Evaluation of Different Methods for Identification of Structural Alerts Using Chemical Ames Mutagenicity Data Set as a Benchmark

In Silico Prediction of ERRα Agonists Based on Combined Features and Stacking Ensemble Method

Estrogen-related receptor α (ERRα) is considered a very promising target for treating metabolic diseases such as type 2 diabetes. Development of a prediction model to quickly identify potential ERRα agonists can significantly reduce the time spent on virtual screening. In this study, 298 ERRα agonists and numerous nonagonists were collected from various sources to build a new dataset of ERRα agonists. Then a total of 90 models were built using a combination of different algorithms, molecular characterization methods, and data sampling techniques. The consensus model with optimal performance was also validated on the test set (AUC=0.876, BA=0.816) and external validation set (AUC=0.867, BA=0.777) based on five selected baseline models. Furthermore, the model's applicability domain and privileged substructures were examined, and the feature importance was analyzed using the SHAP method to help interpret the model. Based on the above, it's hoped that our publicly accessible data, models, codes, and analytical techniques will prove valuable in quick screening and rational designing more novel and potent ERRα agonists.

Fragment-based structural exploration and chemico-biological interaction study of HDAC3 inhibitors through non-linear pattern recognition, chemical space, and binding mode of interaction analysis

HDAC3 is an emerging target for the identification and discovery of novel drug candidates against several disease conditions including cancer. Here, a fragment-based non-linear machine learning (ML) method along with chemical space exploration followed by a structure-based binding mode of interaction analysis study was carried out on some HDAC3 inhibitors to obtain the key structural features modulating HDAC3 inhibition. Both the ML and chemical space analysis identified several physicochemical and structural properties namely lipophilicity, polar and relative polar surface area, arylcarboxamide moiety, bulky fused aromatic group, n-alkyl, and cinnamoyl moieties, the higher number of oxygen atoms, π-electrons for the substituted tetrahydrofuronaphthodioxolone moiety favorable for higher HDAC3 inhibition. Moreover, hydrogen bond forming capabilities, the length and substitution position of the linker moiety, the importance of phenyl ring in the linker motif, the contribution of heterocyclic cap moieties for effective inhibitor binding at the HDAC3 catalytic site that correspondingly affects the HDAC3 inhibitory potency. Again, macrocyclic ring structure and cyclohexyl cap moiety are responsible for lower HDAC3 inhibition. The MD simulation study of selected compounds explained strong binding patterns at the HDAC3 active site as evidenced by the lower RMSD and RMSF values. Nevertheless, it also explained the importance of the crucial structural fragments derived from the fragment-based analysis during ligand-enzyme interactions. Therefore, the outcomes of this current structural analysis will be a useful tool for fragment-based drug discovery of effective HDAC3 inhibitors for clinical therapeutics in the future.Communicated by Ramaswamy H. Sarma.

Exploring molecular fragments for fraction unbound in human plasma of chemicals: a fragment-based cheminformatics approach

Fraction unbound in plasma (fu,p) of drugs is an significant factor for drug delivery and other biological incidences related to the pharmacokinetic behaviours of drugs. Exploration of different molecular fragments for fu,p of different small molecules/agents can facilitate in identification of suitable candidates in the preliminary stage of drug discovery. Different researchers have implemented strategies to build several prediction models for fu,p of different drugs. However, these studies did not focus on the identification of responsible molecular fragments to determine the fraction unbound in plasma. In the current work, we tried to focus on the development of robust classification-based QSAR models and evaluated these models with multiple statistical metrics to identify essential molecular fragments/structural attributes for fractions unbound in plasma. The study unequivocally suggests various N-containing aromatic rings and aliphatic groups have positive influences and sulphur-containing thiadiazole rings have negative influences for the fu,p values. The molecular fragments may help for the assessment of the fu,p values of different small molecules/drugs in a speedy way in comparison to experiment-based in vivo and in vitro studies.

Exploring different classification-dependent QSAR modelling strategies for HDAC3 inhibitors in search of meaningful structural contributors

Histone deacetylase 3 (HDAC3), a Zn2+-dependent class I HDACs, contributes to numerous disorders such as neurodegenerative disorders, diabetes, cardiovascular disease, kidney disease and several types of cancers. Therefore, the development of novel and selective HDAC3 inhibitors might be promising to combat such diseases. Here, different classification-based molecular modelling studies such as Bayesian classification, recursive partitioning (RP), SARpy and linear discriminant analysis (LDA) were conducted on a set of HDAC3 inhibitors to pinpoint essential structural requirements contributing to HDAC3 inhibition followed by molecular docking study and molecular dynamics (MD) simulation analyses. The current study revealed the importance of hydroxamate function for Zn2+ chelation as well as hydrogen bonding interaction with Tyr298 residue. The importance of hydroxamate function for higher HDAC3 inhibition was noticed in the case of Bayesian classification, recursive partitioning and SARpy models. Also, the importance of substituted thiazole ring was revealed, whereas the presence of linear alkyl groups with carboxylic acid function, any type of ester function, benzodiazepine moiety and methoxy group in the molecular structure can be detrimental to HDAC3 inhibition. Therefore, this study can aid in the design and discovery of effective novel HDAC3 inhibitors in the future.

