Acute oral toxicity is currently not available for most polycyclic aromatic hydrocarbons (PAHs), especially their derivatives, because it is cost-prohibitive to experimentally determine all of them. Here, quantitative structure-activity relationship (QSAR) models using machine learning (ML) for predicting the toxicity of PAH derivatives were developed, based on oral toxicity data points of 788 individual substances of rats. Both the individual ML algorithm gradient boosting regression trees (GBRT) and the stacking ML algorithm (extreme gradient boosting + GBRT + random forest regression) provided the best prediction results with satisfactory determination coefficients for both cross-validation and the test set. It was found that those PAH derivatives with fewer polar hydrogens, more large-sized atoms, more branches, and lower polarizability have higher toxicity. Software based on the optimal ML-QSAR model was successfully developed to expand the application potential of the developed model, obtaining reliable prediction of pLD50 values and reference doses for 6893 external PAH derivatives. Among these chemicals, 472 were identified as moderately or highly toxic; 10 out of them had clear environment detection or use records. The findings provide valuable insights into the toxicity of PAHs and their derivatives, offering a standard platform for effectively evaluating chemical toxicity using ML-QSAR models.

The insufficient hazard thresholds of specific individual aromatic hydrocarbon compounds (AHCs) with diverse structures limit their ecological risk assessment. Thus, herein, quantitative structure-activity relationship (QSAR) models for estimating the hazard threshold of AHCs were developed based on the hazardous concentration for 5% of species (HC5) determined using the optimal species sensitivity distribution models and on the molecular descriptors calculated via the PADEL software and ORCA software. Results revealed that the optimal QSAR model, which involved eight descriptors, namely, Zagreb, GATS2m, VR3_Dzs, AATSC2s, GATS2c, ATSC2i, ω, and Vm, displayed excellent performance, as reflected by an optimal goodness of fit (R2adj = 0.918), robustness (Q2LOO = 0.869), and external prediction ability (Q2F1 = 0.760, Q2F2 = 0.782, and Q2F3 = 0.774). The hazard thresholds estimated using the optimal QSAR model were approximately close to the published water quality criteria developed by different countries and regions. The quantitative structure-toxicity relationship demonstrated that the molecular descriptors associated with electrophilicity and topological and electrotopological properties were important factors that affected the risks of AHCs. A new and reliable approach to estimate the hazard threshold of ecological risk assessment for various aromatic hydrocarbon pollutants was provided in this study, which can be widely popularised to similar contaminants with diverse structures.

In order to predict the anti-trypanosome effect of carbazole-derived compounds by quantitative structure-activity relationship, five models were established by the linear method, random forest, radial basis kernel function support vector machine, linear combination mix-kernel function support vector machine, and nonlinear combination mix-kernel function support vector machine (NLMIX-SVM). The heuristic method and optimized CatBoost were used to select two different key descriptor sets for building linear and nonlinear models, respectively. Hyperparameters in all nonlinear models were optimized by comprehensive learning particle swarm optimization with low complexity and fast convergence. Furthermore, the models\' robustness and reliability underwent rigorous assessment using fivefold and leave-one-out cross-validation, y-randomization, and statistics including concordance correlation coefficient (CCC), [Formula: see text] , [Formula: see text] , and [Formula: see text] . Among all the models, the NLMIX-SVM model, which was established by support vector regression using a nonlinear combination of radial basis kernel function, sigmoid kernel function, and linear kernel function as a new kernel function, demonstrated excellent learning and generalization abilities as well as robustness: [Formula: see text] = 0.9581, mean square error (MSE) = 0.0199 for the training set and [Formula: see text] = 0.9528, MSE = 0.0174 for the test set. [Formula: see text] , [Formula: see text] , CCC, [Formula: see text] , [Formula: see text], and [Formula: see text] are 0.9539, 0.8908, 0.9752, 0.9529, 0.9528, and 0.9633, respectively. The NLMIX-SVM method proved to be a promising way in quantitative structure-activity relationship research. In addition, molecular docking experiments were conducted to analyze the properties of new derivatives, and a new potential candidate drug molecule was ultimately found. In summary, this study will provide help for the design and screening of novel anti-trypanosome drugs.

