Derivation and Validation of Toxicophores for Mutagenicity Prediction

How to nurture natural products to create new therapeutics: Strategic innovations and molecule-to-medicinal insights into therapeutic advancements

Natural products (NPs) are privileged structures interacting with biomacromolecular targets and exhibiting biological effects important for human health. In this review, we have presented NP-inspired strategic innovations that are promising for addressing preclinical and clinical challenges. An analysis of 'molecule-to-medicinal' properties for improvement of P3 and absorption, distribution, metabolism, excretion, and toxicity (ADMET) profiles has been illustrated. The strategies include chemical evolution through knowledge of structure-medicinal properties, truncation of NPs to avoid molecular obesity, pseudo-NPs, selection of common structural features of NPs, medicinophore installation, scaffold hopping, and induced proximity. Molecule-to-medicinal property analysis can guide the development of 'nature-to-new' chemical therapeutics. Coupled with scientific advances and innovations in instrumentation, these strategies hold great potential for enhancing drug design and discovery.

Identification of novel PHGDH inhibitors based on computational investigation: an all-in-one combination strategy to develop potential anti-cancer candidates

Objective

Biological studies have elucidated that phosphoglycerate dehydrogenase (PHGDH) is the rate-limiting enzyme in the serine synthesis pathway in humans that is abnormally expressed in numerous cancers. Inhibition of the PHGDH activity is thought to be an attractive approach for novel anti-cancer therapy. The development of structurally diverse novel PHGDH inhibitors with high efficiency and low toxicity is a promising drug discovery strategy.

Methods

A ligand-based 3D-QSAR pharmacophore model was developed using the HypoGen algorithm methodology of Discovery Studio. The selected pharmacophore model was further validated by test set validation, cost analysis, and Fischer randomization validation and was then used as a 3D query to screen compound libraries with various chemical scaffolds. The estimated activity, drug-likeness, molecular docking, growing scaffold, and molecular dynamics simulation processes were applied in combination to reduce the number of virtual hits.

Results

The potential candidates against PHGDH were screened based on estimated activity, docking scores, predictive absorption, distribution, metabolism, excretion, and toxicity (ADME/T) properties, and molecular dynamics simulation.

Conclusion

Finally, an all-in-one combination was employed successfully to design and develop three potential anti-cancer candidates.

Machine Learning Prediction of On/Off Target-driven Clinical Adverse Events

OBJECTIVE

Currently, 90% of clinical drug development fails, where 30% of these failures are due to clinical toxicity. The current extensive animal toxicity studies are not predictive of clinical adverse events (AEs) at clinical doses, while current computation models only consider very few factors with limited success in clinical toxicity prediction. We aimed to address these issues by developing a machine learning (ML) model to directly predict clinical AEs.

METHODS

Using a dataset with 759 FDA-approved drugs with known AEs, we first adapted the ConPLex ML model to predict IC50 values of these FDA-approved drugs against their on-target and off-target binding among 477 protein targets. Subsequently, we constructed a new ML model to predict clinical AEs using IC50 values of 759 drugs' primary on-target and off-target effects along with tissue-specific protein expression profiles.

RESULTS

The adapted ConPLex model predicted drug-target interactions for both on- and off-target effects, as shown by co-localization of the 6 small molecule kinase inhibitors with their respective kinases. The coupled ML models demonstrated good predictive capability of clinical AEs, with accuracy over 75%.

CONCLUSIONS

Our approach provides a new insight into the mechanistic understanding of in vivo drug toxicity in relationship with drug on-/off-target interactions. The coupled ML models, once validated with larger datasets, may offer advantages to directly predict clinical AEs using in vitro/ex vivo and preclinical data, which will help to reduce drug development failure due to clinical toxicity.

Deep-PK: deep learning for small molecule pharmacokinetic and toxicity prediction

Evaluating pharmacokinetic properties of small molecules is considered a key feature in most drug development and high-throughput screening processes. Generally, pharmacokinetics, which represent the fate of drugs in the human body, are described from four perspectives: absorption, distribution, metabolism and excretion-all of which are closely related to a fifth perspective, toxicity (ADMET). Since obtaining ADMET data from in vitro, in vivo or pre-clinical stages is time consuming and expensive, many efforts have been made to predict ADMET properties via computational approaches. However, the majority of available methods are limited in their ability to provide pharmacokinetics and toxicity for diverse targets, ensure good overall accuracy, and offer ease of use, interpretability and extensibility for further optimizations. Here, we introduce Deep-PK, a deep learning-based pharmacokinetic and toxicity prediction, analysis and optimization platform. We applied graph neural networks and graph-based signatures as a graph-level feature to yield the best predictive performance across 73 endpoints, including 64 ADMET and 9 general properties. With these powerful models, Deep-PK supports molecular optimization and interpretation, aiding users in optimizing and understanding pharmacokinetics and toxicity for given input molecules. The Deep-PK is freely available at https://biosig.lab.uq.edu.au/deeppk/.

Applications of intelligent technology in the evaluation of mutagenicity

Bioassays are widely used in assessment of mutagenicity. Alternative methods have also been developed, including "intelligent evaluation", which depends on the quality of data, strategies, and techniques. CISOC-PSMT is an Ames test prediction system. The strategies and techniques for intelligent evaluation and four applications of CISOC-PSMT are presented; roles in pesticide management, environmental protection, drug discovery, and safety management of chemicals are introduced.

Low-cost quantum mechanical descriptors for data efficient skin sensitization QSAR models

Quantitative Structure Activity Relationship modelling methodologies need to incorporate relevant mechanistic information to have high predictive performance and validity. Electrophilic reactivity is a common mechanistic feature of skin sensitization endpoints which could be concisely characterized with electronic descriptors which is key to enabling the modelling of small datasets in this domain. However, quantum mechanical methodologies have previously featured high computational costs which would exclude the use of large datasets. Consequently, we investigate the use of electronic descriptors calculated using the Hartree Fock with 3 corrections (Hf-3c) method, a low-cost ab initio methodology that has higher chemical accuracy than previous semiempirical methodologies for modelling in vitro skin sensitization assay outcomes. We also model the Ames assay as a surrogate for determining skin sensitization outcomes. The quantum chemical descriptors calculated using the Hf-3c method with conductor-like polarizable continuum model (CPCM) implicit solvation found improved QSAR model performance for the in vitro Ames (n = 6049, 0.770 AUC), KeratinoSens (n = 164, 0.763 AUC), and Direct Peptide Reactivity Assay (n = 122, 0.750 AUC) datasets, with their combination producing high predictive performance for unseen in vivo Local Lymph Node Assay (n = 86, 0.789 AUC) and Human Repeated Insult Patch Test (n = 86, 0.791 AUC) assay toxicant outcomes.

