Assessing the functional structure of genomic data Export

@article{citeulike:3099775, abstract = {Motivation: The availability of genome-scale data has enabled an abundance of novel analysis techniques for investigating a variety of systems-level biological relationships. As thousands of such datasets become available, they provide an opportunity to study high-level associations between cellular pathways and processes. This also allows the exploration of shared functional enrichments between diverse biological datasets, and it serves to direct experimenters to areas of low data coverage or with high probability of new discoveries. Results: We analyze the functional structure of Saccharomyces cerevisiae datasets from over 950 publications in the context of over 140 biological processes. This includes a coverage analysis of biological processes given current high-throughput data, a data-driven map of associations between processes, and a measure of similar functional activity between genome-scale datasets. This uncovers subtle gene expression similarities in three otherwise disparate microarray datasets due to a shared strain background. We also provide several means of predicting areas of yeast biology likely to benefit from additional high-throughput experimental screens. Availability: Predictions are provided in supplementary tables; software and additional data are available from the authors by request. Contact: ogt@princeton.edu Supplementary information: Supplementary data are available at Bioinformatics online. 10.1093/bioinformatics/btn160}, address = {Department of Computer Science, Princeton University, 35 Olden Street, Princeton, NJ 08540, USA.}, author = {Huttenhower, C. and Troyanskaya, O. G.}, citeulike-article-id = {3099775}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btn160}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/24/13/i330.abstract}, citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/24/13/i330.full.pdf}, citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/18586732}, citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=18586732}, day = {1}, doi = {10.1093/bioinformatics/btn160}, issn = {1460-2059}, journal = {Bioinformatics}, keywords = {biological\_processes, coverage\_analysis, dataset\_bias, datasets, high\_throughput}, month = {July}, number = {13}, pages = {i330--338}, posted-at = {2009-11-11 12:58:39}, priority = {2}, title = {Assessing the functional structure of genomic data}, url = {http://dx.doi.org/10.1093/bioinformatics/btn160}, volume = {24}, year = {2008} }

TY - JOUR ID - citeulike:3099775 L3 - citeulike-article-id:3099775 N2 - Motivation: The availability of genome-scale data has enabled an abundance of novel analysis techniques for investigating a variety of systems-level biological relationships. As thousands of such datasets become available, they provide an opportunity to study high-level associations between cellular pathways and processes. This also allows the exploration of shared functional enrichments between diverse biological datasets, and it serves to direct experimenters to areas of low data coverage or with high probability of new discoveries. Results: We analyze the functional structure of Saccharomyces cerevisiae datasets from over 950 publications in the context of over 140 biological processes. This includes a coverage analysis of biological processes given current high-throughput data, a data-driven map of associations between processes, and a measure of similar functional activity between genome-scale datasets. This uncovers subtle gene expression similarities in three otherwise disparate microarray datasets due to a shared strain background. We also provide several means of predicting areas of yeast biology likely to benefit from additional high-throughput experimental screens. Availability: Predictions are provided in supplementary tables; software and additional data are available from the authors by request. Contact: ogt@princeton.edu Supplementary information: Supplementary data are available at Bioinformatics online. 10.1093/bioinformatics/btn160 IS - 13 JF - Bioinformatics SN - 1460-2059 AD - Department of Computer Science, Princeton University, 35 Olden Street, Princeton, NJ 08540, USA. EP - 338 TI - Assessing the functional structure of genomic data VL - 24 SP - i330 KW - biological_processes KW - coverage_analysis KW - dataset_bias KW - datasets KW - high_throughput AU - Huttenhower, C AU - Troyanskaya, OG PY - 2008/07/01/ UR - http://dx.doi.org/10.1093/bioinformatics/btn160 ER -