Prediction of serious eye damage or eye irritation potential of compounds via consensus labelling models and active learning models based on uncertainty strategies.

Serious eye damage and eye irritation have been authenticated to be significant human health issues in various fields such as ophthalmic pharmaceuticals. Due to the shortcomings of traditional animal testing methods, in silico methods have advanced to study eye toxicity. The models for predicting serious eye damage and eye irritation potential of compounds were developed using 2299 and 5214 compounds, respectively. The 40 global single models and 40 local models were developed by combining 5 molecular description methods and 4 machine learning methods. The 40 active learning models were developed by adopting uncertainty-based active learning strategies and taking local models as initial models. The 110 global consensus models based on 40 global single models were developed using a consensus strategy. Active learning models and global consensus models performed high prediction accuracy. The test accuracy of the best serious eye damage model and eye irritation model reached 0.972 and 0.959, respectively. The applicability domains for all models were calculated to verify the rationality of prediction effect. In addition, 8 structural alerts probably causing serious eye damage or eye irritation were sought out. The prediction models and structural alerts contributed to providing hazard identification and assessing chemical safety.

Prediction of the allergic mechanism of haptens via a reaction-substructure-compound-target-pathway network system.

Skin sensitization, frequently leading to allergic contact dermatitis (ACD), is authenticated to be a significant endpoint in the field of drug discovery and cosmetics. The initiation of ACD, also known as the skin sensitization mechanism, has been documented as an adverse outcome pathway (AOP), which can be studied experimentally and computationally. In this study, we collected 154 haptens and applied systems toxicology methods to develop a reaction-substructure-compound- target-pathway network system. For the collected haptens, their key substructures were identified and associated with their protein binding reactions. The targets of haptens, including the known targets collected from four databases and the potential targets predicted via our balanced substructure-drug-target network-based inference (bSDTNBI) method, were matched to skin proteins to obtain skin targets. The dermatitis-related pathways were enriched and were subject to literature verification. The network system we developed can be applied to predict the reactions, targets and pathways of new haptens, which contributed to evaluating chemical safety and optimizing chemical structures. The study of skin sensitization mechanism is helpful for understanding the skin immunity and resisting ACD.

Prediction of the skin sensitising potential and potency of compounds via mechanism-based binary and ternary classification models.

Skin sensitisation, one of the most frequent forms of human immune toxicity, is authenticated to be a significant endpoint in the field of drug discovery and cosmetics. Due to the drawbacks of traditional animal testing methods, in silico methods have advanced to study skin sensitisation. In this study, mechanism-based binary and ternary classification models were constructed with a comprehensive data set. 1007 compounds were collected to develop five series of local and global models based on mechanisms. In each series, compounds were classified into five groups according to EC3 values, and applied as training sets, test sets and external validation sets. For each of the five series, 81 binary classification models and 81 ternary classification models were acquired via 9 molecular fingerprints and 9 machine learning methods using a novel KNIME workflow. Meanwhile, the applicability domains for the best 10 models were figured out to certify the rationality of prediction effect. In addition, 8 toxic substructures probably causing skin sensitisation were identified to speculate whether a compound is a skin sensitiser. The mechanism-based prediction models and the toxic substructures can be applied to predict the skin sensitising potential and potency of compounds.

ADMET-score - a comprehensive scoring function for evaluation of chemical drug-likeness.

Chemical absorption, distribution, metabolism, excretion, and toxicity (ADMET), play key roles in drug discovery and development. A high-quality drug candidate should not only have sufficient efficacy against the therapeutic target, but also show appropriate ADMET properties at a therapeutic dose. A lot of in silico models are hence developed for prediction of chemical ADMET properties. However, it is still not easy to evaluate the drug-likeness of compounds in terms of so many ADMET properties. In this study, we proposed a scoring function named the ADMET-score to evaluate drug-likeness of a compound. The scoring function was defined on the basis of 18 ADMET properties predicted via our web server admetSAR. The weight of each property in the ADMET-score was determined by three parameters: the accuracy rate of the model, the importance of the endpoint in the process of pharmacokinetics, and the usefulness index. The FDA-approved drugs from DrugBank, the small molecules from ChEMBL and the old drugs withdrawn from the market due to safety concerns were used to evaluate the performance of the ADMET-score. The indices of the arithmetic mean and p-value showed that the ADMET-score among the three data sets differed significantly. Furthermore, we learned that there was no obvious linear correlation between the ADMET-score and QED (quantitative estimate of drug-likeness). These results suggested that the ADMET-score would be a comprehensive index to evaluate chemical drug-likeness, and might be helpful for users to select appropriate drug candidates for further development.

In silico prediction of chemical reproductive toxicity using machine learning.

Reproductive toxicity is an important regulatory endpoint in health hazard assessment. Because the in vivo tests are expensive, time consuming and require a large number of animals, which must be killed, in silico approaches as the alternative strategies have been developed to assess the potential reproductive toxicity (reproductive toxicity) of chemicals. Some prediction models for reproductive toxicity have been developed, but most of them were built only based on one single endpoint such as embryo teratogenicity; therefore, these models may not provide reliable predictions for toxic chemicals with other endpoints, such as sperm reduction or gonadal dysgenesis. Here, a total of 1823 chemicals for reproductive toxicity characterized by multiple endpoints were used to develop structure-activity relationship models by six machine-learning approaches with nine molecular fingerprints. Among the models, MACCSFP-SVM model has the best performance for the external validation set (area under the curve = 0.900, classification accuracy = 0.836). The applicability domain was analyzed, and a rational boundary was found to distinguish inaccurate predictions and accurate predictions. Moreover, several structural alerts for characterizing reproductive toxicity were identified using the information gain combining substructure frequency analysis. Our results would be helpful for the prediction of the reproductive toxicity of chemicals.

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.

Improving the physicochemical properties of bicalutamide by complex formation with bovine serum albumin.

Bicalutamide-bovine serum albumin (Bic-BSA) complexes were prepared by anti-solvent precipitation. Bovine serum albumin (BSA) was used as a stabilizer for particle growth. The physicochemical properties of Bic-BSA were analyzed by scanning electron microscopy, X-ray powder diffraction and differential scanning calorimetry. The interaction between Bic and BSA was characterized by Fourier transform infrared spectroscopy, Raman spectroscopy, fluorescence spectroscopy and molecular docking. The particle size could be easily reduced to 1-10µm with a good lognormal distribution. The Bic-BSA complexes exhibited nonporous spherical morphology with a uniformly plicated surface. Moreover, the crystal form and thermostability of Bic were altered in the presence of BSA. Bic was found to make hydrogen bonding and hydrophobic interactions with BSA by spectroscopic studies and molecular docking. Results from the Van't Hoff equation and binding free energy calculations indicated that the improvement of physicochemical properties was the consequence of a variety of interactions in the Bic-BSA system. Bic-BSA tablets showed significantly enhanced dissolution. It was concluded that BSA plays an important role in improving the physicochemical properties of Bic due to strong multiple interactions between Bic and BSA.