Exploring the impact of size of training sets for the development of predictive QSAR models

By Partha Roy, J. Leonard, Kunal Roy. 2008

292 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

On further application of r m2 as a metric for validation of QSAR models (2009, background): “[25–27], setting optimum size of the training set [28], selection of optimum set of variables for a model (whether based on internal or external validation) [24], defining domain of applicability of the”
CORAL: QSPR model of water solubility based on local and global SMILES attributes. (2013, methodology): “algorithms of the splitting of data into the training and test sets (Roy et al., 2008; Puzyn et al., 2011).”
CAESAR models for developmental toxicity (2010, background): “The selection of optimal training and test set sizes has been discussed in several papers [25,26] leading to the conclusion that while it is important to validate a QSAR model with a good external set, if the splitting leads to a training set smaller than 75-85% of the original data set, the modelin”