Pharmaceutical Perspectives of Nonlinear QSAR Strategies

Predictive Modelling in pharmacokinetics: from in-silico simulations to personalized medicine

INTRODUCTION

Pharmacokinetic parameters assessment is a critical aspect of drug discovery and development, yet challenges persist due to limited training data. Despite advancements in machine learning and in-silico predictions, scarcity of data hampers accurate prediction of drug candidates' pharmacokinetic properties.

AREAS COVERED

The study highlights current developments in human pharmacokinetic prediction, talks about attempts to apply synthetic approaches for molecular design, and searches several databases, including Scopus, PubMed, Web of Science, and Google Scholar. The article stresses importance of rigorous analysis of machine learning model performance in assessing progress and explores molecular modeling (MM) techniques, descriptors, and mathematical approaches. Transitioning to clinical drug development, article highlights AI (Artificial Intelligence) based computer models optimizing trial design, patient selection, dosing strategies, and biomarker identification. In-silico models, including molecular interactomes and virtual patients, predict drug performance across diverse profiles, underlining the need to align model results with clinical studies for reliability. Specialized training for human specialists in navigating predictive models is deemed critical. Pharmacogenomics, integral to personalized medicine, utilizes predictive modeling to anticipate patient responses, contributing to more efficient healthcare system. Challenges in realizing potential of predictive modeling, including ethical considerations and data privacy concerns, are acknowledged.

EXPERT OPINION

AI models are crucial in drug development, optimizing trials, patient selection, dosing, and biomarker identification and hold promise for streamlining clinical investigations.

Computational Approaches in Preclinical Studies on Drug Discovery and Development

Because undesirable pharmacokinetics and toxicity are significant reasons for the failure of drug development in the costly late stage, it has been widely recognized that drug ADMET properties should be considered as early as possible to reduce failure rates in the clinical phase of drug discovery. Concurrently, drug recalls have become increasingly common in recent years, prompting pharmaceutical companies to increase attention toward the safety evaluation of preclinical drugs. In vitro and in vivo drug evaluation techniques are currently more mature in preclinical applications, but these technologies are costly. In recent years, with the rapid development of computer science, in silico technology has been widely used to evaluate the relevant properties of drugs in the preclinical stage and has produced many software programs and in silico models, further promoting the study of ADMET in vitro. In this review, we first introduce the two ADMET prediction categories (molecular modeling and data modeling). Then, we perform a systematic classification and description of the databases and software commonly used for ADMET prediction. We focus on some widely studied ADMT properties as well as PBPK simulation, and we list some applications that are related to the prediction categories and web tools. Finally, we discuss challenges and limitations in the preclinical area and propose some suggestions and prospects for the future.

Aqueous Drug Solubility: What Do We Measure, Calculate and QSPR Predict?

Detailed critical analysis of publications devoted to QSPR of aqueous solubility is presented in the review with discussion of four types of aqueous solubility (three different thermodynamic solubilities with unknown solute structure, intrinsic solubility, solubility in physiological media at pH=7.4 and kinetic solubility), variety of molecular descriptors (from topological to quantum chemical), traditional statistical and machine learning methods as well as original QSPR models.

Applying Mondrian Cross-Conformal Prediction To Estimate Prediction Confidence on Large Imbalanced Bioactivity Data Sets

Conformal prediction has been proposed as a more rigorous way to define prediction confidence compared to other application domain concepts that have earlier been used for QSAR modeling. One main advantage of such a method is that it provides a prediction region potentially with multiple predicted labels, which contrasts to the single valued (regression) or single label (classification) output predictions by standard QSAR modeling algorithms. Standard conformal prediction might not be suitable for imbalanced data sets. Therefore, Mondrian cross-conformal prediction (MCCP) which combines the Mondrian inductive conformal prediction with cross-fold calibration sets has been introduced. In this study, the MCCP method was applied to 18 publicly available data sets that have various imbalance levels varying from 1:10 to 1:1000 (ratio of active/inactive compounds). Our results show that MCCP in general performed well on bioactivity data sets with various imbalance levels. More importantly, the method not only provides confidence of prediction and prediction regions compared to standard machine learning methods but also produces valid predictions for the minority class. In addition, a compound similarity based nonconformity measure was investigated. Our results demonstrate that although it gives valid predictions, its efficiency is much worse than that of model dependent metrics.

