Multi-label classification and label dependence in in silico toxicity prediction

Most computational predictive models are specifically trained for a single toxicity endpoint and lack the ability to learn dependencies between endpoints, such as those targeting similar biological pathways. In this study, we compare the performance of 3 multi-label classification (MLC) models, namely Classifier Chains (CC), Label Powersets (LP) and Stacking (SBR), against independent classifiers (Binary Relevance) on Tox21 challenge data. Also, we develop a novel label dependence measure that shows full range of values, even at low prior probabilities, for the purpose of data-driven label partitioning. Using Logistic Regression as the base classifier and random label partitioning (k = 3), CC show statistically significant improvements in model performance using Hamming and multi-label accuracy scores (p