Integration of Microbial Ecology and Statistics: a Test To Compare Gene Libraries

@article{citeulike:2215671, abstract = {Libraries of 16S rRNA genes provide insight into the membership of microbial communities. Statistical methods help to determine whether differences in library composition are artifacts of sampling or are due to underlying differences in the communities from which they are derived. To contribute to a growing statistical framework for comparing 16S rRNA libraries, we present a computer program, {int}-LIBSHUFF, which calculates the integral form of the Cramer-von Mises statistic. This implementation builds upon the LIBSHUFF program, which uses an approximation of the statistic and makes a number of modifications that improve precision and accuracy. Once {int}-LIBSHUFF calculates the P values, when pairwise comparisons are tested at the 0.05 level, the probability of falsely identifying a significant P value is 0.098 for a study with two libraries, 0.265 for three libraries, and 0.460 for four libraries. The potential negative effects of making the multiple pairwise comparisons necessitate correcting for the increased likelihood that differences between treatments are due to chance and do not reflect biological differences. Using {int}-LIBSHUFF, we found that previously published 16S rRNA gene libraries constructed from Scottish and Wisconsin soils contained different bacterial lineages. We also analyzed the published libraries constructed for the zebrafish gut microflora and found statistically significant changes in the community during development of the host. These analyses illustrate the power of {int}-LIBSHUFF to detect differences between communities, providing the basis for ecological inference about the association of soil productivity or host gene expression and microbial community composition. 10.1128/AEM.70.9.5485-5492.2004}, author = {Schloss, Patrick D. and Larget, Bret R. and Handelsman, Jo }, citeulike-article-id = {2215671}, doi = {http://dx.doi.org/10.1128/AEM.70.9.5485-5492.2004}, journal = {Appl. Environ. Microbiol.}, keywords = {diversity, ecology, metagenomics, microbes}, month = {September}, number = {9}, pages = {5485--5492}, posted-at = {2008-07-24 18:39:36}, priority = {0}, title = {Integration of Microbial Ecology and Statistics: a Test To Compare Gene Libraries}, url = {http://dx.doi.org/10.1128/AEM.70.9.5485-5492.2004}, volume = {70}, year = {2004} }

TY - JOUR ID - citeulike:2215671 L3 - citeulike-article-id:2215671 TI - Integration of Microbial Ecology and Statistics: a Test To Compare Gene Libraries JF - Appl. Environ. Microbiol. VL - 70 IS - 9 SP - 5485 EP - 5492 N2 - Libraries of 16S rRNA genes provide insight into the membership of microbial communities. Statistical methods help to determine whether differences in library composition are artifacts of sampling or are due to underlying differences in the communities from which they are derived. To contribute to a growing statistical framework for comparing 16S rRNA libraries, we present a computer program, {int}-LIBSHUFF, which calculates the integral form of the Cramer-von Mises statistic. This implementation builds upon the LIBSHUFF program, which uses an approximation of the statistic and makes a number of modifications that improve precision and accuracy. Once {int}-LIBSHUFF calculates the P values, when pairwise comparisons are tested at the 0.05 level, the probability of falsely identifying a significant P value is 0.098 for a study with two libraries, 0.265 for three libraries, and 0.460 for four libraries. The potential negative effects of making the multiple pairwise comparisons necessitate correcting for the increased likelihood that differences between treatments are due to chance and do not reflect biological differences. Using {int}-LIBSHUFF, we found that previously published 16S rRNA gene libraries constructed from Scottish and Wisconsin soils contained different bacterial lineages. We also analyzed the published libraries constructed for the zebrafish gut microflora and found statistically significant changes in the community during development of the host. These analyses illustrate the power of {int}-LIBSHUFF to detect differences between communities, providing the basis for ecological inference about the association of soil productivity or host gene expression and microbial community composition. 10.1128/AEM.70.9.5485-5492.2004 KW - diversity KW - ecology KW - metagenomics KW - microbes AU - Schloss, Patrick AU - Larget, Bret AU - Handelsman, Jo PY - 2004/09/01/ UR - http://dx.doi.org/10.1128/AEM.70.9.5485-5492.2004 ER -