AMPred-CNN: Ames mutagenicity prediction model based on convolutional neural networks

Mutagenicity assessment plays a pivotal role in the safety evaluation of chemicals, pharmaceuticals, and environmental compounds. In recent years, the development of robust computational models for predicting chemical mutagenicity has gained significant attention, driven by the need for efficient and cost-effective toxicity assessments. In this paper, we proposed AMPred-CNN, an innovative Ames mutagenicity prediction model based on Convolutional Neural Networks (CNNs), uniquely employing molecular structures as images to leverage CNNs' powerful feature extraction capabilities. The study employs the widely used benchmark mutagenicity dataset from Hansen et al. for model development and evaluation. Comparative analyses with traditional ML models on different molecular features reveal substantial performance enhancements. AMPred-CNN outshines these models, demonstrating superior accuracy, AUC, F1 score, MCC, sensitivity, and specificity on the test set. Notably, AMPred-CNN is further benchmarked against seven recent ML and DL models, consistently showcasing superior performance with an impressive AUC of 0.954. Our study highlights the effectiveness of CNNs in advancing mutagenicity prediction, paving the way for broader applications in toxicology and drug development.

Interpreting Neural Network Models for Toxicity Prediction by Extracting Learned Chemical Features

Neural network models have become a popular machine-learning technique for the toxicity prediction of chemicals. However, due to their complex structure, it is difficult to understand predictions made by these models which limits confidence. Current techniques to tackle this problem such as SHAP or integrated gradients provide insights by attributing importance to the input features of individual compounds. While these methods have produced promising results in some cases, they do not shed light on how representations of compounds are transformed in hidden layers, which constitute how neural networks learn. We present a novel technique to interpret neural networks which identifies chemical substructures in training data found to be responsible for the activation of hidden neurons. For individual test compounds, the importance of hidden neurons is determined, and the associated substructures are leveraged to explain the model prediction. Using structural alerts for mutagenicity from the Derek Nexus expert system as ground truth, we demonstrate the validity of the approach and show that model explanations are competitive with and complementary to explanations obtained from an established feature attribution method.

Predicting the Activity of Unidentified Chemicals in Complementary Bioassays from the HRMS Data to Pinpoint Potential Endocrine Disruptors

The majority of chemicals detected via nontarget liquid chromatography high-resolution mass spectrometry (HRMS) in environmental samples remain unidentified, challenging the capability of existing machine learning models to pinpoint potential endocrine disruptors (EDs). Here, we predict the activity of unidentified chemicals across 12 bioassays related to EDs within the Tox21 10K dataset. Single- and multi-output models, utilizing various machine learning algorithms and molecular fingerprint features as an input, were trained for this purpose. To evaluate the models under near real-world conditions, Monte Carlo sampling was implemented for the first time. This technique enables the use of probabilistic fingerprint features derived from the experimental HRMS data with SIRIUS+CSI:FingerID as an input for models trained on true binary fingerprint features. Depending on the bioassay, the lowest false-positive rate at 90% recall ranged from 0.251 (sr.mmp, mitochondrial membrane potential) to 0.824 (nr.ar, androgen receptor), which is consistent with the trends observed in the models' performances submitted for the Tox21 Data Challenge. These findings underscore the informativeness of fingerprint features that can be compiled from HRMS in predicting the endocrine-disrupting activity. Moreover, an in-depth SHapley Additive exPlanations analysis unveiled the models' ability to pinpoint structural patterns linked to the modes of action of active chemicals. Despite the superior performance of the single-output models compared to that of the multi-output models, the latter's potential cannot be disregarded for similar tasks in the field of in silico toxicology. This study presents a significant advancement in identifying potentially toxic chemicals within complex mixtures without unambiguous identification and effectively reducing the workload for postprocessing by up to 75% in nontarget HRMS.

MolProphet: A One-Stop, General Purpose, and AI-Based Platform for the Early Stages of Drug Discovery

Artificial intelligence (AI) is an effective tool to accelerate drug discovery and cut costs in discovery processes. Many successful AI applications are reported in the early stages of small molecule drug discovery. However, most of those applications require a deep understanding of software and hardware, and focus on a single field that implies data normalization and transfer between those applications is still a challenge for normal users. It usually limits the application of AI in drug discovery. Here, based on a series of robust models, we formed a one-stop, general purpose, and AI-based drug discovery platform, MolProphet, to provide complete functionalities in the early stages of small molecule drug discovery, including AI-based target pocket prediction, hit discovery and lead optimization, and compound targeting, as well as abundant analyzing tools to check the results. MolProphet is an accessible and user-friendly web-based platform that is fully designed according to the practices in the drug discovery industry. The molecule screened, generated, or optimized by the MolProphet is purchasable and synthesizable at low cost but with good drug-likeness. More than 400 users from industry and academia have used MolProphet in their work. We hope this platform can provide a powerful solution to assist each normal researcher in drug design and related research areas. It is available for everyone at https://www.molprophet.com/.

Enhancing property and activity prediction and interpretation using multiple molecular graph representations with MMGX

Graph Neural Networks (GNNs) excel in compound property and activity prediction, but the choice of molecular graph representations significantly influences model learning and interpretation. While atom-level molecular graphs resemble natural topology, they overlook key substructures or functional groups and their interpretation partially aligns with chemical intuition. Recent research suggests alternative representations using reduced molecular graphs to integrate higher-level chemical information and leverages both representations for model. However, there is a lack of studies about applicability and impact of different molecular graphs on model learning and interpretation. Here, we introduce MMGX (Multiple Molecular Graph eXplainable discovery), investigating the effects of multiple molecular graphs, including Atom, Pharmacophore, JunctionTree, and FunctionalGroup, on model learning and interpretation with various perspectives. Our findings indicate that multiple graphs relatively improve model performance, but in varying degrees depending on datasets. Interpretation from multiple graphs in different views provides more comprehensive features and potential substructures consistent with background knowledge. These results help to understand model decisions and offer valuable insights for subsequent tasks. The concept of multiple molecular graph representations and diverse interpretation perspectives has broad applicability across tasks, architectures, and explanation techniques, enhancing model learning and interpretation for relevant applications in drug discovery.

Using test-time augmentation to investigate explainable AI: inconsistencies between method, model and human intuition

Stakeholders of machine learning models desire explainable artificial intelligence (XAI) to produce human-understandable and consistent interpretations. In computational toxicity, augmentation of text-based molecular representations has been used successfully for transfer learning on downstream tasks. Augmentations of molecular representations can also be used at inference to compare differences between multiple representations of the same ground-truth. In this study, we investigate the robustness of eight XAI methods using test-time augmentation for a molecular-representation model in the field of computational toxicity prediction. We report significant differences between explanations for different representations of the same ground-truth, and show that randomized models have similar variance. We hypothesize that text-based molecular representations in this and past research reflect tokenization more than learned parameters. Furthermore, we see a greater variance between in-domain predictions than out-of-domain predictions, indicating XAI measures something other than learned parameters. Finally, we investigate the relative importance given to expert-derived structural alerts and find similar importance given irregardless of applicability domain, randomization and varying training procedures. We therefore caution future research to validate their methods using a similar comparison to human intuition without further investigation. SCIENTIFIC CONTRIBUTION: In this research we critically investigate XAI through test-time augmentation, contrasting previous assumptions about using expert validation and showing inconsistencies within models for identical representations. SMILES augmentation has been used to increase model accuracy, but was here adapted from the field of image test-time augmentation to be used as an independent indication of the consistency within SMILES-based molecular representation models.

