Exploring the functional landscape of gene expression: directed search of large microarray compendia. Export

@article{citeulike:1651954, abstract = {MOTIVATION: The increasing availability of gene expression microarray technology has resulted in the publication of thousands of microarray gene expression datasets investigating various biological conditions. This vast repository is still underutilized due to the lack of methods for fast, accurate exploration of the entire compendium. RESULTS: We have collected Saccharomyces cerevisiae gene expression microarray data containing roughly 2400 experimental conditions. We analyzed the functional coverage of this collection and we designed a context-sensitive search algorithm for rapid exploration of the compendium. A researcher using our system provides a small set of query genes to establish a biological search context; based on this query, we weight each dataset's relevance to the context, and within these weighted datasets we identify additional genes that are co-expressed with the query set. Our method exhibits an average increase in accuracy of 273\% compared to previous mega-clustering approaches when recapitulating known biology. Further, we find that our search paradigm identifies novel biological predictions that can be verified through further experimentation. Our methodology provides the ability for biological researchers to explore the totality of existing microarray data in a manner useful for drawing conclusions and formulating hypotheses, which we believe is invaluable for the research community. AVAILABILITY: Our query-driven search engine, called SPELL, is available at http://function.princeton.edu/SPELL. SUPPLEMENTARY INFORMATION: Several additional data files, figures and discussions are available at http://function.princeton.edu/SPELL/supplement.}, address = {Lewis-Sigler Institute for Integrative Genomics, Princeton University, Carl Icahn Laboratory, Princeton, NJ, USA.}, author = {Hibbs, Matthew A. and Hess, David C. and Myers, Chad L. and Huttenhower, Curtis and Li, Kai and Troyanskaya, Olga G.}, citeulike-article-id = {1651954}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btm403}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/23/20/2692}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/17724061}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=17724061}, day = {15}, doi = {10.1093/bioinformatics/btm403}, issn = {1460-2059}, journal = {Bioinformatics (Oxford, England)}, keywords = {algorithm, expression, microarray, visualization}, month = {October}, number = {20}, pages = {2692--2699}, posted-at = {2008-10-02 15:39:17}, priority = {2}, title = {Exploring the functional landscape of gene expression: directed search of large microarray compendia.}, url = {http://dx.doi.org/10.1093/bioinformatics/btm403}, volume = {23}, year = {2007} }

TY - JOUR ID - citeulike:1651954 L3 - citeulike-article-id:1651954 N2 - MOTIVATION: The increasing availability of gene expression microarray technology has resulted in the publication of thousands of microarray gene expression datasets investigating various biological conditions. This vast repository is still underutilized due to the lack of methods for fast, accurate exploration of the entire compendium. RESULTS: We have collected Saccharomyces cerevisiae gene expression microarray data containing roughly 2400 experimental conditions. We analyzed the functional coverage of this collection and we designed a context-sensitive search algorithm for rapid exploration of the compendium. A researcher using our system provides a small set of query genes to establish a biological search context; based on this query, we weight each dataset's relevance to the context, and within these weighted datasets we identify additional genes that are co-expressed with the query set. Our method exhibits an average increase in accuracy of 273% compared to previous mega-clustering approaches when recapitulating known biology. Further, we find that our search paradigm identifies novel biological predictions that can be verified through further experimentation. Our methodology provides the ability for biological researchers to explore the totality of existing microarray data in a manner useful for drawing conclusions and formulating hypotheses, which we believe is invaluable for the research community. AVAILABILITY: Our query-driven search engine, called SPELL, is available at http://function.princeton.edu/SPELL. SUPPLEMENTARY INFORMATION: Several additional data files, figures and discussions are available at http://function.princeton.edu/SPELL/supplement. IS - 20 JF - Bioinformatics (Oxford, England) SN - 1460-2059 AD - Lewis-Sigler Institute for Integrative Genomics, Princeton University, Carl Icahn Laboratory, Princeton, NJ, USA. EP - 2699 TI - Exploring the functional landscape of gene expression: directed search of large microarray compendia. VL - 23 SP - 2692 KW - algorithm KW - expression KW - microarray KW - visualization AU - Hibbs, Matthew AU - Hess, David AU - Myers, Chad AU - Huttenhower, Curtis AU - Li, Kai AU - Troyanskaya, Olga PY - 2007/10/15/ UR - http://dx.doi.org/10.1093/bioinformatics/btm403 ER -