TY - JOUR
T1 - Structure-based virtual screening of perfluoroalkyl and polyfluoroalkyl substances (PFASs) as endocrine disruptors of androgen receptor activity using molecular docking and machine learning
AU - Azhagiya Singam, Ettayapuram Ramaprasad
AU - Tachachartvanich, Phum
AU - Fourches, Denis
AU - Soshilov, Anatoly
AU - Hsieh, Jennifer C.Y.
AU - La Merrill, Michele A.
AU - Smith, Martyn T.
AU - Durkin, Kathleen A.
PY - 2020/11
Y1 - 2020/11
N2 - Perfluoroalkyl and polyfluoroalkyl substances (PFASs) pose a substantial threat as endocrine disruptors, and thus early identification of those that may interact with steroid hormone receptors, such as the androgen receptor (AR), is critical. In this study we screened 5,206 PFASs from the CompTox database against the different binding sites on the AR using both molecular docking and machine learning techniques. We developed support vector machine models trained on Tox21 data to classify the active and inactive PFASs for AR using different chemical fingerprints as features. The maximum accuracy was 95.01% and Matthew's correlation coefficient (MCC) was 0.76 respectively, based on MACCS fingerprints (MACCSFP). The combination of docking-based screening and machine learning models identified 29 PFASs that have strong potential for activity against the AR and should be considered priority chemicals for biological toxicity testing.
AB - Perfluoroalkyl and polyfluoroalkyl substances (PFASs) pose a substantial threat as endocrine disruptors, and thus early identification of those that may interact with steroid hormone receptors, such as the androgen receptor (AR), is critical. In this study we screened 5,206 PFASs from the CompTox database against the different binding sites on the AR using both molecular docking and machine learning techniques. We developed support vector machine models trained on Tox21 data to classify the active and inactive PFASs for AR using different chemical fingerprints as features. The maximum accuracy was 95.01% and Matthew's correlation coefficient (MCC) was 0.76 respectively, based on MACCS fingerprints (MACCSFP). The combination of docking-based screening and machine learning models identified 29 PFASs that have strong potential for activity against the AR and should be considered priority chemicals for biological toxicity testing.
KW - Modeling
KW - Steroid hormones
KW - Tox21
UR - http://www.scopus.com/inward/record.url?scp=85089199552&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089199552&partnerID=8YFLogxK
U2 - 10.1016/j.envres.2020.109920
DO - 10.1016/j.envres.2020.109920
M3 - Article
C2 - 32795691
AN - SCOPUS:85089199552
VL - 190
JO - Environmental Research
JF - Environmental Research
SN - 0013-9351
M1 - 109920
ER -