"DompeKeys": a set of novel substructure-based descriptors for efficient chemical space mapping, development and structural interpretation of machine learning models, and indexing of large databases

The conversion of chemical structures into computer-readable descriptors, able to capture key structural aspects, is of pivotal importance in the field of cheminformatics and computer-aided drug design. Molecular fingerprints represent a widely employed class of descriptors; however, their generation process is time-consuming for large databases and is susceptible to bias. Therefore, descriptors able to accurately detect predefined structural fragments and devoid of lengthy generation procedures would be highly desirable. To meet additional needs, such descriptors should also be interpretable by medicinal chemists, and suitable for indexing databases with trillions of compounds. To this end, we developed-as integral part of EXSCALATE, Dompé's end-to-end drug discovery platform-the DompeKeys (DK), a new substructure-based descriptor set, which encodes the chemical features that characterize compounds of pharmaceutical interest. DK represent an exhaustive collection of curated SMARTS strings, defining chemical features at different levels of complexity, from specific functional groups and structural patterns to simpler pharmacophoric points, corresponding to a network of hierarchically interconnected substructures. Because of their extended and hierarchical structure, DK can be used, with good performance, in different kinds of applications. In particular, we demonstrate how they are very well suited for effective mapping of chemical space, as well as substructure search and virtual screening. Notably, the incorporation of DK yields highly performing machine learning models for the prediction of both compounds' activity and metabolic reaction occurrence. The protocol to generate the DK is freely available at https://dompekeys.exscalate.eu and is fully integrated with the Molecular Anatomy protocol for the generation and analysis of hierarchically interconnected molecular scaffolds and frameworks, thus providing a comprehensive and flexible tool for drug design applications.

Discovery of dual kinase inhibitors targeting VEGFR2 and FAK: structure-based pharmacophore modeling, virtual screening, and molecular docking studies

VEGFR2 and FAK signaling pathways are interconnected and have synergistic effects on tumor angiogenesis, growth, and metastasis. Thus, instead of the conventional targeting of each of these proteins individually with a specific inhibitor, the present work aimed to discover novel dual inhibitors targeting both VEGFR2 and FAK exploiting their association. To this end, receptor-based pharmacophore modeling technique was opted to generate 3D pharmacophore models for VEGFR2 and FAK type II kinase inhibitors. The generated pharmacophore models were validated by assessing their ability to discriminate between active and decoy compounds in a pre-compiled test set of VEGFR2 and FAK active compounds and decoys. ZINCPharmer web tool was then used to screen the ZINC database purchasable subset using the validated pharmacophore models retrieving 42,616 hits for VEGFR2 and 28,475 hits for FAK. Subsequently, they were filtered using various filters leaving 13,023 and 6,832 survived compounds for VEGFR2 and FAK, respectively, with 124 common compounds. Based on molecular docking simulations, thirteen compounds were found to satisfy all necessary interactions with VEGFR2 and FAK kinase domains. Thus, they are predicted to have a possible dual VEGFR2/FAK inhibitory activity. Finally, SwissADME web tool showed that compound ZINC09875266 is not only promising in terms of binding pattern to our target kinases, but also in terms of pharmacokinetic properties.

Discovery of dual rho-associated protein kinase 1 (ROCK1)/apoptosis signal-regulating kinase 1 (ASK1) inhibitors as a novel approach for non-alcoholic steatohepatitis (NASH) treatment

In the current study we suggest a novel approach to curb non-alcoholic steatohepatitis (NASH) progression, and we suggest privileged scaffolds for the design of novel compounds for this aim. NASH is an advanced form of non-alcoholic fatty liver disease that can further progress into fibrosis, cirrhosis, and hepatocellular carcinoma. It is a widely emerging disease affecting 25% of the global population and has no current approved treatments. Protein kinases are key regulators of cellular pathways, of which, Rho-associated protein kinase 1 (ROCK1) and apoptosis signal-regulating kinase 1 (ASK1) play an important role in the progression of NASH and they stand out as promising targets for NASH therapy. Interestingly, their kinase domains are found to be similar in sequence and topology; therefore, dual inhibition of ROCK1 and ASK1 is expected to be amenable and could achieve a more favourable outcome. To reach this goal, a training set of ROCK1 and ASK1 protein structures co-crystalized with type 1 (ATP-competitive) inhibitors was constructed to manually generate receptor-based pharmacophore models representing ROCK1 and ASK1 inhibitors' common pharmacophoric features. The models produced were assessed using a test set of both ROCK1 and ASK1 actives and decoys, and their performance was evaluated using different assessment metrics. The best pharmacophore model obtained, showing a Mathew's correlation coefficient (MCC) of 0.71, was then used to screen the ZINC purchasable database retrieving 6178 hits that were filtered accordingly using several medicinal chemistry and pharmacokinetics filters returning 407 promising compounds. To confirm that these compounds are capable of binding to the target kinases, they were subjected to molecular docking simulations at both protein structures. The results were then assessed individually and filtered, setting the spotlight on various privileged scaffolds that could be exploited as the nucleus for designing novel ROCK1/ASK1 dual inhibitors.

Potential Antidiabetic Activity of β-sitosterol from Zingiber roseum Rosc. via Modulation of Peroxisome Proliferator-activated Receptor Gamma (PPARγ)

AIM

To evaluate the antidiabetic potential of β-sitosterol from Zingiber roseum.

BACKGROUND

Diabetes mellitus is a cluster of metabolic disorders, and 90% of diabetic patients are affected with Type II diabetes (DM2). For the treatment of DM2, thiazolidinedione drugs (TZDs) were proposed, but recent studies have shown that TZDs have several detrimental effects, such as weight gain, kidney enlargement (hypertrophy), fluid retention, increased risk of bone fractures, and potential harm to the liver (hepatotoxicity). That is why a new molecule is needed to treat DM2.

OBJECTIVE

The current research aimed to assess the efficacy of β-Sitosterol from methanolic extract of Zingiber roseum in managing diabetes via PPARγ modulation.

METHODS

Zingiber roseum was extracted using methanol, and GC-MS was employed to analyze the extract. Through homology modeling, PPARγ structure was predicted. Molecular docking, MD simulation, free binding energies, QSAR, ADMET, and bioactivity and toxicity scores were all used during the in-depth computer-based research.

RESULTS

Clinically, agonists of synthetic thiazolidinedione (TZDs) have been used therapeutically to treat DM2, but these TZDs are associated with significant risks. Hence, GC-MS identified phytochemicals to search for a new PPAR-γ agonist. Based on the in-silico investigation, β-sitosterol was found to have a higher binding affinity (-8.9 kcal/mol) than standard drugs. MD simulations and MMGBSA analysis also demonstrated that β-sitosterol bound to the PPAR-γ active site stably.

CONCLUSION

It can be concluded that β-sitosterol from Z. roseum attenuates Type-II diabetes by modulating PPARγ activity.

