Prediction of Farnesoid X Receptor Disruptors with Machine Learning Methods

PBScreen: A server for the high-throughput screening of placental barrier-permeable contaminants based on multifusion deep learning

Contaminants capable of crossing the placental barrier (PB) adversely affect female reproduction and fetal development. The rapid identification of PB-permeable contaminants is urgently needed due to the inefficiencies of conventional cell-based transwell assays for the screening of large quantities of chemicals. Herein, we construct a PBScreen server using a multifusion deep learning (DL) model for the accurate and rapid screening of PB-permeable chemicals. This model is trained using graph convolutional networks and deep neural networks algorithms. It achieves state-of-the-art performance with an accuracy of 0.927, a false negative rate of 0.074, and an area under the receiver operating characteristic curve of 0.960. The robustness and generalization of the model as assessed using the external validation set and BeWo cell-based transwell assays demonstrate its potential for diverse applications. Our study establishes an efficient high-throughput screening tool that aids in screening PB-permeable chemicals, thereby enhancing the risk assessment of contaminants associated with key public health concerns.

Machine Learning-Based Toxicological Modeling for Screening Environmental Obesogens

The emerging presence of environmental obesogens, chemicals that disrupt energy balance and contribute to adipogenesis and obesity, has become a major public health challenge. Molecular initiating events (MIEs) describe biological outcomes resulting from chemical interactions with biomolecules. Machine learning models based on MIEs can predict complex toxic end points due to chemical exposure and improve the interpretability of models. In this study, a system was constructed that integrated six MIEs associated with adipogenesis and obesity. This system showed high accuracy in external validation, with an area under the receiver operating characteristic curve of 0.78. Molecular hydrophobicity (SlogP_VSA) and direct electrostatic interactions (PEOE_VSA) were identified as the two most critical molecular descriptors representing the obesogenic potential of chemicals. This system was further used to predict the obesogenic effects of chemicals on the candidate list of substances of very high concern (SVHCs). Results from 3T3-L1 adipogenesis assays verified that the system correctly predicted obesogenic or nonobesogenic effects of 10 of the 12 SVHCs tested, and identified four novel potential obesogens, including 2-benzotriazol-2-yl-4,6-ditert-butylphenol (UV-320), 4-(1,1,5-trimethylhexyl)phenol (p262-NP), 2-[4-(1,1,3,3-tetramethylbutyl)phenoxy]ethanol (OP1EO) and endosulfan. These validation data suggest that the screening system has good performance in adipogenic prediction.

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.

From molecular descriptors to the developmental toxicity prediction of pesticides/veterinary drugs/bio-pesticides against zebrafish embryo: Dual computational toxicological approaches for prioritization

The escalating introduction of pesticides/veterinary drugs into the environment has necessitated a rapid evaluation of their potential risks to ecosystems and human health. The developmental toxicity of pesticides/veterinary drugs was less explored, and much less the large-scale predictions for untested pesticides, veterinary drugs and bio-pesticides. Alternative methods like quantitative structure-activity relationship (QSAR) are promising because their potential to ensure the sustainable and safe use of these chemicals. We collected 133 pesticides and veterinary drugs with half-maximal active concentration (AC50) as the zebrafish embryo developmental toxicity endpoint. The QSAR model development adhered to rigorous OECD principles, ensuring that the model possessed good internal robustness (R2 > 0.6 and QLOO2 > 0.6) and external predictivity (Rtest2 > 0.7, QFn2 >0.7, and CCCtest > 0.85). To further enhance the predictive performance of the model, a quantitative read-across structure-activity relationship (q-RASAR) model was established using the combined set of RASAR and 2D descriptors. Mechanistic interpretation revealed that dipole moment, the presence of C-O fragment at 10 topological distance, molecular size, lipophilicity, and Euclidean distance (ED)-based RA function were main factors influencing toxicity. For the first time, the established QSAR and q-RASAR models were combined to prioritize the developmental toxicity of a vast array of true external compounds (pesticides/veterinary drugs/bio-pesticides) lacking experimental values. The prediction reliability of each query molecule was evaluated by leverage approach and prediction reliability indicator. Overall, the dual computational toxicology models can inform decision-making and guide the design of new pesticides/veterinary drugs with improved safety profiles.

