@ARTICLE{10.3389/fgene.2016.00102, AUTHOR={Grellmann, Claudia and Neumann, Jane and Bitzer, Sebastian and Kovacs, Peter and Tönjes, Anke and Westlye, Lars T. and Andreassen, Ole A. and Stumvoll, Michael and Villringer, Arno and Horstmann, Annette}, TITLE={Random Projection for Fast and Efficient Multivariate Correlation Analysis of High-Dimensional Data: A New Approach}, JOURNAL={Frontiers in Genetics}, VOLUME={7}, YEAR={2016}, URL={https://www.frontiersin.org/articles/10.3389/fgene.2016.00102}, DOI={10.3389/fgene.2016.00102}, ISSN={1664-8021}, ABSTRACT={In recent years, the advent of great technological advances has produced a wealth of very high-dimensional data, and combining high-dimensional information from multiple sources is becoming increasingly important in an extending range of scientific disciplines. Partial Least Squares Correlation (PLSC) is a frequently used method for multivariate multimodal data integration. It is, however, computationally expensive in applications involving large numbers of variables, as required, for example, in genetic neuroimaging. To handle high-dimensional problems, dimension reduction might be implemented as pre-processing step. We propose a new approach that incorporates Random Projection (RP) for dimensionality reduction into PLSC to efficiently solve high-dimensional multimodal problems like genotype-phenotype associations. We name our new method PLSC-RP. Using simulated and experimental data sets containing whole genome SNP measures as genotypes and whole brain neuroimaging measures as phenotypes, we demonstrate that PLSC-RP is drastically faster than traditional PLSC while providing statistically equivalent results. We also provide evidence that dimensionality reduction using RP is data type independent. Therefore, PLSC-RP opens up a wide range of possible applications. It can be used for any integrative analysis that combines information from multiple sources.} }