references.bib

@article{knuth84,
  author = {Knuth, Donald E.},
  title = {Literate Programming},
  year = {1984},
  issue_date = {May 1984},
  publisher = {Oxford University Press, Inc.},
  address = {USA},
  volume = {27},
  number = {2},
  issn = {0010-4620},
  url = {https://doi.org/10.1093/comjnl/27.2.97},
  doi = {10.1093/comjnl/27.2.97},
  journal = {Comput. J.},
  month = may,
  pages = {97–111},
  numpages = {15}
}

@ARTICLE{Scholz2008-xs,
  title     = "Genetic diversity and phylogenetic relationships of bacteria
               belonging to the {Ochrobactrum-Brucella} group by recA and {16S}
               {rRNA} gene-based comparative sequence analysis",
  author    = "Scholz, Holger C and Al Dahouk, Sascha and Tomaso, Herbert and
               Neubauer, Heinrich and Witte, Angela and Schloter, Michael and
               K{\"a}mpfer, Peter and Falsen, Enevold and Pfeffer, Martin and
               Engel, Marion",
  abstract  = "The genetic diversity and phylogenetic interrelationships among
               106 Ochrobactrum strains (O. anthropi: 72, O. intermedium: 22,
               O. tritici: 5, O. oryzae: 2, O. grignonense: 2, O.
               gallinifaecis: 1, O. lupini: 2), the type strains of the eight
               Brucella species and other closely related taxa were studied by
               recA and rrs gene (16S rRNA) comparative sequence analysis. Both
               markers correctly delineated the various Ochrobactrum species;
               however, resolution at the subspecies level was considerably
               higher in the recA gene-based approach. Phylogenetic analyses
               using neighbor-joining, parsimony, and maximum likelihood
               algorithms generated trees with similar topologies but the
               overall branching order, and also the order of the subclades,
               were not stable in either assay, which could be explained by
               generally high recA and rrs sequence similarities. Ochrobactrum
               and Pseudochrobactrum formed separate clades distinct from other
               Alphaproteobacteria with Bartonella, Agrobacterium, and
               Rhizobium as the closest relatives. O. gallinifaecis was the
               most distinct member, when compared to the type species O.
               anthropi, with rrs and recA similarities of 96.2\% and 81.4\%.
               Brucella species were indistinguishable, exhibiting high rrs and
               recA gene similarities of 98.6\% and 85.5\% compared with
               Ochrobactrum intermedium. At the protein level, all RecA
               sequences among the various Ochrobactrum species and between
               Ochrobactrum and Brucella were highly similar with only a few
               amino acid substitutions. O. anthropi and O. tritici were
               indistinguishable by means of their RecA proteins. A set of
               initially biochemically classified strains did not cluster
               within their assigned species and they either grouped within
               other known species or grouped as potential novel Ochrobactrum
               species. In further investigations, these strains were
               reclassified and described as novel species. In summary,
               Ochrobactrum is a highly diverse genus comprising several novel
               species. We recommend recA- in addition to rrs gene-analysis for
               correct species allocation and subtyping of novel Ochrobactrum
               isolates.",
  journal   = "Syst. Appl. Microbiol.",
  publisher = "Elsevier BV",
  volume    =  31,
  number    =  1,
  pages     = "1--16",
  month     =  mar,
  year      =  2008,
  language  = "en"
}

@ARTICLE{Laine2023-py,
  title     = "Global estimate of human brucellosis incidence",
  author    = "Laine, Christopher G and Johnson, Valen E and Scott, H Morgan
               and Arenas-Gamboa, Angela M",
  abstract  = "Brucellosis is a major public health concern worldwide,
               especially for persons living in resource-limited settings.
               Historically, an evidence-based estimate of the global annual
               incidence of human cases has been elusive. We used international
               public health data to fill this information gap through
               application of risk metrics to worldwide and regional at-risk
               populations. We performed estimations using 3 statistical models
               (weighted average interpolation, bootstrap resampling, and
               Bayesian inference) and considered missing information. An
               evidence-based conservative estimate of the annual global
               incidence is 2.1 million, significantly higher than was
               previously assumed. Our models indicate Africa and Asia sustain
               most of the global risk and cases, although areas within the
               Americas and Europe remain of concern. This study reveals that
               disease risk and incidence are higher than previously suggested
               and lie mainly within resource-limited settings. Clarification
               of both misdiagnosis and underdiagnosis is required because
               those factors will amplify case estimates.",
  journal   = "Emerg. Infect. Dis.",
  publisher = "Centers for Disease Control and Prevention (CDC)",
  volume    =  29,
  number    =  9,
  pages     = "1789--1797",
  month     =  sep,
  year      =  2023,
  keywords  = "Brucella; bacteria; brucellosis; brucellosis epidemiology;
               brucellosis incidence; human brucellosis",
  language  = "en"
}

