Garcia-Sosa, A. T.; Maran, U. Combined Naïve Bayesian, chemical fingerprints, and molecular docking classifiers to model and predict androgen receptor binding activity data for environmentally- and health-sensitive substances. Int. J. Mol. Sci. 2021, 22, 6695.

QsarDB Repository

Garcia-Sosa, A. T.; Maran, U. Combined Naïve Bayesian, chemical fingerprints, and molecular docking classifiers to model and predict androgen receptor binding activity data for environmentally- and health-sensitive substances. Int. J. Mol. Sci. 2021, 22, 6695.

QDB archive DOI: 10.15152/QDB.235   DOWNLOAD

QsarDB content

Property BindingClass: Activity in Androgen Receptor

Procedure_13: Multivariate Logistic Regression Model

Logistic regression (classification)

Open in:QDB ExplorerQDB Predictor

NameTypenAccuracy
Training settraining16850.916
Evaluation setvalidation38820.884

Citing

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

  • Garcia-Sosa, A. T.; Maran, U. Data for: Combined Naïve Bayesian, chemical fingerprints, and molecular docking classifiers to model and predict androgen receptor binding activity data for environmentally- and health-sensitive substances. QsarDB repository, QDB.235. 2021. http://dx.doi.org/10.15152/QDB.235

  • Garcia-Sosa, A. T.; Maran, U. Combined Naïve Bayesian, chemical fingerprints, and molecular docking classifiers to model and predict androgen receptor binding activity data for environmentally- and health-sensitive substances. Int. J. Mol. Sci. 2021, 22, 6695. http://dx.doi.org/10.3390/ijms22136695

Metadata

Show full item record

Title: Garcia-Sosa, A. T.; Maran, U. Combined Naïve Bayesian, chemical fingerprints, and molecular docking classifiers to model and predict androgen receptor binding activity data for environmentally- and health-sensitive substances. Int. J. Mol. Sci. 2021, 22, 6695.
Abstract:Many chemicals that enter the environment, food chain, and the human body can disrupt androgen-dependent pathways and mimic hormones and therefore, may be responsible for multiple diseases from reproductive to tumor. Thus, modeling and predicting androgen binding activity is an important area of research. The aim of the current study was to find a method or combination of methods to predict compounds that can bind to and/or disrupt the androgen receptor, and thereby guide decision making and further analysis. A stepwise procedure proceeded from analysis of protein structures from human, chimp, and rat, followed by docking and subsequent ligand- and statistics based techniques that improved classification gradually. The best methods used multivariate logistic regression of combinations of chimpanzee protein structural docking scores, extended connectivity fingerprints, and Naive Bayesians of known binders and non-binders. Combination or consensus methods included data from a variety of procedures to improve the final model accuracy.
URI:http://hdl.handle.net/10967/235
http://dx.doi.org/10.15152/QDB.235
Date:2021-06-22


Files in this item

NameDescriptionFormatSizeView
newQDBroundedPreds.zipArticle Garcia-Sosa and Maranapplication/zip1.552MbView/Open
Files associated with this item are distributed
under Creative Commons license.

This item appears in the following Collection(s)

Show full item record