De novo molecular design is the process of searching chemical space for drug-like molecules with desired properties, and deep learning has been recognized as a promising solution. In this study, I developed an effective computational method called Scoring-Assisted Generative Exploration (SAGE) to enhance chemical diversity and property optimization through virtual synthesis simulation, the generation of bridged bicyclic rings, and multiple scoring models for drug-likeness. In six protein targets, SAGE generated molecules with high scores within reasonable numbers of steps by optimizing target specificity without a constraint and even with multiple constraints such as synthetic accessibility, solubility, and metabolic stability. Furthermore, I suggested a top-ranked molecule with SAGE as dual inhibitors of acetylcholinesterase and monoamine oxidase B through multiple desired property optimization. Therefore, SAGE can generate molecules with desired properties by optimizing multiple properties simultaneously, indicating the importance of de novo design strategies in the future of drug discovery and development. SCIENTIFIC CONTRIBUTION: The scientific contribution of this study lies in the development of the Scoring-Assisted Generative Exploration (SAGE) method, a novel computational approach that significantly enhances de novo molecular design. SAGE uniquely integrates virtual synthesis simulation, the generation of complex bridged bicyclic rings, and multiple scoring models to optimize drug-like properties comprehensively. By efficiently generating molecules that meet a broad spectrum of pharmacological criteria-including target specificity, synthetic accessibility, solubility, and metabolic stability-within a reasonable number of steps, SAGE represents a substantial advancement over traditional methods. Additionally, the application of SAGE to discover dual inhibitors for acetylcholinesterase and monoamine oxidase B not only demonstrates its potential to streamline and enhance the drug development process but also highlights its capacity to create more effective and precisely targeted therapies. This study emphasizes the critical and evolving role of de novo design strategies in reshaping the future of drug discovery and development, providing promising avenues for innovative therapeutic discoveries.

Identification of estrogen receptor (ER) agonists among environmental toxicants is essential for assessing the potential impact of toxicants on human health. Using 2D autocorrelation descriptors as predictor variables, two binary logistic regression models were developed to identify active ER agonists among hydroxylated polychlorinated biphenyls (OH-PCBs). The classifications made by the two models on the training set compounds resulted in accuracy, sensitivity and specificity of 95.9 %, 93.9 % and 97.6 % for ERα dataset and 91.9 %, 90.9 % and 92.7 % for ERβ dataset. The areas under the ROC curves, constructed with the training set data, were found to be 0.985 and 0.987 for the two models. Predictions made by models I and II correctly classified 84.0 % and 88.0 % of the test set compounds and 89.8 % and 85.8% of the cross-validation set compounds respectively. The two classification-based QSAR models proposed in this paper are considered robust and reliable for rapid identification of ERα and ERβ agonists among OH-PCB congeners.

Synthetic surfactant products are continuously released into the aquatic environment in large quantities, posing a burden on ecosystems as a \"pseudo-persistent\" organic pollutant. Threshold derivation for protecting aquatic ecosystems is challenging due to the various homologous components of surfactants. In this study, five commercially available products were chosen as representative major types of surfactants. Corresponding quantitative structure-activity relationships (QSAR) were screened and subsequently combined with interspecific correlation estimation (ICE) to develop species sensitivity distributions (SSDs) for each component. Then, the 5th percentile hazard concentrations (HC5s) were calculated. The results indicated that the developed QSAR-ICE models demonstrated good toxicity prediction performance. The HC5 of each component showed a negatively correlation with alkyl chain length and a positive correlation with the amount of ethylene oxide. The HC5s of surfactants correlate with variations in their charged properties. Quaternary ammonium compounds (QAC) exhibited the lowest HC5s (8.5 ± 18.3 μg/L), followed by alcohol ethoxylates (AE), linear alkylbenzene sulfonates (LAS), and alcohol ethoxylated sulfates (AES); and alkyl oxide (AO) exhibited the highest HC5s (15784.2 ± 21552.6 μg/L). For cationic surfactants, the HC5s in the invertebrates were significantly lower than those in the fish; conversely, for anionic surfactants, the opposite was true, indicating a difference in the toxic mechanisms of surfactants with different charged properties across species taxa. Additionally, among invertebrates, shellfish demonstrated heightened sensitivity to surfactants, owing to their high accumulation and low metabolism of pollutants. Salmoniformes were the most sensitive among all species, indicating the necessity of prioritizing these species for aquatic ecological conservation in surfactant-contaminated waters.

