four dengue virus NS3 proteases on 56 small peptides. Finally, we have gathered bioactivity information of small molecule ligands on 91 aminergic GPCRs from 9 different species, leading to a dataset of 24,593 datapoints with a matrix completeness of only 2.43%.

GP models trained on these datasets are statistically sound, at the same level of statistical significance as Support Vector Machines (SVM), with R02 values on the external dataset ranging from 0.68 to 0.92, and RMSEP values close to the experimental error. Furthermore, the best GP models obtained with the normalized polynomial and radial kernels provide intervals of confidence for the predictions in agreement with the cumulative Gaussian distribution. GP models were also interpreted on the basis of individual targets and of ligand descriptors. In the dengue dataset, the model interpretation in terms of the amino-acid positions in the tetra-peptide ligands gave biologically meaningful results.

Computer modeling of blood brain barrier permeability of physiologically active compounds

At present work discusses the current level of computer modeling the relationship structure of organic compounds and drugs and their ability to penetrate the BBB. All descriptors that influence to this permeability within classification and regression QSAR models are generalized and analyzed. The crucial role of H-bond in processes both passive, and active transport across BBB is observed. It is concluded that further research should be focused on interpretation the spatial structure of a full-size P-glycoprotein molecule with high resolution and the creation of QSAR models describing the quantitative relationship between structure and active transport of substances across BBB.

Computational methods in drug discovery

Computer-aided drug discovery/design methods have played a major role in the development of therapeutically important small molecules for over three decades. These methods are broadly classified as either structure-based or ligand-based methods. Structure-based methods are in principle analogous to high-throughput screening in that both target and ligand structure information is imperative. Structure-based approaches include ligand docking, pharmacophore, and ligand design methods. The article discusses theory behind the most important methods and recent successful applications. Ligand-based methods use only ligand information for predicting activity depending on its similarity/dissimilarity to previously known active ligands. We review widely used ligand-based methods such as ligand-based pharmacophores, molecular descriptors, and quantitative structure-activity relationships. In addition, important tools such as target/ligand data bases, homology modeling, ligand fingerprint methods, etc., necessary for successful implementation of various computer-aided drug discovery/design methods in a drug discovery campaign are discussed. Finally, computational methods for toxicity prediction and optimization for favorable physiologic properties are discussed with successful examples from literature.

Physicochemical and DMPK in silico models: facilitating their use by medicinal chemists

It is known that the developability of drugs is related to their physicochemical and DMPK properties. Given the time and expense involved in discovering and developing new drugs, maximizing the chance of success by calculating properties ahead of chemical synthesis and testing, and only acting on those candidates whose properties fall into a desired range, would seem to make sense. This paper provides an overview of calculable physicochemical and DMPK properties, an assessment of their relative difficulty of their calculation and accuracy, and available software. Methods companies have employed to communicate results will be discussed, including the use of composite scoring functions and ranking schemes. Calculations do no good if chemists will not use them to prioritize synthesis decisions. Strategies are presented for facilitating model usage. An approach adopted at Genentech for presenting results that involves the close coupling of property calculations with 3D structure based drug design is described.

Towards in silico identification of the human ether-a-go-go-related gene channel blockers: discriminative vs. generative classification models

HERG potassium channels have a critical role in the normal electrical activity of the heart. The blockade of hERG channels in heart cells can result in a potentially fatal disorder called long QT syndrome. HERG channels can be blocked by compounds with diverse structures belonging to several drug classes. Presented herein are generative (Generative Topographic Maps) and discriminative (Support Vector Machines) classification models to categorize the compounds in silico into active and inactive classes by using different types of descriptors. The predictive performance of discriminative and generative classification models has been compared. Here, the possibility of using Generative Topographic Maps as an approach for applicability domain analysis and to generate probability-based descriptors was demonstrated to our knowledge for the first time. Comparison of obtained results with the models developed by other teams on the same data set has been performed.