Synthesis, molecular modeling Insights, and anticancer assessment of novel polyfunctionalized Pyridine congeners

The present study describes synthesizing a novel series of polyfunctionalized pyridine congeners 1-18 and assessed for cytotoxic efficacies versus HCT-116, MCF-7, and HepG-2 among one non-cancerous BJ-1 human normal cell. Most compounds were precisely potent anticancer candidate drugs. The molecular impact of the most active compounds 9, 10, 11, 13, 15, and 17 was evaluated after MCF-7 treatment. The gene expression of pro- and ant-apoptosis markers P53, Bax, Caspase-3 and Bcl-2 as well as VEGFR-2 and HER2 were determined. Compounds 13 and 15 induced upregulation of pro-apoptosis of P53, Bax, Caspase-3 and downregulation of anti-apoptosis Bcl-2 gene. However, compound 15 showed higher effect compared to 13 and respective control. Moreover, a slight reduction in HER2 gene expression was detected due to compound 15 treatment, while VEGFR-2 gene was upregulated. In agreement, the immunoblotting analysis showed higher accumulation of P53, Bax, Caspase-3 proteins and of decrease the Bcl-2 protein levels. Furthermore, docking studies united with molecular dynamic simulation exposed compounds 13 and 15 fitting in the middle of the active site at the interface linking the ATP binding site and the allosteric hydrophobic binding pocket. Finally, we performed Petra/Osiris/ Molinspiration (POM) analysis for the newly synthesized compounds. The evaluation of primary in silico parameters revealed significant differences among individual polyfunctionalized pyridine compounds, highlighting the most promising candidates. These preliminary results may help in coordinating and initiating other research projects focused on polyfunctionalized pyridine compounds, especially those with predicted bioactivity, low toxicity, optimal ADME parameters, and promising perspectives.

Metabophore-mediated retro-metabolic ('MeMeReMe') approach in drug design

Preclinical toxicity assessments of new drugs require the use of in silico prediction techniques as ethics, cost, time, and complexity limit in vitro and in vivo methods. This review discusses the fundamental concepts of biophores especially toxicophores and their detection methodologies, tools and techniques, as well as ongoing challenges, and methods for overcoming them. This will guide the design community in manipulating lead compounds via a pre-determined pathway based on the MeMeReMe approach. The ideas discussed will be useful both for predicting toxicity and for de-risking leads through optimization.

Calix[4]arene-pyrazole conjugates as potential cancer therapeutics

Tumor selectivity is yet a challenge in chemotherapy-based cancer treatment. A series of calixarenes derivatized at the lower rim with 3-phenyl-1H-pyrazole units with variable upper-rim substituent and conformations of macrocyclic core, alkyl chain length between heterocycle and core, as well as phenolic monomer (5-(4-tert-butylphenyloxy)methoxy-3-phenyl-1H-pyrazole) have been synthesized and characterized in a range of therapeutically relevant cellular models (M-HeLa, MCF7, A-549, PC3, Chang liver, and Wi38) from different target organs/systems. Specific cytotoxicity for M-HeLa cells has been observed in tert-butylcalix[4]arene pyrazoles in 1,3-alternate (compound 7b) and partial cone (compound 7c) conformations with low mutagenicity and haemotoxicity and in vivo toxicity in mice. Compounds 7b,c have induced mitochondrial pathway of apoptosis of M-HeLa cells through caspase-9 activation preceded by the cell cycle arrest at G0/G1 phase. A concomitant overexpression of DNA damage markers in pyrazole-treated M-HeLa cells suggests that calixarene pyrazoles target DNA, which was supported by the presence of interactions between calixarenes and ctDNA at the air-water interface.

DeepAmes: A deep learning-powered Ames test predictive model with potential for regulatory application

The Ames assay is required by the regulatory agencies worldwide to assess the mutagenic potential risk of consumer products. As well as this in vitro assay, in silico approaches have been widely used to predict Ames test results as outlined in the International Council for Harmonization (ICH) guidelines. Building on this in silico approach, here we describe DeepAmes, a high performance and robust model developed with a novel deep learning (DL) approach for potential utility in regulatory science. DeepAmes was developed with a large and consistent Ames dataset (>10,000 compounds) and was compared with other five standard Machine Learning (ML) methods. Using a test set of 1,543 compounds, DeepAmes was the best performer in predicting the outcome of Ames assay. In addition, DeepAmes yielded the best and most stable performance up to when compounds were >30% outside of the applicability domain (AD). Regarding the potential for regulatory application, a revised version of DeepAmes with a much-improved sensitivity of 0.87 from 0.47. In conclusion, DeepAmes provides a DL-powered Ames test predictive model for predicting the results of Ames tests; with its defined AD and clear context of use, DeepAmes has potential for utility in regulatory application.

Revolutionizing Medicinal Chemistry: The Application of Artificial Intelligence (AI) in Early Drug Discovery

Artificial intelligence (AI) has permeated various sectors, including the pharmaceutical industry and research, where it has been utilized to efficiently identify new chemical entities with desirable properties. The application of AI algorithms to drug discovery presents both remarkable opportunities and challenges. This review article focuses on the transformative role of AI in medicinal chemistry. We delve into the applications of machine learning and deep learning techniques in drug screening and design, discussing their potential to expedite the early drug discovery process. In particular, we provide a comprehensive overview of the use of AI algorithms in predicting protein structures, drug-target interactions, and molecular properties such as drug toxicity. While AI has accelerated the drug discovery process, data quality issues and technological constraints remain challenges. Nonetheless, new relationships and methods have been unveiled, demonstrating AI's expanding potential in predicting and understanding drug interactions and properties. For its full potential to be realized, interdisciplinary collaboration is essential. This review underscores AI's growing influence on the future trajectory of medicinal chemistry and stresses the importance of ongoing synergies between computational and domain experts.

A Review on the Recent Applications of Deep Learning in Predictive Drug Toxicological Studies

Drug toxicity prediction is an important step in ensuring patient safety during drug design studies. While traditional preclinical studies have historically relied on animal models to evaluate toxicity, recent advances in deep-learning approaches have shown great promise in advancing drug safety science and reducing animal use in preclinical studies. However, deep-learning-based approaches also face challenges in handling large biological data sets, model interpretability, and regulatory acceptance. In this review, we provide an overview of recent developments in deep-learning-based approaches for predicting drug toxicity, highlighting their potential advantages over traditional methods and the need to address their limitations. Deep-learning models have demonstrated excellent performance in predicting toxicity outcomes from various data sources such as chemical structures, genomic data, and high-throughput screening assays. The potential of deep learning for automated feature engineering is also discussed. This review emphasizes the need to address ethical concerns related to the use of deep learning in drug toxicity studies, including the reduction of animal use and ensuring regulatory acceptance. Furthermore, emerging applications of deep learning in drug toxicity prediction, such as predicting drug-drug interactions and toxicity in rare subpopulations, are highlighted. The integration of deep-learning-based approaches with traditional methods is discussed as a way to develop more reliable and efficient predictive models for drug safety assessment, paving the way for safer and more effective drug discovery and development. Overall, this review highlights the critical role of deep learning in predictive toxicology and drug safety evaluation, emphasizing the need for continued research and development in this rapidly evolving field. By addressing the limitations of traditional methods, leveraging the potential of deep learning for automated feature engineering, and addressing ethical concerns, deep-learning-based approaches have the potential to revolutionize drug toxicity prediction and improve patient safety in drug discovery and development.

