%% This BibTeX bibliography file was created using BibDesk. %% https://bibdesk.sourceforge.io/ %% Created for Eric Coissac at 2026-04-18 08:19:36 +0200 %% Saved with string encoding Unicode (UTF-8) @article{Zheng2020-ji, abstract = {MOTIVATION: Minimizers are methods to sample k-mers from a string, with the guarantee that similar set of k-mers will be chosen on similar strings. It is parameterized by the k-mer length k, a window length w and an order on the k-mers. Minimizers are used in a large number of softwares and pipelines to improve computation efficiency and decrease memory usage. Despite the method's popularity, many theoretical questions regarding its performance remain open. The core metric for measuring performance of a minimizer is the density, which measures the sparsity of sampled k-mers. The theoretical optimal density for a minimizer is 1/w, provably not achievable in general. For given k and w, little is known about asymptotically optimal minimizers, that is minimizers with density O(1/w). RESULTS: We derive a necessary and sufficient condition for existence of asymptotically optimal minimizers. We also provide a randomized algorithm, called the Miniception, to design minimizers with the best theoretical guarantee to date on density in practical scenarios. Constructing and using the Miniception is as easy as constructing and using a random minimizer, which allows the design of efficient minimizers that scale to the values of k and w used in current bioinformatics software programs. AVAILABILITY AND IMPLEMENTATION: Reference implementation of the Miniception and the codes for analysis can be found at https://github.com/kingsford-group/miniception. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.}, author = {Zheng, Hongyu and Kingsford, Carl and Mar{\c c}ais, Guillaume}, doi = {10.1093/bioinformatics/btaa472}, issn = {1367-4803,1367-4811}, journal = {Bioinformatics (Oxford, England)}, language = {en}, month = jul, number = {Suppl_1}, pages = {i119--i127}, pmc = {PMC8248892}, pmid = 32657376, publisher = {Oxford University Press (OUP)}, title = {Improved design and analysis of practical minimizers}, url = {http://dx.doi.org/10.1093/bioinformatics/btaa472}, volume = 36, year = 2020, bdsk-url-1 = {http://dx.doi.org/10.1093/bioinformatics/btaa472}} @article{Zheng2021-cc, abstract = {MOTIVATION: Minimizers are efficient methods to sample k-mers from genomic sequences that unconditionally preserve sufficiently long matches between sequences. Well-established methods to construct efficient minimizers focus on sampling fewer k-mers on a random sequence and use universal hitting sets (sets of k-mers that appear frequently enough) to upper bound the sketch size. In contrast, the problem of sequence-specific minimizers, which is to construct efficient minimizers to sample fewer k-mers on a specific sequence such as the reference genome, is less studied. Currently, the theoretical understanding of this problem is lacking, and existing methods do not specialize well to sketch specific sequences. RESULTS: We propose the concept of polar sets, complementary to the existing idea of universal hitting sets. Polar sets are k-mer sets that are spread out enough on the reference, and provably specialize well to specific sequences. Link energy measures how well spread out a polar set is, and with it, the sketch size can be bounded from above and below in a theoretically sound way. This allows for direct optimization of sketch size. We propose efficient heuristics to construct polar sets, and via experiments on the human reference genome, show their practical superiority in designing efficient sequence-specific minimizers. AVAILABILITY AND IMPLEMENTATION: A reference implementation and code for analyses under an open-source license are at https://github.com/kingsford-group/polarset. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.