Probabilistic base calling of Solexa sequencing data Export

@article{citeulike:3400802, abstract = {BACKGROUND:Solexa/Illumina short-read ultra-high throughput DNA sequencing technology produces millions of short tags (up to 36 bases) by parallel sequencing-by-synthesis of DNA colonies. The processing and statistical analysis of such high-throughput data poses new challenges; currently a fair proportion of the tags are routinely discarded due to an inability to match them to a reference sequence, thereby reducing the effective throughput of the technology.RESULTS:We propose a novel base calling algorithm using model-based clustering and probability theory to identify ambiguous bases and code them with IUPAC symbols. We also select optimal sub-tags using a score based on information content to remove uncertain bases towards the ends of the reads.CONCLUSION:We show that the method improves genome coverage and number of usable tags as compared with Solexa's data processing pipeline by an average of 15\%. An R package is provided which allows fast and accurate base calling of Solexa's fluorescence intensity files and the production of informative diagnostic plots.}, author = {Rougemont, Jacques and Amzallag, Arnaud and Iseli, Christian and Farinelli, Laurent and Xenarios, Ioannis and Naef, Felix}, citeulike-article-id = {3400802}, citeulike-linkout-0 = {http://dx.doi.org/10.1186/1471-2105-9-431}, citeulike-linkout-1 = {http://view.ncbi.nlm.nih.gov/pubmed/18851737}, citeulike-linkout-2 = {http://www.hubmed.org/display.cgi?uids=18851737}, doi = {10.1186/1471-2105-9-431}, issn = {1471-2105}, journal = {BMC Bioinformatics}, keywords = {sequencing, solexa, statistics}, number = {1}, pages = {431+}, posted-at = {2008-10-17 13:19:49}, priority = {2}, title = {Probabilistic base calling of Solexa sequencing data}, url = {http://dx.doi.org/10.1186/1471-2105-9-431}, volume = {9}, year = {2008} }

TY - JOUR ID - citeulike:3400802 L3 - citeulike-article-id:3400802 N2 - BACKGROUND:Solexa/Illumina short-read ultra-high throughput DNA sequencing technology produces millions of short tags (up to 36 bases) by parallel sequencing-by-synthesis of DNA colonies. The processing and statistical analysis of such high-throughput data poses new challenges; currently a fair proportion of the tags are routinely discarded due to an inability to match them to a reference sequence, thereby reducing the effective throughput of the technology.RESULTS:We propose a novel base calling algorithm using model-based clustering and probability theory to identify ambiguous bases and code them with IUPAC symbols. We also select optimal sub-tags using a score based on information content to remove uncertain bases towards the ends of the reads.CONCLUSION:We show that the method improves genome coverage and number of usable tags as compared with Solexa's data processing pipeline by an average of 15%. An R package is provided which allows fast and accurate base calling of Solexa's fluorescence intensity files and the production of informative diagnostic plots. IS - 1 JF - BMC Bioinformatics SN - 1471-2105 TI - Probabilistic base calling of Solexa sequencing data VL - 9 SP - 431 KW - sequencing KW - solexa KW - statistics AU - Rougemont, Jacques AU - Amzallag, Arnaud AU - Iseli, Christian AU - Farinelli, Laurent AU - Xenarios, Ioannis AU - Naef, Felix PY - 2008/// UR - http://dx.doi.org/10.1186/1471-2105-9-431 ER -