Validating ADME QSAR Models Using Marketed Drugs

Developing Robust Human Liver Microsomal Stability Prediction Models: Leveraging Inter-Species Correlation with Rat Data

Objectives: Pharmacokinetic issues were the leading cause of drug attrition, accounting for approximately 40% of all cases before the turn of the century. To this end, several high-throughput in vitro assays like microsomal stability have been developed to evaluate the pharmacokinetic profiles of compounds in the early stages of drug discovery. At NCATS, a single-point rat liver microsomal (RLM) stability assay is used as a Tier I assay, while human liver microsomal (HLM) stability is employed as a Tier II assay. We experimentally screened and collected data on over 30,000 compounds for RLM stability and over 7000 compounds for HLM stability. Although HLM stability screening provides valuable insights, the increasing number of hits generated, along with the time- and resource-intensive nature of the assay, highlights the need for alternative strategies. One promising approach is leveraging in silico models trained on these experimental datasets. Methods: We describe the development of an HLM stability prediction model using our in-house HLM stability dataset. Results: Employing both classical machine learning methods and advanced techniques, such as neural networks, we achieved model accuracies exceeding 80%. Moreover, we validated our model using external test sets and found that our models are comparable to some of the best models in literature. Additionally, the strong correlation observed between our RLM and HLM data was further reinforced by the fact that our HLM model performance improved when using RLM stability predictions as an input descriptor. Conclusions: The best model along with a subset of our dataset (PubChem AID: 1963597) has been made publicly accessible on the ADME@NCATS website for the benefit of the greater drug discovery community. To the best of our knowledge, it is the largest open-source model of its kind and the first to leverage cross-species data.

Small-Molecule Disruptors of the Interaction between Calcium- and Integrin-Binding Protein 1 and Integrin αIIbβ3 as Novel Antiplatelet Agents

Thrombosis, a key factor in most cardiovascular diseases, is a major contributor to human mortality. Existing antithrombotic agents carry a risk of bleeding. Consequently, there is a keen interest in discovering innovative antithrombotic agents that can prevent thrombosis without negatively impacting hemostasis. Platelets play crucial roles in both hemostasis and thrombosis. We have previously characterized calcium- and integrin-binding protein 1 (CIB1) as a key regulatory molecule that regulates platelet function. CIB1 interacts with several platelet proteins including integrin αIIbβ3, the major glycoprotein receptor for fibrinogen on platelets. Given that CIB1 regulates platelet function through its interaction with αIIbβ3, we developed a fluorescence polarization (FP) assay to screen for potential inhibitors. The assay was miniaturized to 1536-well and screened in quantitative high-throughput screening (qHTS) format against a diverse compound library of 14,782 compounds. After validation and selectivity testing using the FP assay, we identified 19 candidate inhibitors and validated them using an in-gel binding assay that monitors the interaction of CIB1 with αIIb cytoplasmic tail peptide, followed by testing of top hits by intrinsic tryptophan fluorescence (ITF) and microscale thermophoresis (MST) to ascertain their interaction with CIB1. Two of the validated hits shared similar chemical structures, suggesting a common mechanism of action. Docking studies further revealed promising interactions within the hydrophobic binding pocket of the target protein, particularly forming key hydrogen bonds with Ser180. The compounds exhibited a potent antiplatelet activity based on their inhibition of thrombin-induced human platelet aggregation, thus indicating that disruptors of the CIB1- αIIbβ3 interaction could carry a translational potential as antithrombotic agents.

