Identification of putative estrogen receptor-mediated endocrine disrupting chemicals using QSAR- and structure-based virtual screening approaches.
Academic Article
Overview
Research
Identity
Additional Document Info
Other
View All
Overview
abstract
Identification of endocrine disrupting chemicals is one of the important goals of environmental chemical hazard screening. We report on the development of validated in silico predictors of chemicals likely to cause estrogen receptor (ER)-mediated endocrine disruption to facilitate their prioritization for future screening. A database of relative binding affinity of a large number of ER and/or ER ligands was assembled (546 for ER and 137 for ER). Both single-task learning (STL) and multi-task learning (MTL) continuous quantitative structure-activity relationship (QSAR) models were developed for predicting ligand binding affinity to ER or ER. High predictive accuracy was achieved for ER binding affinity (MTL R(2)=0.71, STL R(2)=0.73). For ER binding affinity, MTL models were significantly more predictive (R(2)=0.53, p<0.05) than STL models. In addition, docking studies were performed on a set of ER agonists/antagonists (67 agonists and 39 antagonists for ER, 48 agonists and 32 antagonists for ER, supplemented by putative decoys/non-binders) using the following ER structures (in complexes with respective ligands) retrieved from the Protein Data Bank: ER agonist (PDB ID: 1L2I), ER antagonist (PDB ID: 3DT3), ER agonist (PDB ID: 2NV7), and ER antagonist (PDB ID: 1L2J). We found that all four ER conformations discriminated their corresponding ligands from presumed non-binders. Finally, both QSAR models and ER structures were employed in parallel to virtually screen several large libraries of environmental chemicals to derive a ligand- and structure-based prioritized list of putative estrogenic compounds to be used for in vitro and in vivo experimental validation.
