Ternary classification models for predicting hormonal activities of chemicals via nuclear receptors

Highlights: • Ternary classification models based on known hormonal activities' chemicals were developed. • Both of the optimum models for AR and TR was support vector machines (SVM). • A system for identifying different hormone activities was constituted. Endocrine disrupting chemicals (EDCs) can exhibit adverse effects by increasing or blocking hormonal activities as agonists or antagonists through nuclear receptors. Computational toxicology research provides a fast and automated screening tool for determining the potential effects of EDCs. Here, we collected a large dataset of known hormonal activities to develop ternary classification models of androgen receptor (AR) and thyroid hormone receptor (TR), in combination linear discriminant analysis (LDA), classification and regression trees (CART), and support vector machines (SVM). The optimum model for classifying AR and TR activities was SVM. These newly developed models constitute a rapidly systematic early-warning technical system for identifying different hormone activities.