Exploring crucial structural attributes of quinolinyl methoxyphenyl sulphonyl-based hydroxamate derivatives as ADAM17 inhibitors through classification-dependent molecular modelling approaches

A Disintegrin and Metalloproteinase 17 (ADAM17), a Zn2+-dependent metalloenzyme of the adamalysin family of the metzincin superfamily, is associated with various pathophysiological conditions including rheumatoid arthritis and cancer. However, no specific inhibitors have been marketed yet for ADAM17-related disorders. In this study, 94 quinolinyl methoxyphenyl sulphonyl-based hydroxamates as ADAM17 inhibitors were subjected to classification-based molecular modelling and binding pattern analysis to identify the significant structural attributes contributing to ADAM17 inhibition. The statistically validated classification-based models identified the importance of the P1' substituents such as the quinolinyl methoxyphenyl sulphonyl group of these compounds for occupying the S1' - S3' pocket of the enzyme. The quinolinyl function of these compounds was found to explore stable binding of the P1' substituents at the S1' - S3' pocket whereas the importance of the sulphonyl and the orientation of the P1' moiety also revealed stable binding. Based on the outcomes of the current study, four novel compounds of different classes were designed as promising ADAM17 inhibitors. These findings regarding the crucial structural aspects and binding patterns of ADAM17 inhibitors will aid the design and discovery of novel and effective ADAM17 inhibitors for therapeutic advancements of related diseases.

Deep Learning Algorithm Based on Molecular Fingerprint for Prediction of Drug-Induced Liver Injury

Drug-induced liver injury (DILI) is one the rare adverse drug reaction (ADR) and multifactorial endpoints. Current preclinical animal models struggle to anticipate it, and in silico methods have emerged as a way with significant potential for doing so. In this study, a high-quality dataset of 1573 compounds was assembled. The 48 classification models, which depended on six different molecular fingerprints, were built via deep neural network (DNN) and seven machine learning algorithms. Comparing the results of the DNN and machine learning models, the optional performing model was found as the one developed based on the DNN with ECFP_6 as input, which achieved the area under the receiver operating characteristic curve (AUC) of 0.713, balanced accuracy (BA) of 0.680, and F1 of 0.753. In addition, we used the SHapley Additive exPlanations (SHAP) algorithm to interpret the models, identified the crucial structural fragments related to DILI risk, and selected the top ten substructures with the highest contribution rankings to serve as warning indicators for subsequent drug hepatotoxicity screening studies. The study demonstrates that the DNN models developed based on molecular fingerprints can be a trustworthy and efficient tool for determining the risk of DILI during the pre-development of novel medications.

MolToxPred: small molecule toxicity prediction using machine learning approach

Different types of chemicals and products may exhibit various health risks when administered into the human body. For toxicity reasons, the number of new drugs entering the market through the conventional drug development process has been reduced over the years. However, with the advent of big data and artificial intelligence, machine learning techniques have emerged as a potential solution for predicting toxicity and ensuring efficient drug development and chemical safety. An ML model for toxicity prediction can reduce experimental costs and time while addressing ethical concerns by drastically reducing the need for animals and clinical trials. Herein, MolToxPred, an ML-based tool, has been developed using a stacked model approach to predict the potential toxicity of small molecules and metabolites. The stacked model consists of random forest, multi-layer perceptron, and LightGBM as base classifiers and Logistic Regression as the meta classifier. For training and validation purposes, a comprehensive set of toxic and non-toxic molecules is curated. Different structural and physicochemical-based features in the form of molecular descriptors and fingerprints were employed. MolToxPred utilizes a comprehensive feature selection process and optimizes its hyperparameters through Bayesian optimization with stratified 5-fold cross-validation. In the evaluation phase, MolToxPred achieved an AUROC of 87.76% on the test set and 88.84% on an external validation set. The McNemar test was used as the post-hoc test to determine if the stacked models' performance was significantly different compared to the base learners. The developed stacked model outperformed its base classifiers and an existing tool in the literature, reaffirming its better performance. The hypothesis is that the incorporation of a diverse set of data, the subsequent feature selection, and a stacked ensemble approach give MolToxPred the edge over other methods. In addition to this, an attempt has been made to identify structural alerts responsible for endpoints of the Tox21 data to determine the association of a molecule with a plausible downstream pathway of action. MolToxPred may be helpful for drug discovery and regulatory pipelines in pharmaceutical and other industries for in silico toxicity prediction of small molecule candidates.

Fragment-based investigation of thiourea derivatives as VEGFR-2 inhibitors: a cross-validated approach of ligand-based and structure-based molecular modeling studies

Angiogenesis is mediated by the vascular endothelial growth factor (VEGF) that plays a key role in the modulation of progression, invasion and metastasis, related to solid tumors and hematological malignancies. Several small-molecule VEGFR-2 inhibitors are marketed, but their usage is restricted to specific cancers due to severe toxicities. Therefore, cost-effective novel small molecule VEGFR-2 inhibitors may be an alternative to overcome these adverse effects. Here, a set of thiourea-based VEGFR-2 inhibitors were considered for a combined fragment-based QSAR technique, structure-based molecular docking followed by molecular dynamics simulation studies to acquire insights into the key structural attributes and the binding pattern of enzyme-ligand interactions. Noticeably, amine-substituted quinazoline phenyl ring and a higher number of nitrogen atoms, and the hydrazide function in the molecular structure are crucial for VEGFR-2 inhibition whereas methoxy groups are detrimental to VEGFR-2 inhibition. The MD simulation study of sorafenib and thiourea derivatives explored the significance of urea and thiourea moiety binding at VEGFR-2 active site that can be utilized further in the future to design molecules for greater binding stability and better VEGFR-2 selectivity. Therefore, such findings can be beneficial for the development of newer VEGFR-2 inhibitors for further refinement to acquire better therapeutic efficacy.Communicated by Ramaswamy H. Sarma.