@ARTICLE{Hordt2020-ba,
  title     = "Analysis of 1,000+ type-strain genomes substantially improves
               taxonomic classification of Alphaproteobacteria",
  author    = "H{\"o}rdt, Anton and L{\'o}pez, Marina Garc{\'\i}a and
               Meier-Kolthoff, Jan P and Schleuning, Marcel and Weinhold,
               Lisa-Maria and Tindall, Brian J and Gronow, Sabine and Kyrpides,
               Nikos C and Woyke, Tanja and G{\"o}ker, Markus",
  abstract  = "The class Alphaproteobacteria is comprised of a diverse
               assemblage of Gram-negative bacteria that includes organisms of
               varying morphologies, physiologies and habitat preferences many
               of which are of clinical and ecological importance.
               Alphaproteobacteria classification has proved to be difficult,
               not least when taxonomic decisions rested heavily on a limited
               number of phenotypic features and interpretation of poorly
               resolved 16S rRNA gene trees. Despite progress in recent years
               regarding the classification of bacteria assigned to the class,
               there remains a need to further clarify taxonomic relationships.
               Here, draft genome sequences of a collection of genomes of more
               than 1000 Alphaproteobacteria and outgroup type strains were
               used to infer phylogenetic trees from genome-scale data using
               the principles drawn from phylogenetic systematics. The majority
               of taxa were found to be monophyletic but several orders,
               families and genera, including taxa recognized as problematic
               long ago but also quite recent taxa, as well as a few species
               were shown to be in need of revision. According proposals are
               made for the recognition of new orders, families and genera, as
               well as the transfer of a variety of species to other genera and
               of a variety of genera to other families. In addition, emended
               descriptions are given for many species mainly involving
               information on DNA G+C content and (approximate) genome size,
               both of which are confirmed as valuable taxonomic markers.
               Similarly, analysis of the gene content was shown to provide
               valuable taxonomic insights in the class. Significant
               incongruities between 16S rRNA gene and whole genome trees were
               not found in the class. The incongruities that became obvious
               when comparing the results of the present study with existing
               classifications appeared to be caused mainly by insufficiently
               resolved 16S rRNA gene trees or incomplete taxon sampling.
               Another probable cause of misclassifications in the past is the
               partially low overall fit of phenotypic characters to the
               sequence-based tree. Even though a significant degree of
               phylogenetic conservation was detected in all characters
               investigated, the overall fit to the tree varied considerably.",
  journal   = "Front. Microbiol.",
  publisher = "Frontiers Media SA",
  volume    =  11,
  pages     = "468",
  month     =  apr,
  year      =  2020,
  keywords  = "G+C content; Genome BLAST Distance Phylogeny; chemotaxonomy;
               genome size; morphology; phylogenetic systematics; phylogenomics",
  copyright = "https://creativecommons.org/licenses/by/4.0/",
  language  = "en"
}

@ARTICLE{Moreno2023-yu,
  title    = "If you're not confused, you're not paying attention: Ochrobactrum
              is not Brucella",
  author   = "Moreno, Edgardo and Middlebrook, Earl A and Altamirano-Silva,
              Pamela and Al Dahouk, Sascha and Araj, George F and Arce-Gorvel,
              Vilma and Arenas-Gamboa, {\'A}ngela and Ariza, Javier and
              Barquero-Calvo, El{\'\i}as and Battelli, Giorgio and Bertu,
              Wilson J and Blasco, Jos{\'e} Mar{\'\i}a and Bosilkovski, Mile
              and Cadmus, Simeon and Caswell, Clayton C and Celli, Jean and
              Chac{\'o}n-D{\'\i}az, Carlos and Chaves-Olarte, Esteban and
              Comerci, Diego J and Conde-{\'A}lvarez, Raquel and Cook,
              Elizabeth and Cravero, Silvio and Dadar, Maryam and De Boelle,
              Xavier and De Massis, Fabrizio and D{\'\i}az, Ram{\'o}n and
              Escobar, Gabriela I and Fern{\'a}ndez-Lago, Luis and Ficht,
              Thomas A and Foster, Jeffrey T and Garin-Bastuji, Bruno and
              Godfroid, Jacques and Gorvel, Jean-Pierre and G{\"u}ler, Leyla
              and Erdenli{\u g}-G{\"u}rbilek, Sevil and Gusi, Amayel M and
              Guzm{\'a}n-Verri, Caterina and Hai, Jiang and Hern{\'a}ndez-Mora,
              Gabriela and Iriarte, Maite and Jacob, Nestor R and Keriel, Anne
              and Khames, Maamar and K{\"o}hler, Stephan and Letesson,
              Jean-Jacques and Loperena-Barber, Maite and L{\'o}pez-Go{\~n}i,
              Ignacio and McGiven, John and Melzer, Falk and Mora-Cartin,
              Ricardo and Moran-Gilad, Jacob and Mu{\~n}oz, Pilar M and
              Neubauer, Heinrich and O'Callaghan, David and Ocholi, Reuben and
              O{\~n}ate, {\'A}ngel and Pandey, Piyush and Pappas, Georgios and
              Pembroke, J Tony and Roop, Martin and Ruiz-Villalonos, Nazaret
              and Ryan, Michael P and Salcedo, Suzana P and
              Salvador-Besc{\'o}s, Miriam and Sangari, F{\'e}lix J and de Lima
              Santos, Renato and Seimenis, Aristarchos and Splitter, Gary and
              Su{\'a}rez-Esquivel, Marcela and Tabbaa, Darem and Trangoni,
              Marcos David and Tsolis, Renee M and Vizca{\'\i}no, Nieves and
              Wareth, Gamal and Welburn, Susan C and Whatmore, Adrian and
              Z{\'u}{\~n}iga-Ripa, Amaia and Moriy{\'o}n, Ignacio",
  abstract = "Bacteria of the genus Brucella are facultative intracellular
              parasites that cause brucellosis, a severe animal and human
              disease. Recently, a group of taxonomists merged the brucellae
              with the primarily free-living, phylogenetically related
              Ochrobactrum spp. in the genus Brucella. This change, founded
              only on global genomic analysis and the fortuitous isolation of
              some opportunistic Ochrobactrum spp. from medically compromised
              patients, has been automatically included in culture collections
              and databases. We argue that clinical and environmental
              microbiologists should not accept this nomenclature, and we
              advise against its use because (i) it was presented without
              in-depth phylogenetic analyses and did not consider alternative
              taxonomic solutions; (ii) it was launched without the input of
              experts in brucellosis or Ochrobactrum; (iii) it applies a
              non-consensus genus concept that disregards taxonomically
              relevant differences in structure, physiology, population
              structure, core-pangenome assemblies, genome structure, genomic
              traits, clinical features, treatment, prevention, diagnosis,
              genus description rules, and, above all, pathogenicity; and (iv)
              placing these two bacterial groups in the same genus creates
              risks for veterinarians, medical doctors, clinical laboratories,
              health authorities, and legislators who deal with brucellosis, a
              disease that is particularly relevant in low- and middle-income
              countries. Based on all this information, we urge
              microbiologists, bacterial collections, genomic databases,
              journals, and public health boards to keep the Brucella and
              Ochrobactrum genera separate to avoid further bewilderment and
              harm.",
  journal  = "J. Clin. Microbiol.",
  volume   =  61,
  number   =  8,
  pages    = "e0043823",
  month    =  aug,
  year     =  2023,
  keywords = "Brucella; Ochrobactrum",
  language = "en"
}