The Ames/quantitative structure-activity relationship (QSAR) International Challenge Projects, held during 2014-2017 and 2020-2022, evaluated the performance of various predictive models. Despite the significant insights gained, the rules allowing participants to select prediction targets introduced ambiguity in model performance evaluation. This reanalysis identified the highest-performing prediction model, assuming a 100% coverage rate (COV) for all prediction target compounds and an estimated performance variation due to changes in COV. All models from both projects were evaluated using balance accuracy (BA), the Matthews correlation coefficient (MCC), the F1 score (F1), and the first principal component (PC1). After normalizing the COV, a correlation analysis with these indicators was conducted, and the evaluation index for all prediction models in terms of the COV was estimated. In total, using 109 models, the model with the highest estimated BA (76.9) at 100% COV was MMI-VOTE1, as reported by Meiji Pharmaceutical University (MPU). The best models for MCC, F1, and PC1 were all MMI-STK1, also reported by MPU. All the models reported by MPU ranked in the top four. MMI-STK1 was estimated to have F1 scores of 59.2, 61.5, and 63.1 at COV levels of 90%, 60%, and 30%, respectively. These findings highlight the current state and potential of the Ames prediction technology.

Topical and transdermal treatments have been dramatically growing recently and it is crucial to consider skin sensitization during the drug discovery and development process for these administration routes. Various tests, including animal and non-animal approaches, have been devised to assess the potential for skin sensitization. Furthermore, numerous in silico models have been created, providing swift and cost-effective alternatives to traditional methods such as in vivo, in vitro, and in chemico methods for categorizing compounds. In this study, a quantitative structure-activity relationship (QSAR) model was developed using the innovative hierarchical support vector regression (HSVR) scheme. The aim was to quantitatively predict the potential for skin sensitization by analyzing the percent of cysteine depletion in Direct Peptide Reactivity Assay (DPRA). The results demonstrated accurate, consistent, and robust predictions in the training set, test set, and outlier set. Consequently, this model can be employed to estimate skin sensitization potential of novel or virtual compounds.

A series of 2-azolylmethylene-3-(2H)-benzofuranone derivatives, 2-indolylmethylene-3-(2H)-benzofuranone and 2-pyrrolylmethylene-3-(2H)-benzofuranone derivatives, were synthesized, and their monoamine oxidase (MAO) A and B inhibitory activities were evaluated. Compounds 1b, 3b, 6b, 7b, and 10b showed strong inhibitory activity against MAO-A, and compound 3b showed the highest potency and selectivity, with an IC50 value of 21 nM and a MAO-A selectivity index of 48. Compounds 3c, 4c, 9a, 9c, 10c, 11a, and 11c showed strong inhibitory activity against MAO-B, and compound 4c showed the highest potency and selectivity, with an IC50 value of 16 nM and a MAO-B selectivity index of >1100. Further analysis of these compounds indicated that compound 3b for MAO-A and compound 4c for MAO-B were competitive inhibitors, with Ki values of 10 and 6.1 nM, respectively. Furthermore, computational analyses, such as quantitative structure-activity relationship (QSAR) analysis of the 2-azolylmethylene-3-(2H)-benzofuranone derivatives conducting their pIC50 values with the Molecular Operating Environment (MOE) and Mordred, and molecular docking analysis using MOE-Dock supported that the 2-azolylmethylene-3-(2H)-benzofuranone derivatives are a privileged scaffold for the design and development of novel MAO inhibitors.

Tea polyphenols have been reported as potential α-amylase inhibitors. However, the quantitative structure-activity relationship (QSAR) between tea polyphenols and human pancreas α-amylase (HPA) is not well understood. Herein, the inhibitory effect of twelve tea polyphenol monomers on HPA was investigated in terms of inhibitory activity, as well as QSAR analysis and interaction mechanism. The results revealed that the HPA inhibitory activity of theaflavins (TFs), especially theaflavin-3\'-gallate (TF-3\'-G, IC50: 0.313 mg/mL), was much stronger than that of catechins (IC50: 18.387-458.932 mg/mL). The QSAR analysis demonstrated that the determinant for the inhibitory activity of HPA was not the number of hydroxyl and galloyl groups in tea polyphenol monomers, while the substitution sites of these groups potentially might play a more important role in modulating the inhibitory activity. The inhibition kinetics and molecular docking revealed that TF-3\'-G as a mixed-type inhibitor had the lowest inhibition constant and bound to the active sites of HPA with the lowest binding energy (-7.74 kcal/mol). These findings could provide valuable insights into the structures-activity relationships between tea polyphenols and the HPA inhibitors.