CrossFuse-XGBoost: accurate prediction of the maximum recommended daily dose through multi-feature fusion, cross-validation screening and extreme gradient boosting

In the drug development process, approximately 30% of failures are attributed to drug safety issues. In particular, the first-in-human (FIH) trial of a new drug represents one of the highest safety risks, and initial dose selection is crucial for ensuring safety in clinical trials. With traditional dose estimation methods, which extrapolate data from animals to humans, catastrophic events have occurred during Phase I clinical trials due to interspecies differences in compound sensitivity and unknown molecular mechanisms. To address this issue, this study proposes a CrossFuse-extreme gradient boosting (XGBoost) method that can directly predict the maximum recommended daily dose of a compound based on existing human research data, providing a reference for FIH dose selection. This method not only integrates multiple features, including molecular representations, physicochemical properties and compound-protein interactions, but also improves feature selection based on cross-validation. The results demonstrate that the CrossFuse-XGBoost method not only improves prediction accuracy compared to that of existing local weighted methods [k-nearest neighbor (k-NN) and variable k-NN (v-NN)] but also solves the low prediction coverage issue of v-NN, achieving full coverage of the external validation set and enabling more reliable predictions. Furthermore, this study offers a high level of interpretability by identifying the importance of different features in model construction. The 241 features with the most significant impact on the maximum recommended daily dose were selected, providing references for optimizing the structure of new compounds and guiding experimental research. The datasets and source code are freely available at https://github.com/cqmu-lq/CrossFuse-XGBoost.

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.

Automated detection of toxicophores and prediction of mutagenicity using PMCSFG algorithm

Maximum common substructures (MCS) have received a lot of attention in the chemoinformatics community. They are typically used as a similarity measure between molecules, showing high predictive performance when used in classification tasks, while being easily explainable substructures. In the present work, we applied the Pairwise Maximum Common Subgraph Feature Generation (PMCSFG) algorithm to automatically detect toxicophores (structural alerts) and to compute fingerprints based on MCS. We present a comparison between our MCS-based fingerprints and 12 well-known chemical fingerprints when used as features in machine learning models. We provide an experimental evaluation and discuss the usefulness of the different methods on mutagenicity data. The features generated by the MCS method have a state-of-the-art performance when predicting mutagenicity, while they are more interpretable than the traditional chemical fingerprints.

A KNIME Workflow to Assist the Analogue Identification for Read-Across, Applied to Aromatase Activity

The reduction and replacement of in vivo tests have become crucial in terms of resources and animal benefits. The read-across approach reduces the number of substances to be tested, exploiting existing experimental data to predict the properties of untested substances. Currently, several tools have been developed to perform read-across, but other approaches, such as computational workflows, can offer a more flexible and less prescriptive approach. In this paper, we are introducing a workflow to support analogue identification for read-across. The implementation of the workflow was performed using a database of azole chemicals with in vitro toxicity data for human aromatase enzymes. The workflow identified analogues based on three similarities: structural similarity (StrS), metabolic similarity (MtS), and mechanistic similarity (McS). Our results showed how multiple similarity metrics can be combined within a read-across assessment. The use of the similarity based on metabolism and toxicological mechanism improved the predictions in particular for sensitivity. Beyond the results predicting a large population of substances, practical examples illustrate the advantages of the proposed approach.

New Approach Methodologies in Immunotoxicology: Challenges and Opportunities

To maintain the integrity of an organism, a well-functioning immune system is essential. Immunity is dynamic, with constant surveillance needed to determine whether to initiate an immune response or to not respond. Both inappropriate immunostimulation and decreased immune response can be harmful to the host. A reduced immune response can lead to high susceptibility to cancer or infections, whereas an increased immune response can be related to autoimmunity or hypersensitivity reactions. Animal testing has been the gold standard for hazard assessment in immunotoxicity but a lot of efforts are ongoing to develop non-animal-based test systems, and important successes have been achieved. The term "new approach methodologies" (NAMs) refer to the approaches which are not based on animal models. They are applied in hazard and risk assessment of chemicals and include approaches such as defined approaches for data interpretation and integrated approaches to testing and assessment. This review aims to summarize the available NAMs for immunotoxicity assessment, taking into consideration both inappropriate immunostimulation and immunosuppression, including implication for cancer development.

Molecular Docking, Validation, Dynamics Simulations, and Pharmacokinetic Prediction of Phytochemicals Isolated From Croton dichogamus Against the HIV-1 Reverse Transcriptase

The human immunodeficiency virus (HIV) infection and the associated acquired immune deficiency syndrome (AIDS) remain global challenges even after decades of successful treatment, with eastern and southern Africa still bearing the highest burden of disease. Following a thorough computational study, we report top 10 phytochemicals isolated from Croton dichogamus as potent reverse transcriptase inhibitors. The pentacyclic triterpenoid, aleuritolic acid (L12) has displayed best docking pose with binding energy of -8.48 kcal/mol and Ki of 0.61 μM making it superior in binding efficiency when compared to all docked compounds including the FDA-approved drugs. Other phytochemicals such as crotoxide A, crothalimene A, crotodichogamoin B and crotonolide E have also displayed strong binding energies. These compounds could further be investigated as potential antiretroviral medication.