Predicting Subtype Selectivity for Adenosine Receptor Ligands with Three-Dimensional Biologically Relevant Spectrum (BRS-3D)

Adenosine receptors (ARs) are potential therapeutic targets for Parkinson’s disease, diabetes, pain, stroke and cancers. Prediction of subtype selectivity is therefore important from both therapeutic and mechanistic perspectives. In this paper, we introduced a shape similarity profile as molecular descriptor, namely three-dimensional biologically relevant spectrum (BRS-3D), for AR selectivity prediction. Pairwise regression and discrimination models were built with the support vector machine methods. The average determination coefficient (r²) of the regression models was 0.664 (for test sets). The 2B-3 (A_2Bvs A₃) model performed best with q² = 0.769 for training sets (10-fold cross-validation), and r² = 0.766, RMSE = 0.828 for test sets. The models’ robustness and stability were validated with 100 times resampling and 500 times Y-randomization. We compared the performance of BRS-3D with 3D descriptors calculated by MOE. BRS-3D performed as good as, or better than, MOE 3D descriptors. The performances of the discrimination models were also encouraging, with average accuracy (ACC) 0.912 and MCC 0.792 (test set). The 2A-3 (A_2Avs A₃) selectivity discrimination model (ACC = 0.882 and MCC = 0.715 for test set) outperformed an earlier reported one (ACC = 0.784). These results demonstrated that, through multiple conformation encoding, BRS-3D can be used as an effective molecular descriptor for AR subtype selectivity prediction.

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.

Prediction and interpretation of the lipophilicity of small peptides

Peptide-based drug discovery has considerably expanded and solid in silico tools for the prediction of physico-chemical properties of peptides are urgently needed. In this work we tested some combinations of descriptors/algorithms to find the best model to predict [Formula: see text] of a series of peptides. To do that we evaluate the models statistical performances but also their skills in providing a reliable deconvolution of the balance of intermolecular forces governing the partitioning phenomenon. Results prove that a PLS model based on VolSurf+ descriptors is the best tool to predict [Formula: see text] of neutral and ionised peptides. The mechanistic interpretation also reveals that the inclusion in the chemical structure of a HBD group is more efficient in decreasing lipophilicity than the inclusion of a HBA group.

In silico mechanistic profiling to probe small molecule binding to sulfotransferases

Drug metabolizing enzymes play a key role in the metabolism, elimination and detoxification of xenobiotics, drugs and endogenous molecules. While their principal role is to detoxify organisms by modifying compounds, such as pollutants or drugs, for a rapid excretion, in some cases they render their substrates more toxic thereby inducing severe side effects and adverse drug reactions, or their inhibition can lead to drug–drug interactions. We focus on sulfotransferases (SULTs), a family of phase II metabolizing enzymes, acting on a large number of drugs and hormones and showing important structural flexibility. Here we report a novel in silico structure-based approach to probe ligand binding to SULTs. We explored the flexibility of SULTs by molecular dynamics (MD) simulations in order to identify the most suitable multiple receptor conformations for ligand binding prediction. Then, we employed structure-based docking-scoring approach to predict ligand binding and finally we combined the predicted interaction energies by using a QSAR methodology. The results showed that our protocol successfully prioritizes potent binders for the studied here SULT1 isoforms, and give new insights on specific molecular mechanisms for diverse ligands’ binding related to their binding sites plasticity. Our best QSAR models, introducing predicted protein-ligand interaction energy by using docking, showed accuracy of 67.28%, 78.00% and 75.46%, for the isoforms SULT1A1, SULT1A3 and SULT1E1, respectively. To the best of our knowledge our protocol is the first in silico structure-based approach consisting of a protein-ligand interaction analysis at atomic level that considers both ligand and enzyme flexibility, along with a QSAR approach, to identify small molecules that can interact with II phase dug metabolizing enzymes.

Mutagenicity, carcinogenicity, and other end points

Aiming at understanding the structural and physical chemical basis of the biological activity of chemicals, the science of structure-activity relationships has seen dramatic progress in the last decades. Coarse-grain, qualitative approaches (e.g., the structural alerts), and fine-tuned quantitative structure-activity relationship models have been developed and used to predict the toxicological properties of untested chemicals. More recently, a number of approaches and concepts have been developed as support to, and corollary of, the structure-activity methods. These approaches (e.g., chemical relational databases, expert systems, software tools for manipulating the chemical information) have dramatically expanded the reach of the structure-activity work; at present, they are powerful and inescapable tools for computer chemists, toxicologists, and regulators. This chapter, after a general overview of traditional and well-known approaches, gives a detailed presentation of the latter more recent support tools freely available in the public domain.

