Development of binary classification models for grouping hydroxylated polychlorinated biphenyls into active and inactive thyroid hormone receptor agonists
Authors:
- 3 April 2023
- journal article
- research article
- Published by Taylor & Francis in SAR and QSAR in Environmental Research
- Vol. 34 (4) , 267-284
Abstract
Some adverse effects of hydroxylated polychlorinated biphenyls (OH-PCBs) in humans are presumed to be initiated via thyroid hormone receptor (TR) binding. Due to the trial-and-error approach adopted for OH-PCB selection in previous studies, experiments designed to test the TR binding hypothesis mostly utilized inactive OH-PCBs, leading to considerable waste of time, effort and other material resources. In this paper, linear discriminant analysis (LDA) and binary logistic regression (LR) were used to develop classification models to group OH-PCBs into active and inactive TR agonists using radial distribution function (RDF) descriptors as predictor variables. The classifications made by both LDA and LR models on the training set compounds resulted in an accuracy of 84.3%, sensitivity of 72.2% and specificity of 90.9%. The areas under the ROC curves, constructed with the training set data, were found to be 0.872 and 0.880 for LDA and LR models, respectively. External validation of the models revealed that 76.5% of the test set compounds were correctly classified by both LDA and LR models. These findings suggest that the two models reported in this paper are good and reliable for classifying OH-PCB congeners into active and inactive TR agonists.Keywords
Funding Information
- funding
This publication has 59 references indexed in Scilit:
- Structural Overview of the Nuclear Receptor Superfamily: Insights into Physiology and TherapeuticsAnnual Review of Physiology, 2010
- Exposure to Polychlorinated Biphenyls (PCBs) and Male ReproductionSystems Biology in Reproductive Medicine, 2010
- Exposure to Hydroxylated Polychlorinated Biphenyls (OH-PCBs) in the Prenatal Period and Subsequent Neurodevelopment in Eastern SlovakiaEnvironmental Health Perspectives, 2009
- Binary classification models for endocrine disrupter effects mediated through the estrogen receptorSAR and QSAR in Environmental Research, 2008
- Long-Term Effects of Polychlorinated Biphenyls and Dioxins on Pregnancy Outcomes in Women Affected by the Yusho IncidentEnvironmental Health Perspectives, 2008
- A radial-distribution-function approach for predicting rodent carcinogenicityJournal of Molecular Modeling, 2006
- Long-Term Effects of Neonatal Exposure to Hydroxylated Polychlorinated Biphenyls in the BALB/cCrgl MouseEnvironmental Health Perspectives, 2005
- Designing Antibacterial Compounds through a Topological Substructural ApproachJournal of Chemical Information and Computer Sciences, 2004
- Modeling Discrimination between Antibacterial and Non‐Antibacterial Activity based on 3D Molecular DescriptorsQSAR & Combinatorial Science, 2003
- Computer Aided Design of ExperimentsTechnometrics, 1969