SApredictor: An Expert System for Screening Chemicals Against Structural Alerts

The rapid and accurate evaluation of chemical toxicity is of great significance for estimation of chemical safety. In the past decades, a great number of excellent computational models have been developed for chemical toxicity prediction. But most machine learning models tend to be “black box”, which bring about poor interpretability. In the present study, we focused on the identification and collection of structural alerts (SAs) responsible for a series of important toxicity endpoints. Then, we carried out effective storage of these structural alerts and developed a web-server named SApredictor (www.sapredictor.cn) for screening chemicals against structural alerts. People can quickly estimate the toxicity of chemicals with SApredictor, and the specific key substructures which cause the chemical toxicity will be intuitively displayed to provide valuable information for the structural optimization by medicinal chemists.

Progress and Challenges in Targeting the SARS-CoV-2 Papain-like Protease

SARS-CoV-2 is the causative agent of the COVID-19 pandemic. The approval of vaccines and small-molecule antivirals is vital in combating the pandemic. The viral polymerase inhibitors remdesivir and molnupiravir and the viral main protease inhibitor nirmatrelvir/ritonavir have been approved by the U.S. FDA. However, the emergence of variants of concern/interest calls for additional antivirals with novel mechanisms of action. The SARS-CoV-2 papain-like protease (PLpro) mediates the cleavage of viral polyprotein and modulates the host's innate immune response upon viral infection, rendering it a promising antiviral drug target. This Perspective highlights major achievements in structure-based design and high-throughput screening of SARS-CoV-2 PLpro inhibitors since the beginning of the pandemic. Encouraging progress includes the design of non-covalent PLpro inhibitors with favorable pharmacokinetic properties and the first-in-class covalent PLpro inhibitors. In addition, we offer our opinion on the knowledge gaps that need to be filled to advance PLpro inhibitors to the clinic.

Exploration of structural requirements for azole chemicals towards human aromatase CYP19A1 activity: Classification modeling, structure-activity relationships and read-across study

Human aromatase, also called CYP19A1, plays a major role in the conversion of androgens into estrogens. Inhibition of aromatase is an important target for estrogen receptor (ER)-responsive breast cancer therapy. Use of azole compounds as aromatase inhibitors is widespread despite their low selectivity. A toxicological evaluation of commonly used azole-based drugs and agrochemicals with respect to CYP19A1is currently requested by the European Union- Registration, Evaluation, Authorization and Restriction of Chemicals (EU-REACH) regulations due to their potential as endocrine disruptors. In this connection, identification of structural alerts (SAs) is an effective strategy for the toxicological assessment and safe drug design. The present study describes the identification of SAs of azole-based chemicals as guiding experts to predict the aromatase activity. Total 21 SAs associated with aromatase activity were extracted from dataset of 326 azole-based drugs/chemicals obtained from Tox21 library. A cross-validated classification model having high accuracy (error rate 5%) was proposed which can precisely classify azole chemicals into active/inactive toward aromatase. In addition, mechanistic details and toxicological properties (agonism/antagonism) of azoles with respect to aromatase were explored by comparing active and inactive chemicals using structure-activity relationships (SAR). Lastly, few structural alerts were applied to form chemical categories for read-across applications.

Prediction of Micronucleus Assay Outcome Using In Vivo Activity Data and Molecular Structure Features

In vivo micronucleus assay is the widely used genotoxic test to determine the extent of chromosomal aberrations caused by the chemicals in human beings, which plays a significant role in the drug discovery paradigm. To reduce the uncertainties of the in vivo experiments and the expenses, we intended to develop novel machine learning-based tools to predict the toxicity of the compounds with high precision. A total of 372 compounds with known toxicity information were retrieved from the PubChem Bioassay database and literature. The fingerprints and descriptors of the compounds were generated using PaDEL and ChemSAR, respectively, for the analysis. The performance of the models was assessed using the three tires of evaluation strategies such as fivefold, tenfold, and validation by external dataset. Further, structural alerts causing genotoxicity of the compounds were identified using SARpy method. Of note, fingerprint-based random forest model built in our analysis is able to demonstrate the highest accuracy of about 0.97 during tenfold cross-validation. In essence, our study highlights that structural alerts such as chlorocyclohexane and trimethylamine are likely to be the leading cause of toxicity in humans. Indeed, we believe that random forest model generated in this study is appropriate for reduction of test animals and should be considered in the future for the good practice of animal welfare.

Unmasking of crucial structural fragments for coronavirus protease inhibitors and its implications in COVID-19 drug discovery

Fragment based drug discovery (FBDD) by the aid of different modelling techniques have been emerged as a key drug discovery tool in the area of pharmaceutical science and technology. The merits of employing these methods, in place of other conventional molecular modelling techniques, endorsed clear detection of the possible structural fragments present in diverse set of investigated compounds and can create alternate possibilities of lead optimization in drug discovery. In this work, two fragment identification tools namely SARpy and Laplacian-corrected Bayesian analysis were used for previous SARS-CoV PLpro and 3CLpro inhibitors. A robust and predictive SARpy based fragments identification was performed which have been validated further by Laplacian-corrected Bayesian model. These comprehensive approaches have advantages since fragments are straight forward to interpret. Moreover, distinguishing the key molecular features (with respect to ECFP_6 fingerprint) revealed good or bad influences for the SARS-CoV protease inhibitory activities. Furthermore, the identified fragments could be implemented in the medicinal chemistry endeavors of COVID-19 drug discovery.

