Rational selection of training and test sets for the development of validated QSAR models

By A. Golbraikh, Min Shen, Zhiyan Xiao, Yunde Xiao, K. Lee, Alexander Tropsha. J. Comput. Aided Mol. Des., 2003

629 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.

Evaluation of model predictive ability by external validation techniques (2010, methodology): “Sometimes selection strategies, such as those based on cluster analysis, optimal design, sphere exclusion algorithm or other similarity/diversity tools [7,10–13], are used to design an external test set that results sufficiently representative of the entire set of data.”
Error Metrics and Performance Fitness Indicators for Artificial Intelligence and Machine Learning in Engineering and Sciences (2020, methodology): “This seems to stem from our familiarity with these indicators, as 170 opposed to others; such as Golbraikh and Tropsha’s [58] criterion, QSAR model by Roy and Roy 171 [59], Frank and Todeschini [60], and specifically designed objective functions, often used in the 172 realms of other fields and data”