Structure-activity relationship-based chemical classification of highly imbalanced Tox21 datasets.

The specificity of toxicant-target biomolecule interactions lends to the very imbalanced nature of many toxicity datasets, causing poor performance in Structure-Activity Relationship (SAR)-based chemical classification. Undersampling and oversampling are representative techniques for handling such an imbalance challenge. However, removing inactive chemical compound instances from the majority class using an undersampling technique can result in information loss, whereas increasing active toxicant instances in the minority class by interpolation tends to introduce artificial minority instances that often cross into the majority class space, giving rise to class overlapping and a higher false prediction rate. In this study, in order to improve the prediction accuracy of imbalanced learning, we employed SMOTEENN, a combination of Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbor (ENN) algorithms, to oversample the minority class by creating synthetic samples, followed by cleaning the mislabeled instances. We chose the highly imbalanced Tox21 dataset, which consisted of 12 in vitro bioassays for > 10,000 chemicals that were distributed unevenly between binary classes. With Random Forest (RF) as the base classifier and bagging as the ensemble strategy, we applied four hybrid learning methods, i.e., RF without imbalance handling (RF), RF with Random Undersampling (RUS), RF with SMOTE (SMO), and RF with SMOTEENN (SMN). The performance of the four learning methods was compared using nine evaluation metrics, among which F1 score, Matthews correlation coefficient and Brier score provided a more consistent assessment of the overall performance across the 12 datasets. The Friedman's aligned ranks test and the subsequent Bergmann-Hommel post hoc test showed that SMN significantly outperformed the other three methods. We also found that a strong negative correlation existed between the prediction accuracy and the imbalance ratio (IR), which is defined as the number of inactive compounds divided by the number of active compounds. SMN became less effective when IR exceeded a certain threshold (e.g., > 28). The ability to separate the few active compounds from the vast amounts of inactive ones is of great importance in computational toxicology. This work demonstrates that the performance of SAR-based, imbalanced chemical toxicity classification can be significantly improved through the use of data rebalancing.

Deep Learning-Based Structure-Activity Relationship Modeling for Multi-Category Toxicity Classification: A Case Study of 10K Tox21 Chemicals With High-Throughput Cell-Based Androgen Receptor Bioassay Data.

Deep learning (DL) has attracted the attention of computational toxicologists as it offers a potentially greater power for in silico predictive toxicology than existing shallow learning algorithms. However, contradicting reports have been documented. To further explore the advantages of DL over shallow learning, we conducted this case study using two cell-based androgen receptor (AR) activity datasets with 10K chemicals generated from the Tox21 program. A nested double-loop cross-validation approach was adopted along with a stratified sampling strategy for partitioning chemicals of multiple AR activity classes (i.e., agonist, antagonist, inactive, and inconclusive) at the same distribution rates amongst the training, validation and test subsets. Deep neural networks (DNN) and random forest (RF), representing deep and shallow learning algorithms, respectively, were chosen to carry out structure-activity relationship-based chemical toxicity prediction. Results suggest that DNN significantly outperformed RF (p < 0.001, ANOVA) by 22-27% for four metrics (precision, recall, F-measure, and AUPRC) and by 11% for another (AUROC). Further in-depth analyses of chemical scaffolding shed insights on structural alerts for AR agonists/antagonists and inactive/inconclusive compounds, which may aid in future drug discovery and improvement of toxicity prediction modeling.

Target-specific toxicity knowledgebase (TsTKb): a novel toolkit for in silico predictive toxicology.

As the number of man-made chemicals increases at an unprecedented pace, efforts of quickly screening and accurately evaluating their potential adverse biological effects have been hampered by prohibitively high costs of in vivo/vitro toxicity testing. While it is unrealistic and unnecessary to test every uncharacterized chemical, it remains a major challenge to develop alternative in silico tools with high reliability and precision in toxicity prediction. To address this urgent need, we have developed a novel mode-of-action-guided, molecular modeling-based, and machine learning-enabled modeling approach for in silico chemical toxicity prediction. Here we introduce the core element of this approach, Target-specific Toxicity Knowledgebase (TsTKb), which consists of two main components: Chemical Mode of Action (ChemMoA) database and a suite of prediction model libraries.

A review on machine learning methods for in silico toxicity prediction.

In silico toxicity prediction plays an important role in the regulatory decision making and selection of leads in drug design as in vitro/vivo methods are often limited by ethics, time, budget, and other resources. Many computational methods have been employed in predicting the toxicity profile of chemicals. This review provides a detailed end-to-end overview of the application of machine learning algorithms to Structure-Activity Relationship (SAR)-based predictive toxicology. From raw data to model validation, the importance of data quality is stressed as it greatly affects the predictive power of derived models. Commonly overlooked challenges such as data imbalance, activity cliff, model evaluation, and definition of applicability domain are highlighted, and plausible solutions for alleviating these challenges are discussed.

Evaluation of the polyphenol content and antioxidant properties of methanol extracts of the leaves, stem, and root barks of Moringa oleifera Lam.

Medicinal plants have been shown to have both chemopreventive and/or therapeutic effects on cancer and other diseases related to oxidative damage. Moringa oleifera Lam., known in the Hausa and Igala languages of Nigeria as "Zogale" and "Gergedi," respectively, and drumstick in English, is a plant that is used both as food and in folkloric medicine in Nigeria and elsewhere. Different parts of the plant were analyzed for polyphenol content as well as in vitro antioxidant potential. The methanol extract of the leaves of M. oleifera contained chlorogenic acid, rutin, quercetin glucoside, and kaempferol rhamnoglucoside, whereas in the root and stem barks, several procyanidin peaks were detected. With the xanthine oxidase model system, all the extracts exhibited strong in vitro antioxidant activity, with 50% inhibitory concentration (IC(50)) values of 16, 30, and 38 microL for the roots, leaves, and stem bark, respectively. Similarly, potent radical scavenging capacity was observed when extracts were evaluated with the 2-deoxyguanosine assay model system, with IC(50) values of 40, 58, and 72 microL for methanol extracts of the leaves, stem, and root barks, respectively. The high antioxidant/radical scavenging effects observed for different parts of M. oleifera appear to provide justification for their widespread therapeutic use in traditional medicine in different continents. The possibility that this high antioxidant/radical scavenging capacity may impact on the cancer chemopreventive potential of the plant must be considered.