On Using Classification Datasets to Evaluate Graph Outlier Detection: Peculiar Observations and New Insights

It is common practice of the outlier mining community to repurpose classification datasets toward evaluating various detection models. To that end, often a binary classification dataset is used, where samples from one of the classes are designated as the "inlier" samples, and the other class is substantially down-sampled to create the (ground-truth) "outlier" samples. Graph-level outlier detection (GLOD) is rarely studied but has many potentially influential real-world applications. In this study, we identify an intriguing issue with repurposing graph classification datasets for GLOD. We find that ROC-AUC performance of the models changes significantly ("flips" from high to very low, even worse than random) depending on which class is down-sampled. Interestingly, ROC-AUCs on these two variants approximately sum to 1 and their performance gap is amplified with increasing propagations for a certain family of propagation-based outlier detection models. We carefully study the graph embedding space produced by propagation-based models and find two driving factors: (1) disparity between within-class densities, which is amplified by propagation, and (2) overlapping support (mixing of embeddings) across classes. We also study other graph embedding methods and downstream outlier detectors, and we find that the intriguing "performance flip" issue still widely exists but which version of the down-sample achieves higher performance may vary. Thoughtful analysis over comprehensive results further deepens our understanding of the established issue. With this study, we aim at drawing attention to this (to our knowledge) previously unnoticed issue for the rarely studied GLOD problem, and specifically to the following questions: (1) Given the performance flip issue we identified, where one version of the down-sample often yields worse-than-random performance, is it appropriate to evaluate GLOD by average performance across all down-sampled versions when repurposing graph classification datasets? (2) Considering consistently observed performance flip issue across different graph embedding methods we studied, is it possible to design better graph embedding methods to overcome the issue? We conclude the article with our insights to these questions.

Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking

Graph neural networks (GNNs) have been widely used in molecular property prediction, but explaining their black-box predictions is still a challenge. Most existing explanation methods for GNNs in chemistry focus on attributing model predictions to individual nodes, edges or fragments that are not necessarily derived from a chemically meaningful segmentation of molecules. To address this challenge, we propose a method named substructure mask explanation (SME). SME is based on well-established molecular segmentation methods and provides an interpretation that aligns with the understanding of chemists. We apply SME to elucidate how GNNs learn to predict aqueous solubility, genotoxicity, cardiotoxicity and blood-brain barrier permeation for small molecules. SME provides interpretation that is consistent with the understanding of chemists, alerts them to unreliable performance, and guides them in structural optimization for target properties. Hence, we believe that SME empowers chemists to confidently mine structure-activity relationship (SAR) from reliable GNNs through a transparent inspection on how GNNs pick up useful signals when learning from data.

Artificial Intelligence in Drug Toxicity Prediction: Recent Advances, Challenges, and Future Perspectives

Toxicity prediction is a critical step in the drug discovery process that helps identify and prioritize compounds with the greatest potential for safe and effective use in humans, while also reducing the risk of costly late-stage failures. It is estimated that over 30% of drug candidates are discarded owing to toxicity. Recently, artificial intelligence (AI) has been used to improve drug toxicity prediction as it provides more accurate and efficient methods for identifying the potentially toxic effects of new compounds before they are tested in human clinical trials, thus saving time and money. In this review, we present an overview of recent advances in AI-based drug toxicity prediction, including the use of various machine learning algorithms and deep learning architectures, of six major toxicity properties and Tox21 assay end points. Additionally, we provide a list of public data sources and useful toxicity prediction tools for the research community and highlight the challenges that must be addressed to enhance model performance. Finally, we discuss future perspectives for AI-based drug toxicity prediction. This review can aid researchers in understanding toxicity prediction and pave the way for new methods of drug discovery.

Accurate clinical toxicity prediction using multi-task deep neural nets and contrastive molecular explanations

Explainable machine learning for molecular toxicity prediction is a promising approach for efficient drug development and chemical safety. A predictive ML model of toxicity can reduce experimental cost and time while mitigating ethical concerns by significantly reducing animal and clinical testing. Herein, we use a deep learning framework for simultaneously modeling in vitro, in vivo, and clinical toxicity data. Two different molecular input representations are used; Morgan fingerprints and pre-trained SMILES embeddings. A multi-task deep learning model accurately predicts toxicity for all endpoints, including clinical, as indicated by the area under the Receiver Operator Characteristic curve and balanced accuracy. In particular, pre-trained molecular SMILES embeddings as input to the multi-task model improved clinical toxicity predictions compared to existing models in MoleculeNet benchmark. Additionally, our multitask approach is comprehensive in the sense that it is comparable to state-of-the-art approaches for specific endpoints in in vitro, in vivo and clinical platforms. Through both the multi-task model and transfer learning, we were able to indicate the minimal need of in vivo data for clinical toxicity predictions. To provide confidence and explain the model's predictions, we adapt a post-hoc contrastive explanation method that returns pertinent positive and negative features, which correspond well to known mutagenic and reactive toxicophores, such as unsubstituted bonded heteroatoms, aromatic amines, and Michael receptors. Furthermore, toxicophore recovery by pertinent feature analysis captures more of the in vitro (53%) and in vivo (56%), rather than of the clinical (8%), endpoints, and indeed uncovers a preference in known toxicophore data towards in vitro and in vivo experimental data. To our knowledge, this is the first contrastive explanation, using both present and absent substructures, for predictions of clinical and in vivo molecular toxicity.

Evaluating explainability for graph neural networks

As explanations are increasingly used to understand the behavior of graph neural networks (GNNs), evaluating the quality and reliability of GNN explanations is crucial. However, assessing the quality of GNN explanations is challenging as existing graph datasets have no or unreliable ground-truth explanations. Here, we introduce a synthetic graph data generator, SHAPEGGEN, which can generate a variety of benchmark datasets (e.g., varying graph sizes, degree distributions, homophilic vs. heterophilic graphs) accompanied by ground-truth explanations. The flexibility to generate diverse synthetic datasets and corresponding ground-truth explanations allows SHAPEGGEN to mimic the data in various real-world areas. We include SHAPEGGEN and several real-world graph datasets in a graph explainability library, GRAPHXAI. In addition to synthetic and real-world graph datasets with ground-truth explanations, GRAPHXAI provides data loaders, data processing functions, visualizers, GNN model implementations, and evaluation metrics to benchmark GNN explainability methods.

Quantum-Mechanical Approach to Predicting the Carcinogenic Potency of N-Nitroso Impurities in Pharmaceuticals

N-Nitroso contaminants in medicinal products are of concern due to their high carcinogenic potency; however, not all these compounds are created equal, and some are relatively benign chemicals. Understanding the structure-activity relationships (SARs) that drive hazards in one molecule versus another is key to both protecting human health and alleviating costly and sometimes inaccurate animal testing. Here, we report on an extension of the CADRE (computer-aided discovery and REdesign) platform, which is used broadly by the pharmaceutical and personal care industries to assess environmental and human health endpoints, to predict the carcinogenic potency of N-nitroso compounds. The model distinguishes compounds in three potency categories with 77% accuracy in external testing, which surpasses the reproducibility of rodent cancer bioassays and constraints imposed by limited (high-quality) data. The robustness of predictions for more complex pharmaceuticals is maximized by capturing key SARs using quantum mechanics, that is, by hinging the model on the underlying chemistry versus chemicals in the training set. To this end, the present approach can be leveraged in a quantitative hazard assessment and to offer qualitative guidance using electronic structure comparisons between well-studied analogues and unknown contaminants.