In silico ADME/tox comes of age: twenty years later

In the early 2000s pharmaceutical drug discovery was beginning to use computational approaches for absorption, distribution, metabolism, excretion and toxicity (ADME/Tox, also known as ADMET) prediction. This emphasis on prediction was an effort to reduce the risk of later stage failures from ADME/Tox.Much has been written in the intervening twenty plus years and significant expenditure has occurred in companies developing these in silico capabilities which can be gleaned from publications. It is therefore an appropriate time to briefly reflect on what was proposed then and what the reality is today.20 years ago, we tended to optimise bioactivity and perhaps one ADME/Tox property at a time. Previously pharmaceutical companies needed a whole infrastructure for models - in silico and in vitro experts, IT, champions on a project team, educators and management support. Now we are in the age of generative de novo design where bioactivity and many ADME/Tox properties can be optimised and large language model technologies are available.There are also some challenges such as the focus on very large molecules which may be outside of current ADME/Tox models.We provide an opportunity to look forward with the increasing public data for ADME/Tox as well as expanded types of algorithms available.

Prediction of the First-Pass Metabolism of a Drug After Oral Intake Based on Structural Parameters and Physicochemical Properties

BACKGROUND AND OBJECTIVE

The oral first-pass metabolism is a crucial factor that plays a key role in a drug's pharmacokinetic profile. Prediction of the oral first-pass metabolism based on chemical structural parameters can be useful in the drug-design process. Developing an orally administered drug with an acceptable pharmacokinetic profile is necessary to reduce the cost and time associated with evaluating the extent of the first-pass metabolism of a candidate compound in preclinical studies. The aim of this study is to estimate the first-pass metabolism of an orally administered drug.

METHODS

A set of compounds with reported first-pass metabolism data were collected. Moreover, human intestinal absorption percentage and oral bioavailability data were extracted from the literature to propose a classification system that split the drugs up based on their first-pass metabolism extents. Various structural parameters were calculated for each compound. The relations of the structural and physicochemical values of each compound to the class the compound belongs to were obtained using logistic regression.

RESULTS

Initial analysis showed that compounds with logD7.4 > 1 or a rugosity factor of > 1.5 are more likely to have high first-pass metabolism. Four different models that can predict the oral first-pass metabolism with acceptable error were introduced. The overall accuracies of the models were in the range of 72% (for models with simple descriptors) to 78% (for models with complex descriptors). Although the models with simple descriptors have lower accuracies compared to complex models, they are more interpretable and easier for researchers to utilize.

CONCLUSION

A novel classification of drugs based on the extent of the oral first-pass metabolism was introduced, and mechanistic models were developed to assign candidate compounds to the appropriate proposed classes.

Bovine carbonic anhydrase (bCA) inhibitors: Synthesis, molecular docking and theoretical studies of bisoxadiazole-substituted sulfonamide derivatives

This paper describes the in vitro inhibition potential of bisoxadiazole-substituted sulfonamide derivatives (6a-t) against bovine carbonic anhydrase (bCA) after they were designed through computational analyses and evaluated the predicted interaction via molecular docking. First, in silico ADMET predictions and physicochemical property analysis of the compounds provided insights into solubility and permeability, then density functional theory (DFT) calculations were performed to analyse their ionization energies, nucleophilicity, in vitro electron affinity, dipole moments and molecular interactions under vacuum and dimethyl sulfoxide (DMSO) conditions. After calculating the theoretical inhibition constants, IC50 values determined from enzymatic inhibition were found between 12.93 and 45.77 μM. Molecular docking evaluation revealed favorable hydrogen bonding and π-interactions of the compounds within the bCA active site. The experimentally most active compound, 6p, exhibited the strongest inhibitory activity with a theoretical inhibition constant value of 9.41 nM and H-bonds with Gln91, Thr198, and Trp4 residues and His63 Pi-cation interactions with His63 residues. Overall, the study reveals promising bCA blocking potential for the synthesized derivatives, similar to acetazolamide.

Artificial Intelligence for Drug Discovery: Are We There Yet?