NICEdrug.ch, a workflow for rational drug design and systems-level analysis of drug metabolism

The discovery of a drug requires over a decade of intensive research and financial investments - and still has a high risk of failure. To reduce this burden, we developed the NICEdrug.ch resource, which incorporates 250,000 bioactive molecules, and studied their enzymatic metabolic targets, fate, and toxicity. NICEdrug.ch includes a unique fingerprint that identifies reactive similarities between drug-drug and drug-metabolite pairs. We validated the application, scope, and performance of NICEdrug.ch over similar methods in the field on golden standard datasets describing drugs and metabolites sharing reactivity, drug toxicities, and drug targets. We use NICEdrug.ch to evaluate inhibition and toxicity by the anticancer drug 5-fluorouracil, and suggest avenues to alleviate its side effects. We propose shikimate 3-phosphate for targeting liver-stage malaria with minimal impact on the human host cell. Finally, NICEdrug.ch suggests over 1300 candidate drugs and food molecules to target COVID-19 and explains their inhibitory mechanism for further experimental screening. The NICEdrug.ch database is accessible online to systematically identify the reactivity of small molecules and druggable enzymes with practical applications in lead discovery and drug repurposing.

Robust classification-based molecular modelling of diverse chemical entities as potential SARS-CoV-2 3CLpro inhibitors: theoretical justification in light of experimental evidences

COVID-19 is the most unanticipated incidence of 2020 affecting the human population worldwide. Currently, it is utmost important to produce novel small molecule anti-SARS-CoV-2 drugs urgently that can save human lives globally. Based on the earlier SARS-CoV and MERS-CoV infection along with the general characters of coronaviral replication, a number of drug molecules have been proposed. However, one of the major limitations is the lack of experimental observations with different drug molecules. In this article, 70 diverse chemicals having experimental SARS-CoV-2 3CL^proinhibitory activity were accounted for robust classification-based QSAR analysis statistically validated with 4 different methodologies to recognize the crucial structural features responsible for imparting the activity. Results obtained from all these methodologies supported and validated each other. Important observations obtained from these analyses were also justified with the ligand-bound crystal structure of SARS-CoV-2 3CL^pro enzyme. Our results suggest that molecules should contain a 2-oxopyrrolidine scaffold as well as a methylene (hydroxy) sulphonic acid warhead in proper orientation to achieve higher inhibitory potency against SARS-CoV-2 3CL^pro. Outcomes of our study may be able to design and discover highly effective SARS-CoV-2 3CL^pro inhibitors as potential anticoronaviral therapy to crusade against COVID-19.

Discovery of Natural Products Targeting NQO1 via an Approach Combining Network-Based Inference and Identification of Privileged Substructures

NAD(P)H:quinone oxidoreductase 1 (NQO1) has been shown to be a potential therapeutic target for various human diseases, such as cancer and neurodegenerative disorders. Recent advances in computational methods, especially network-based methods, have made it possible to identify novel compounds for a target with high efficiency and low cost. In this study, we designed a workflow combining network-based methods and identification of privileged substructures to discover new compounds targeting NQO1 from a natural product library. According to the prediction results, we purchased 56 compounds for experimental validation. Without the assistance of privileged substructures, 31 compounds (31/56 = 55.4%) showed IC₅₀ < 100 μM, and 11 compounds (11/56 = 19.6%) showed IC₅₀ < 10 μM. With the assistance of privileged substructures, the two success rates were increased to 61.8 and 26.5%, respectively. Seven natural products further showed inhibitory activity on NQO1 at the cellular level, which may serve as lead compounds for further development. Moreover, network analysis revealed that osthole may exert anticancer effects against multiple cancer types by inhibiting not only carbonic anhydrases IX and XII but also NQO1. Our workflow and computational methods can be easily applied in other targets and become useful tools in drug discovery and development.

Green toxicological investigation for biofuel candidates

To avoid potential risks of biofuels on the environment and human, ecotoxicity investigation should be integrated into the early design stage for promising biofuel candidates. In the present study, a green toxicology testing strategy combining experimental bioassays with in silico tools was established to investigate the potential ecotoxicity of biofuel candidates. Experimental results obtained from the acute immobilisation test, the fish embryo acute toxicity test and the in vitro micronucleus assay (Chinese hamster lung fibroblast cell line V79) were compared with model prediction results by ECOSAR and OECD QSAR Toolbox. Both our experimental and model prediction results showed that 1-Octanol (1-Oct) and Di-n-butyl ether (DNBE) were the most toxic to Daphnia magna and zebrafish among all the biofuel candidates we investigated, while Methyl ethyl ketone (MEK), Dimethoxymethane (DMM) and Diethoxymethane (DEM) were the least toxic. Moreover, both in vitro micronucleus assay and OECD QSAR Toolbox evaluation suggested that the metabolites present higher genotoxicity than biofuel candidates themselves. Overall, our results proved that this green toxicology testing strategy is a useful tool for assessing ecotoxicity of biofuel candidates.

In silico prediction of mitochondrial toxicity of chemicals using machine learning methods

Mitochondria are important organelles in human cells, providing more than 95% of the energy. However, some drugs and environmental chemicals could induce mitochondrial dysfunction, which might cause complex diseases and even worsen the condition of patients with mitochondrial damage. Some drugs have been withdrawn from the market due to their severe mitochondrial toxicity, such as troglitazone. Therefore, there is an urgent need to develop models that could accurately predict the mitochondrial toxicity of chemicals. In this paper, suitable data were obtained from literature and databases first. Then nine types of fingerprints were used to characterize these compounds. Finally, different algorithms were used to build models. Meanwhile, the applicability domain of the prediction models was defined. We have also explored the structural alerts of mitochondrial toxicity, which would be helpful for medicinal chemists to better predict mitochondrial toxicity and further optimize lead compounds.

