Annotation of metagenome short reads using proxygenes. Export

@article{citeulike:3180397, abstract = {MOTIVATION: A typical metagenome dataset generated using a 454 pyrosequencing platform consists of short reads sampled from the collective genome of a microbial community. The amount of sequence in such datasets is usually insufficient for assembly, and traditional gene prediction cannot be applied to unassembled short reads. As a result, analysis of such datasets usually involves comparisons in terms of relative abundances of various protein families. The latter requires assignment of individual reads to protein families, which is hindered by the fact that short reads contain only a fragment, usually small, of a protein. RESULTS: We have considered the assignment of pyrosequencing reads to protein families directly using RPS-BLAST against COG and Pfam databases and indirectly via proxygenes that are identified using BLASTx searches against protein sequence databases. Using simulated metagenome datasets as benchmarks, we show that the proxygene method is more accurate than the direct assignment. We introduce a clustering method which significantly reduces the size of a metagenome dataset while maintaining a faithful representation of its functional and taxonomic content.}, address = {Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA.}, author = {Dalevi, D. and Ivanova, N. N. and Mavromatis, K. and Hooper, S. D. and Szeto, E. and Hugenholtz, P. and Kyrpides, N. C. and Markowitz, V. M.}, citeulike-article-id = {3180397}, citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/18689842}, citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=18689842}, day = {15}, issn = {1460-2059}, journal = {Bioinformatics (Oxford, England)}, keywords = {annotation, metagenomics}, month = {August}, number = {16}, posted-at = {2008-09-02 02:54:40}, priority = {0}, title = {Annotation of metagenome short reads using proxygenes.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/18689842}, volume = {24}, year = {2008} }

TY - JOUR ID - citeulike:3180397 L3 - citeulike-article-id:3180397 N2 - MOTIVATION: A typical metagenome dataset generated using a 454 pyrosequencing platform consists of short reads sampled from the collective genome of a microbial community. The amount of sequence in such datasets is usually insufficient for assembly, and traditional gene prediction cannot be applied to unassembled short reads. As a result, analysis of such datasets usually involves comparisons in terms of relative abundances of various protein families. The latter requires assignment of individual reads to protein families, which is hindered by the fact that short reads contain only a fragment, usually small, of a protein. RESULTS: We have considered the assignment of pyrosequencing reads to protein families directly using RPS-BLAST against COG and Pfam databases and indirectly via proxygenes that are identified using BLASTx searches against protein sequence databases. Using simulated metagenome datasets as benchmarks, we show that the proxygene method is more accurate than the direct assignment. We introduce a clustering method which significantly reduces the size of a metagenome dataset while maintaining a faithful representation of its functional and taxonomic content. IS - 16 JF - Bioinformatics (Oxford, England) SN - 1460-2059 AD - Biological Data Management and Technology Center, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA. TI - Annotation of metagenome short reads using proxygenes. VL - 24 KW - annotation KW - metagenomics AU - Dalevi, D AU - Ivanova, NN AU - Mavromatis, K AU - Hooper, SD AU - Szeto, E AU - Hugenholtz, P AU - Kyrpides, NC AU - Markowitz, VM PY - 2008/08/15/ UR - http://view.ncbi.nlm.nih.gov/pubmed/18689842 ER -