Development and Validation of Predictive QSAR Models for Estrogenic Activities of Hydroxylated Polychlorinated Biphenyls.
Lukman K AkinolaAdamu UzairuGideon Adamu ShallangwaStephen E AbechiPublished in: Environmental toxicology and chemistry (2023)
Disruption of the endocrine system by hydroxylated polychlorinated biphenyls (OH-PCBs) is hypothesized, among other potential mechanisms, to be mediated via nuclear receptor binding. Due to high cost and lengthy time required to produce high quality experimental data, empirical data to support the nuclear receptor binding hypothesis are in short supply. In this paper, two quantitative structure-activity relationship models were developed for predicting estrogenic activities of OH-PCBs. Findings revealed that model I (for ERα dataset) contained five 2D descriptors belonging to the following classes-autocorrelation, Burden modified eigenvalues, chi path and atom type electrotopological state while model II (for ERβ dataset) contained three 2D and three 3D descriptors belonging to the following classes-autocorrelation, atom type electrotopological state and RDF descriptors. The internal and external validation metrics reported for models I and II indicate that both models are robust, reliable and suitable for predicting the estrogenic activities of untested OH-PCB congeners. This article is protected by copyright. All rights reserved. Environ Toxicol Chem 2023;00:0-0. © 2023 SETAC.
Keyphrases
- structure activity relationship
- molecular dynamics
- estrogen receptor
- electronic health record
- big data
- polycyclic aromatic hydrocarbons
- high resolution
- endoplasmic reticulum
- dna binding
- breast cancer cells
- machine learning
- risk assessment
- risk factors
- data analysis
- deep learning
- artificial intelligence
- molecular dynamics simulations