Prediction and mechanistic analysis of drug-induced liver injury (DILI) based on chemical structure

BACKGROUND

Drug-induced liver injury (DILI) is a major safety concern characterized by a complex and diverse pathogenesis. In order to identify DILI early in drug development, a better understanding of the injury and models with better predictivity are urgently needed. One approach in this regard are in silico models which aim at predicting the risk of DILI based on the compound structure. However, these models do not yet show sufficient predictive performance or interpretability to be useful for decision making by themselves, the former partially stemming from the underlying problem of labeling the in vivo DILI risk of compounds in a meaningful way for generating machine learning models.

RESULTS

As part of the Critical Assessment of Massive Data Analysis (CAMDA) "CMap Drug Safety Challenge" 2019 ( http://camda2019.bioinf.jku.at ), chemical structure-based models were generated using the binarized DILIrank annotations. Support Vector Machine (SVM) and Random Forest (RF) classifiers showed comparable performance to previously published models with a mean balanced accuracy over models generated using 5-fold LOCO-CV inside a 10-fold training scheme of 0.759 ± 0.027 when predicting an external test set. In the models which used predicted protein targets as compound descriptors, we identified the most information-rich proteins which agreed with the mechanisms of action and toxicity of nonsteroidal anti-inflammatory drugs (NSAIDs), one of the most important drug classes causing DILI, stress response via TP53 and biotransformation. In addition, we identified multiple proteins involved in xenobiotic metabolism which could be novel DILI-related off-targets, such as CLK1 and DYRK2. Moreover, we derived potential structural alerts for DILI with high precision, including furan and hydrazine derivatives; however, all derived alerts were present in approved drugs and were over specific indicating the need to consider quantitative variables such as dose.

CONCLUSION

Using chemical structure-based descriptors such as structural fingerprints and predicted protein targets, DILI prediction models were built with a predictive performance comparable to previous literature. In addition, we derived insights on proteins and pathways statistically (and potentially causally) linked to DILI from these models and inferred new structural alerts related to this adverse endpoint.

In silico toxicology: From structure–activity relationships towards deep learning and adverse outcome pathways

In silico toxicology is an emerging field. It gains increasing importance as research is aiming to decrease the use of animal experiments as suggested in the 3R principles by Russell and Burch. In silico toxicology is a means to identify hazards of compounds before synthesis, and thus in very early stages of drug development. For chemical industries, as well as regulatory agencies it can aid in gap‐filling and guide risk minimization strategies. Techniques such as structural alerts, read‐across, quantitative structure–activity relationship, machine learning, and deep learning allow to use in silico toxicology in many cases, some even when data is scarce. Especially the concept of adverse outcome pathways puts all techniques into a broader context and can elucidate predictions by mechanistic insights.

This article is categorized under:

Structure and Mechanism > Computational Biochemistry and Biophysics

Data Science > Chemoinformatics

Elucidating Compound Mechanism of Action and Predicting Cytotoxicity Using Machine Learning Approaches, Taking Prediction Confidence into Account

The modes of action (MoAs) of drugs frequently are unknown, because many are small molecules initially identified from phenotypic screens, giving rise to the need to elucidate their MoAs. In addition, the high attrition rate for candidate drugs in preclinical studies due to intolerable toxicity has motivated the development of computational approaches to predict drug candidate (cyto)toxicity as early as possible in the drug-discovery process. Here, we provide detailed instructions for capitalizing on bioactivity predictions to elucidate the MoAs of small molecules and infer their underlying phenotypic effects. We illustrate how these predictions can be used to infer the underlying antidepressive effects of marketed drugs. We also provide the necessary functionalities to model cytotoxicity data using single and ensemble machine-learning algorithms. Finally, we give detailed instructions on how to calculate confidence intervals for individual predictions using the conformal prediction framework. © 2019 by John Wiley & Sons, Inc.

Modeling and insights into molecular basis of low molecular weight respiratory sensitizers

Respiratory sensitization has been considered an important toxicological endpoint, because of the severe risk to human health. A great part of sensitization events were caused by low molecular weight (< 1000) respiratory sensitizers in the past decades. However, there is currently no widely accepted test method that can identify prospective low molecular weight respiratory sensitisers. Herein, we performed the study of modeling and insights into molecular basis of low molecular weight respiratory sensitizers with a high-quality data set containing 136 respiratory sensitizers and 518 nonsensitizers. We built a number of classification models by using OCHEM tools, and a consensus model was developed based on the ten best individual models. The consensus model showed good predictive ability with a balanced accuracy of 0.78 and 0.85 on fivefold cross-validation and external validation, respectively. The readers can predict the respiratory sensitization of organic compounds via https://ochem.eu/article/114857 . The effect of several molecular properties on respiratory sensitization was also evaluated. The results indicated that these properties differ significantly between respiratory sensitizers and nonsensitizers. Furthermore, 14 privileged substructures responsible for respiratory sensitization were identified. We hope the models and the findings could provide useful help for environmental risk assessment.

In silico prediction of toxicity and its applications for chemicals at work

OBJECTIVE AND METHODS

This study reviewed the concept of in silico prediction of chemical toxicity for prevention of occupational cancer and future prospects in workers' health. In this review, a new approach to determine the credibility of in silico predictions with raw data is explored, and the method of determining the confidence level of evaluation based on the credibility of data is discussed. I searched various papers and books related to the in silico prediction of chemical toxicity and carcinogenicity. The intention was to utilize the most recent reports after 2015 regarding in silico prediction.