The rat acute oral toxicity of trifluoromethyl compounds (TFMs): a computational toxicology study combining the 2D-QSTR, read-across and consensus modeling methods

All areas of the modern society are affected by fluorine chemistry. In particular, fluorine plays an important role in medical, pharmaceutical and agrochemical sciences. Amongst various fluoro-organic compounds, trifluoromethyl (CF3) group is valuable in applications such as pharmaceuticals, agrochemicals and industrial chemicals. In the present study, following the strict OECD modelling principles, a quantitative structure-toxicity relationship (QSTR) modelling for the rat acute oral toxicity of trifluoromethyl compounds (TFMs) was established by genetic algorithm-multiple linear regression (GA-MLR) approach. All developed models were evaluated by various state-of-the-art validation metrics and the OECD principles. The best QSTR model included nine easily interpretable 2D molecular descriptors with clear physical and chemical significance. The mechanistic interpretation showed that the atom-type electro-topological state indices, molecular connectivity, ionization potential, lipophilicity and some autocorrelation coefficients are the main factors contributing to the acute oral toxicity of TFMs against rats. To validate that the selected 2D descriptors can effectively characterize the toxicity, we performed the chemical read-across analysis. We also compared the best QSTR model with public OPERA tool to demonstrate the reliability of the predictions. To further improve the prediction range of the QSTR model, we performed the consensus modelling. Finally, the optimum QSTR model was utilized to predict a true external set containing many untested/unknown TFMs for the first time. Overall, the developed model contributes to a more comprehensive safety assessment approach for novel CF3-containing pharmaceuticals or chemicals, reducing unnecessary chemical synthesis whilst saving the development cost of new drugs.

Exploring molecular fingerprints of different drugs having bile interaction: a stepping stone towards better drug delivery

Bile acids are amphiphilic substances produced naturally in humans. In the context of drug delivery and dosage form design, it is critical to understand whether a drug interacts with bile inside the gastrointestinal (GI) tract or not. This study focuses on the identification of structural fingerprints/features important for bile interaction. Molecular modelling methods such as Bayesian classification and recursive partitioning (RP) studies are executed to find important fingerprints/features for the bile interaction. For the Bayesian classification study, the ROC score of 0.837 and 0.950 are found for the training set and the test set compounds, respectively. The fluorine-containing aliphatic/aromatic group, the branched chain of the alkyl group containing hydroxyl moiety and the phenothiazine ring etc. are identified as good fingerprints having a positive contribution towards bile interactions, whereas, the bad fingerprints such as free carboxylate group, purine, and pyrimidine ring etc. have a negative contribution towards bile interactions. The best tree (tree ID: 1) from the RP study classifies the bile interacting or non-interacting compounds with a ROC score of 0.941 for the training and 0.875 for the test set. Additionally, SARpy and QSAR-Co analyses are also been performed to classify compounds as bile interacting/non-interacting. Moreover, forty-six recently FDA-approved drugs have been screened by the developed SARpy and QSAR-Co models to assess their bile interaction properties. Overall, this attempt may facilitate the researchers to identify bile interacting/non-interacting molecules in a faster way and help in the design of formulations and target-specific drug development.

Graph Convolutional Network-Enhanced Model for Screening Persistent, Mobile, and Toxic and Very Persistent and Very Mobile Substances

The global management for persistent, mobile, and toxic (PMT) and very persistent and very mobile (vPvM) substances has been further strengthened with the rapid increase of emerging contaminants. The development of a ready-to-use and publicly available tool for the high-throughput screening of PMT/vPvM substances is thus urgently needed. However, the current model building with the coupling of conventional algorithms, small-scale data set, and simplistic features hinders the development of a robust model for screening PMT/vPvM with wide application domains. Here, we construct a graph convolutional network (GCN)-enhanced model with feature fusion of a molecular graph and molecular descriptors to effectively utilize the significant correlation between critical descriptors and PMT/vPvM substances. The model is built with 213,084 substances following the latest PMT classification criteria. The application domains of the GCN-enhanced model assessed by kernel density estimation demonstrate the high suitability for high-throughput screening PMT/vPvM substances with both a high accuracy rate (86.6%) and a low false-negative rate (6.8%). An online server named PMT/vPvM profiler is further developed with a user-friendly web interface (http://www.pmt.zj.cn/). Our study facilitates a more efficient evaluation of PMT/vPvM substances with a globally accessible screening platform.

