You are here:
Prediction of in vitro and in vivo oestrogen receptor activity using hierarchical clustering
Citation:
Martin, T. Prediction of in vitro and in vivo oestrogen receptor activity using hierarchical clustering. SAR AND QSAR IN ENVIRONMENTAL RESEARCH. Taylor & Francis, Inc., Philadelphia, PA, 27(1):17-30, (2016).
Impact/Purpose:
The purpose of this paper is to develop in silico models for in vitro estrogen receptor activity for use in alternatives assessment tools such as the Sustainability Dashboard
Description:
In this study, hierarchical clustering classification models were developed to predict in vitro and in vivo oestrogen receptor (ER) activity. Classification models were developed for binding, agonist, and antagonist in vitro ER activity and for mouse in vivo uterotrophic ER binding. In vitro classification models yielded balanced accuracies ranging from 0.65 to 0.85 for the external prediction set. In vivo ER classification models yielded balanced accuracies ranging from 0.72 to 0.83. If used as additional biological descriptors for in vivo models, in vitro scores were found to increase the prediction accuracy of in vivo ER models. If in vitro activity was used directly as a surrogate for in vivo activity, the results were poor (balanced accuracy ranged from 0.49 to 0.72). Under-sampling negative compounds in the training set was found to increase the coverage (fraction of chemicals which can be predicted) and increase prediction sensitivity.