Drug discovery is adapting to novel technologies such as data science, informatics, and artificial intelligence (AI) to accelerate effective treatment development while reducing costs and animal experiments. AI is transforming drug discovery, as indicated by increasing interest from investors, industrial and academic scientists, and legislators. Successful drug discovery requires optimizing properties related to pharmacodynamics, pharmacokinetics, and clinical outcomes. This review discusses the use of AI in the three pillars of drug discovery: diseases, targets, and therapeutic modalities, with a focus on small-molecule drugs. AI technologies, such as generative chemistry, machine learning, and multiproperty optimization, have enabled several compounds to enter clinical trials. The scientific community must carefully vet known information to address the reproducibility crisis. The full potential of AI in drug discovery can only be realized with sufficient ground truth and appropriate human intervention at later pipeline stages.

Neural Network Models for Predicting Solubility and Metabolism Class of Drugs in the Biopharmaceutics Drug Disposition Classification System (BDDCS)

BACKGROUND AND OBJECTIVE

The biopharmaceutics drug disposition classification system (BDDCS) categorizes drugs into four classes on the basis of their solubility and metabolism. This framework allows for the study of the pharmacokinetics of transporters and enzymatic metabolization on biopharmaceuticals, as well as drug-drug interactions in the body. The objective of the present study was to develop computational models by neural network models and structural parameters and physicochemical properties to estimate the class of a drug in the BDDCS system.

METHODS

In this study, deep learning methods were utilized to explore the potential of artificial and convolutional neural networks (ANNs and CNNs) in predicting the BDDCS class of 721 substances. The structural parameters and physicochemical properties [Abraham solvation parameters, octanol-water partition (log P) and over the pH range 1-7.5 (log D), number of rotatable bonds, hydrogen bond acceptor numbers, as well as hydrogen bond donor count] are calculated with various software. These compounds were then split into a training set consisting of 602 molecules and a test set of 119 compounds to validate the models.

RESULTS

The results of this study showed that neural network models using applied parameters of the drug, i.e., log D and Abraham solvation parameters, are able to predict the class of solubility and metabolism in the BDDCS system with good accuracy.

CONCLUSIONS

Neural network models are well equipped to deal with the relations between the structural parameters and physicochemical properties of drugs and BDDCS classes. In addition, log D is a more suitable parameter compared with log P in predicting BDDCS.

Consideration of vendor-related differences in hepatic metabolic stability data to optimize early ADME screening in drug discovery

Hepatic metabolic stability is a crucial determinant of oral bioavailability and plasma concentrations of a compound, and its measurement is important in early drug discovery. Preliminary metabolic stability estimations are commonly performed in liver microsomal fractions. At the National Center for Advancing Translational Sciences, a single-point assay in rat liver microsomes (RLM) is employed for initial stability assessment (Tier I) and a multi-point detailed stability assay is employed as a Tier II assay for promising compounds. Although the in vitro and in vivo metabolic stability of compounds typically exhibit good correlation, conflicting results may arise in certain cases. While investigating one such instance, we serendipitously found vendor-related RLM differences in metabolic stability and metabolite formation, which had implications for in vitro and in vivo correlations. In this study, we highlight the importance of considering vendor differences in hepatic metabolic stability data and discuss strategies to avoid these pitfalls.

Development and validation of PAMPA-BBB QSAR model to predict brain penetration potential of novel drug candidates

Efficiently circumventing the blood-brain barrier (BBB) poses a major hurdle in the development of drugs that target the central nervous system. Although there are several methods to determine BBB permeability of small molecules, the Parallel Artificial Membrane Permeability Assay (PAMPA) is one of the most common assays in drug discovery due to its robust and high-throughput nature. Drug discovery is a long and costly venture, thus, any advances to streamline this process are beneficial. In this study, ∼2,000 compounds from over 60 NCATS projects were screened in the PAMPA-BBB assay to develop a quantitative structure-activity relationship model to predict BBB permeability of small molecules. After analyzing both state-of-the-art and latest machine learning methods, we found that random forest based on RDKit descriptors as additional features provided the best training balanced accuracy (0.70 ± 0.015) and a message-passing variant of graph convolutional neural network that uses RDKit descriptors provided the highest balanced accuracy (0.72) on a prospective validation set. Finally, we correlated in vitro PAMPA-BBB data with in vivo brain permeation data in rodents to observe a categorical correlation of 77%, suggesting that models developed using data from PAMPA-BBB can forecast in vivo brain permeability. Given that majority of prior research has relied on in vitro or in vivo data for assessing BBB permeability, our model, developed using the largest PAMPA-BBB dataset to date, offers an orthogonal means to estimate BBB permeability of small molecules. We deposited a subset of our data into PubChem bioassay database (AID: 1845228) and deployed the best performing model on the NCATS Open Data ADME portal (https://opendata.ncats.nih.gov/adme/). These initiatives were undertaken with the aim of providing valuable resources for the drug discovery community.