@ARTICLE{Moreno2022-ha,
  title    = "Pathogenicity and its implications in taxonomy: The Brucella and
              Ochrobactrum case",
  author   = "Moreno, Edgardo and Blasco, Jos{\'e} Mar{\'\i}a and Letesson,
              Jean Jacques and Gorvel, Jean Pierre and Moriy{\'o}n, Ignacio",
  abstract = "The intracellular pathogens of the genus Brucella are
              phylogenetically close to Ochrobactrum, a diverse group of
              free-living bacteria with a few species occasionally infecting
              medically compromised patients. A group of taxonomists recently
              included all Ochrobactrum organisms in the genus Brucella based
              on global genome analyses and alleged equivalences with genera
              such as Mycobacterium. Here, we demonstrate that such
              equivalencies are incorrect because they overlook the
              complexities of pathogenicity. By summarizing Brucella and
              Ochrobactrum divergences in lifestyle, structure, physiology,
              population, closed versus open pangenomes, genomic traits, and
              pathogenicity, we show that when they are adequately understood,
              they are highly relevant in taxonomy and not unidimensional
              quantitative characters. Thus, the Ochrobactrum and Brucella
              differences are not limited to their assignments to different
              ``risk-groups'', a biologically (and hence, taxonomically)
              oversimplified description that, moreover, does not support
              ignoring the nomen periculosum rule, as proposed. Since the
              epidemiology, prophylaxis, diagnosis, and treatment are
              thoroughly unrelated, merging free-living Ochrobactrum organisms
              with highly pathogenic Brucella organisms brings evident risks
              for veterinarians, medical doctors, and public health authorities
              who confront brucellosis, a significant zoonosis worldwide.
              Therefore, from taxonomical and practical standpoints, the
              Brucella and Ochrobactrum genera must be maintained apart.
              Consequently, we urge researchers, culture collections, and
              databases to keep their canonical nomenclature.",
  journal  = "Pathogens",
  volume   =  11,
  number   =  3,
  month    =  mar,
  year     =  2022,
  keywords = "Brucella; Ochrobactrum; brucellosis; core genome; genus;
              pangenome; species",
  language = "en"
}

