BioWarehouse: a bioinformatics database warehouse toolkit Export

@article{citeulike:1122519, abstract = {BACKGROUND:This article addresses the problem of interoperation of heterogeneous bioinformatics databases.RESULTS:We introduce BioWarehouse, an open source toolkit for constructing bioinformatics database warehouses using the MySQL and Oracle relational database managers. BioWarehouse integrates its component databases into a common representational framework within a single database management system, thus enabling multi-database queries using the Structured Query Language (SQL) but also facilitating a variety of database integration tasks such as comparative analysis and data mining. BioWarehouse currently supports the integration of a pathway-centric set of databases including ENZYME, KEGG, and BioCyc, and in addition the UniProt, GenBank, NCBI Taxonomy, and CMR databases, and the Gene Ontology. Loader tools, written in the C and JAVA languages, parse and load these databases into a relational database schema. The loaders also apply a degree of semantic normalization to their respective source data, decreasing semantic heterogeneity. The schema supports the following bioinformatics datatypes: chemical compounds, biochemical reactions, metabolic pathways, proteins, genes, nucleic acid sequences, features on protein and nucleic-acid sequences, organisms, organism taxonomies, and controlled vocabularies. As an application example, we applied BioWarehouse to determine the fraction of biochemically characterized enzyme activities for which no sequences exist in the public sequence databases. The answer is that no sequence exists for 36\% of enzyme activities for which EC numbers have been assigned. These gaps in sequence data significantly limit the accuracy of genome annotation and metabolic pathway prediction, and are a barrier for metabolic engineering. Complex queries of this type provide examples of the value of the data warehousing approach to bioinformatics research.CONCLUSION:BioWarehouse embodies significant progress on the database integration problem for bioinformatics.}, author = {Lee, Thomas and Pouliot, Yannick and Wagner, Valerie and Gupta, Priyanka and Calvert, David S. and Tenenbaum, Jessica and Karp, Peter}, citeulike-article-id = {1122519}, citeulike-linkout-0 = {http://dx.doi.org/10.1186/1471-2105-7-170}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/16556315}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=16556315}, doi = {10.1186/1471-2105-7-170}, issn = {1471-2105}, journal = {BMC Bioinformatics}, keywords = {database, software}, number = {1}, pages = {170+}, posted-at = {2009-10-03 23:31:06}, priority = {2}, title = {BioWarehouse: a bioinformatics database warehouse toolkit}, url = {http://dx.doi.org/10.1186/1471-2105-7-170}, volume = {7}, year = {2006} }

TY - JOUR ID - citeulike:1122519 L3 - citeulike-article-id:1122519 N2 - BACKGROUND:This article addresses the problem of interoperation of heterogeneous bioinformatics databases.RESULTS:We introduce BioWarehouse, an open source toolkit for constructing bioinformatics database warehouses using the MySQL and Oracle relational database managers. BioWarehouse integrates its component databases into a common representational framework within a single database management system, thus enabling multi-database queries using the Structured Query Language (SQL) but also facilitating a variety of database integration tasks such as comparative analysis and data mining. BioWarehouse currently supports the integration of a pathway-centric set of databases including ENZYME, KEGG, and BioCyc, and in addition the UniProt, GenBank, NCBI Taxonomy, and CMR databases, and the Gene Ontology. Loader tools, written in the C and JAVA languages, parse and load these databases into a relational database schema. The loaders also apply a degree of semantic normalization to their respective source data, decreasing semantic heterogeneity. The schema supports the following bioinformatics datatypes: chemical compounds, biochemical reactions, metabolic pathways, proteins, genes, nucleic acid sequences, features on protein and nucleic-acid sequences, organisms, organism taxonomies, and controlled vocabularies. As an application example, we applied BioWarehouse to determine the fraction of biochemically characterized enzyme activities for which no sequences exist in the public sequence databases. The answer is that no sequence exists for 36% of enzyme activities for which EC numbers have been assigned. These gaps in sequence data significantly limit the accuracy of genome annotation and metabolic pathway prediction, and are a barrier for metabolic engineering. Complex queries of this type provide examples of the value of the data warehousing approach to bioinformatics research.CONCLUSION:BioWarehouse embodies significant progress on the database integration problem for bioinformatics. IS - 1 JF - BMC Bioinformatics SN - 1471-2105 TI - BioWarehouse: a bioinformatics database warehouse toolkit VL - 7 SP - 170 KW - database KW - software AU - Lee, Thomas AU - Pouliot, Yannick AU - Wagner, Valerie AU - Gupta, Priyanka AU - Calvert, David AU - Tenenbaum, Jessica AU - Karp, Peter PY - 2006/// UR - http://dx.doi.org/10.1186/1471-2105-7-170 ER -