RESULTS AND CONCLUSION

The application of in silico methods is increasing with the prediction of toxic risks to human and the environment. The various toxic effects of industrial chemicals have triggered the recognition of the importance of using a combination of in silico models in the risk assessments. In silico occupational exposure models, industrial accidents, and occupational cancers are effectively managed and chemicals evaluated. It is important to identify and manage hazardous substances proactively through the rigorous evaluation of chemicals.

Discovery of isoxazolyl-based inhibitors of Plasmodium falciparum cGMP-dependent protein kinase

The cGMP-dependent protein kinase in Plasmodium falciparum (PfPKG) plays multiple roles in the life cycle of the parasite. As a result, this enzyme is a potential target for new antimalarial agents. Existing inhbitors, while potent and active in malaria models are not optimal. This communication describes initial optimization of a structurally distinct class of PfPKG inhibitors.

Discovering Highly Potent Molecules from an Initial Set of Inactives Using Iterative Screening

The versatility of similarity searching and quantitative structure-activity relationships to model the activity of compound sets within given bioactivity ranges (i.e., interpolation) is well established. However, their relative performance in the common scenario in early stage drug discovery where lots of inactive data but no active data points are available (i.e., extrapolation from the low-activity to the high-activity range) has not been thoroughly examined yet. To this aim, we have designed an iterative virtual screening strategy which was evaluated on 25 diverse bioactivity data sets from ChEMBL. We benchmark the efficiency of random forest (RF), multiple linear regression, ridge regression, similarity searching, and random selection of compounds to identify a highly active molecule in the test set among a large number of low-potency compounds. We use the number of iterations required to find this active molecule to evaluate the performance of each experimental setup. We show that linear and ridge regression often outperform RF and similarity searching, reducing the number of iterations to find an active compound by a factor of 2 or more. Even simple regression methods seem better able to extrapolate to high-bioactivity ranges than RF, which only provides output values in the range covered by the training set. In addition, examination of the scaffold diversity in the data sets used shows that in some cases similarity searching and RF require two times as many iterations as random selection depending on the chemical space covered in the initial training data. Lastly, we show using bioactivity data for COX-1 and COX-2 that our framework can be extended to multitarget drug discovery, where compounds are selected by concomitantly considering their activity against multiple targets. Overall, this study provides an approach for iterative screening where only inactive data are present in early stages of drug discovery in order to discover highly potent compounds and the best experimental set up in which to do so.

e-Bitter: Bitterant Prediction by the Consensus Voting From the Machine-Learning Methods

In-silico bitterant prediction received the considerable attention due to the expensive and laborious experimental-screening of the bitterant. In this work, we collect the fully experimental dataset containing 707 bitterants and 592 non-bitterants, which is distinct from the fully or partially hypothetical non-bitterant dataset used in the previous works. Based on this experimental dataset, we harness the consensus votes from the multiple machine-learning methods (e.g., deep learning etc.) combined with the molecular fingerprint to build the bitter/bitterless classification models with five-fold cross-validation, which are further inspected by the Y-randomization test and applicability domain analysis. One of the best consensus models affords the accuracy, precision, specificity, sensitivity, F1-score, and Matthews correlation coefficient (MCC) of 0.929, 0.918, 0.898, 0.954, 0.936, and 0.856 respectively on our test set. For the automatic prediction of bitterant, a graphic program “e-Bitter” is developed for the convenience of users via the simple mouse click. To our best knowledge, it is for the first time to adopt the consensus model for the bitterant prediction and develop the first free stand-alone software for the experimental food scientist.

In silico prediction of chemical genotoxicity using machine learning methods and structural alerts

Genotoxicity tests can detect compounds that have an adverse effect on the process of heredity. The in vivo micronucleus assay, a genotoxicity test method, has been widely used to evaluate the presence and extent of chromosomal damage in human beings. Due to the high cost and laboriousness of experimental tests, computational approaches for predicting genotoxicity based on chemical structures and properties are recognized as an alternative. In this study, a dataset containing 641 diverse chemicals was collected and the molecules were represented by both fingerprints and molecular descriptors. Then classification models were constructed by six machine learning methods, including the support vector machine (SVM), naïve Bayes (NB), k-nearest neighbor (kNN), C4.5 decision tree (DT), random forest (RF) and artificial neural network (ANN). The performance of the models was estimated by five-fold cross-validation and an external validation set. The top ten models showed excellent performance for the external validation with accuracies ranging from 0.846 to 0.938, among which models Pubchem_SVM and MACCS_RF showed a more reliable predictive ability. The applicability domain was also defined to distinguish favorable predictions from unfavorable ones. Finally, ten structural fragments which can be used to assess the genotoxicity potential of a chemical were identified by using information gain and structural fragment frequency analysis. Our models might be helpful for the initial screening of potential genotoxic compounds.

In Silico Prediction of Chemical Toxicity for Drug Design Using Machine Learning Methods and Structural Alerts

During drug development, safety is always the most important issue, including a variety of toxicities and adverse drug effects, which should be evaluated in preclinical and clinical trial phases. This review article at first simply introduced the computational methods used in prediction of chemical toxicity for drug design, including machine learning methods and structural alerts. Machine learning methods have been widely applied in qualitative classification and quantitative regression studies, while structural alerts can be regarded as a complementary tool for lead optimization. The emphasis of this article was put on the recent progress of predictive models built for various toxicities. Available databases and web servers were also provided. Though the methods and models are very helpful for drug design, there are still some challenges and limitations to be improved for drug safety assessment in the future.

