Piir, G.; Sild, S.; Maran, U. Interpretable machine learning for the identification of estrogen receptor agonists, antagonists, and binders. Chemosphere 2023.

QsarDB Repository

Piir, G.; Sild, S.; Maran, U. Interpretable machine learning for the identification of estrogen receptor agonists, antagonists, and binders. Chemosphere 2023.

QDB archive DOI: 10.15152/QDB.259   DOWNLOAD

QsarDB content

Property er_ago: Activity in ER agonist pathway

Tab3.agonists: Model for ER activity on agonists pathway

Random forest (classification)

Open in:QDB ExplorerQDB Predictor

NameTypenAccuracy
Training settraining3501.000
Out of baginternal validation3500.760
Test setexternal validation13270.789
Evaluation setexternal validation50330.818

Property er_ant: Activity in ER antagonist pathway

Tab3.antagonists: Model for ER activity on antagonists pathway

Random forest (classification)

Open in:QDB ExplorerQDB Predictor

NameTypenAccuracy
Training settraining641.000
Out of baginternal validation640.734
Test setexternal validation16130.653
Evaluation setexternal validation50740.683

Property er_bin: Binding activity in estrogen receptor

Tab3.binders: Model for binding in ER

Random forest (classification)

Open in:QDB ExplorerQDB Predictor

NameTypenAccuracy
Training settraining3781.000
Out of baginternal validation3780.706
Test setexternal validation12990.766
Evaluation setexternal validation47400.767

Citing

When using this QDB archive, please cite (see details) it together with the original article:

  • Piir, G.; Sild, S.; Maran, U. Data for: Interpretable machine learning for the identification of estrogen receptor agonists, antagonists, and binders. QsarDB repository, QDB.259. 2023. http://dx.doi.org/10.15152/QDB.259

  • Piir, G.; Sild, S.; Maran, U. Interpretable machine learning for the identification of estrogen receptor agonists, antagonists, and binders. Chemosphere 2024, 347, 140671. http://dx.doi.org/10.1016/j.chemosphere.2023.140671

Metadata

Show simple item record

dc.date.accessioned2023-09-14T13:44:47Z
dc.date.available2023-09-14T13:44:47Z
dc.date.issued2023-09-14
dc.identifier.urihttp://hdl.handle.net/10967/259
dc.identifier.urihttp://dx.doi.org/10.15152/QDB.259
dc.description.abstractAn abnormal hormonal activity or exposure to endocrine-disrupting chemicals (EDCs) can cause endocrine system malfunction. Among the many interactions EDCs can affect is the disruption of estrogen signalling, which can lead to adverse health effects such as cancer, osteoporosis, neurodegenerative diseases, cardiovascular disease, insulin resistance, and obesity. Knowing which chemical can act as an EDC is a significant advantage and a practical necessity. New Approach Methodologies (NAM) computational models offer a quick and cost-effective solution for preliminary hazard assessment of chemicals without animal testing. Therefore, a machine learning approach was used to investigate the relationships between estrogen receptor (ER) activity and chemical structure to identify chemicals that can interact with ER. For this purpose, the consolidated in vitro assay data from ToxCast/Tox21 projects was used for developing Random Forest classification models for ER binding, agonists, and antagonists. The overall classification prediction accuracy reaches up to 82%, depending on whether the model predicted agonists, antagonists, or compounds that bind to the active site. Given the imbalance in endocrine disruption data, the derived models are good candidates for deprioritising chemicals and reducing animal testing. The interpretation of theoretical molecular descriptors of the models was consistent with the molecular interactions known in the ligand binding pocket. The estimated class probabilities enabled the analysis of the applicability domain of the developed models and the assessment of the predictions’ reliability, followed by the guidelines for interpreting prediction results. The models are openly accessible and usable at QsarDB.org according to the FAIR (Findable, Accessible, Interoperable, Reusable) principles.en_US
dc.publisherGeven Piir
dc.publisherSulev Sild
dc.publisherUko Maran
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.titlePiir, G.; Sild, S.; Maran, U. Interpretable machine learning for the identification of estrogen receptor agonists, antagonists, and binders. Chemosphere 2023.
qdb.property.endpoint4. Human health effects 4.18. Endocrine Activityen_US
qdb.descriptor.applicationDRAGON 6.0.38en_US
qdb.prediction.applicationR 4.0.2 / Random Forest 4.6-14en_US
bibtex.entryarticleen_US
bibtex.entry.authorPiir, Geven
bibtex.entry.authorSild, Sulev
bibtex.entry.authorMaran, Uko
bibtex.entry.doi10.1016/j.chemosphere.2023.140671
bibtex.entry.journalChemosphereen_US
bibtex.entry.pages140671
bibtex.entry.titleInterpretable machine learning for the identification of estrogen receptor agonists, antagonists, and bindersen_US
bibtex.entry.volume347
bibtex.entry.year2024
qdb.model.typeRandom forest (classification)en_US
qdb.descriptor.calculationTab3.agonists
qdb.descriptor.calculationTab3.antagonists
qdb.descriptor.calculationTab3.binders


Files in this item

NameDescriptionFormatSizeView
Estrogen.RF.qdb.zipModels for estrogen activityapplication/zip5.822MbView/Open
Files associated with this item are distributed
under Creative Commons license.

This item appears in the following Collection(s)

Show simple item record