CatNet: Sequence-based deep learning with cross-attention mechanism for identifying endocrine-disrupting chemicals

Endocrine-disrupting chemicals (EDCs) pose significant environmental and health risks due to their potential to interfere with nuclear receptors (NRs), key regulators of physiological processes. Despite the evident risks, the majority of existing research narrows its focus on the interaction between compounds and the individual NR target, neglecting a comprehensive assessment across the entire NR family. In response, this study assembled a comprehensive human NR dataset, capturing 49,244 interactions between 35,467 unique compounds and 42 NRs. We introduced a cross-attention network framework, "CatNet", innovatively integrating compound and protein representations through cross-attention mechanisms. The results showed that CatNet model achieved excellent performance with an area under the receiver operating characteristic curve (AUCROC) = 0.916 on the test set, and exhibited reliable generalization on unseen compound-NR pairs. A distinguishing feature of our research is its capacity to expand to novel targets. Beyond its predictive accuracy, CatNet offers a valuable mechanistic perspective on compound-NR interactions through feature visualization. Augmenting the utility of our research, we have also developed a graphical user interface, empowering researchers to predict chemical binding to diverse NRs. Our model enables the prediction of human NR-related EDCs and shows the potential to identify EDCs related to other targets.

Application of ensemble learning for predicting GABAA receptor agonists

BACKGROUND

Over the past few decades, agonists binding to the benzodiazepine site of the GABAA receptor have been successfully developed as clinical drugs. Different modulators (agonist, antagonist, and reverse agonist) bound to benzodiazepine sites exhibit different or even opposite pharmacological effects, however, their structures are so similar that it is difficult to distinguish them based solely on molecular skeleton. This study aims to develop classification models for predicting the agonists.

METHODS

306 agonists or non-agonists were collected from literature. Six machine learning algorithms including RF, XGBoost, AdaBoost, GBoost, SVM, and ANN algorithms were employed for model development. Using six descriptors including 1D/2D Descriptors, ECFP4, 2D-Pharmacophore, MACCS, PubChem, and Estate fingerprint to characterize chemical structures. The model interpretability was explored by SHAP method.

RESULTS

The best model demonstrated an AUC value of 0.905 and an MCC value of 0.808 for the test set. The PubMac-based model (PubMac-GB) achieved best AUC values of 0.935 for test set. The SHAP analysis results emphasized that MaccsFP62, ECFP_624, ECFP_724, and PubchemFP213 were the crucial molecular features. Applicability domain analysis was also performed to determine reliable prediction boundaries for the model. The PubMac-GB model was applied to virtual screening for potential GABAA agonists and the top 100 compounds were given.

CONCLUSION

Overall, our ensemble learning-based model (PubMac-GB) achieved comparable performance and would be helpful in effectively identifying agonists of GABAA receptors.

A fragment-based exploration of diverse MMP-9 inhibitors through classification-dependent structural assessment

Matrix metalloproteinases (MMPs) are belonging to the Zn2+-dependent metalloenzymes. These can degenerate the extracellular matrix (ECM) that is entailed with various biological processes. Among the MMP family members, MMP-9 is associated with several pathophysiological circumstances. Apart from wound healing, remodeling of bone, inflammatory mechanisms, and rheumatoid arthritis, MMP-9 has also significant roles in tumor invasion and metastasis. Therefore, MMP-9 has been in the spotlight of anticancer drug discovery programs for more than a decade. In this present study, classification-based QSAR techniques along with fragment-based data mining have been carried out on divergent MMP-9 inhibitors to point out the important structural attributes. This current study may be able to elucidate the importance of several pivotal molecular fragments such as sulfonamide, hydroxamate, i-butyl, and ethoxy functions for imparting potential MMP-9 inhibition. These observations are in correlation with the ligand-bound co-crystal structures of MMP-9. Therefore, these findings are beneficial for the design and discovery of effective MMP-9 inhibitors in the future.

Predicting the retention time of Synthetic Cannabinoids using a combinatorial QSAR approach

Background

Abuse of Synthetic Cannabinoids (SCs) has become a serious threat to public health. Due to the various structural and chemical group modified by criminals, their detection is a major challenge in forensic toxicological identification. Therefore, rapid and efficient identification of SCs is important for forensic toxicology and drug bans. The prediction of an analyte's retention time in liquid chromatography is an important index for the qualitative analysis of compounds and can provide informatics solutions for the interpretation of chromatographic data.

Methods

In this study, experimental data from high-resolution mass spectrometry (HRMS) are used to construct a regression model for predicting the retention time of SCs using machine learning methods. The prediction ability of the model is improved by adopting a strategy that combines different descriptors in different independent machine-learning methods.

Results

The best model was obtained with a method that combined Substructure Fingerprint Count and Finger printer features and the support vector regression (SVR) method, as it exhibited an R² value of 0.81 for the validation set and 0.83 for the test set. In addition, 4 new SCs were predicted by the optimized model, with a prediction error within 3%.

Conclusions

Our study provides a model that can predict the retention time of compounds and it can be used as a filter to reduce false-positive candidates when used in combination with LC-HRMS, especially in the absence of reference standards. This can improve the confidence of identification in non-targeted analysis and the reliability of identifying unknown substances.

