Human genomes as email attachments Export

@article{citeulike:3508436, abstract = {Summary: The amount of genomic sequence data being generated and made available through public databases continues to increase at an ever-expanding rate. Downloading, copying, sharing and manipulating these large datasets are becoming difficult and time consuming for researchers. We need to consider using advanced compression techniques as part of a standard data format for genomic data. The inherent structure of genome data allows for more efficient lossless compression than can be obtained through the use of generic compression programs. We apply a series of techniques to James Watson's genome that in combination reduce it to a mere 4MB, small enough to be sent as an email attachment. Availability: Our algorithms are implemented in C++ and are freely available from http://www.ics.uci.edu/\~{}xhx/project/DNAzip. Contact: chenli@ics.uci.edu; xhx@ics.uci.edu Supplementary information: Supplementary data are available at Bioinformatics online. 10.1093/bioinformatics/btn582}, author = {Christley, Scott and Lu, Yiming and Li, Chen and Xie, Xiaohui}, citeulike-article-id = {3508436}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btn582}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/cgi/content/abstract/25/2/274}, citeulike-linkout-2 = {http://view.ncbi.nlm.nih.gov/pubmed/18996942}, citeulike-linkout-3 = {http://www.hubmed.org/display.cgi?uids=18996942}, day = {15}, doi = {10.1093/bioinformatics/btn582}, issn = {1460-2059}, journal = {Bioinformatics}, keywords = {bioinformatics, genomics}, month = {January}, number = {2}, pages = {274--275}, posted-at = {2009-01-16 02:44:33}, priority = {2}, title = {Human genomes as email attachments}, url = {http://dx.doi.org/10.1093/bioinformatics/btn582}, volume = {25}, year = {2009} }

TY - JOUR ID - citeulike:3508436 L3 - citeulike-article-id:3508436 N2 - Summary: The amount of genomic sequence data being generated and made available through public databases continues to increase at an ever-expanding rate. Downloading, copying, sharing and manipulating these large datasets are becoming difficult and time consuming for researchers. We need to consider using advanced compression techniques as part of a standard data format for genomic data. The inherent structure of genome data allows for more efficient lossless compression than can be obtained through the use of generic compression programs. We apply a series of techniques to James Watson's genome that in combination reduce it to a mere 4MB, small enough to be sent as an email attachment. Availability: Our algorithms are implemented in C++ and are freely available from http://www.ics.uci.edu/~xhx/project/DNAzip. Contact: chenli@ics.uci.edu; xhx@ics.uci.edu Supplementary information: Supplementary data are available at Bioinformatics online. 10.1093/bioinformatics/btn582 IS - 2 JF - Bioinformatics SN - 1460-2059 EP - 275 TI - Human genomes as email attachments VL - 25 SP - 274 KW - bioinformatics KW - genomics AU - Christley, Scott AU - Lu, Yiming AU - Li, Chen AU - Xie, Xiaohui PY - 2009/01/15/ UR - http://dx.doi.org/10.1093/bioinformatics/btn582 ER -