}, author = {Zheng, Hongyu and Kingsford, Carl and Mar{\c c}ais, Guillaume}, doi = {10.1093/bioinformatics/btab313}, issn = {1367-4803,1367-4811}, journal = {Bioinformatics (Oxford, England)}, language = {en}, month = jul, number = {Suppl\_1}, pages = {i187--i195}, pmc = {PMC8686682}, pmid = 34252928, publisher = {Oxford University Press (OUP)}, title = {Sequence-specific minimizers via polar sets}, url = {http://dx.doi.org/10.1093/bioinformatics/btab313}, volume = 37, year = 2021, bdsk-url-1 = {http://dx.doi.org/10.1093/bioinformatics/btab313}} @article{Pan2024-hb, abstract = {MOTIVATION: The minimizer concept is a data structure for sequence sketching. The standard canonical minimizer selects a subset of k-mers from the given DNA sequence by comparing the forward and reverse k-mers in a window simultaneously according to a predefined selection scheme. It is widely employed by sequence analysis such as read mapping and assembly. k-mer density, k-mer repetitiveness (e.g. k-mer bias), and computational efficiency are three critical measurements for minimizer selection schemes. However, there exist trade-offs between kinds of minimizer variants. Generic, effective, and efficient are always the requirements for high-performance minimizer algorithms. RESULTS: We propose a simple minimizer operator as a refinement of the standard canonical minimizer. It takes only a few operations to compute. However, it can improve the k-mer repetitiveness, especially for the lexicographic order. It applies to other selection schemes of total orders (e.g. random orders). Moreover, it is computationally efficient and the density is close to that of the standard minimizer. The refined minimizer may benefit high-performance applications like binning and read mapping. AVAILABILITY AND IMPLEMENTATION: The source code of the benchmark in this work is available at the github repository https://github.com/xp3i4/mini\_benchmark.}, author = {Pan, Chenxu and Reinert, Knut}, doi = {10.1093/bioinformatics/btae045}, issn = {1367-4803,1367-4811}, journal = {Bioinformatics (Oxford, England)}, language = {en}, month = feb, number = 2, pmc = {PMC10868324}, pmid = 38269626, publisher = {Oxford University Press (OUP)}, title = {A simple refined DNA minimizer operator enables 2-fold faster computation}, url = {http://dx.doi.org/10.1093/bioinformatics/btae045}, volume = 40, year = 2024, bdsk-url-1 = {http://dx.doi.org/10.1093/bioinformatics/btae045}} @article{Kille2023-px, abstract = {MOTIVATION: The Jaccard similarity on k-mer sets has shown to be a convenient proxy for sequence identity. By avoiding expensive base-level alignments and comparing reduced sequence representations, tools such as MashMap can scale to massive numbers of pairwise comparisons while still providing useful similarity estimates. However, due to their reliance on minimizer winnowing, previous versions of MashMap were shown to be biased and inconsistent estimators of Jaccard similarity. This directly impacts downstream tools that rely on the accuracy of these estimates. RESULTS: To address this, we propose the minmer winnowing scheme, which generalizes the minimizer scheme by use of a rolling minhash with multiple sampled k-mers per window. We show both theoretically and empirically that minmers yield an unbiased estimator of local Jaccard similarity, and we implement this scheme in an updated version of MashMap. The minmer-based implementation is over 10 times faster than the minimizer-based version under the default ANI threshold, making it well-suited for large-scale comparative genomics applications. AVAILABILITY AND IMPLEMENTATION: MashMap3 is available at https://github.com/marbl/MashMap.}, author = {Kille, Bryce and Garrison, Erik and Treangen, Todd J and Phillippy, Adam M}, doi = {10.1093/bioinformatics/btad512}, issn = {1367-4803,1367-4811}, journal = {Bioinformatics (Oxford, England)}, language = {en}, month = sep, number = 9, pmc = {PMC10505501}, pmid = 37603771, publisher = {Oxford University Press (OUP)}, title = {Minmers are a generalization of minimizers that enable unbiased local Jaccard estimation}, url = {http://dx.doi.org/10.1093/bioinformatics/btad512}, volume = 39, year = 2023, bdsk-url-1 = {http://dx.doi.org/10.1093/bioinformatics/btad512}} @incollection{Golan2025-xf, address = {Cham}, author = {Golan, Shay and Shur, Arseny M}, booktitle = {Lecture Notes in Computer Science}, doi = {10.1007/978-3-031-82670-2\_25}, isbn = {9783031826696,9783031826702}, issn = {0302-9743,1611-3349}, language = {en}, pages = {347--360}, publisher = {Springer Nature Switzerland}, series = {Lecture Notes in Computer Science}, title = {Expected density of random minimizers}, url = {http://dx.doi.org/10.1007/978-3-031-82670-2_25}, year = 2025, bdsk-url-1 = {http://dx.doi.org/10.1007/978-3-031-82670-2_25}, bdsk-url-2 = {http://dx.doi.org/10.1007/978-3-031-82670-2%5C_25}} @article{Mohamadi2017-ok, abstract = {Motivation: Many bioinformatics algorithms are designed for the analysis of sequences of some uniform length, conventionally referred to as k -mers. These