A kernel-based integration of genome-wide data for clinical decision support. Export

@article{citeulike:4364095, abstract = {ABSTRACT : BACKGROUND : Although microarray technology allows the investigation of the transcriptomic make-up of a tumor in one experiment, the transcriptome does not completely reflect the underlying biology due to alternative splicing, post-translational modifications, as well as the influence of pathological conditions (for example, cancer) on transcription and translation. This increases the importance of fusing more than one source of genome-wide data, such as the genome, transcriptome, proteome, and epigenome. The current increase in the amount of available omics data emphasizes the need for a methodological integration framework. METHODS : We propose a kernel-based approach for clinical decision support in which many genome-wide data sources are combined. Integration occurs within the patient domain at the level of kernel matrices before building the classifier. As supervised classification algorithm, a weighted least squares support vector machine is used. We apply this framework to two cancer cases, namely, a rectal cancer data set containing microarray and proteomics data and a prostate cancer data set containing microarray and genomics data. For both cases, multiple outcomes are predicted. RESULTS : For the rectal cancer outcomes, the highest leave-one-out (LOO) areas under the receiver operating characteristic curves (AUC) were obtained when combining microarray and proteomics data gathered during therapy and ranged from 0.927 to 0.987. For prostate cancer, all four outcomes had a better LOO AUC when combining microarray and genomics data, ranging from 0.786 for recurrence to 0.987 for metastasis. CONCLUSIONS : For both cancer sites the prediction of all outcomes improved when more than one genome-wide data set was considered. This suggests that integrating multiple genome-wide data sources increases the predictive performance of clinical decision support models. This emphasizes the need for comprehensive multi-modal data. We acknowledge that, in a first phase, this will substantially increase costs; however, this is a necessary investment to ultimately obtain cost-efficient models usable in patient tailored therapy.}, author = {Daemen, Anneleen and Gevaert, Olivier and Ojeda, Fabian and Debucquoy, Annelies and Suykens, Johan Ak A. and Sempoux, Christine and Machiels, Jean-Pascal P. and Haustermans, Karin and De Moor, Bart}, citeulike-article-id = {4364095}, citeulike-linkout-0 = {http://dx.doi.org/10.1186/gm39}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/19356222}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=19356222}, day = {3}, doi = {10.1186/gm39}, issn = {1756-994X}, journal = {Genome medicine}, keywords = {analysis, correlations}, month = {April}, number = {4}, posted-at = {2009-04-19 01:23:13}, priority = {5}, title = {A kernel-based integration of genome-wide data for clinical decision support.}, url = {http://dx.doi.org/10.1186/gm39}, volume = {1}, year = {2009} }

TY - JOUR ID - citeulike:4364095 L3 - citeulike-article-id:4364095 N2 - ABSTRACT : BACKGROUND : Although microarray technology allows the investigation of the transcriptomic make-up of a tumor in one experiment, the transcriptome does not completely reflect the underlying biology due to alternative splicing, post-translational modifications, as well as the influence of pathological conditions (for example, cancer) on transcription and translation. This increases the importance of fusing more than one source of genome-wide data, such as the genome, transcriptome, proteome, and epigenome. The current increase in the amount of available omics data emphasizes the need for a methodological integration framework. METHODS : We propose a kernel-based approach for clinical decision support in which many genome-wide data sources are combined. Integration occurs within the patient domain at the level of kernel matrices before building the classifier. As supervised classification algorithm, a weighted least squares support vector machine is used. We apply this framework to two cancer cases, namely, a rectal cancer data set containing microarray and proteomics data and a prostate cancer data set containing microarray and genomics data. For both cases, multiple outcomes are predicted. RESULTS : For the rectal cancer outcomes, the highest leave-one-out (LOO) areas under the receiver operating characteristic curves (AUC) were obtained when combining microarray and proteomics data gathered during therapy and ranged from 0.927 to 0.987. For prostate cancer, all four outcomes had a better LOO AUC when combining microarray and genomics data, ranging from 0.786 for recurrence to 0.987 for metastasis. CONCLUSIONS : For both cancer sites the prediction of all outcomes improved when more than one genome-wide data set was considered. This suggests that integrating multiple genome-wide data sources increases the predictive performance of clinical decision support models. This emphasizes the need for comprehensive multi-modal data. We acknowledge that, in a first phase, this will substantially increase costs; however, this is a necessary investment to ultimately obtain cost-efficient models usable in patient tailored therapy. IS - 4 JF - Genome medicine SN - 1756-994X TI - A kernel-based integration of genome-wide data for clinical decision support. VL - 1 KW - analysis KW - correlations AU - Daemen, Anneleen AU - Gevaert, Olivier AU - Ojeda, Fabian AU - Debucquoy, Annelies AU - Suykens, Johan Ak AU - Sempoux, Christine AU - Machiels, Jean-Pascal AU - Haustermans, Karin AU - De Moor, Bart PY - 2009/04/03/ UR - http://dx.doi.org/10.1186/gm39 ER -