Assessing machine learning approaches for predicting failures of investigational drug candidates during clinical trials

One of the major challenges in drug development is having acceptable levels of efficacy and safety throughout all the phases of clinical trials followed by the successful launch in the market. While there are many factors such as molecular properties, toxicity parameters, mechanism of action at the target site, etc. that regulates the therapeutic action of a compound, a holistic approach directed towards data-driven studies will invariably strengthen the predictive toxicological sciences. Our quest for the current study is to find out various reasons as to why an investigational candidate would fail in the clinical trials after multiple iterations of refinement and optimization. We have compiled a dataset that comprises of approved and withdrawn drugs as well as toxic compounds and essentially have used time-split based approach to generate the training and validation set. Five highly robust and scalable machine learning binary classifiers were used to develop the predictive models that were trained with features like molecular descriptors and fingerprints and then validated rigorously to achieve acceptable performance in terms of a set of performance metrics. The mean AUC scores for all the five classifiers with the hold-out test set were obtained in the range of 0.66-0.71. The models were further used to predict the probability score for the clinical candidate dataset. The top compounds predicted to be toxic were analyzed to estimate different dimensions of toxicity. Apparently, through this study, we propose that with the appropriate use of feature extraction and machine learning methods, one can estimate the likelihood of success or failure of investigational drugs candidates thereby opening an avenue for future trends in computational toxicological studies. The models developed in the study can be accessed at https://github.com/gnsastry/predicting_clinical_trials.git.

Reinforced Causal Explainer for Graph Neural Networks

Explainability is crucial for probing graph neural networks (GNNs), answering questions like "Why the GNN model makes a certain prediction?". Feature attribution is a prevalent technique of highlighting the explanatory subgraph in the input graph, which plausibly leads the GNN model to make its prediction. Various attribution methods have been proposed to exploit gradient-like or attention scores as the attributions of edges, then select the salient edges with top attribution scores as the explanation. However, most of these works make an untenable assumption - the selected edges are linearly independent - thus leaving the dependencies among edges largely unexplored, especially their coalition effect. We demonstrate unambiguous drawbacks of this assumption - making the explanatory subgraph unfaithful and verbose. To address this challenge, we propose a reinforcement learning agent, Reinforced Causal Explainer (RC-Explainer). It frames the explanation task as a sequential decision process - an explanatory subgraph is successively constructed by adding a salient edge to connect the previously selected subgraph. Technically, its policy network predicts the action of edge addition, and gets a reward that quantifies the action's causal effect on the prediction. Such reward accounts for the dependency of the newly-added edge and the previously-added edges, thus reflecting whether they collaborate together and form a coalition to pursue better explanations. It is trained via policy gradient to optimize the reward stream of edge sequences. As such, RC-Explainer is able to generate faithful and concise explanations, and has a better generalization power to unseen graphs. When explaining different GNNs on three graph classification datasets, RC-Explainer achieves better or comparable performance to state-of-the-art approaches w.r.t. two quantitative metrics: predictive accuracy, contrastivity, and safely passes sanity checks and visual inspections. Codes and datasets are available at https://github.com/xiangwang1223/reinforced_causal_explainer.

Artificial neural networks in contemporary toxicology research

Artificial neural networks (ANNs) have a huge potential in toxicology research. They may be used to predict toxicity of various chemical compounds or classify the compounds based on their toxic effects. Today, numerous ANN models have been developed, some of which may be used to detect and possibly explain complex chemico-biological interactions. Fully connected multilayer perceptrons may in some circumstances have high classification accuracy and discriminatory power in separating damaged from intact cells after exposure to a toxic substance. Regularized and not fully connected convolutional neural networks can detect and identify discrete changes in patterns of two-dimensional data associated with toxicity. Bayesian neural networks with weight marginalization sometimes may have better prediction performance when compared to traditional approaches. With the further development of artificial intelligence, it is expected that ANNs will in the future become important parts of various accurate and affordable biosensors for detection of various toxic substances and evaluation of their biochemical properties. In this concise review article, we discuss the recent research focused on the scientific value of ANNs in evaluation and prediction of toxicity of chemical compounds.

Supervised chemical graph mining improves drug-induced liver injury prediction

Drug-induced liver injury (DILI) is the main cause of drug failure in clinical trials. The characterization of toxic compounds in terms of chemical structure is important because compounds can be metabolized to toxic substances in the liver. Traditional machine learning approaches have had limited success in predicting DILI, and emerging deep graph neural network (GNN) models are yet powerful enough to predict DILI. In this study, we developed a completely different approach, supervised subgraph mining (SSM), a strategy to mine explicit subgraph features by iteratively updating individual graph transitions to maximize DILI fidelity. Our method outperformed previous methods including state-of-the-art GNN tools in classifying DILI on two different datasets: DILIst and TDC-benchmark. We also combined the subgraph features by using SMARTS-based frequent structural pattern matching and associated them with drugs' ATC code.

Multitask Deep Neural Networks for Ames Mutagenicity Prediction

The Ames mutagenicity test constitutes the most frequently used assay to estimate the mutagenic potential of drug candidates. While this test employs experimental results using various strains of Salmonella typhimurium, the vast majority of the published in silico models for predicting mutagenicity do not take into account the test results of the individual experiments conducted for each strain. Instead, such QSAR models are generally trained employing overall labels (i.e., mutagenic and nonmutagenic). Recently, neural-based models combined with multitask learning strategies have yielded interesting results in different domains, given their capabilities to model multitarget functions. In this scenario, we propose a novel neural-based QSAR model to predict mutagenicity that leverages experimental results from different strains involved in the Ames test by means of a multitask learning approach. To the best of our knowledge, the modeling strategy hereby proposed has not been applied to model Ames mutagenicity previously. The results yielded by our model surpass those obtained by single-task modeling strategies, such as models that predict the overall Ames label or ensemble models built from individual strains. For reproducibility and accessibility purposes, all source code and datasets used in our experiments are publicly available.

MS2Tox Machine Learning Tool for Predicting the Ecotoxicity of Unidentified Chemicals in Water by Nontarget LC-HRMS

To achieve water quality objectives of the zero pollution action plan in Europe, rapid methods are needed to identify the presence of toxic substances in complex water samples. However, only a small fraction of chemicals detected with nontarget high-resolution mass spectrometry can be identified, and fewer have ecotoxicological data available. We hypothesized that ecotoxicological data could be predicted for unknown molecular features in data-rich high-resolution mass spectrometry (HRMS) spectra, thereby circumventing time-consuming steps of molecular identification and rapidly flagging molecules of potentially high toxicity in complex samples. Here, we present MS2Tox, a machine learning method, to predict the toxicity of unidentified chemicals based on high-resolution accurate mass tandem mass spectra (MS²). The MS2Tox model for fish toxicity was trained and tested on 647 lethal concentration (LC₅₀) values from the CompTox database and validated for 219 chemicals and 420 MS² spectra from MassBank. The root mean square error (RMSE) of MS2Tox predictions was below 0.89 log-mM, while the experimental repeatability of LC₅₀ values in CompTox was 0.44 log-mM. MS2Tox allowed accurate prediction of fish LC₅₀ values for 22 chemicals detected in water samples, and empirical evidence suggested the right directionality for another 68 chemicals. Moreover, by incorporating structural information, e.g., the presence of carbonyl-benzene, amide moieties, or hydroxyl groups, MS2Tox outperforms baseline models that use only the exact mass or log K_OW.

