REPOSITORY QDB GUIDELINES CITING BLOG

Piir, G.; Sild, S.; Maran, U. Binary and multi-class classification for androgen receptor agonists, antagonists and binders. Chemosphere 2020, accepted.

QsarDB Repository

Piir, G.; Sild, S.; Maran, U. Binary and multi-class classification for androgen receptor agonists, antagonists and binders. Chemosphere 2020, accepted.

QDB archive DOI: 10.15152/QDB.236   DOWNLOAD

QsarDB content

Property Agonists: Activity in AR agonist pathway

Agonists_model: Agonist model

Random forest (classification)

Open in:QDB Explorer QDB Predictor

Name Type n Accuracy
Training set training 68 1.000
OOB internal validation 68 0.824
Test set external validation 1591 0.820
Evaluation set external validation 4613 0.805

Property Antagonists: Activity in AR antagonist pathway

Antagonists_model: Antagonist model

Random forest (classification)

Open in:QDB Explorer QDB Predictor

Name Type n Accuracy
Training set training 254 1.000
OOB internal validation 254 0.858
Test set external validation 1271 0.749
Evaluation set external validation 3834 0.719

Property Binders: Activity in androgen receptor

Binders_model: Binding model

Random forest (classification)

Open in:QDB Explorer QDB Predictor

Name Type n Accuracy
Training set training 316 1.000
OOB internal validation 316 0.788
Test set external validation 1216 0.760
Evaluation set external validation 3717 0.778

Property MultiClass: Activity in AR agonist and antagonist pathway

MultiClass_model: Multi-Class model

Random forest (classification)

Open in:QDB Explorer QDB Predictor

Name Type n Accuracy
Training set training 93 1.000
OOB internal validation 93 0.720
Test set external validation 1435 0.674
Evaluation set external validation 3683 0.638

Citing

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

Metadata

Show full item record

Title: Piir, G.; Sild, S.; Maran, U. Binary and multi-class classification for androgen receptor agonists, antagonists and binders. Chemosphere 2020, accepted.
Abstract: Androgens and androgen receptor regulate a variety of biological effects in the human body. The impaired functioning of androgen receptor may have different adverse health effects from cancer to infertility. Therefore, it is important to determine whether new chemicals have any binding activity and act as androgen agonists or antagonists before commercial use. Due to the large number of chemicals that require experimental testing, the computational methods are a viable alternative. Therefore, the aim of the present study was to develop predictive QSAR models for classifying compounds according to their activity at the androgen receptor. A large data set of chemicals from the CoMPARA project was used for this purpose and random forest classification models have been developed for androgen binding, agonist, and antagonist activity. In addition, a unique effort has been made for multi-class approach that discriminates between inactive compounds, agonists and antagonists simultaneously. For the evaluation set, the classification models predicted agonists with 80% of accuracy and for the antagonists’ and binders’ the respective metrics were 72% and 78%. Combining agonists, antagonists and inactive compounds into a multi-class approach added complexity to the modelling task and resulted to 64% prediction accuracy for the evaluation set. Considering the size of the training data sets and their imbalance, the achieved evaluation accuracy is very good.
URI: http://hdl.handle.net/10967/236
http://dx.doi.org/10.15152/QDB.236
Date: 2020-07-16


Files in this item

Name Description Format Size View
2020Cxxx.qdb.zip Models for androgen receptor activity application/x-zip 3.231Mb View/Open
Files associated with this item are distributed
under Creative Commons license.

This item appears in the following Collection(s)

Show full item record