Identification of putative estrogen receptor-mediated endocrine disrupting chemicals using QSAR- and structure-based virtual screening approaches

TY - JOUR

T1 - Identification of putative estrogen receptor-mediated endocrine disrupting chemicals using QSAR- and structure-based virtual screening approaches

AU - Zhang, Liying

AU - Sedykh, Alexander

AU - Tripathi, Ashutosh

AU - Zhu, Hao

AU - Afantitis, Antreas

AU - Mouchlis, Varnavas D.

AU - Melagraki, Georgia

AU - Rusyn, Ivan

AU - Tropsha, Alexander

N1 - Funding Information: This work was supported, in part, by grants from NIH ( GM076059 ), EPA ( RD83499901 , RD83382501 ), and Cyprus Research Promotion Foundation ( ΔΙΕΘΝΗ/ΣΤΟΧΟΣ/0308/05 ). The content does not necessarily reflect the views and policies of the EPA and mention of trade names or commercial products does not constitute endorsement or recommendation for use.

PY - 2013/10/1

Y1 - 2013/10/1

N2 - 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 ERα and/or ERβ ligands was assembled (546 for ERα and 137 for ERβ). 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 ERα or ERβ. High predictive accuracy was achieved for ERα binding affinity (MTL R2=0.71, STL R2=0.73). For ERβ binding affinity, MTL models were significantly more predictive (R2=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 ERα, 48 agonists and 32 antagonists for ERβ, supplemented by putative decoys/non-binders) using the following ER structures (in complexes with respective ligands) retrieved from the Protein Data Bank: ERα agonist (PDB ID: 1L2I), ERα antagonist (PDB ID: 3DT3), ERβ agonist (PDB ID: 2NV7), and ERβ 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.

AB - 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 ERα and/or ERβ ligands was assembled (546 for ERα and 137 for ERβ). 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 ERα or ERβ. High predictive accuracy was achieved for ERα binding affinity (MTL R2=0.71, STL R2=0.73). For ERβ binding affinity, MTL models were significantly more predictive (R2=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 ERα, 48 agonists and 32 antagonists for ERβ, supplemented by putative decoys/non-binders) using the following ER structures (in complexes with respective ligands) retrieved from the Protein Data Bank: ERα agonist (PDB ID: 1L2I), ERα antagonist (PDB ID: 3DT3), ERβ agonist (PDB ID: 2NV7), and ERβ 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.

KW - Docking

KW - Endocrine disrupting chemicals

KW - Estrogen receptor

KW - Multi-task learning

KW - Quantitative structure-activity relationships modeling

KW - Virtual screening

UR - http://www.scopus.com/inward/record.url?scp=84882809589&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882809589&partnerID=8YFLogxK

U2 - https://doi.org/10.1016/j.taap.2013.04.032

DO - https://doi.org/10.1016/j.taap.2013.04.032

M3 - Article

C2 - 23707773

SN - 0041-008X

VL - 272

SP - 67

EP - 76

JO - Toxicology and Applied Pharmacology

JF - Toxicology and Applied Pharmacology

IS - 1

ER -