GSAML-DTA: An interpretable drug-target binding affinity prediction model based on graph neural networks with self-attention mechanism and mutual information

Identifying drug-target affinity (DTA) has great practical importance in the process of designing efficacious drugs for known diseases. Recently, numerous deep learning-based computational methods have been developed to predict drug-target affinity and achieved impressive performance. However, most of them construct the molecule (drug or target) encoder without considering the weights of features of each node (atom or residue). Besides, they generally combine drug and target representations directly, which may contain irrelevant-task information. In this study, we develop GSAML-DTA, an interpretable deep learning framework for DTA prediction. GSAML-DTA integrates a self-attention mechanism and graph neural networks (GNNs) to build representations of drugs and target proteins from the structural information. In addition, mutual information is introduced to filter out redundant information and retain relevant information in the combined representations of drugs and targets. Extensive experimental results demonstrate that GSAML-DTA outperforms state-of-the-art methods for DTA prediction on two benchmark datasets. Furthermore, GSAML-DTA has the interpretation ability to analyze binding atoms and residues, which may be conducive to chemical biology studies from data. Overall, GSAML-DTA can serve as a powerful and interpretable tool suitable for DTA modelling.

Hierarchical Virtual Screening and Binding Free Energy Prediction of Potential Modulators of Aedes Aegypti Odorant-Binding Protein 1

The Aedes aegypti mosquito is the main hematophagous vector responsible for arbovirus transmission in Brazil. The disruption of A. aegypti hematophagy remains one of the most efficient and least toxic methods against these diseases and, therefore, efforts in the research of new chemical entities with repellent activity have advanced due to the elucidation of the functionality of the olfactory receptors and the behavior of mosquitoes. With the growing interest of the pharmaceutical and cosmetic industries in the development of chemical entities with repellent activity, computational studies (e.g., virtual screening and molecular modeling) are a way to prioritize potential modulators with stereoelectronic characteristics (e.g., pharmacophore models) and binding affinity to the AaegOBP1 binding site (e.g., molecular docking) at a lower computational cost. Thus, pharmacophore- and docking-based virtual screening was employed to prioritize compounds from Sigma-Aldrich® (n = 126,851) and biogenic databases (n = 8766). In addition, molecular dynamics (MD) was performed to prioritize the most potential potent compounds compared to DEET according to free binding energy calculations. Two compounds showed adequate stereoelectronic requirements (QFIT > 81.53), AaegOBP1 binding site score (Score > 42.0), volatility and non-toxic properties and better binding free energy value (∆G < −24.13 kcal/mol) compared to DEET ((N,N-diethyl-meta-toluamide)) (∆G = −24.13 kcal/mol).

toxCSM: comprehensive prediction of small molecule toxicity profiles

Drug discovery is a lengthy, costly and high-risk endeavour that is further convoluted by high attrition rates in later development stages. Toxicity has been one of the main causes of failure during clinical trials, increasing drug development time and costs. To facilitate early identification and optimisation of toxicity profiles, several computational tools emerged aiming at improving success rates by timely pre-screening drug candidates. Despite these efforts, there is an increasing demand for platforms capable of assessing both environmental as well as human-based toxicity properties at large scale. Here, we present toxCSM, a comprehensive computational platform for the study and optimisation of toxicity profiles of small molecules. toxCSM leverages on the well-established concepts of graph-based signatures, molecular descriptors and similarity scores to develop 36 models for predicting a range of toxicity properties, which can assist in developing safer drugs and agrochemicals. toxCSM achieved an Area Under the Receiver Operating Characteristic (ROC) Curve (AUC) of up to 0.99 and Pearson's correlation coefficients of up to 0.94 on 10-fold cross-validation, with comparable performance on blind test sets, outperforming all alternative methods. toxCSM is freely available as a user-friendly web server and API at http://biosig.lab.uq.edu.au/toxcsm.

Location-aware convolutional neural networks for graph classification

Graph patterns play a critical role in various graph classification tasks, e.g., chemical patterns often determine the properties of molecular graphs. Researchers devote themselves to adapting Convolutional Neural Networks (CNNs) to graph classification due to their powerful capability in pattern learning. The varying numbers of neighbor nodes and the lack of canonical order of nodes on graphs pose challenges in constructing receptive fields for CNNs. Existing methods generally follow a heuristic ranking-based framework, which constructs receptive fields by selecting a fixed number of nodes and dropping the others according to predetermined rules. However, such methods may lose important structure information through dropping nodes, and they also cannot learn task-oriented graph patterns. In this paper, we propose a Location learning-based Convolutional Neural Networks (LCNN) for graph classification. LCNN constructs receptive fields by learning the location of each node according to its embedding that contains structures and features information, then standard CNNs are applied to capture graph patterns. Such a location learning mechanism not only retains the information of all nodes, but also provides the ability for task-oriented pattern learning. Experimental results show the effectiveness of the proposed LCNN, and visualization results further illustrate the valid pattern learning ability of our method for graph classification.

Classification models and SAR analysis on thromboxane A2 synthase inhibitors by machine learning methods

Thromboxane A2 synthase (TXS) is a promising drug target for cardiovascular diseases and cancer. In this work, we conducted a structure-activity relationship (SAR) study on 526 TXS inhibitors for bioactivity prediction. Three types of descriptors (MACCS fingerprints, ECFP4 fingerprints, and MOE descriptors) were utilized to characterize inhibitors, 24 classification models were developed by support vector machine (SVM), random forest (RF), extreme gradient boosting (XGBoost), and deep neural networks (DNN). Then we reduced the number of fingerprints according to the contribution of descriptors to the models, and constructed 16 extra models on simplified fingerprints. In general, Model_4D built by DNN algorithm and 67 bits MACCS fingerprints performs best. The prediction accuracy of the model on the test set is 0.969, and Matthews correlation coefficient (MCC) is 0.936. The distance between compound and model (dSTD-PRO) was used to characterize the application domain of the model. In the test set of Model_4D, dSTD-PRO of 91.5% compounds is lower than the corresponding training set threshold (threshold0.90 = 0.1055), and the accuracy of these compounds is 0.983. In addition, the important descriptors were summarized and further analyzed. It showed that aromatic nitrogenous heterocyclic groups were beneficial to improve the bioactivity of TXS inhibitors.

