PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

BiasCorrection of Regression Models: A Case Study on hERG Inhibition
Katja Hansen, Fabian Rathke, Timon Schröter, Georg Rast, Thomas Fox, Jan M. Kriegl and Sebastian Mika
Journal of Chemical Information and Modelling Volume 49, Number 6, pp. 1486-1496, 2009.

Abstract

In the present work we develop a predictive QSAR model for the blockade of the hERG channel. Additionally, this specific end point is used as a test scenario to develop and evaluate several techniques for fusing predictions from multiple regression models. hERG inhibition models which are resented here are based on a combined data set of roughly 550 roprietary and 110 public domain compounds. Models are built using various statistical learning techniques and different sets of molecular descriptors. Single Support Vector Regression, Gaussian Process, or Random Forest models achieve root mean-squared errors of roughly 0.6 log units as determined from leave-group-out cross-validation. An analysis of the evaluation strategy on the performance estimates shows that standard leave-group-out cross-validation yields overly optimistic results. As an alternative, a clustered cross-validation scheme is introduced to obtain a more realistic estimate of the model performance. The evaluation of several techniques to combine multiple prediction models shows that the root mean squared error as determined from clustered cross-validation an be reduced from 0.73 +/- 0.01 to 0.57 +/- 0.01 using a local bias correction trategy.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:6916
Deposited By:Katja Hansen
Deposited On:15 April 2010