Quality scores and SNP detection in sequencing-by-synthesis systems Export

@article{citeulike:2742043, abstract = {10.1101/gr.070227.107 Promising new sequencing technologies, based on sequencing-by-synthesis (SBS), are starting to deliver large amounts of DNA sequence at very low cost. Polymorphism detection is a key application. We describe general methods for improved quality scores and accurate automated polymorphism detection, and apply them to data from the Roche (454) Genome Sequencer 20. We assess our methods using known-truth data sets, which is critical to the validity of the assessments. We developed informative, base-by-base error predictors for this sequencer and used a variant of the binning algorithm to combine them into a single empirically derived quality score. These quality scores are more useful than those produced by the system software: They both better predict actual error rates and identify many more high-quality bases. We developed a SNP detection method, with variants for low coverage, high coverage, and PCR amplicon applications, and evaluated it on known-truth data sets. We demonstrate good specificity in single reads, and excellent specificity (no false positives in 215 kb of genome) in high-coverage data.}, author = {Brockman, William and Alvarez, Pablo and Young, Sarah and Garber, Manuel and Giannoukos, Georgia and Lee, William L. and Russ, Carsten and Lander, Eric S. and Nusbaum, Chad and Jaffe, David B.}, citeulike-article-id = {2742043}, citeulike-linkout-0 = {http://dx.doi.org/10.1101/gr.070227.107}, citeulike-linkout-1 = {http://genome.cshlp.org/content/18/5/763.full.abstract}, citeulike-linkout-2 = {http://genome.cshlp.org/content/18/5/763.full.full.pdf}, citeulike-linkout-3 = {http://www.genome.org/cgi/content/abstract/18/5/763}, citeulike-linkout-4 = {http://view.ncbi.nlm.nih.gov/pubmed/18212088}, citeulike-linkout-5 = {http://www.hubmed.org/display.cgi?uids=18212088}, day = {22}, doi = {10.1101/gr.070227.107}, issn = {1088-9051}, journal = {Genome Research}, keywords = {discovery, snp}, month = {May}, number = {5}, pages = {763--770}, posted-at = {2009-06-11 22:57:06}, priority = {3}, title = {Quality scores and SNP detection in sequencing-by-synthesis systems}, url = {http://dx.doi.org/10.1101/gr.070227.107}, volume = {18}, year = {2008} }

TY - JOUR ID - citeulike:2742043 L3 - citeulike-article-id:2742043 N2 - 10.1101/gr.070227.107 Promising new sequencing technologies, based on sequencing-by-synthesis (SBS), are starting to deliver large amounts of DNA sequence at very low cost. Polymorphism detection is a key application. We describe general methods for improved quality scores and accurate automated polymorphism detection, and apply them to data from the Roche (454) Genome Sequencer 20. We assess our methods using known-truth data sets, which is critical to the validity of the assessments. We developed informative, base-by-base error predictors for this sequencer and used a variant of the binning algorithm to combine them into a single empirically derived quality score. These quality scores are more useful than those produced by the system software: They both better predict actual error rates and identify many more high-quality bases. We developed a SNP detection method, with variants for low coverage, high coverage, and PCR amplicon applications, and evaluated it on known-truth data sets. We demonstrate good specificity in single reads, and excellent specificity (no false positives in 215 kb of genome) in high-coverage data. IS - 5 JF - Genome Research SN - 1088-9051 EP - 770 TI - Quality scores and SNP detection in sequencing-by-synthesis systems VL - 18 SP - 763 KW - discovery KW - snp AU - Brockman, William AU - Alvarez, Pablo AU - Young, Sarah AU - Garber, Manuel AU - Giannoukos, Georgia AU - Lee, William AU - Russ, Carsten AU - Lander, Eric AU - Nusbaum, Chad AU - Jaffe, David PY - 2008/05/22/ UR - http://dx.doi.org/10.1101/gr.070227.107 ER -