@ARTICLE{Bosilkovski2021-wt,
  title     = "The current therapeutical strategies in human brucellosis",
  author    = "Bosilkovski, Mile and Keramat, Fariba and Arapovi{\'c}, Jurica",
  abstract  = "Prompt and adequate treatment of human brucellosis continues to
               be the most important strategy in its management, as eradication
               of animal brucellosis is not possible so far, and there is no
               adequate vaccine for humans. The goal of antibrucellar treatment
               is to alleviate and shorten the symptomatic period and reduce
               complications, relapses, and chronicity. Contemporary trends in
               the treatment of human brucellosis are postulated on the ability
               of Brucellae to persist in host macrophages through the
               inhibition of phagolysosome fusion and to survive for prolonged
               periods intracellularly without restricting basic cellular
               functions. As a result of this and despite satisfactory
               antibiotic treatment, relapses and therapeutical failures are
               inevitable to a certain degree. The current principles for the
               treatment of brucellosis advocate for a long enough treatment
               duration combined with antimicrobial regimens that possess
               activity in the intracellular acidic environment. In the future,
               other antimicrobial agents, immunomodulation, decrease in the
               intracellular acidic environment, or development of agents that
               would act on well-defined molecular bacterial targets, might be
               incorporated to improve the therapeutical effects.",
  journal   = "Infection",
  publisher = "Springer Science and Business Media LLC",
  volume    =  49,
  number    =  5,
  pages     = "823--832",
  month     =  oct,
  year      =  2021,
  keywords  = "Brucellosis; Outcome; Relapse; Treatment",
  copyright = "https://www.springernature.com/gp/researchers/text-and-data-mining",
  language  = "en"
}

@ARTICLE{Hagiya2013-mv,
  title     = "Clinical characteristics of Ochrobactrum anthropi bacteremia",
  author    = "Hagiya, Hideharu and Ohnishi, Kouhei and Maki, Miyako and
               Watanabe, Naoto and Murase, Tomoko",
  abstract  = "The clinical picture of Ochrobactrum anthropi infection is not
               well described because the infection is rare in humans and
               identification of the pathogen is difficult. We present a case
               of O. anthropi bacteremia that was initially misidentified as
               Ralstonia paucula and later identified by 16S rRNA sequencing
               and recA analysis.",
  journal   = "J. Clin. Microbiol.",
  publisher = "American Society for Microbiology",
  volume    =  51,
  number    =  4,
  pages     = "1330--1333",
  month     =  apr,
  year      =  2013,
  language  = "en"
}

@ARTICLE{Franco2007-lj,
  title     = "Human brucellosis",
  author    = "Franco, Mar{\'\i}a P{\'\i}a and Mulder, Maximilian and Gilman,
               Robert H and Smits, Henk L",
  abstract  = "Human brucellosis still presents scientists and clinicians with
               several challenges, such as the understanding of pathogenic
               mechanisms of Brucella spp, the identification of markers for
               disease severity, progression, and treatment response, and the
               development of improved treatment regimens. Molecular studies
               have shed new light on the pathogenesis of Brucella spp, and new
               technologies have permitted the development of diagnostic tools
               that will be useful in developing countries, where brucellosis
               is still a very common but often neglected disease. However,
               further studies are needed to establish optimum treatment
               regimens and local and international control programmes. This
               Review summarises current knowledge of the pathogenic
               mechanisms, new diagnostic advances, therapeutic options, and
               the situation of developing countries in regard to human
               brucellosis.",
  journal   = "Lancet Infect. Dis.",
  publisher = "Elsevier BV",
  volume    =  7,
  number    =  12,
  pages     = "775--786",
  month     =  dec,
  year      =  2007,
  language  = "en"
}

@ARTICLE{Woese1990-mo,
  title     = "Towards a natural system of organisms: proposal for the domains
               Archaea, Bacteria, and Eucarya",
  author    = "Woese, C R and Kandler, O and Wheelis, M L",
  abstract  = "Molecular structures and sequences are generally more revealing
               of evolutionary relationships than are classical phenotypes
               (particularly so among microorganisms). Consequently, the basis
               for the definition of taxa has progressively shifted from the
               organismal to the cellular to the molecular level. Molecular
               comparisons show that life on this planet divides into three
               primary groupings, commonly known as the eubacteria, the
               archaebacteria, and the eukaryotes. The three are very
               dissimilar, the differences that separate them being of a more
               profound nature than the differences that separate typical
               kingdoms, such as animals and plants. Unfortunately, neither of
               the conventionally accepted views of the natural relationships
               among living systems--i.e., the five-kingdom taxonomy or the
               eukaryote-prokaryote dichotomy--reflects this primary tripartite
               division of the living world. To remedy this situation we
               propose that a formal system of organisms be established in
               which above the level of kingdom there exists a new taxon called
               a ``domain.'' Life on this planet would then be seen as
               comprising three domains, the Bacteria, the Archaea, and the
               Eucarya, each containing two or more kingdoms. (The Eucarya, for
               example, contain Animalia, Plantae, Fungi, and a number of
               others yet to be defined). Although taxonomic structure within
               the Bacteria and Eucarya is not treated herein, Archaea is
               formally subdivided into the two kingdoms Euryarchaeota
               (encompassing the methanogens and their phenotypically diverse
               relatives) and Crenarchaeota (comprising the relatively tight
               clustering of extremely thermophilic archaebacteria, whose
               general phenotype appears to resemble most the ancestral
               phenotype of the Archaea.",
  journal   = "Proc. Natl. Acad. Sci. U. S. A.",
  publisher = "Proceedings of the National Academy of Sciences",
  volume    =  87,
  number    =  12,
  pages     = "4576--4579",
  month     =  jun,
  year      =  1990,
  language  = "en"
}

