@article{Dharuri2013, abstract = {Abstract Background Genome-wide association studies (GWAS) have identified many common single nucleotide polymorphisms (SNPs) that associate with clinical phenotypes, but these SNPs usually explain just a small part of the heritability and have relatively modest effect sizes. In contrast, SNPs that associate with metabolite levels generally explain a higher percentage of the genetic variation and demonstrate larger effect sizes. Still, the discovery of SNPs associated with metabolite levels is challenging since testing all metabolites measured in typical metabolomics studies with all SNPs comes with a severe multiple testing penalty. We have developed an automated workflow approach that utilizes prior knowledge of biochemical pathways present in databases like KEGG and BioCyc to generate a smaller SNP set relevant to the metabolite. This paper explores the opportunities and challenges in the analysis of GWAS of metabolomic phenotypes and provides novel insights into the genetic basis of metabolic variation through the re-analysis of published GWAS datasets. Results Re-analysis of the published GWAS dataset from Illig et al. (Nature Genetics, 2010) using a pathway-based workflow (http://www.myexperiment.org/packs/319.html), confirmed previously identified hits and identified a new locus of human metabolic individuality, associating Aldehyde dehydrogenase family1 L1 (ALDH1L1) with serine/glycine ratios in blood. Replication in an independent GWAS dataset of phospholipids (Demirkan et al., PLoS Genetics, 2012) identified two novel loci supported by additional literature evidence: GPAM (Glycerol-3 phosphate acyltransferase) and CBS (Cystathionine beta-synthase). In addition, the workflow approach provided novel insight into the affected pathways and relevance of some of these gene-metabolite pairs in disease development and progression. Conclusions We demonstrate the utility of automated exploitation of background knowledge present in pathway databases for the analysis of GWAS datasets of metabolomic phenotypes. We report novel loci and potential biochemical mechanisms that contribute to our understanding of the genetic basis of metabolic variation and its relationship to disease development and progression. }, author = {Dharuri, Harish and Henneman, Peter and van Klinken, Jan Bert and Demirkan, Ayse and Mook-Kanamori, Dennis Owen and Wang-Sattler, Rui and Gieger, Christian and van Dijk, Ko Willems and Adamski, Jerzy and Ugocsai, P. and Jb, van Klinken and Isaacs, A. and Wilson, J. F. and Pramstaller, P. P. and Hettne, Kristina and Van Duijn, Cornelia M. and Liebisch, G. and Roos, Marco and Johansson, A. and Suhre, Karsten and Rudan, I. and 't Hoen, Peter Ac C. and Aulchenko, Y. S. and Wild, S. H. and Do, Mook Kanamori and Kirichenko, A. and Janssens, A. C. J. W. and Zorkoltseva, and Jansen, R. C. and Gnewuch, C. and Domingues, F. S. and Pattaro, C. and Jonasson, I. and Polasek, O. and Hofman, A. and Zaboli, G. and Karssen, L. and Struchalin, M. and Floyd, J. and Igl, W. and Biloglav, Z. and Broer, L. and Pfeufer, A. and Pichler, I. and Witteman, J. C. M. and Campbell, S. and Kolcic, I. and Rivadeneira, F. and Huffman, J. and Wright, A. F. and Hastie, N. D. and Uitterlinden, A. and Franke, L. and Eurospan, Consortia and Franklin, C. S. and Vitart, and Cm, Van Duijn and Kw, van Dijk and Axenovich, T. and Oostra, and Meitinger, T. and Hoen, Peter AC 't and Hicks, A. A. and Hayward, C. and Gyllensten, U. and Campbell, H. and Pa, 't Hoen and Schmitz, G.}, doi = {10.1186/1471-2164-14-865}, journal = {BMC Genomics}, month = {dec}, title = {Automated workflow-based exploitation of pathway databases provides new insights into genetic associations of metabolite profiles}, url = {http://dx.doi.org/10.1186/1471-2164-14-865}, volume = {14}, year = {2013} }