Matrix correlations for high-dimensional data: the modified RV-coefficient Export

@article{citeulike:3979947, abstract = {Motivation: Modern functional genomics generates high-dimensional datasets. It is often convenient to have a single simple number characterizing the relationship between pairs of such high-dimensional datasets in a comprehensive way. Matrix correlations are such numbers and are appealing since they can be interpreted in the same way as Pearson's correlations familiar to biologists. The high-dimensionality of functional genomics data is, however, problematic for existing matrix correlations. The motivation of this article is 2-fold: (i) we introduce the idea of matrix correlations to the bioinformatics community and (ii) we give an improvement of the most promising matrix correlation coefficient (the RV-coefficient) circumventing the problems of high-dimensional data. Results: The modified RV-coefficient can be used in high-dimensional data analysis studies as an easy measure of common information of two datasets. This is shown by theoretical arguments, simulations and applications to two real-life examples from functional genomics, i.e. a transcriptomics and metabolomics example. Availability: The Matlab m-files of the methods presented can be downloaded from http://www.bdagroup.nl. Contact: a.k.smilde@uva.nl 10.1093/bioinformatics/btn634}, author = {Smilde, A. K. and Kiers, H. A. L. and Bijlsma, S. and Rubingh, C. M. and van Erk, M. J.}, citeulike-article-id = {3979947}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btn634}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/25/3/401}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/19073588}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=19073588}, day = {1}, doi = {10.1093/bioinformatics/btn634}, journal = {Bioinformatics}, keywords = {correlation}, month = {February}, number = {3}, pages = {401--405}, posted-at = {2009-01-29 22:00:23}, priority = {2}, title = {Matrix correlations for high-dimensional data: the modified RV-coefficient}, url = {http://dx.doi.org/10.1093/bioinformatics/btn634}, volume = {25}, year = {2009} }

TY - JOUR ID - citeulike:3979947 L3 - citeulike-article-id:3979947 N2 - Motivation: Modern functional genomics generates high-dimensional datasets. It is often convenient to have a single simple number characterizing the relationship between pairs of such high-dimensional datasets in a comprehensive way. Matrix correlations are such numbers and are appealing since they can be interpreted in the same way as Pearson's correlations familiar to biologists. The high-dimensionality of functional genomics data is, however, problematic for existing matrix correlations. The motivation of this article is 2-fold: (i) we introduce the idea of matrix correlations to the bioinformatics community and (ii) we give an improvement of the most promising matrix correlation coefficient (the RV-coefficient) circumventing the problems of high-dimensional data. Results: The modified RV-coefficient can be used in high-dimensional data analysis studies as an easy measure of common information of two datasets. This is shown by theoretical arguments, simulations and applications to two real-life examples from functional genomics, i.e. a transcriptomics and metabolomics example. Availability: The Matlab m-files of the methods presented can be downloaded from http://www.bdagroup.nl. Contact: a.k.smilde@uva.nl 10.1093/bioinformatics/btn634 IS - 3 JF - Bioinformatics EP - 405 TI - Matrix correlations for high-dimensional data: the modified RV-coefficient VL - 25 SP - 401 KW - correlation AU - Smilde, AK AU - Kiers, HAL AU - Bijlsma, S AU - Rubingh, CM AU - van Erk, MJ PY - 2009/02/01/ UR - http://dx.doi.org/10.1093/bioinformatics/btn634 ER -