Development of classification- and regression-based QSAR models andin silicoscreening of skin sensitisation potential of diverse organic chemicals

Identification of structural features of surface modifiers in engineered nanostructured metal oxides regarding cell uptake through ML-based classification

Nanoparticles (NPs) are considered as versatile tools in various fields including medicine, electronics, and environmental science. Understanding the structural aspects of surface modifiers in nanoparticles that govern their cellular uptake is crucial for optimizing their efficacy and minimizing potential cytotoxicity. The cellular uptake is influenced by multiple factors, namely, size, shape, and surface charge of NPs, as well as their surface functionalization. In the current study, classification-based ML models (i.e., Bayesian classification, random forest, support vector classifier, and linear discriminant analysis) have been developed to identify the features/fingerprints that significantly contribute to the cellular uptake of ENMOs in multiple cell types, including pancreatic cancer cells (PaCa2), human endothelial cells (HUVEC), and human macrophage cells (U937). The best models have been identified for each cell type and analyzed to detect the structural fingerprints/features governing the cellular uptake of ENMOs. The study will direct scientists in the design of ENMOs of higher cellular uptake efficiency for better therapeutic response.

Correlation intensity index-index of ideality of correlation: A hyphenated target function for furtherance of MAO-B inhibitory activity assessment

Monoamine oxidases are the enzymes involved in the management of brain homeostasis through oxidative deamination of monoamines such as neurotransmitters, tyramine etc. The excessive production of monoamine oxidase-B specifically results in numerous neurodegenerative disorders like Alzheimer's and Parkinson's diseases. Inhibitors of monoamine oxidase-B are applied in the management of these disorders. Here in this article we have developed robust hybrid descriptor based QSAR models related to 123 monoamine oxidase-B inhibitors through CORAL software by means of Monte Carlo optimization method. Three target functions were applied to prepare QSAR models and three splits were made for each target function. The most reliable, robust and better predictive QSAR models were developed with TF3 (correlation intensity index -index of ideality of correlation). Correlation intensity index showed positive effect on QSAR models. The structural features obtained from the QSAR modeling were incorporated in newly designed molecules and exhibited positive effect on their endpoint. Significant binding interactions were represented by these molecules in docking studies. Molecule B5 displayed prominent pIC50 (8.3) and binding affinity (-11.5 kcal mol-1) towards monoamine oxidase-B.

Prediction-Inspired Intelligent Training for the Development of Classification Read-across Structure-Activity Relationship (c-RASAR) Models for Organic Skin Sensitizers: Assessment of Classification Error Rate from Novel Similarity Coefficients

The advancements in the field of cheminformatics have led to a reduction in animal testing to estimate the activity, property, and toxicity of query chemicals. Read-across structure-activity relationship (RASAR) is an emerging concept that utilizes various similarity functions derived from chemical information to develop highly predictive models. Unlike quantitative structure-activity relationship (QSAR) models, RASAR descriptors of a query compound are computed from its close congeners instead of the compound itself, thus targeting predictions in the model training phase. The objective of the present study is not to propose new QSAR models for skin sensitization but to demonstrate the enhancement in the quality of predictions of the skin-sensitizing potential of organic compounds by developing classification-based RASAR (c-RASAR) models. A diverse, previously curated data set was collected from the literature for which 2D descriptors were computed. The extracted essential features were then used to develop a classification-based linear discriminant analysis (LDA) QSAR model. Furthermore, from the read-across-based predictions, RASAR descriptors were calculated using the basic settings of the hyperparameters for the Laplacian Kernel-based optimum similarity measure. After feature selection, an LDA c-RASAR model was developed, which superseded the prediction quality of the LDA-QSAR model. Various other combinations of RASAR descriptors were also taken to develop additional c-RASAR models, all showing better prediction quality than the LDA QSAR model while using a lower number of descriptors. Various other machine learning c-RASAR models were also developed for comparison purposes. In this work, we have proposed and analyzed three new similarity metrics: gm_class, sm1, and sm2. The first one is an indicator variable used to generate a simple univariate c-RASAR model with good prediction ability, while the remaining two are similarity indices used to analyze possible activity cliffs in the training and test sets and are believed to play an important role in the modelability analysis of data sets.