Chemoinformatics and chemical genomics: potential utility of in silico methods

Computational life sciences and informatics are inseparably intertwined and they lie at the heart of modern biology, predictive quantitative modeling and high-performance computing. Two of the applied biological disciplines that are poised to benefit from such progress are pharmacology and toxicology. This review will describe in silico chemoinformatics methods such as (quantitative) structure-activity relationship modeling and will overview how chemoinformatic technologies are considered in applied regulatory research. Given the post-genomics era and large-scale repositories of omics data that are available, this review will also address potential applications of in silico techniques in chemical genomics. Chemical genomics utilizes small molecules to explore the complex biological phenomena that may not be not amenable to straightforward genetic approach. The reader will gain the understanding that chemoinformatics stands at the interface of chemistry and biology with enabling systems for mapping, statistical modeling, pattern recognition, imaging and database tools. The great potential of these technologies to help address complex issues in the toxicological sciences is appreciated with the applied goal of the protection of public health.

ADMET evaluation in drug discovery. 12. Development of binary classification models for prediction of hERG potassium channel blockage

Inhibition of the human ether-a-go-go related gene (hERG) potassium channel may result in QT interval prolongation, which causes severe cardiac side effects and is a major problem in clinical studies of drug candidates. The development of in silico tools to filter out potential hERG potassium channel blockers in early stages of the drug discovery process is of considerable interest. Here, a diverse set of 806 compounds with hERG inhibition data was assembled, and the binary hERG classification models using naive Bayesian classification and recursive partitioning (RP) techniques were established and evaluated. The naive Bayesian classifier based on molecular properties and the ECFP_8 fingerprints yielded 84.8% accuracy for the training set using the leave-one-out (LOO) cross-validation procedure and 85% accuracy for the test set of 120 molecules. For the two additional test sets, the model achieved 89.4% accuracy for the WOMBAT-PK test set, and 86.1% accuracy for the PubChem test set. The naive Bayesian classifiers gave better predictions than the RP classifiers. Moreover, the Bayesian classifier, employing molecular fingerprints, highlights the important structural fragments favorable or unfavorable for hERG potassium channel blockage, which offers extra valuable information for the design of compounds avoiding undesirable hERG activity.

Decision tree models for data mining in hit discovery

INTRODUCTION

Decision tree induction (DTI) is a powerful means of modeling data without much prior preparation. Models are readable by humans, robust and easily applied in real-world applications, features that are mutually exclusive in other commonly used machine learning paradigms. While DTI is widely used in disciplines ranging from economics to medicine, they are an intriguing option in pharmaceutical research, especially when dealing with large data stores.

AREAS COVERED

This review covers the automated technologies available for creating decision trees and other rules efficiently, even from large datasets such as chemical libraries. The authors discuss the need for properly documented and validated models. Lastly, the authors cover several case studies in hit discovery, drug metabolism and toxicology, and drug surveillance, and compare them with other established techniques.

EXPERT OPINION

DTI is a competitive and easy-to-use tool in basic research as well as in hit and drug discovery. Its strengths lie in its ability to handle all sorts of different data formats, the visual nature of the models, and the small computational effort needed for implementation in real-world systems. Limitations include lack of robustness and over-fitted models for certain types of data. As with any modeling technique, proper validation and quality measures are of utmost importance.

A classification study of respiratory Syncytial Virus (RSV) inhibitors by variable selection with random forest

Experimental pEC₅₀s for 216 selective respiratory syncytial virus (RSV) inhibitors are used to develop classification models as a potential screening tool for a large library of target compounds. Variable selection algorithm coupled with random forests (VS-RF) is used to extract the physicochemical features most relevant to the RSV inhibition. Based on the selected small set of descriptors, four other widely used approaches, i.e., support vector machine (SVM), Gaussian process (GP), linear discriminant analysis (LDA) and k nearest neighbors (kNN) routines are also employed and compared with the VS-RF method in terms of several of rigorous evaluation criteria. The obtained results indicate that the VS-RF model is a powerful tool for classification of RSV inhibitors, producing the highest overall accuracy of 94.34% for the external prediction set, which significantly outperforms the other four methods with the average accuracy of 80.66%. The proposed model with excellent prediction capacity from internal to external quality should be important for screening and optimization of potential RSV inhibitors prior to chemical synthesis in drug development.