include de Bruijn graph assembly methods and sequence alignment tools. An efficient algorithm to enumerate the number of unique k -mers, or even better, to build a histogram of k -mer frequencies would be desirable for these tools and their downstream analysis pipelines. Among other applications, estimated frequencies can be used to predict genome sizes, measure sequencing error rates, and tune runtime parameters for analysis tools. However, calculating a k -mer histogram from large volumes of sequencing data is a challenging task. Results: Here, we present ntCard, a streaming algorithm for estimating the frequencies of k -mers in genomics datasets. At its core, ntCard uses the ntHash algorithm to efficiently compute hash values for streamed sequences. It then samples the calculated hash values to build a reduced representation multiplicity table describing the sample distribution. Finally, it uses a statistical model to reconstruct the population distribution from the sample distribution. We have compared the performance of ntCard and other cardinality estimation algorithms. We used three datasets of 480 GB, 500 GB and 2.4 TB in size, where the first two representing whole genome shotgun sequencing experiments on the human genome and the last one on the white spruce genome. Results show ntCard estimates k -mer coverage frequencies >15× faster than the state-of-the-art algorithms, using similar amount of memory, and with higher accuracy rates. Thus, our benchmarks demonstrate ntCard as a potentially enabling technology for large-scale genomics applications. Availability and Implementation: ntCard is written in C ++ and is released under the GPL license. It is freely available at https://github.com/bcgsc/ntCard. Contact: hmohamadi@bcgsc.ca or ibirol@bcgsc.ca. Supplementary information: Supplementary data are available at Bioinformatics online.}, author = {Mohamadi, Hamid and Khan, Hamza and Birol, Inanc}, date-modified = {2026-04-18 08:19:36 +0200}, doi = {10.1093/bioinformatics/btw832}, issn = {1367-4803,1367-4811}, journal = {Bioinformatics (Oxford, England)}, language = {en}, month = may, number = 9, pages = {1324--1330}, pmc = {PMC5408799}, pmid = 28453674, publisher = {Oxford University Press (OUP)}, title = {ntCard: a streaming algorithm for cardinality estimation in genomics data}, url = {http://dx.doi.org/10.1093/bioinformatics/btw832}, volume = 33, year = 2017, bdsk-url-1 = {http://dx.doi.org/10.1093/bioinformatics/btw832}} @misc{Mash-distances-doc, author = {{Marbl Lab}}, howpublished = {Mash documentation}, title = {Mash Distance}, url = {https://mash.readthedocs.io/en/latest/distances.html}, urldate = {2026-07-09}, year = 2026} @article{Fan2015-mash-formula, author = {Fan, Huan and Ives, Anthony R and Surget-Groba, Yann and Cannon, Charles H}, doi = {10.1186/s12864-015-1647-5}, journal = {BMC Genomics}, number = 1, title = {An assembly and alignment-free method of phylogeny reconstruction from next-generation sequencing data}, url = {https://doi.org/10.1186/s12864-015-1647-5}, volume = 16, year = 2015} @article{Roberts2004-rz, title = "{Reducing storage requirements for biological sequence comparison}", author = "Roberts, Michael and Hayes, Wayne and Hunt, Brian R and Mount, Stephen M and Yorke, James A", journal = "Bioinformatics (Oxford, England)", publisher = "Oxford University Press (OUP)", volume = 20, number = 18, pages = "3363--3369", abstract = "MOTIVATION: Comparison of nucleic acid and protein sequences is a fundamental tool of modern bioinformatics. A dominant method of such string matching is the 'seed-and-extend' approach, in which occurrences of short subsequences called 'seeds' are used to search for potentially longer matches in a large database of sequences. Each such potential match is then checked to see if it extends beyond the seed. To be effective, the seed-and-extend approach needs to catalogue seeds from virtually every substring in the database of search strings. Projects such as mammalian genome assemblies and large-scale protein matching, however, have such large sequence databases that the resulting list of seeds cannot be stored in RAM on a single computer. This significantly slows the matching process. RESULTS: We present a simple and elegant method in which only a small fraction of seeds, called 'minimizers', needs to be stored. Using minimizers can speed up string-matching computations by a large factor while missing only a small fraction of the matches found using all