@ARTICLE{Barth2023-am,
  title     = "Rapid bacterial identification by {MALDI-TOF} {MS} directly from
               blood cultures and rapid susceptibility testing: A simple
               approach to reduce the turnaround time of blood cultures",
  author    = "Barth, Patricia Orlandi and Roesch, Eliane Wurdig and Lutz,
               Larissa and de Souza, {\^A}ndrea Celestino and Goldani, Luciano
               Zubaran and Pereira, Dariane Castro",
  abstract  = "Antimicrobial treatment of patients with bloodstream infections
               (BSI) is time-sensitive. In an era of increasing antimicrobial
               resistance, rapid detection and identification of bacteria with
               antimicrobial susceptibility are critical for targeted therapy
               early in the disease course. This study describes the
               performance of a rapid method for identifying and testing
               antimicrobial susceptibility of Gram-negative bacteria performed
               directly from blood culture bottles in a routine microbiology
               laboratory. A total of 284, 120, and 24 samples were analyzed by
               rapid identification (Rid), rapid susceptibility testing (RAST),
               and rapid broth microdilution for polymyxin B (rMIC),
               respectively, and compared with standard methods. Our protocol
               was able to identify 93\% of isolates at the species level using
               matrix-assisted laser desorption/ionization time-of-flight mass
               spectrometry (MALDI-TOF MS). We obtained 100\% agreement for
               RAST compared to the standard method and 96\% agreement for
               rMIC. Our protocol has proven to be an excellent tool for rapid
               identification of Gram-negative bacilli causing BSIs. It can
               also be used in microbiology laboratory routine along with RAST
               and faster polymyxin microdilution, especially for
               carbapenemase-producing bacteria, allowing for rapid, simple,
               accurate, and cost-effective diagnosis.",
  journal   = "Braz. J. Infect. Dis.",
  publisher = "Elsevier BV",
  volume    =  27,
  number    =  1,
  pages     = "102721",
  month     =  jan,
  year      =  2023,
  keywords  = "Blood cultures; MALDI-TOF; Polymyxin; RAST; Rapid
               identification; Sepsis",
  copyright = "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  language  = "en"
}

@ARTICLE{Johnson2019-rb,
  title     = "Evaluation of {16S} {rRNA} gene sequencing for species and
               strain-level microbiome analysis",
  author    = "Johnson, Jethro S and Spakowicz, Daniel J and Hong, Bo-Young and
               Petersen, Lauren M and Demkowicz, Patrick and Chen, Lei and
               Leopold, Shana R and Hanson, Blake M and Agresta, Hanako O and
               Gerstein, Mark and Sodergren, Erica and Weinstock, George M",
  abstract  = "The 16S rRNA gene has been a mainstay of sequence-based
               bacterial analysis for decades. However, high-throughput
               sequencing of the full gene has only recently become a realistic
               prospect. Here, we use in silico and sequence-based experiments
               to critically re-evaluate the potential of the 16S gene to
               provide taxonomic resolution at species and strain level. We
               demonstrate that targeting of 16S variable regions with
               short-read sequencing platforms cannot achieve the taxonomic
               resolution afforded by sequencing the entire (~1500 bp) gene. We
               further demonstrate that full-length sequencing platforms are
               sufficiently accurate to resolve subtle nucleotide substitutions
               (but not insertions/deletions) that exist between intragenomic
               copies of the 16S gene. In consequence, we argue that modern
               analysis approaches must necessarily account for intragenomic
               variation between 16S gene copies. In particular, we demonstrate
               that appropriate treatment of full-length 16S intragenomic copy
               variants has the potential to provide taxonomic resolution of
               bacterial communities at species and strain level.",
  journal   = "Nat. Commun.",
  publisher = "Springer Science and Business Media LLC",
  volume    =  10,
  number    =  1,
  pages     = "5029",
  month     =  nov,
  year      =  2019,
  copyright = "https://creativecommons.org/licenses/by/4.0",
  language  = "en"
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Edgar2018-qb,
  title     = "Taxonomy annotation and guide tree errors in {16S} {rRNA}
               databases",
  author    = "Edgar, Robert",
  abstract  = "Sequencing of the 16S ribosomal RNA (rRNA) gene is widely used
               to survey microbial communities. Specialized 16S rRNA databases
               have been developed to support this approach including
               Greengenes, RDP and SILVA. Most taxonomy annotations in these
               databases are predictions from sequence rather than
               authoritative assignments based on studies of type strains or
               isolates. In this work, I investigated the taxonomy annotations
               and guide trees provided by these databases. Using a blinded
               test, I estimated that the annotation error rate of the RDP
               database is ∼10\%. The branching orders of the Greengenes and
               SILVA guide trees were found to disagree at comparable rates
               with each other and with taxonomy annotations according to the
               training set (authoritative reference) provided by RDP,
               indicating that the trees have comparable quality. Pervasive
               conflicts between tree branching order and type strain
               taxonomies strongly suggest that the guide trees are unreliable
               guides to phylogeny. I found 249,490 identical sequences with
               conflicting annotations in SILVA v128 and Greengenes v13.5 at
               ranks up to phylum (7,804 conflicts), indicating that the
               annotation error rate in these databases is ∼17\%.",
  journal   = "PeerJ",
  publisher = "PeerJ",
  volume    =  6,
  number    = "e5030",
  pages     = "e5030",
  month     =  jun,
  year      =  2018
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Edgar2018-qi,
  title     = "Accuracy of taxonomy prediction for {16S} {rRNA} and fungal
               {ITS} sequences",
  author    = "Edgar, Robert C",
  abstract  = "Prediction of taxonomy for marker gene sequences such as 16S
               ribosomal RNA (rRNA) is a fundamental task in microbiology. Most
               experimentally observed sequences are diverged from reference
               sequences of authoritatively named organisms, creating a
               challenge for prediction methods. I assessed the accuracy of
               several algorithms using cross-validation by identity, a new
               benchmark strategy which explicitly models the variation in
               distances between query sequences and the closest entry in a
               reference database. When the accuracy of genus predictions was
               averaged over a representative range of identities with the
               reference database (100\%, 99\%, 97\%, 95\% and 90\%), all
               tested methods had $\leq$50\% accuracy on the currently-popular
               V4 region of 16S rRNA. Accuracy was found to fall rapidly with
               identity; for example, better methods were found to have V4
               genus prediction accuracy of ∼100\% at 100\% identity but ∼50\%
               at 97\% identity. The relationship between identity and taxonomy
               was quantified as the probability that a rank is the lowest
               shared by a pair of sequences with a given pair-wise identity.
               With the V4 region, 95\% identity was found to be a twilight
               zone where taxonomy is highly ambiguous because the
               probabilities that the lowest shared rank between pairs of
               sequences is genus, family, order or class are approximately
               equal.",
  journal   = "PeerJ",
  publisher = "PeerJ",
  volume    =  6,
  number    = "e4652",
  pages     = "e4652",
  month     =  apr,
  year      =  2018
}

% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Edgar2018-cm,
  title     = "Updating the 97\% identity threshold for {16S} ribosomal {RNA}
               {OTUs}",
  author    = "Edgar, Robert C",
  abstract  = "Abstract Motivation The 16S ribosomal RNA (rRNA) gene is widely
               used to survey microbial communities. Sequences are often
               clustered into Operational Taxonomic Units (OTUs) as proxies for
               species. The canonical clustering threshold is 97\% identity,
               which was proposed in 1994 when few 16S rRNA sequences were
               available, motivating a reassessment on current data. Results
               Using a large set of high-quality 16S rRNA sequences from
               finished genomes, I assessed the correspondence of OTUs to
               species for five representative clustering algorithms using four
               accuracy metrics. All algorithms had comparable accuracy when
               tuned to a given metric. Optimal identity thresholds were ∼99\%
               for full-length sequences and ∼100\% for the V4 hypervariable
               region. Availability and implementation Reference sequences and
               source code are provided in the Supplementary Material.
               Supplementary information Supplementary data are available at
               Bioinformatics online.",
  journal   = "Bioinformatics",
  publisher = "Oxford University Press (OUP)",
  volume    =  34,
  number    =  14,
  pages     = "2371--2375",
  month     =  jul,
  year      =  2018,
  copyright = "https://academic.oup.com/journals/pages/about\_us/legal/notices",
  language  = "en"
}

@ARTICLE{Maiden2013-jh,
  title     = "{MLST} revisited: the gene-by-gene approach to bacterial
               genomics",
  author    = "Maiden, Martin C J and Jansen van Rensburg, Melissa J and Bray,
               James E and Earle, Sarah G and Ford, Suzanne A and Jolley, Keith
               A and McCarthy, Noel D",
  abstract  = "Multilocus sequence typing (MLST) was proposed in 1998 as a
               portable sequence-based method for identifying clonal
               relationships among bacteria. Today, in the whole-genome era of
               microbiology, the need for systematic, standardized descriptions
               of bacterial genotypic variation remains a priority. Here, to
               meet this need, we draw on the successes of MLST and 16S rRNA
               gene sequencing to propose a hierarchical gene-by-gene approach
               that reflects functional and evolutionary relationships and
               catalogues bacteria 'from domain to strain'. Our gene-based
               typing approach using online platforms such as the Bacterial
               Isolate Genome Sequence Database (BIGSdb) allows the scalable
               organization and analysis of whole-genome sequence data.",
  journal   = "Nat. Rev. Microbiol.",
  publisher = "Springer Science and Business Media LLC",
  volume    =  11,
  number    =  10,
  pages     = "728--736",
  month     =  oct,
  year      =  2013,
  language  = "en"
}

