Evolving gene/transcript definitions significantly alter the interpretation of GeneChip data Export

@article{dai05, abstract = {Genome-wide expression profiling is a powerful tool for implicating novel gene ensembles in cellular mechanisms of health and disease. The most popular platform for genome-wide expression profiling is the Affymetrix GeneChip. However, its selection of probes relied on earlier genome and transcriptome annotation which is significantly different from current knowledge. The resultant informatics problems have a profound impact on analysis and interpretation the data. Here, we address these critical issues and offer a solution. We identified several classes of problems at the individual probe level in the existing annotation, under the assumption that current genome and transcriptome databases are more accurate than those used for GeneChip design. We then reorganized probes on more than a dozen popular GeneChips into gene-, transcript- and exon-specific probe sets in light of up-to-date genome, cDNA/EST clustering and single nucleotide polymorphism information. Comparing analysis results between the original and the redefined probe sets reveals [\~{}]30-50\% discrepancy in the genes previously identified as differentially expressed, regardless of analysis method. Our results demonstrate that the original Affymetrix probe set definitions are inaccurate, and many conclusions derived from past GeneChip analyses may be significantly flawed. It will be beneficial to re-analyze existing GeneChip data with updated probe set definitions. 10.1093/nar/gni179}, author = {Dai, Manhong and Wang, Pinglang and Boyd, Andrew D. and Kostov, Georgi and Athey, Brian and Jones, Edward G. and Bunney, William E. and Myers, Richard M. and Speed, Terry P. and Akil, Huda and Watson, Stanley J. and Meng, Fan}, booktitle = {Nucl. Acids Res.}, citeulike-article-id = {436785}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/nar/gni179}, citeulike-linkout-1 = {http://nar.oxfordjournals.org/cgi/content/abstract/33/20/e175}, citeulike-linkout-2 = {http://www.ingentaconnect.com/content/oup/nar/2005/00000033/00000020/e175}, citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/16284200}, citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=16284200}, day = {10}, doi = {10.1093/nar/gni179}, issn = {0305-1048}, journal = {Nucl. Acids Res.}, keywords = {affy, sma\_exon}, month = {November}, number = {20}, pages = {e175}, posted-at = {2007-07-23 12:21:06}, priority = {3}, publisher = {Oxford University Press}, title = {Evolving gene/transcript definitions significantly alter the interpretation of GeneChip data}, url = {http://dx.doi.org/10.1093/nar/gni179}, volume = {33}, year = {2005} }

TY - JOUR ID - dai05 L3 - citeulike-article-id:436785 N2 - Genome-wide expression profiling is a powerful tool for implicating novel gene ensembles in cellular mechanisms of health and disease. The most popular platform for genome-wide expression profiling is the Affymetrix GeneChip. However, its selection of probes relied on earlier genome and transcriptome annotation which is significantly different from current knowledge. The resultant informatics problems have a profound impact on analysis and interpretation the data. Here, we address these critical issues and offer a solution. We identified several classes of problems at the individual probe level in the existing annotation, under the assumption that current genome and transcriptome databases are more accurate than those used for GeneChip design. We then reorganized probes on more than a dozen popular GeneChips into gene-, transcript- and exon-specific probe sets in light of up-to-date genome, cDNA/EST clustering and single nucleotide polymorphism information. Comparing analysis results between the original and the redefined probe sets reveals [~]30-50% discrepancy in the genes previously identified as differentially expressed, regardless of analysis method. Our results demonstrate that the original Affymetrix probe set definitions are inaccurate, and many conclusions derived from past GeneChip analyses may be significantly flawed. It will be beneficial to re-analyze existing GeneChip data with updated probe set definitions. 10.1093/nar/gni179 IS - 20 JF - Nucl. Acids Res. SN - 0305-1048 EP - e175 TI - Evolving gene/transcript definitions significantly alter the interpretation of GeneChip data PB - Oxford University Press VL - 33 T2 - Nucl. Acids Res. SP - e175 KW - affy KW - sma_exon AU - Dai, Manhong AU - Wang, Pinglang AU - Boyd, Andrew AU - Kostov, Georgi AU - Athey, Brian AU - Jones, Edward AU - Bunney, William AU - Myers, Richard AU - Speed, Terry AU - Akil, Huda AU - Watson, Stanley AU - Meng, Fan PY - 2005/11/10/ UR - http://dx.doi.org/10.1093/nar/gni179 ER -