In Silico Identification of Anti-SARS-CoV-2 Medicinal Plants Using Cheminformatics and Machine Learning

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the causative pathogen of COVID-19, is spreading rapidly and has caused hundreds of millions of infections and millions of deaths worldwide. Due to the lack of specific vaccines and effective treatments for COVID-19, there is an urgent need to identify effective drugs. Traditional Chinese medicine (TCM) is a valuable resource for identifying novel anti-SARS-CoV-2 drugs based on the important contribution of TCM and its potential benefits in COVID-19 treatment. Herein, we aimed to discover novel anti-SARS-CoV-2 compounds and medicinal plants from TCM by establishing a prediction method of anti-SARS-CoV-2 activity using machine learning methods. We first constructed a benchmark dataset from anti-SARS-CoV-2 bioactivity data collected from the ChEMBL database. Then, we established random forest (RF) and support vector machine (SVM) models that both achieved satisfactory predictive performance with AUC values of 0.90. By using this method, a total of 1011 active anti-SARS-CoV-2 compounds were predicted from the TCMSP database. Among these compounds, six compounds with highly potent activity were confirmed in the anti-SARS-CoV-2 experiments. The molecular fingerprint similarity analysis revealed that only 24 of the 1011 compounds have high similarity to the FDA-approved antiviral drugs, indicating that most of the compounds were structurally novel. Based on the predicted anti-SARS-CoV-2 compounds, we identified 74 anti-SARS-CoV-2 medicinal plants through enrichment analysis. The 74 plants are widely distributed in 68 genera and 43 families, 14 of which belong to antipyretic detoxicate plants. In summary, this study provided several medicinal plants with potential anti-SARS-CoV-2 activity, which offer an attractive starting point and a broader scope to mine for potentially novel anti-SARS-CoV-2 drugs.

Machine Learning-Based Models with High Accuracy and Broad Applicability Domains for Screening PMT/vPvM Substances

Persistent, mobile, and toxic (PMT) substances and very persistent and very mobile (vPvM) substances can transport over long distances from various sources, increasing the public health risk. A rapid and high-throughput screening of PMT/vPvM substances is thus warranted to the risk prevention and mitigation measures. Herein, we construct a machine learning-based screening system integrated with five models for high-throughput classification of PMT/vPvM substances. The models are constructed with 44 971 substances by conventional learning, deep learning, and ensemble learning algorithms, among which, LightGBM and XGBoost outperform other algorithms with metrics exceeding 0.900. Good model interpretability is achieved through the number of free halogen atoms (fr_halogen) and the logarithm of partition coefficient (MolLogP) as the two most critical molecular descriptors representing the persistence and mobility of substances, respectively. Our screening system exhibits a great generalization capability with area under the receiver operating characteristic curve (AUROC) above 0.951 and is successfully applied to the persistent organic pollutants (POPs), prioritized PMT/vPvM substances, and pesticides. The screening system constructed in this study can serve as an efficient and reliable tool for high-throughput risk assessment and the prioritization of managing emerging contaminants.

Environmental toxicity risk evaluation of nitroaromatic compounds: Machine learning driven binary/multiple classification and design of safe alternatives

Nitroaromatic compounds (NACs) represent a significant source of organic pollutants in the environment. In this study, a well-rounded dataset containing 371 NACs with rat oral median lethal doses (LD50s) was developed. Based on the dataset, binary and multiple classification models were established. Seven machine learning algorithms were used to establish the prediction models in combination with six fingerprints. In the binary classification models, the overall predictive accuracy of 10-fold cross-validation for training set in the top ten models ranged from 0.823 to 0.874. In the multiple classification models, the combination of graph fingerprint and random forest (Graph-RF) yielded the best predictive effects with AUC values of 0.929 and 0.956 for the training set and the test set, respectively. Model prediction performance was further evaluated using the true external set comprising 1366 NACs, including 96.6% belonging to the applicability domain. Further, we determined the structural features influencing the acute oral toxicity based on information gain and substructure frequency analysis. Finally, we identified highly toxic compounds based on the structural alerts and successfully transformed a representative highly toxic compound into low-toxic alternatives via structural modification. Overall, the models constructed facilitate environmental risk assessment and the design of green and safe chemicals.