Toward in silico structure-based ADMET prediction in drug discovery

Quantitative structure-activity relationship (QSAR) methods and related approaches have been used to investigate the molecular features that influence the absorption, distribution, metabolism, excretion and toxicity (ADMET) of drugs. As the three-dimensional structures of several major ADMET proteins become available, structure-based (docking-scoring) computations can be carried out to complement or to go beyond QSAR studies. Applying docking-scoring methods to ADMET proteins is a challenging process because they usually have a large and flexible binding cavity; however, promising results relating to metabolizing enzymes have been reported. After reviewing current trends in the field we applied structure-based methods in the context of receptor flexibility in a case study involving the phase II metabolizing sulfotransferases. Overall, the explored concepts and results suggested that structure-based ADMET profiling will probably join the mainstream during the coming years.

A binary ant colony optimization classifier for molecular activities

Chemical fingerprints encode the presence or absence of molecular features and are available in many large databases. Using a variation of the Ant Colony Optimization (ACO) paradigm, we describe a binary classifier based on feature selection from fingerprints. We discuss the algorithm and possible cross-validation procedures. As a real-world example, we use our algorithm to analyze a Plasmodium falciparum inhibition assay and contrast its performance with other machine learning paradigms in use today (decision tree induction, random forests, support vector machines, artificial neural networks). Our algorithm matches established paradigms in predictive power, yet supplies the medicinal chemist and basic researcher with easily interpretable results. Furthermore, models generated with our paradigm are easy to implement and can complement virtual screenings by additionally exploiting the precalculated fingerprint information.

Computational ligand-based rational design: Role of conformational sampling and force fields in model development

A significant number of drug discovery efforts are based on natural products or high throughput screens from which compounds showing potential therapeutic effects are identified without knowledge of the target molecule or its 3D structure. In such cases computational ligand-based drug design (LBDD) can accelerate the drug discovery processes. LBDD is a general approach to elucidate the relationship of a compound's structure and physicochemical attributes to its biological activity. The resulting structure-activity relationship (SAR) may then act as the basis for the prediction of compounds with improved biological attributes. LBDD methods range from pharmacophore models identifying essential features of ligands responsible for their activity, quantitative structure-activity relationships (QSAR) yielding quantitative estimates of activities based on physiochemical properties, and to similarity searching, which explores compounds with similar properties as well as various combinations of the above. A number of recent LBDD approaches involve the use of multiple conformations of the ligands being studied. One of the basic components to generate multiple conformations in LBDD is molecular mechanics (MM), which apply an empirical energy function to relate conformation to energies and forces. The collection of conformations for ligands is then combined with functional data using methods ranging from regression analysis to neural networks, from which the SAR is determined. Accordingly, for effective application of LBDD for SAR determinations it is important that the compounds be accurately modelled such that the appropriate range of conformations accessible to the ligands is identified. Such accurate modelling is largely based on use of the appropriate empirical force field for the molecules being investigated and the approaches used to generate the conformations. The present chapter includes a brief overview of currently used SAR methods in LBDD followed by a more detailed presentation of issues and limitations associated with empirical energy functions and conformational sampling methods.

In silico prediction of Tetrahymena pyriformis toxicity for diverse industrial chemicals with substructure pattern recognition and machine learning methods

There is an increasing need for the rapid safety assessment of chemicals by both industries and regulatory agencies throughout the world. In silico techniques are practical alternatives in the environmental hazard assessment. It is especially true to address the persistence, bioaccumulative and toxicity potentials of organic chemicals. Tetrahymena pyriformis toxicity is often used as a toxic endpoint. In this study, 1571 diverse unique chemicals were collected from the literature and composed of the largest diverse data set for T. pyriformis toxicity. Classification predictive models of T. pyriformis toxicity were developed by substructure pattern recognition and different machine learning methods, including support vector machine (SVM), C4.5 decision tree, k-nearest neighbors and random forest. The results of a 5-fold cross-validation showed that the SVM method performed better than other algorithms. The overall predictive accuracies of the SVM classification model with radial basis functions kernel was 92.2% for the 5-fold cross-validation and 92.6% for the external validation set, respectively. Furthermore, several representative substructure patterns for characterizing T. pyriformis toxicity were also identified via the information gain analysis methods.