On Information Granulation via Data Clustering for Granular Computing-Based Pattern Recognition: A Graph Embedding Case Study

Granular Computing is a powerful information processing paradigm, particularly useful for the synthesis of pattern recognition systems in structured domains (e.g., graphs or sequences). According to this paradigm, granules of information play the pivotal role of describing the underlying (possibly complex) process, starting from the available data. Under a pattern recognition viewpoint, granules of information can be exploited for the synthesis of semantically sound embedding spaces, where common supervised or unsupervised problems can be solved via standard machine learning algorithms. In this work, we show a comparison between different strategies for the automatic synthesis of information granules in the context of graph classification. These strategies mainly differ on the specific topology adopted for subgraphs considered as candidate information granules and the possibility of using or neglecting the ground-truth class labels in the granulation process. Computational results on 10 different open-access datasets show that by using a class-aware granulation, performances tend to improve (regardless of the information granules topology), counterbalanced by a possibly higher number of information granules.

Jumping From Fragment To Drug Via Smart Scaffolds

A focused drug repurposing approach is described where an FDA-approved drug is rationally selected for biological testing based on structural similarities to a fragment compound found to bind a target protein by an NMR screen. The approach is demonstrated by first screening a curated fragment library using 19F NMR to discover a quality binder to ACE2, the human receptor required for entry and infection by the SARS-CoV-2 virus. Based on this binder, a highly related scaffold was derived and used as a "smart scaffold" or template in a computer-aided finger-print search of a library of FDA-approved or marketed drugs. The most interesting structural match involved the drug vortioxetine which was then experimentally shown by NMR spectroscopy to bind directly to human ACE2. Also, an ELISA assay showed that the drug inhibits the interaction of human ACE2 to the SARS-CoV-2 receptor-binding-domain (RBD). Moreover, our cell-culture infectivity assay confirmed that vortioxetine is active against SARS-CoV-2 and inhibits viral replication. Thus, the use of "smart scaffolds" based on binders from fragment screens may have general utility for identifying candidates of FDA-approved or marketed drugs as a rapid repurposing strategy. Similar approaches can be envisioned for other fields involving small-molecule chemical applications.

Use of Lhasa Limited Products for the In Silico Prediction of Drug Toxicity

Lhasa Limited have had a role in the in silico prediction of drug and other chemical toxicity for over 30 years. This role has always been multifaceted, both as a provider of predictive software such as Derek Nexus, and as an honest broker for the sharing of proprietary chemical and toxicity data. A changing regulatory environment and the drive for the Replacement, Reduction and Refinement (the 3Rs) of animal testing have led both to increased acceptance of in silico predictions and a desire for the sharing of data to reduce duplicate testing. The combination of these factors has led to Lhasa Limited providing a suite of products and coordinating numerous data-sharing consortia that do indeed facilitate a significant reduction in the testing burden that companies would otherwise be laboring under. Many of these products and consortia can be organized into workflows for specific regulatory use cases, and it is these that will be used to frame the narrative in this chapter.

The Chemical Property Position of Bedaquiline Construed by a Chemical Global Positioning System-Natural Product

Bedaquiline is a novel adenosine triphosphate synthase inhibitor anti-tuberculosis drug. Bedaquiline belongs to the class of diarylquinolines, which are antituberculosis drugs that are quite different mechanistically from quinolines and flouroquinolines. The fact that relatively similar chemical drugs produce different mechanisms of action is still not widely understood. To enhance discrimination in favor of bedaquiline, a new approach using eight-score principal component analysis (PCA), provided by a ChemGPS-NP model, is proposed. PCA scores were calculated based on 35 + 1 different physicochemical properties and demonstrated clear differences when compared with other quinolines. The ChemGPS-NP model provided an exceptional 100 compounds nearest to bedaquiline from antituberculosis screening sets (with a cumulative Euclidian distance of 196.83), compared with the different 2Dsimilarity provided by Tanimoto methods (extended connective fingerprints and the Molecular ACCess System, showing 30% and 182% increases in cumulative Euclidian distance, respectively). Potentially similar compounds from publicly available antituberculosis compounds and Maybridge sets, based on bedaquiline’s eight-dimensional similarity and different filtrations, were identified too.

The Chemical Property Position of Bedaquiline Construed by a Chemical Global Positioning System-Natural Product

Bedaquiline is a novel adenosine triphosphate synthase inhibitor anti-tuberculosis drug. Bedaquiline belongs to the class of diarylquinolines, which are antituberculosis drugs that are quite different mechanistically from quinolines and flouroquinolines. The fact that relatively similar chemical drugs produce different mechanisms of action is still not widely understood. To enhance discrimination in favor of bedaquiline, a new approach using eight-score principal component analysis (PCA), provided by a ChemGPS-NP model, is proposed. PCA scores were calculated based on 35 + 1 different physicochemical properties and demonstrated clear differences when compared with other quinolines. The ChemGPS-NP model provided an exceptional 100 compounds nearest to bedaquiline from antituberculosis screening sets (with a cumulative Euclidian distance of 196.83), compared with the different 2Dsimilarity provided by Tanimoto methods (extended connective fingerprints and the Molecular ACCess System, showing 30% and 182% increases in cumulative Euclidian distance, respectively). Potentially similar compounds from publicly available antituberculosis compounds and Maybridge sets, based on bedaquiline’s eight-dimensional similarity and different filtrations, were identified too.

MGraphDTA: deep multiscale graph neural network for explainable drug-target binding affinity prediction

Predicting drug-target affinity (DTA) is beneficial for accelerating drug discovery. Graph neural networks (GNNs) have been widely used in DTA prediction. However, existing shallow GNNs are insufficient to capture the global structure of compounds. Besides, the interpretability of the graph-based DTA models highly relies on the graph attention mechanism, which can not reveal the global relationship between each atom of a molecule. In this study, we proposed a deep multiscale graph neural network based on chemical intuition for DTA prediction (MGraphDTA). We introduced a dense connection into the GNN and built a super-deep GNN with 27 graph convolutional layers to capture the local and global structure of the compound simultaneously. We also developed a novel visual explanation method, gradient-weighted affinity activation mapping (Grad-AAM), to analyze a deep learning model from the chemical perspective. We evaluated our approach using seven benchmark datasets and compared the proposed method to the state-of-the-art deep learning (DL) models. MGraphDTA outperforms other DL-based approaches significantly on various datasets. Moreover, we show that Grad-AAM creates explanations that are consistent with pharmacologists, which may help us gain chemical insights directly from data beyond human perception. These advantages demonstrate that the proposed method improves the generalization and interpretation capability of DTA prediction modeling.

Increasing the Value of Data Within a Large Pharmaceutical Company Through In Silico Models

The present contribution describes how in silico models and methods are applied at different stages of the drug discovery process in the pharmaceutical industry. A description of the most relevant computational methods and tools is given along with an evaluation of their performance in the assessment of potential genotoxic impurities and the prediction of off-target in vitro pharmacology. The challenges of predicting the outcome of highly complex in vivo studies are discussed followed by considerations on how novel ways to manage, store, exchange, and analyze data may advance knowledge and facilitate modeling efforts. In this context, the current status of broad data sharing initiatives, namely, eTOX and eTransafe, will be described along with related projects that could significantly reduce the use of animals in drug discovery in the future.