SMILES-based 2D-QSAR and similarity search for identification of potential new scaffolds for development of SARS-CoV-2 MPRO inhibitors

COVID-19, whose etiological agent is the SARS-CoV-2 virus, has caused over 537.5 million cases and killed over 6.3 million people since its discovery in 2019. Despite the recent development of the first drugs indicated for treating people already infected, the great need to develop new anti-SARS-CoV-2 drugs still exists, mainly due to the possible emergence of new variants of this virus and resistant strains of the current variants. Thus, this work presents the results of QSAR and similarity search studies based only on 2D structures from a set of 32 bicycloproline derivatives, aiming to quickly, reproducibly, and reliably identify potentially useful compounds as scaffolds of new major protease inhibitors (M^pro) of the virus. The obtained QSAR model is based only on topological molecular descriptors. The model has good internal and external statistics, is robust, and does not present a chance correlation. This model was used as one of the tools to support the virtual screening stage carried out in the SwissADME web tool. Five molecules, from an initial set of 2695 molecules, proved to be the most promising, as they were within the model’s applicability domain and linearity range, with low potential to cause carcinogenic, teratogenic, and reproductive toxicity effects and promising pharmacokinetic properties. These five compounds were then selected as the most competent to generate, in future studies, new anti-SARS-CoV-2 agents with drug-likeness properties suitable for use in therapy.

Network Pharmacology and Molecular Docking Study of Zhishi-Baizhu Herb Pair in the Treatment of Gastric Cancer

Objective

This study aimed to investigate the possible mechanism of the Zhishi and Baizhu herb pair in the treatment of gastric cancer by means of network pharmacology and molecular docking and to provide a theoretical basis for experiments and clinical application of traditional Chinese medicine for treating gastric cancer.

Methods

The main active chemical components of Zhishi and Baizhu were screened through Traditional Chinese Medicine Systems Pharmacology (TCMSP) database and selected by using the thresholds of oral bioavailability ≥30% and drug-likeness ≥18%. The targets of Zhishi and Baizhu were obtained from TCMSP, Therapeutic Targets Database (TTD), and the DrugBank database. The corresponding genes of the targets were retrieved from the UniProt database, and the gastric cancer targets were obtained from the GeneCards database and TTD. Subsequently, the networks were built between the main drug components, drug targets, and gastric cancer targets. Then, the enrichment analyses of GO and KEGG were applied to predict the potential roles of gastric cancer pathogenesis via the R package clusterProfiler. Finally, molecular docking was used to determine the affinity between the targets and components.

Results

Twenty-seven main active components were predicted from the Zhishi-Baizhu herb pair, and a total of 120 intersection genes were screened from 303 potential medicine genes and 1,839 disease genes. The enrichment included the PI3K-Akt and IL-17 signaling pathways, and the network analysis showed that the Zhishi-Baizhu herb pair acted on seven key targets, namely, AKT1, MMP9, IL-6, CCND1, BCL2, MTOR, and MDM2 (where they played a role in treating gastric cancer). Molecular docking showed that luteolin and naringenin could stably bind to the targets.

Conclusion

The possible mechanisms of the components of the Zhishi-Baizhu herb pair in treating gastric cancer might be related to luteolin and naringenin, which intervened with the targets AKT1, MMP9, IL-6, CCND1, BCL2, MTOR, and MDM2, and are linked with the PI3K-Akt and IL-17 signaling pathways. This knowledge will lay a solid foundation for further experimental and clinical studies.

QSAR modeling of Daphnia magna and fish toxicities of biocides using 2D descriptors

In the recent years, ecotoxicological hazard potential of biocidal products has been receiving increasing attention in the industries and regulatory agencies. Biocides/pesticides are currently one of the most studied groups of compounds, and their registration cannot be done without the empirical toxicity information. In view of limited experimental data available for these compounds, we have developed Quantitative Structure-Activity Relationship (QSAR) models for the toxicity of biocides to fish and Daphnia magna following principles of QSAR modeling recommended by the OECD (Organization for Economic Cooperation and Development). The models were developed using simple and interpretable 2D descriptors and validated using stringent tests. Both models showed encouraging statistical quality in terms of determination coefficient R² (0.800 and 0.648), cross-validated leave-one-out Q² (0.760 and 0.602) and predictive R²_pred or Q²_ext (0.875 and 0.817) for fish (n_Training = 66, n_Test = 22) and Daphnia magna (n_Training = 100, n_Test = 33) toxicity datasets, respectively. These models should be applicable for data gap filling in case of new or untested biocidal compounds falling within the applicability domain of the models. In general, the models indicate that the toxicity increases with lipophilicity and decreases with polarity, branching and unsaturation. We have also developed interspecies toxicity models for biocides using the daphnia and fish toxicity data and used the models for data gap filling.