@INPROCEEDINGS{Mazloom2022-uv,
  title      = "{LINgroups} as a principled approach to compare and integrate
                multiple bacterial taxonomies",
  booktitle  = "Proceedings of the 13th {ACM} International Conference on
                Bioinformatics, Computational Biology and Health Informatics",
  author     = "Mazloom, Reza and Pritchard, Leighton and Brown, C Titus and
                Vinatzer, Boris A and Heath, Lenwood S",
  publisher  = "ACM",
  month      =  aug,
  year       =  2022,
  address    = "New York, NY, USA",
  copyright  = "http://www.acm.org/publications/policies/copyright\_policy\#Background",
  conference = "BCB '22: 13th ACM International Conference on Bioinformatics,
                Computational Biology and Health Informatics",
  location   = "Northbrook Illinois"
}

@ARTICLE{Tian2021-xc,
  title     = "{LINflow}: a computational pipeline that combines an
               alignment-free with an alignment-based method to accelerate
               generation of similarity matrices for prokaryotic genomes",
  author    = "Tian, Long and Mazloom, Reza and Heath, Lenwood S and Vinatzer,
               Boris A",
  abstract  = "BACKGROUND: Computing genomic similarity between strains is a
               prerequisite for genome-based prokaryotic classification and
               identification. Genomic similarity was first computed as Average
               Nucleotide Identity (ANI) values based on the alignment of
               genomic fragments. Since this is computationally expensive,
               faster and computationally cheaper alignment-free methods have
               been developed to estimate ANI. However, these methods do not
               reach the level of accuracy of alignment-based methods. METHODS:
               Here we introduce LINflow, a computational pipeline that infers
               pairwise genomic similarity in a set of genomes. LINflow takes
               advantage of the speed of the alignment-free sourmash tool to
               identify the genome in a dataset that is most similar to a query
               genome and the precision of the alignment-based pyani software
               to precisely compute ANI between the query genome and the most
               similar genome identified by sourmash. This is repeated for each
               new genome that is added to a dataset. The sequentially computed
               ANI values are stored as Life Identification Numbers (LINs),
               which are then used to infer all other pairwise ANI values in
               the set. We tested LINflow on four sets, 484 genomes in total,
               and compared the needed time and the generated similarity
               matrices with other tools. RESULTS: LINflow is up to 150 times
               faster than pyani and pairwise ANI values generated by LINflow
               are highly correlated with those computed by pyani. However,
               because LINflow infers most pairwise ANI values instead of
               computing them directly, ANI values occasionally depart from the
               ANI values computed by pyani. In conclusion, LINflow is a fast
               and memory-efficient pipeline to infer similarity among a large
               set of prokaryotic genomes. Its ability to quickly add new
               genome sequences to an already computed similarity matrix makes
               LINflow particularly useful for projects when new genome
               sequences need to be regularly added to an existing dataset.",
  journal   = "PeerJ",
  publisher = "PeerJ",
  volume    =  9,
  number    = "e10906",
  pages     = "e10906",
  month     =  mar,
  year      =  2021,
  keywords  = "Average nucleotide identity; Comparative genomics; Genome-based
               taxonomy; Genomic similarity; Phylogenomics; Prokaryotes",
  language  = "en"
}

@ARTICLE{Pritchard2022-ti,
  title     = "Could a focus on the ``why'' of taxonomy help taxonomy better
               respond to the needs of science and society?",
  author    = "Pritchard, Leighton and Brown, C Titus and Harrington, Bailey
               and Heath, Lenwood S and Pierce-Ward, N Tessa and Vinatzer,
               Boris A",
  abstract  = "Genomics has put prokaryotic rank-based taxonomy on a solid
               phylogenetic foundation. However, most taxonomic ranks were set
               long before the advent of DNA sequencing and genomics. In this
               concept paper, we thus ask the following question: should
               prokaryotic classification schemes besides the current
               phylum-to-species ranks be explored, developed, and incorporated
               into scientific discourse? Could such alternative schemes
               provide better solutions to the basic need of science and
               society for which taxonomy was developed, namely, precise and
               meaningful identification? A neutral genome-similarity based
               framework is then described that could allow alternative
               classification schemes to be explored, compared, and translated
               into each other without having to choose only one as the gold
               standard. Classification schemes could thus continue to evolve
               and be selected according to their benefits and based on how
               well they fulfill the need for prokaryotic identification.",
  journal   = "Front. Microbiol.",
  publisher = "Frontiers Media SA",
  volume    =  13,
  pages     = "887310",
  month     =  may,
  year      =  2022,
  keywords  = "genomics; identification; phylogeny; prokaryotes; species;
               taxonomic ranks; taxonomy",
  copyright = "https://creativecommons.org/licenses/by/4.0/",
  language  = "en"
}

@article{Hofer2018,
  title = {The majority is uncultured},
  volume = {16},
  ISSN = {1740-1534},
  url = {http://dx.doi.org/10.1038/s41579-018-0097-x},
  DOI = {10.1038/s41579-018-0097-x},
  number = {12},
  journal = {Nature Reviews Microbiology},
  publisher = {Springer Science and Business Media LLC},
  author = {Hofer,  Ursula},
  year = {2018},
  month = oct,
  pages = {716–717}
}

