Quantitative assessment of protein function prediction from metagenomics shotgun sequences

@article{citeulike:1667149, abstract = {To assess the potential of protein function prediction in environmental genomics data, we analyzed shotgun sequences from four diverse and complex habitats. Using homology searches as well as customized gene neighborhood methods that incorporate intergenic and evolutionary distances, we inferred specific functions for 76\% of the 1.4 million predicted ORFs in these samples (83\% when nonspecific functions are considered). Surprisingly, these fractions are only slightly smaller than the corresponding ones in completely sequenced genomes (83\% and 86\%, respectively, by using the same methodology) and considerably higher than previously thought. For as many as 75,448 ORFs (5\% of the total), only neighborhood methods can assign functions, illustrated here by a previously undescribed gene associated with the well characterized heme biosynthesis operon and a potential transcription factor that might regulate a coupling between fatty acid biosynthesis and degradation. Our results further suggest that, although functions can be inferred for most proteins on earth, many functions remain to be discovered in numerous small, rare protein families. 10.1073/pnas.0702636104}, author = {Harrington, E. D. and Singh, A. H. and Doerks, T. and Letunic, I. and von Mering, C. and Jensen, L. J. and Raes, J. and Bork, P. }, citeulike-article-id = {1667149}, doi = {http://dx.doi.org/10.1073/pnas.0702636104}, journal = {Proceedings of the National Academy of Sciences}, keywords = {bork, metagenomics}, month = {August}, number = {35}, pages = {13913--13918}, posted-at = {2007-09-17 21:23:26}, priority = {2}, title = {Quantitative assessment of protein function prediction from metagenomics shotgun sequences}, url = {http://dx.doi.org/10.1073/pnas.0702636104}, volume = {104}, year = {2007} }

TY - JOUR ID - citeulike:1667149 L3 - citeulike-article-id:1667149 N2 - To assess the potential of protein function prediction in environmental genomics data, we analyzed shotgun sequences from four diverse and complex habitats. Using homology searches as well as customized gene neighborhood methods that incorporate intergenic and evolutionary distances, we inferred specific functions for 76% of the 1.4 million predicted ORFs in these samples (83% when nonspecific functions are considered). Surprisingly, these fractions are only slightly smaller than the corresponding ones in completely sequenced genomes (83% and 86%, respectively, by using the same methodology) and considerably higher than previously thought. For as many as 75,448 ORFs (5% of the total), only neighborhood methods can assign functions, illustrated here by a previously undescribed gene associated with the well characterized heme biosynthesis operon and a potential transcription factor that might regulate a coupling between fatty acid biosynthesis and degradation. Our results further suggest that, although functions can be inferred for most proteins on earth, many functions remain to be discovered in numerous small, rare protein families. 10.1073/pnas.0702636104 IS - 35 JF - Proceedings of the National Academy of Sciences EP - 13918 TI - Quantitative assessment of protein function prediction from metagenomics shotgun sequences VL - 104 SP - 13913 KW - bork KW - metagenomics AU - Harrington, ED AU - Singh, AH AU - Doerks, T AU - Letunic, I AU - von Mering, C AU - Jensen, LJ AU - Raes, J AU - Bork, P PY - 2007/08/28/ UR - http://dx.doi.org/10.1073/pnas.0702636104 ER -