Francesca Grisoni (francesca.grisoni '@' unimib.it), Davide Ballabio (davide.ballabio '@' unimib.it), Viviana Consonni, Milano Chemometrics and QSAR Research Group (http://www.michem.unimib.it/), Universit?? degli Studi Milano - Bicocca, Milano (Italy)

Data Set Information:

This dataset was used to develop classification QSAR models for the discrimination of binder/positive (199) and non-binder/negative (1488) molecules by means of different machine learning methods. Details can be found in the quoted reference: F. Grisoni, V. Consonni, D. Ballabio, (2019) Machine Learning Consensus to Predict the Binding to the Androgen Receptor within the CoMPARA project, Journal of chemical information and modeling, 59, 1839-1848; doi: 10.1021/acs.jcim.8b00794.
Attributes (molecular fingerprints) were calculated at the Milano Chemometrics and QSAR Research Group (Universit??  degli Studi Milano - Bicocca, Milano, Italy) on a set of chemicals provided by the National Center of Computational Toxicology, at the U.S. Environmental Protection Agency in the framework of the  CoMPARA collaborative modelling project, which targeted the development of QSAR models to identify binders to the Androgen Receptor.

Attribute Information:

1024 binary molecular fingerprints and 1 experimental class:
1-1024) binary molecular fingerprint
1025) experimental class: positive (binder) and negative (non-binder)

Relevant Papers:

F. Grisoni, V. Consonni, D. Ballabio, (2019) Machine Learning Consensus to Predict the Binding to the Androgen Receptor within the CoMPARA project, Journal of chemical information and modeling, 59, 1839-1848; doi: 10.1021/acs.jcim.8b00794

Citation Request:

Please, cite the following paper if you publish results based on the QSAR androgen receptor dataset: F. Grisoni, V. Consonni, D. Ballabio, (2019) Machine Learning Consensus to Predict the Binding to the Androgen Receptor within the CoMPARA project, Journal of chemical information and modeling, 59, 1839-1848; doi: 10.1021/acs.jcim.8b00794