@article{Ondov2016,
  title = {Mash: fast genome and metagenome distance estimation using MinHash},
  volume = {17},
  ISSN = {1474-760X},
  url = {http://dx.doi.org/10.1186/s13059-016-0997-x},
  DOI = {10.1186/s13059-016-0997-x},
  number = {1},
  journal = {Genome Biology},
  publisher = {Springer Science and Business Media LLC},
  author = {Ondov,  Brian D. and Treangen,  Todd J. and Melsted,  Páll and Mallonee,  Adam B. and Bergman,  Nicholas H. and Koren,  Sergey and Phillippy,  Adam M.},
  year = {2016},
  month = jun 
}

@ARTICLE{Henz2005-th,
  title     = "Whole-genome prokaryotic phylogeny",
  author    = "Henz, Stefan R and Huson, Daniel H and Auch, Alexander F and
               Nieselt-Struwe, Kay and Schuster, Stephan C",
  abstract  = "Current understanding of the phylogeny of prokaryotes is based
               on the comparison of the highly conserved small ssu-rRNA subunit
               and similar regions. Although such molecules have proved to be
               very useful phylogenetic markers, mutational saturation is a
               problem, due to their restricted lengths. Now, a growing number
               of complete prokaryotic genomes are available. This paper
               addresses the problem of determining a prokaryotic phylogeny
               utilizing the comparison of complete genomes. We introduce a new
               strategy, GBDP, 'genome blast distance phylogeny', and show that
               different variants of this approach robustly produce phylogenies
               that are biologically sound, when applied to 91 prokaryotic
               genomes. In this approach, first Blast is used to compare
               genomes, then a distance matrix is computed, and finally a tree-
               or network-reconstruction method such as UPGMA,
               Neighbor-Joining, BioNJ or Neighbor-Net is applied.",
  journal   = "Bioinformatics",
  publisher = "Oxford University Press (OUP)",
  volume    =  21,
  number    =  10,
  pages     = "2329--2335",
  month     =  may,
  year      =  2005,
  language  = "en"
}

@ARTICLE{Meier-Kolthoff2013-ps,
  title     = "Genome sequence-based species delimitation with confidence
               intervals and improved distance functions",
  author    = "Meier-Kolthoff, Jan P and Auch, Alexander F and Klenk,
               Hans-Peter and G{\"o}ker, Markus",
  abstract  = "BACKGROUND: For the last 25 years species delimitation in
               prokaryotes (Archaea and Bacteria) was to a large extent based
               on DNA-DNA hybridization (DDH), a tedious lab procedure designed
               in the early 1970s that served its purpose astonishingly well in
               the absence of deciphered genome sequences. With the rapid
               progress in genome sequencing time has come to directly use the
               now available and easy to generate genome sequences for
               delimitation of species. GBDP (Genome Blast Distance Phylogeny)
               infers genome-to-genome distances between pairs of entirely or
               partially sequenced genomes, a digital, highly reliable
               estimator for the relatedness of genomes. Its application as an
               in-silico replacement for DDH was recently introduced. The main
               challenge in the implementation of such an application is to
               produce digital DDH values that must mimic the wet-lab DDH
               values as close as possible to ensure consistency in the
               Prokaryotic species concept. RESULTS: Correlation and regression
               analyses were used to determine the best-performing methods and
               the most influential parameters. GBDP was further enriched with
               a set of new features such as confidence intervals for
               intergenomic distances obtained via resampling or via the
               statistical models for DDH prediction and an additional family
               of distance functions. As in previous analyses, GBDP obtained
               the highest agreement with wet-lab DDH among all tested methods,
               but improved models led to a further increase in the accuracy of
               DDH prediction. Confidence intervals yielded stable results when
               inferred from the statistical models, whereas those obtained via
               resampling showed marked differences between the underlying
               distance functions. CONCLUSIONS: Despite the high accuracy of
               GBDP-based DDH prediction, inferences from limited empirical
               data are always associated with a certain degree of uncertainty.
               It is thus crucial to enrich in-silico DDH replacements with
               confidence-interval estimation, enabling the user to
               statistically evaluate the outcomes. Such methodological
               advancements, easily accessible through the web service at
               http://ggdc.dsmz.de, are crucial steps towards a consistent and
               truly genome sequence-based classification of microorganisms.",
  journal   = "BMC Bioinformatics",
  publisher = "Springer Science and Business Media LLC",
  volume    =  14,
  number    =  1,
  pages     = "60",
  month     =  feb,
  year      =  2013,
  language  = "en"
}

@ARTICLE{Tindall1999-qe,
  title     = "Misunderstanding the Bacteriological Code",
  author    = "Tindall, B J",
  abstract  = "The Bacteriological Code contains Principles and Rules governing
               the naming of prokaryotic taxa. However, interpretation of the
               Code is not always easy, nor is the dynamic link between the
               names of taxa and a particular taxonomic opinion always fully
               appreciated.",
  journal   = "Int. J. Syst. Bacteriol.",
  publisher = "Microbiology Society",
  volume    = "49 Pt 3",
  number    =  3,
  pages     = "1313--1316",
  month     =  jul,
  year      =  1999,
  language  = "en"
}