Assessing the chemical-induced estrogenicity using in silico and in vitro methods

Multiple substances are considered endocrine disrupting chemicals (EDCs). However, there is a significant gap in the early prioritization of EDC’s effects. In this work, silico and vitro methods were used to model estrogenicity. Two Quantitative Structure-Activity Relationship (QSAR) models based on Logistic Regression REPTree algorithms built using large diverse database estrogen receptor (ESR) agonism. A 10-fold external validation demonstrated their robustness predictive capacity. Mechanistic interpretations molecular descriptors (C-026, nArOH,PW5, B06[Br-Br]) for modelling suggested that heteroatomic fragments, aromatic hydroxyls, bromines, relative bond accessibility areas molecules, structural determinants As QSARs, ESR transactivity thirteen persistent organic pollutants (POPs) suspected EDCs was tested MMV-Luc cell line. good correspondence between predictions experimental bioassays value QSARs agonist compounds.