The development and application of in silico models for drug induced liver injury

Drug-induced liver injury (DILI), caused by drugs, herbal agents or nutritional supplements, is a major issue for patients and the pharmaceutical industry. It has been a leading cause of clinical trials failure and withdrawal of FDA approval. In this research, we focused on in silico estimation of chemical DILI potential on humans based on structurally diverse organic chemicals. We developed a series of binary classification models using five different machine learning methods and eight different feature reduction methods. The model, developed with the support vector machine (SVM) and the MACCS fingerprint, performed best both on the test set and external validation. It achieved a prediction accuracy of 80.39% on the test set and 82.78% on external validation. We made this model available at http://opensource.vslead.com/. The user can freely predict the DILI potential of molecules. Furthermore, we analyzed the difference of distributions of 12 key physical-chemical properties between DILI-positive and DILI-negative compounds and 20 privileged substructures responsible for DILI were identified from the Klekota-Roth fingerprint. Moreover, since traditional Chinese medicine (TCM)-induced liver injury is also one of the major concerns among the toxic effects, we evaluated the DILI potential of TCM ingredients using the MACCS_SVM model developed in this study. We hope the model and privileged substructures could be useful complementary tools for chemical DILI evaluation.

Mutagenicity, anticancer activity and blood brain barrier: similarity and dissimilarity of molecular alerts

The aim of the present work is an attempt to define computable measure of similarity between different endpoints. The similarity of structural alerts of different biochemical endpoints can be used to solve tasks of medicinal chemistry. Optimal descriptors are a tool to build up models for different endpoints. The optimal descriptor is calculated with simplified molecular input-line entry system (SMILES). A group of elements (single symbol or pair of symbols) can represent any SMILES. Each element of SMILES can be represented by so-called correlation weight i.e. coefficient that should be used to calculate descriptor. Numerical data on the correlation weights are calculated by the Monte Carlo method, i.e. by optimization procedure, which gives maximal correlation coefficient between the optimal descriptor and endpoint for the training set. Statistically stable correlation weights observed in several runs of the optimization can be examined as structural alerts, which are promoters of the increase or the decrease of a biochemical activity of a substance. Having data on several runs of the optimization correlation weights, one can extract list of promoters of increase and list of promoters of decrease for an endpoint. The study of similarity and dissimilarity of the above lists has been carried out for the following pairs of endpoints: (i) mutagenicity and anticancer activity; (ii) mutagenicity and blood brain barrier; and (iii) blood brain barrier and anticancer activity. The computational experiment confirms that similarity and dissimilarity for pairs of endpoints can be measured.

Quantitative structure-activity relationship (QSAR) directed the discovery of 3-(pyridin-2-yl)benzenesulfonamide derivatives as novel herbicidal agents

BACKGROUND

Agrochemicals have been crucial to the production of food, and the need for the development of novel agrochemicals continues unceasing owing to the loss of existing produces via the growth of resistance and the desire for products with more propitious environmental and toxicological patterns.

RESULTS

The results of both CoMFA and CoMSIA models indicated that biological activity can effectively be improved through the structural optimisation and molecular design of these synthetic compounds from the aspects of steric, electrostatic, hydrophobic, hydrogen bond donor and acceptor fields. Data of postemergence herbicidal activity in the greenhouse explained that most new 3-(pyridin-2-yl)benzenesulfonamide derivatives (4c-4 t) could control highly effectively against barnyardgrass, foxtail, vetleaf, and youth and old age (herbicidal activity ≥90%); for example, compounds 4q-4 t exhibit excellent biological activity equivalent/superior to commercial saflufenacil/sulcotrione at the low concentration of 37.5 g a.i./ha, and in particular, the herbicidal activity of compound 4 t for four experimental plant species is found to be notably greater than saflufenacil (3.75 g a.i./ha). Meanwhile, compound 4 t also has good crop selectivity for weed control in maize.

CONCLUSION

The novel compounds such as 4 t have remarkable biological activity after the structural optimisation utilising the constructed 3D-QSAR models, i.e. such QSAR models have great accuracy. © 2017 Society of Chemical Industry.

Deep Learning Based Regression and Multiclass Models for Acute Oral Toxicity Prediction with Automatic Chemical Feature Extraction

Median lethal death, LD₅₀, is a general indicator of compound acute oral toxicity (AOT). Various in silico methods were developed for AOT prediction to reduce costs and time. In this study, we developed an improved molecular graph encoding convolutional neural networks (MGE-CNN) architecture to construct three types of high-quality AOT models: regression model (deepAOT-R), multiclassification model (deepAOT-C), and multitask model (deepAOT-CR). These predictive models highly outperformed previously reported models. For the two external data sets containing 1673 (test set I) and 375 (test set II) compounds, the R² and mean absolute errors (MAEs) of deepAOT-R on the test set I were 0.864 and 0.195, and the prediction accuracies of deepAOT-C were 95.5% and 96.3% on test sets I and II, respectively. The two external prediction accuracies of deepAOT-CR are 95.0% and 94.1%, while the R² and MAE are 0.861 and 0.204 for test set I, respectively. We then performed forward and backward exploration of deepAOT models for deep fingerprints, which could support shallow machine learning methods more efficiently than traditional fingerprints or descriptors. We further performed automatic feature learning, a key essence of deep learning, to map the corresponding activation values into fragment space and derive AOT-related chemical substructures by reverse mining of the features. Our deep learning architecture for AOT is generally applicable in predicting and exploring other toxicity or property end points of chemical compounds. The two deepAOT models are freely available at http://repharma.pku.edu.cn/DLAOT/DLAOThome.php or http://www.pkumdl.cn/DLAOT/DLAOThome.php .