seeds.", month = dec, year = 2004, url = "https://dx.doi.org/10.1093/bioinformatics/bth408", doi = "10.1093/bioinformatics/bth408", pmid = 15256412, issn = "1367-4803,1367-4811", language = "en" } @INPROCEEDINGS{Steele2014-cz, title = "{Fast splittable pseudorandom number generators}", author = "Steele, Jr, Guy L and Lea, Doug and Flood, Christine H", booktitle = "{Proceedings of the 2014 ACM International Conference on Object Oriented Programming Systems Languages \& Applications}", publisher = "ACM", address = "New York, NY, USA", abstract = "We describe a new algorithm SplitMix for an object-oriented and splittable pseudorandom number generator (PRNG) that is quite fast: 9 64-bit arithmetic/logical operations per 64 bits generated. A conventional linear PRNG object provides a generate method that returns one pseudorandom value and updates the state of the PRNG, but a splittable PRNG object also has a second operation, split, that replaces the original PRNG object with two (seemingly) independent PRNG objects, by creating and returning a new such object and updating the state of the original object. Splittable PRNG objects make it easy to organize the use of pseudorandom numbers in multithreaded programs structured using fork-join parallelism. No locking or synchronization is required (other than the usual memory fence immediately after object creation). Because the generate method has no loops or conditionals, it is suitable for SIMD or GPU implementation. We derive SplitMix from the DotMix algorithm of Leiserson, Schardl, and Sukha by making a series of program transformations and engineering improvements. The end result is an object-oriented version of the purely functional API used in the Haskell library for over a decade, but SplitMix is faster and produces pseudorandom sequences of higher quality; it is also far superior in quality and speed to java.util.Random, and has been included in Java JDK8 as the class java.util.SplittableRandom. We have tested the pseudorandom sequences produced by SplitMix using two standard statistical test suites (DieHarder and TestU01) and they appear to be adequate for ``everyday'' use, such as in Monte Carlo algorithms and randomized data structures where speed is important.", month = oct, year = 2014, url = "http://dx.doi.org/10.1145/2660193.2660195", doi = "10.1145/2660193.2660195", isbn = 9781450325851 } @online{Stafford2011, author = {Stafford, David}, title = {Better Bit Mixing - Improving on MurmurHash3's 64-bit Finalizer}, date = {2011-09-28}, url = {https://zimbry.blogspot.com/2011/09/better-bit-mixing-improving-on.html}, urldate = {2026-09-12} } @ARTICLE{Hamming1950-cw, title = "{Error detecting and error correcting codes}", author = "Hamming, R W", journal = "The Bell System Technical Journal", publisher = "Institute of Electrical and Electronics Engineers (IEEE)", volume = 29, number = 2, pages = "147--160", abstract = "The author was led to the study given in this paper from a consideration of large scale computing machines in which a large number of operations must be performed without a single error in the end result. This problem of “doing things right” on a large scale is not essentially new; in a telephone central office, for example, a very large number of operations are performed while the errors leading to wrong numbers are kept well under control, though they have not been completely eliminated. This has been achieved, in part, through the use of self-checking circuits. The occasional failure that escapes routine checking is still detected by the customer and will, if it persists, result in customer complaint, while if it is transient it will produce only occasional wrong numbers. At the same time the rest of the central office functions satisfactorily. In a digital computer, on the other hand, a single failure usually means the complete failure, in the sense that if it is detected no more computing can be done until the failure is located and corrected, while if it escapes detection then it invalidates all subsequent operations of the machine. Put in other words, in a telephone central office there are a number of parallel paths which are more or less independent of each other; in a digital machine there is usually a single long path which passes through the same piece of equipment many, many times before the answer is obtained.", month = apr, year = 1950, url = "http://dx.doi.org/10.1002/j.1538-7305.1950.tb00463.x", doi = "10.1002/j.1538-7305.1950.tb00463.x", issn = "0005-8580" } @ARTICLE{Ondov2016-dq, title = "{Mash: fast genome and metagenome distance estimation using {MinHash}}", 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", journal = "Genome biology", volume = 17, number = 1, pages = 132, abstract = "Mash extends the MinHash dimensionality-reduction technique to include a pairwise mutation distance and P value significance test, enabling the efficient clustering and search of massive sequence collections. Mash reduces large sequences and sequence sets to small, representative sketches, from which global mutation distances can be rapidly estimated. We demonstrate several use cases, including the clustering of all 54,118 NCBI RefSeq genomes in 33 CPU h; real-time database search using assembled or unassembled Illumina, Pacific Biosciences, and Oxford Nanopore data; and the scalable clustering of hundreds of metagenomic samples by composition. Mash is freely released under a BSD license ( https://github.com/marbl/mash ).", month = jun, year = 2016, url = "http://dx.doi.org/10.1186/s13059-016-0997-x", keywords = "Alignment; Comparative genomics; Genomic distance; Metagenomics; Nanopore; Sequencing", doi = "10.1186/s13059-016-0997-x", pmc = "PMC4915045", pmid = 27323842, issn = "1465-6906", language = "en" } @ARTICLE{Bray1957-vv, title = "{An ordination of the upland forest communities of southern Wisconsin}", author = "Bray, J Roger and Curtis, J T", journal = "Ecological Monographs", publisher = "Wiley", volume = 27, number = 4, pages = "325--349", month = oct, year = 1957, url = "http://dx.doi.org/10.2307/1942268", doi = "10.2307/1942268", issn = "0012-9615,1557-7015", language = "en" } @ARTICLE{Gower1986-ri, title = "{Metric and Euclidean properties of dissimilarity coefficients}", author = "Gower, J C and Legendre, P", journal = "Journal of Classification", publisher = "Springer Science and Business Media LLC", volume = 3, number = 1, pages = "5--48", abstract = "We assemble here properties of certain dissimilarity coefficients and are specially concerned with their metric and Euclidean status. No attempt is made to be exhaustive as far as coefficients are concerned, but certain mathematical results that we have found useful are presented and should help establish similar properties for other coefficients. The response to different types of data is investigated, leading to guidance on the choice of an appropriate coefficient.", month = mar, year = 1986, url = "http://dx.doi.org/10.1007/bf01896809", doi = "10.1007/bf01896809", issn = "0176-4268,1432-1343", language = "en" } @ARTICLE{Legendre2001-cq, title = "{Ecologically meaningful transformations for ordination of species data}", author = "Legendre, Pierre and Gallagher, Eugene D", journal = "Oecologia", volume = 129, number = 2, pages = "271--280", abstract = "This paper examines how to obtain species biplots in unconstrained or constrained ordination without resorting to the Euclidean distance [used in principal-component analysis (PCA) and redundancy analysis (RDA)] or the chi-square distance [preserved in correspondence analysis (CA) and canonical correspondence analysis (CCA)] which are not always appropriate for the analysis of community composition data. To achieve this goal, transformations are proposed for species data tables. They allow ecologists to use ordination methods such as PCA and RDA, which are Euclidean-based, for the analysis of community data, while circumventing the problems associated with the Euclidean distance, and avoiding CA and CCA which present problems of their own in some cases. This allows the use of the original (transformed) species data in RDA carried out to test for relationships with explanatory variables (i.e. environmental variables, or factors of a multifactorial analysis-of-variance model); ecologists can then draw biplots displaying the relationships of the species to the explanatory variables. Another application allows the use of species data in other methods of multivariate data analysis which optimize a least-squares loss function; an example is K-means partitioning.", month = oct, year = 2001, url = "http://dx.doi.org/10.1007/s004420100716", keywords = "Biplot diagram; Canonical correspondence analysis; Correspondence analysis; Principal-component analysis; Redundancy analysis", doi = "10.1007/s004420100716", pmid = 28547606, issn = "0029-8549,1432-1939", language = "en" } @ARTICLE{Anderson2011-rq, title = "{Navigating the multiple meanings of β