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.

Recent Studies of Artificial Intelligence on In Silico Drug Absorption

Absorption is an important area of research in pharmacochemistry and drug development, because the drug has to be absorbed before any drug effects can occur. Furthermore, the ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) profile of drugs can be directly and considerably altered by modulating factors affecting absorption. Many drugs in development fail because of poor absorption. The research and continuous efforts of researchers in recent years have brought many successes and promises in drug absorption property prediction, especially in silico, which helps to reduce the time and cost significantly for screening undesirable drug candidates. In this report, we explicitly provide an overview of recent in silico studies on predicting absorption properties, especially from 2019 to the present, using artificial intelligence. Additionally, we have collected and investigated public databases that support absorption prediction research. On those grounds, we also proposed the challenges and development directions of absorption prediction in the future. We hope this review can provide researchers with valuable guidelines on absorption prediction to facilitate the development of newer approaches in drug discovery.

First fully-automated AI/ML virtual screening cascade implemented at a drug discovery centre in Africa

Streamlined data-driven drug discovery remains challenging, especially in resource-limited settings. We present ZairaChem, an artificial intelligence (AI)- and machine learning (ML)-based tool for quantitative structure-activity/property relationship (QSAR/QSPR) modelling. ZairaChem is fully automated, requires low computational resources and works across a broad spectrum of datasets. We describe an end-to-end implementation at the H3D Centre, the leading integrated drug discovery unit in Africa, at which no prior AI/ML capabilities were available. By leveraging in-house data collected over a decade, we have developed a virtual screening cascade for malaria and tuberculosis drug discovery comprising 15 models for key decision-making assays ranging from whole-cell phenotypic screening and cytotoxicity to aqueous solubility, permeability, microsomal metabolic stability, cytochrome inhibition, and cardiotoxicity. We show how computational profiling of compounds, prior to synthesis and testing, can inform progression of frontrunner compounds at H3D. This project is a first-of-its-kind deployment at scale of AI/ML tools in a research centre operating in a low-resource setting.

In Silico Prediction of Human and Rat Liver Microsomal Stability via Machine Learning Methods

Liver microsomal stability is an important property considered for the screening of drug candidates in the early stage of drug development. Determination of hepatic metabolic stability can be performed by an in vitro assay, but it requires quite a few resources and time. In recent years, machine learning methods have made much progress. Therefore, development of computational models to predict liver microsomal stability is highly desirable in the drug discovery process. In this study, the in silico classification models for the prediction of the metabolic stability of compounds in rat and human liver microsomes were constructed by the conventional machine learning and deep learning methods. The performance of the models was evaluated using the test and external sets. For the rat liver microsomes (RLM) stability, the best model yielded the AUC values of 0.84 and 0.71 on the test and external validation sets, respectively. For the human liver microsome (HLM) stability, the best model exhibited the AUC values of 0.86 and 0.77 on the test and external validation sets, respectively. In addition, several important substructure fragments were detected using information gain and frequency substructure analysis methods. The applicability domain of the models was defined using the Euclidean distance-based method. We anticipate that our results would be helpful for the prediction of liver microsomal stability of compounds in the early stage of drug discovery.

