Module-based outcome prediction using breast cancer compendia.

@article{citeulike:2140896, abstract = {BACKGROUND: The availability of large collections of microarray datasets (compendia), or knowledge about grouping of genes into pathways (gene sets), is typically not exploited when training predictors of disease outcome. These can be useful since a compendium increases the number of samples, while gene sets reduce the size of the feature space. This should be favorable from a machine learning perspective and result in more robust predictors. METHODOLOGY: We extracted modules of regulated genes from gene sets, and compendia. Through supervised analysis, we constructed predictors which employ modules predictive of breast cancer outcome. To validate these predictors we applied them to independent data, from the same institution (intra-dataset), and other institutions (inter-dataset). CONCLUSIONS: We show that modules derived from single breast cancer datasets achieve better performance on the validation data compared to gene-based predictors. We also show that there is a trend in compendium specificity and predictive performance: modules derived from a single breast cancer dataset, and a breast cancer specific compendium perform better compared to those derived from a human cancer compendium. Additionally, the module-based predictor provides a much richer insight into the underlying biology. Frequently selected gene sets are associated with processes such as cell cycle, E2F regulation, DNA damage response, proteasome and glycolysis. We analyzed two modules related to cell cycle, and the OCT1 transcription factor, respectively. On an individual basis, these modules provide a significant separation in survival subgroups on the training and independent validation data.}, address = {Information and Communication Theory Group, Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, The Netherlands.}, author = {van Vliet, M. H. and Klijn, C. N. and Wessels, L. F. and Reinders, M. J. }, citeulike-article-id = {2140896}, doi = {10.1371/journal.pone.0001047}, issn = {1932-6203}, journal = {PLoS ONE}, number = {10}, posted-at = {2008-01-14 03:44:18}, priority = {3}, title = {Module-based outcome prediction using breast cancer compendia.}, url = {http://dx.doi.org/10.1371/journal.pone.0001047}, volume = {2}, year = {2007} }

TY - JOUR ID - citeulike:2140896 L3 - citeulike-article-id:2140896 TI - Module-based outcome prediction using breast cancer compendia. JF - PLoS ONE VL - 2 IS - 10 AD - Information and Communication Theory Group, Faculty of Electrical Engineering, Mathematics and Computer Science, Delft University of Technology, Delft, The Netherlands. SN - 1932-6203 N2 - BACKGROUND: The availability of large collections of microarray datasets (compendia), or knowledge about grouping of genes into pathways (gene sets), is typically not exploited when training predictors of disease outcome. These can be useful since a compendium increases the number of samples, while gene sets reduce the size of the feature space. This should be favorable from a machine learning perspective and result in more robust predictors. METHODOLOGY: We extracted modules of regulated genes from gene sets, and compendia. Through supervised analysis, we constructed predictors which employ modules predictive of breast cancer outcome. To validate these predictors we applied them to independent data, from the same institution (intra-dataset), and other institutions (inter-dataset). CONCLUSIONS: We show that modules derived from single breast cancer datasets achieve better performance on the validation data compared to gene-based predictors. We also show that there is a trend in compendium specificity and predictive performance: modules derived from a single breast cancer dataset, and a breast cancer specific compendium perform better compared to those derived from a human cancer compendium. Additionally, the module-based predictor provides a much richer insight into the underlying biology. Frequently selected gene sets are associated with processes such as cell cycle, E2F regulation, DNA damage response, proteasome and glycolysis. We analyzed two modules related to cell cycle, and the OCT1 transcription factor, respectively. On an individual basis, these modules provide a significant separation in survival subgroups on the training and independent validation data. AU - van Vliet, MH AU - Klijn, CN AU - Wessels, LF AU - Reinders, MJ PY - 2007/// UR - http://dx.doi.org/10.1371/journal.pone.0001047 ER -