Mapping identifiers for the integration of genomic datasets with the R/Bioconductor package biomaRt. Export

@article{citeulike:5219096, abstract = {Genomic experiments produce multiple views of biological systems, among them are DNA sequence and copy number variation, and mRNA and protein abundance. Understanding these systems needs integrated bioinformatic analysis. Public databases such as Ensembl provide relationships and mappings between the relevant sets of probe and target molecules. However, the relationships can be biologically complex and the content of the databases is dynamic. We demonstrate how to use the computational environment R to integrate and jointly analyze experimental datasets, employing BioMart web services to provide the molecule mappings. We also discuss typical problems that are encountered in making gene-to-transcript-to-protein mappings. The approach provides a flexible, programmable and reproducible basis for state-of-the-art bioinformatic data integration.}, author = {Durinck, Steffen and Spellman, Paul T. and Birney, Ewan and Huber, Wolfgang}, citeulike-article-id = {5219096}, citeulike-linkout-0 = {http://dx.doi.org/10.1038/nprot.2009.97}, citeulike-linkout-1 = {http://dx.doi.org/10.1038/nprot.2009.97}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/19617889}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=19617889}, day = {23}, doi = {10.1038/nprot.2009.97}, issn = {1750-2799}, journal = {Nature protocols}, keywords = {biomart, identifier, mapping}, month = {July}, number = {8}, pages = {1184--1191}, posted-at = {2009-08-07 03:26:09}, priority = {2}, publisher = {Nature Publishing Group}, title = {Mapping identifiers for the integration of genomic datasets with the R/Bioconductor package biomaRt.}, url = {http://dx.doi.org/10.1038/nprot.2009.97}, volume = {4}, year = {2009} }

TY - JOUR ID - citeulike:5219096 L3 - citeulike-article-id:5219096 N2 - Genomic experiments produce multiple views of biological systems, among them are DNA sequence and copy number variation, and mRNA and protein abundance. Understanding these systems needs integrated bioinformatic analysis. Public databases such as Ensembl provide relationships and mappings between the relevant sets of probe and target molecules. However, the relationships can be biologically complex and the content of the databases is dynamic. We demonstrate how to use the computational environment R to integrate and jointly analyze experimental datasets, employing BioMart web services to provide the molecule mappings. We also discuss typical problems that are encountered in making gene-to-transcript-to-protein mappings. The approach provides a flexible, programmable and reproducible basis for state-of-the-art bioinformatic data integration. IS - 8 JF - Nature protocols SN - 1750-2799 EP - 1191 TI - Mapping identifiers for the integration of genomic datasets with the R/Bioconductor package biomaRt. PB - Nature Publishing Group VL - 4 SP - 1184 KW - biomart KW - identifier KW - mapping AU - Durinck, Steffen AU - Spellman, Paul AU - Birney, Ewan AU - Huber, Wolfgang PY - 2009/07/23/ UR - http://dx.doi.org/10.1038/nprot.2009.97 ER -