references.bib

@article{schloss_introducing_2009,
  title = {Introducing Mothur: {{Open}}-Source, Platform-Independent, Community-Supported Software for Describing and Comparing Microbial Communities},
  author = {Schloss, Patrick D. and Westcott, Sarah L. and Ryabin, Thomas and Hall, Justine R. and Hartmann, Martin and Hollister, Emily B. and Lesniewski, Ryan A. and Oakley, Brian B. and Parks, Donovan H. and Robinson, Courtney J. and Sahl, Jason W. and Stres, Blaz and Thallinger, Gerhard G. and Van Horn, David J. and Weber, Carolyn F.},
  year = {2009},
  volume = {75},
  pages = {7537--7541},
  publisher = {{American Society for Microbiology Journals}},
  issn = {0099-2240},
  doi = {10.1128/AEM.01541-09},
  abstract = {mothur aims to be a comprehensive software package that allows users to use a single piece of software to analyze community sequence data. It builds upon previous tools to provide a flexible and powerful software package for analyzing sequencing data. As a case study, we used mothur to trim, screen, and align sequences; calculate distances; assign sequences to operational taxonomic units; and describe the {$\alpha$} and {$\beta$} diversity of eight marine samples previously characterized by pyrosequencing of 16S rRNA gene fragments. This analysis of more than 222,000 sequences was completed in less than 2 h with a laptop computer.},
  eprint = {https://aem.asm.org/content/75/23/7537.full.pdf},
  journal = {Applied and Environmental Microbiology},
  number = {23}
}

@article{westcott_opticlust_2017,
  title = {{{OptiClust}}, an {{Improved Method}} for {{Assigning Amplicon}}-{{Based Sequence Data}} to {{Operational Taxonomic Units}}},
  author = {Westcott, Sarah L. and Schloss, Patrick D.},
  editor = {McMahon, Katherine},
  year = {2017},
  month = mar,
  volume = {2},
  pages = {e00073-17},
  issn = {2379-5042},
  doi = {10.1128/mSphereDirect.00073-17},
  abstract = {Assignment of 16S rRNA gene sequences to operational taxonomic units (OTUs) is a computational bottleneck in the process of analyzing microbial communities. Although this has been an active area of research, it has been difficult to overcome the time and memory demands while improving the quality of the OTU assignments. Here, we developed a new OTU assignment algorithm that iteratively reassigns sequences to new OTUs to optimize the Matthews correlation coefficient (MCC), a measure of the quality of OTU assignments. To assess the new algorithm, OptiClust, we compared it to 10 other algorithms using 16S rRNA gene sequences from two simulated and four natural communities. Using the OptiClust algorithm, the MCC values averaged 15.2 and 16.5\% higher than the OTUs generated when we used the average neighbor and distance-based greedy clustering with VSEARCH, respectively. Furthermore, on average, OptiClust was 94.6 times faster than the average neighbor algorithm and just as fast as distance-based greedy clustering with VSEARCH. An empirical analysis of the efficiency of the algorithms showed that the time and memory required to perform the algorithm scaled quadratically with the number of unique sequences in the data set. The significant improvement in the quality of the OTU assignments over previously existing methods will significantly enhance downstream analysis by limiting the splitting of similar sequences into separate OTUs and merging of dissimilar sequences into the same OTU. The development of the OptiClust algorithm represents a significant advance that is likely to have numerous other applications.},
  journal = {mSphere},
  keywords = {Schloss_Lab},
  language = {en},
  number = {2}
}