Chemometric modeling of Daphnia magna toxicity of agrochemicals

Over the past few years, the ecotoxicological hazard potential of agrochemicals has received much attention in the industries and regulatory agencies. In the current work, we have developed quantitative structure-activity relationship (QSAR) models for Daphnia magna toxicities of different classes of agrochemicals (fungicides, herbicides, insecticides and microbiocides) individually as well as for the combined set with the application of Organization for Economic Co-operation and Development (OECD) recommended guidelines. The models for the individual data sets as well as for the combined set were generated employing only simple and interpretable two-dimensional descriptors, and subsequently strictly validated using test set compounds. The validated individual models were used to generate consensus models, with the objective to improve the prediction quality and reduced prediction errors. All the individual models of different classes of agrochemicals as well as the global set of agrochemicals showed encouraging statistical quality and prediction ability. The general observations from the derived models suggest that the toxicity increases with lipophilicity and decreases with polarity. The generated models of different classes of agrochemicals and also for the combined set should be applicable for data gap filling for new or untested agrochemical compounds falling within the applicability domain of the developed models.

In silico study toward the identification of new and safe potential inhibitors of photosynthetic electron transport

To address the rising global demand for food, it is necessary to search for new herbicides that can control resistant weeds. We performed a 2D-quantitative structure-activity relationship (QSAR) study to predict compounds with photosynthesis-inhibitory activity. A data set of 44 compounds (quinolines and naphthalenes), which are described as photosynthetic electron transport (PET) inhibitors, was used. The obtained model was approved in internal and external validation tests. 2D Similarity-based virtual screening was performed and 64 compounds were selected from the ZINC database. By using the VEGA QSAR software, 48 compounds were shown to have potential toxic effects (mutagenicity and carcinogenicity). Therefore, the model was also tested using a set of 16 molecules obtained by a similarity search of the ZINC database. Six compounds showed good predicted inhibition of PET. The obtained model shows potential utility in the design of new PET inhibitors, and the hit compounds found by virtual screening are novel bicyclic scaffolds of this class.

QSAR models of human data can enrich or replace LLNA testing for human skin sensitization

Skin sensitization is a major environmental and occupational health hazard. Although many chemicals have been evaluated in humans, there have been no efforts to model these data to date. We have compiled, curated, analyzed, and compared the available human and LLNA data. Using these data, we have developed reliable computational models and applied them for virtual screening of chemical libraries to identify putative skin sensitizers. The overall concordance between murine LLNA and human skin sensitization responses for a set of 135 unique chemicals was low (R = 28-43%), although several chemical classes had high concordance. We have succeeded to develop predictive QSAR models of all available human data with the external correct classification rate of 71%. A consensus model integrating concordant QSAR predictions and LLNA results afforded a higher CCR of 82% but at the expense of the reduced external dataset coverage (52%). We used the developed QSAR models for virtual screening of CosIng database and identified 1061 putative skin sensitizers; for seventeen of these compounds, we found published evidence of their skin sensitization effects. Models reported herein provide more accurate alternative to LLNA testing for human skin sensitization assessment across diverse chemical data. In addition, they can also be used to guide the structural optimization of toxic compounds to reduce their skin sensitization potential.

Multi-Layer Identification of Highly-Potent ABCA1 Up-Regulators Targeting LXRβ Using Multiple QSAR Modeling, Structural Similarity Analysis, and Molecular Docking

In this study, in silico approaches, including multiple QSAR modeling, structural similarity analysis, and molecular docking, were applied to develop QSAR classification models as a fast screening tool for identifying highly-potent ABCA1 up-regulators targeting LXRβ based on a series of new flavonoids. Initially, four modeling approaches, including linear discriminant analysis, support vector machine, radial basis function neural network, and classification and regression trees, were applied to construct different QSAR classification models. The statistics results indicated that these four kinds of QSAR models were powerful tools for screening highly potent ABCA1 up-regulators. Then, a consensus QSAR model was developed by combining the predictions from these four models. To discover new ABCA1 up-regulators at maximum accuracy, the compounds in the ZINC database that fulfilled the requirement of structural similarity of 0.7 compared to known potent ABCA1 up-regulator were subjected to the consensus QSAR model, which led to the discovery of 50 compounds. Finally, they were docked into the LXRβ binding site to understand their role in up-regulating ABCA1 expression. The excellent binding modes and docking scores of 10 hit compounds suggested they were highly-potent ABCA1 up-regulators targeting LXRβ. Overall, this study provided an effective strategy to discover highly potent ABCA1 up-regulators.