Using in vitro ADME data for lead compound selection: An emphasis on PAMPA pH 5 permeability and oral bioavailability

Membrane permeability plays an important role in oral drug absorption. Caco-2 and Madin-Darby Canine Kidney (MDCK) cell culture systems have been widely used for assessing intestinal permeability. Since most drugs are absorbed passively, Parallel Artificial Membrane Permeability Assay (PAMPA) has gained popularity as a low-cost and high-throughput method in early drug discovery when compared to high-cost, labor intensive cell-based assays. At the National Center for Advancing Translational Sciences (NCATS), PAMPA pH 5 is employed as one of the Tier I absorption, distribution, metabolism, and elimination (ADME) assays. In this study, we have developed a quantitative structure activity relationship (QSAR) model using our ∼6500 compound PAMPA pH 5 permeability dataset. Along with ensemble decision tree-based methods such as Random Forest and eXtreme Gradient Boosting, we employed deep neural network and a graph convolutional neural network to model PAMPA pH 5 permeability. The classification models trained on a balanced training set provided accuracies ranging from 71% to 78% on the external set. Of the four classifiers, the graph convolutional neural network that directly operates on molecular graphs offered the best classification performance. Additionally, an ∼85% correlation was obtained between PAMPA pH 5 permeability and in vivo oral bioavailability in mice and rats. These results suggest that data from this assay (experimental or predicted) can be used to rank-order compounds for preclinical in vivo testing with a high degree of confidence, reducing cost and attrition as well as accelerating the drug discovery process. Additionally, experimental data for 486 compounds (PubChem AID: 1645871) and the best models have been made publicly available (https://opendata.ncats.nih.gov/adme/).

Advanced Analytical Tools for the Estimation of Gut Permeability of Compounds of Pharmaceutical Interest

The present study aims at developing a quantitative structure–activity relationship (QSAR) model for the determination of gut permeability of 228 pharmacological drugs at different pH conditions (3, 5, 7.4, 9, intrinsic). As a consequence, five different datasets (according to the diverse permeability shown by the compounds at the different pH values) were handled, with the aim of discriminating compounds as low-permeable or high-permeable. In order to achieve this goal, molecular descriptors for all the investigated compounds were computed and then classification models calculated by means of partial least squares discriminant analysis (PLS-DA). A high predictive capability was achieved for all models, providing correct classification rates in external validation between 80% and 96%. In order to test whether a reduction in the molecular descriptors would improve predictions and provide information about the most relevant variables, a feature selection approach, covariance selection, was used to select the most relevant subsets of predictors. This led to a slight improvement in the predictive accuracies, and it has indicated that the most relevant descriptors for the discrimination of the investigated compounds into low- and high-permeable were associated with the 2D and 3D structures.

Hybrid In Silico Approach Reveals Novel Inhibitors of Multiple SARS-CoV-2 Variants

The National Center for Advancing Translational Sciences (NCATS) has been actively generating SARS-CoV-2 high-throughput screening data and disseminates it through the OpenData Portal (https://opendata.ncats.nih.gov/covid19/). Here, we provide a hybrid approach that utilizes NCATS screening data from the SARS-CoV-2 cytopathic effect reduction assay to build predictive models, using both machine learning and pharmacophore-based modeling. Optimized models were used to perform two iterative rounds of virtual screening to predict small molecules active against SARS-CoV-2. Experimental testing with live virus provided 100 (∼16% of predicted hits) active compounds (efficacy > 30%, IC50 ≤ 15 μM). Systematic clustering analysis of active compounds revealed three promising chemotypes which have not been previously identified as inhibitors of SARS-CoV-2 infection. Further investigation resulted in the identification of allosteric binders to host receptor angiotensin-converting enzyme 2; these compounds were then shown to inhibit the entry of pseudoparticles bearing spike protein of wild-type SARS-CoV-2, as well as South African B.1.351 and UK B.1.1.7 variants.