Profiling prediction of nuclear receptor modulators with multi-task deep learning methods: toward the virtual screening

Nuclear receptors (NRs) are ligand-activated transcription factors, which constitute one of the most important targets for drug discovery. Current computational strategies mainly focus on a single target, and the transfer of learned knowledge among NRs was not considered yet. Herein we proposed a novel computational framework named NR-Profiler for prediction of potential NR modulators with high affinity and specificity. First, we built a comprehensive NR data set including 42 684 interactions to connect 42 NRs and 31 033 compounds. Then, we used multi-task deep neural network and multi-task graph convolutional neural network architectures to construct multi-task multi-classification models. To improve the predictive capability and robustness, we built a consensus model with an area under the receiver operating characteristic curve (AUC) = 0.883. Compared with conventional machine learning and structure-based approaches, the consensus model showed better performance in external validation. Using this consensus model, we demonstrated the practical value of NR-Profiler in virtual screening for NRs. In addition, we designed a selectivity score to quantitatively measure the specificity of NR modulators. Finally, we developed a freely available standalone software for users to make profiling predictions for their compounds of interest. In summary, our NR-Profiler provides a useful tool for NR-profiling prediction and is expected to facilitate NR-based drug discovery.

Review of in silico studies dedicated to the nuclear receptor family: Therapeutic prospects and toxicological concerns

Being in the center of both therapeutic and toxicological concerns, NRs are widely studied for drug discovery application but also to unravel the potential toxicity of environmental compounds such as pesticides, cosmetics or additives. High throughput screening campaigns (HTS) are largely used to detect compounds able to interact with this protein family for both therapeutic and toxicological purposes. These methods lead to a large amount of data requiring the use of computational approaches for a robust and correct analysis and interpretation. The output data can be used to build predictive models to forecast the behavior of new chemicals based on their in vitro activities. This atrticle is a review of the studies published in the last decade and dedicated to NR ligands in silico prediction for both therapeutic and toxicological purposes. Over 100 articles concerning 14 NR subfamilies were carefully read and analyzed in order to retrieve the most commonly used computational methods to develop predictive models, to retrieve the databases deployed in the model building process and to pinpoint some of the limitations they faced.

In Silico Prediction of CYP2C8 Inhibition with Machine-Learning Methods

Cytochrome P450 2C8 (CYP2C8) is a major drug-metabolizing enzyme in humans and is responsible for the metabolism of ∼5% drugs in clinical use. Thus, inhibition of CYP2C8, which causes potential adverse drug events, cannot be neglected. The in vitro drug interaction studies guidelines for industry issued by the FDA also point out that it needs to be determined whether investigated drugs are CYP2C8 inhibitors before clinical trials. However, current studies mainly focus on predicting the inhibitors of other major P450 enzymes, and the importance of CYP2C8 inhibition has been overlooked. Therefore, there is a need to develop models for identifying potential CYP2C8 inhibition. In this study, in silico classification models for predicting CYP2C8 inhibition were built by five machine-learning methods combined with nine molecular fingerprints. The performance of the models built was evaluated by test and external validation sets. The best model had AUC values of 0.85 and 0.90 for the test and external validation sets, respectively. The applicability domain was analyzed based on the molecular similarity and exhibited an impact on the improvement of prediction accuracy. Furthermore, several representative privileged substructures such as 1H-benzo[d]imidazole, 1-phenyl-1H-pyrazole, and quinoline were identified by information gain and substructure frequency analysis. Overall, our results would be helpful for the prediction of CYP2C8 inhibition.

The GOLIATH Project: Towards an Internationally Harmonised Approach for Testing Metabolism Disrupting Compounds

The purpose of this project report is to introduce the European "GOLIATH" project, a new research project which addresses one of the most urgent regulatory needs in the testing of endocrine-disrupting chemicals (EDCs), namely the lack of methods for testing EDCs that disrupt metabolism and metabolic functions. These chemicals collectively referred to as "metabolism disrupting compounds" (MDCs) are natural and anthropogenic chemicals that can promote metabolic changes that can ultimately result in obesity, diabetes, and/or fatty liver in humans. This project report introduces the main approaches of the project and provides a focused review of the evidence of metabolic disruption for selected EDCs. GOLIATH will generate the world's first integrated approach to testing and assessment (IATA) specifically tailored to MDCs. GOLIATH will focus on the main cellular targets of metabolic disruption-hepatocytes, pancreatic endocrine cells, myocytes and adipocytes-and using an adverse outcome pathway (AOP) framework will provide key information on MDC-related mode of action by incorporating multi-omic analyses and translating results from in silico, in vitro, and in vivo models and assays to adverse metabolic health outcomes in humans at real-life exposures. Given the importance of international acceptance of the developed test methods for regulatory use, GOLIATH will link with ongoing initiatives of the Organisation for Economic Development (OECD) for test method (pre-)validation, IATA, and AOP development.