Predicting chemically-induced skin reactions. Part I: QSAR models of skin sensitization and their application to identify potentially hazardous compounds

Repetitive exposure to a chemical agent can induce an immune reaction in inherently susceptible individuals that leads to skin sensitization. Although many chemicals have been reported as skin sensitizers, there have been very few rigorously validated QSAR models with defined applicability domains (AD) that were developed using a large group of chemically diverse compounds. In this study, we have aimed to compile, curate, and integrate the largest publicly available dataset related to chemically-induced skin sensitization, use this data to generate rigorously validated and QSAR models for skin sensitization, and employ these models as a virtual screening tool for identifying putative sensitizers among environmental chemicals. We followed best practices for model building and validation implemented with our predictive QSAR workflow using Random Forest modeling technique in combination with SiRMS and Dragon descriptors. The Correct Classification Rate (CCR) for QSAR models discriminating sensitizers from non-sensitizers was 71-88% when evaluated on several external validation sets, within a broad AD, with positive (for sensitizers) and negative (for non-sensitizers) predicted rates of 85% and 79% respectively. When compared to the skin sensitization module included in the OECD QSAR Toolbox as well as to the skin sensitization model in publicly available VEGA software, our models showed a significantly higher prediction accuracy for the same sets of external compounds as evaluated by Positive Predicted Rate, Negative Predicted Rate, and CCR. These models were applied to identify putative chemical hazards in the Scorecard database of possible skin or sense organ toxicants as primary candidates for experimental validation.

Exploring molecular fingerprints of selective PPARδ agonists through comparative and validated chemometric techniques

Peroxysome proliferator-activated receptors (PPARs) have grown greatly in importance due to their role in the metabolic profile. Among three subtypes (α, γ and δ), we here consider the least investigated δ subtype to explore the molecular fingerprints of selective PPARδ agonists. Validated QSAR models (regression based 2D-QSAR, HQSAR and KPLS) and molecular docking with dynamics analyses support the inference of classification-based Bayesian and recursive models. Chemometric studies indicate that the presence of ether linkages and heterocyclic rings has optimum influence in imparting selective bioactivity. Pharmacophore models and docking with molecular dynamics analyses postulate the occurrence of aromatic rings, HB acceptor and a hydrophobic region as crucial molecular fragments for development of PPARδ modulators. Multi-chemometric studies suggest the essential structural requirements of a molecule for imparting potent and selective PPARδ modulation.

Quantitative structure-activity relationship for toxicity of ionic liquids to Daphnia magna: aromaticity vs. lipophilicity

Water solubility of ionic liquids (ILs) allows their dispersion into aquatic systems and raises concerns on their pollutant potential. Again, lipophilicity can contribute to the toxicity of ILs due to increased ability of the compounds to cross lipoidal bio-membranes. In the present work, we have performed statistical model development for toxicity of a set of ionic liquids to Daphnia magna, a widely accepted model organism for toxicity testing, using computed lipophilicity, atom-type fragment, quantum topological molecular similarity (QTMS) and extended topochemical atom (ETA) descriptors. The models have been developed and validated in accordance with the Organization for Economic Co-operation and Development (OECD) guidelines for quantitative structure-activity relationships (QSARs). The best partial least squares (PLS) model outperforms the previously reported multiple linear regression (MLR) model in statistical quality and predictive ability (R(2)=0.955, Q(2)=0.917, Rpred(2)=0.848). In this work, the ETA descriptors show importance of branching and aromaticity while the QTMS descriptor ellipticity efficiently shows which compounds are influential in the data set, with reference to the model. While obvious importance of lipophilicity is evident from the models, the best model clearly shows the importance of aromaticity suggesting that more lipophilic ILs with less toxicity may be designed by avoiding aromaticity, nitrogen atoms and increasing branching in the cationic structure. The developed quantitative models are in consonance with the recent hypothesis of importance of aromaticity for toxicity of ILs.