diversity: a roadmap for the practicing ecologist}", author = "Anderson, Marti J and Crist, Thomas O and Chase, Jonathan M and Vellend, Mark and Inouye, Brian D and Freestone, Amy L and Sanders, Nathan J and Cornell, Howard V and Comita, Liza S and Davies, Kendi F and Harrison, Susan P and Kraft, Nathan J B and Stegen, James C and Swenson, Nathan G", journal = "Ecology Letters", publisher = "Wiley", volume = 14, number = 1, pages = "19--28", abstract = "A recent increase in studies of β diversity has yielded a confusing array of concepts, measures and methods. Here, we provide a roadmap of the most widely used and ecologically relevant approaches for analysis through a series of mission statements. We distinguish two types of β diversity: directional turnover along a gradient vs. non-directional variation. Different measures emphasize different properties of ecological data. Such properties include the degree of emphasis on presence/absence vs. relative abundance information and the inclusion vs. exclusion of joint absences. Judicious use of multiple measures in concert can uncover the underlying nature of patterns in β diversity for a given dataset. A case study of Indonesian coral assemblages shows the utility of a multi-faceted approach. We advocate careful consideration of relevant questions, matched by appropriate analyses. The rigorous application of null models will also help to reveal potential processes driving observed patterns in β diversity.", month = jan, year = 2011, url = "http://dx.doi.org/10.1111/j.1461-0248.2010.01552.x", doi = "10.1111/j.1461-0248.2010.01552.x", pmid = 21070562, issn = "1461-023X,1461-0248", language = "en" } @ARTICLE{Jaccard1901-mx, title = "{Étude comparative de la distribution florale dans une portion des Alpes et du Jura}", author = "Jaccard, Paul", journal = "Bulletin de la Société vaudoise des sciences naturelles", publisher = "Imprimerie Corbaz \& Comp.", volume = 37, number = 142, pages = "547--579", abstract = "Schweizer Zeitschriften online - Ein Service der ETH-Bibliothek. Revues suisses en ligne - Un service de ETH Library. Swiss journals online - A service by ETH Library.", year = 1901, url = "http://dx.doi.org/10.5169/seals-266450", doi = "10.5169/seals-266450", issn = "0037-9603", language = "de" } @ARTICLE{Kosub2019-xt, title = "{A note on the triangle inequality for the Jaccard distance}", author = "Kosub, Sven", journal = "Pattern Recognition Letters", publisher = "Elsevier BV", volume = 120, pages = "36--38", month = apr, year = 2019, url = "http://dx.doi.org/10.1016/j.patrec.2018.12.007", doi = "10.1016/j.patrec.2018.12.007", issn = "0167-8655,1872-7344", language = "en" } @ARTICLE{Fleischmann2014-ed, title = {Evolution of genome size and chromosome number in the carnivorous plant genus Genlisea (Lentibulariaceae), with a new estimate of the minimum genome size in angiosperms}, author = "Fleischmann, Andreas and Michael, Todd P and Rivadavia, Fernando and Sousa, Aretuza and Wang, Wenqin and Temsch, Eva M and Greilhuber, Johann and Müller, Kai F and Heubl, Günther", journal = "Annals of Botany", publisher = "Oxford University Press (OUP)", volume = 114, number = 8, pages = "1651--1663", abstract = "BACKGROUND AND AIMS: Some species of Genlisea possess ultrasmall nuclear genomes, the smallest known among angiosperms, and some have been found to have chromosomes of diminutive size, which may explain why chromosome numbers and karyotypes are not known for the majority of species of the genus. However, other members of the genus do not possess ultrasmall genomes, nor do most taxa studied in related genera of the family or order. This study therefore examined the evolution of genome sizes and chromosome numbers in Genlisea in a phylogenetic context. The correlations of genome size with chromosome number and size, with the phylogeny of the group and with growth forms and habitats were also examined. METHODS: Nuclear genome sizes were measured from cultivated plant material for a comprehensive sampling of taxa, including nearly half of all species of Genlisea and representing all major lineages. Flow cytometric measurements were conducted in parallel in two laboratories in order to compare the consistency of different methods and controls. Chromosome counts were performed for the majority of taxa, comparing different staining techniques for the ultrasmall chromosomes. KEY RESULTS: Genome sizes of 15 taxa of Genlisea are presented and interpreted in a phylogenetic context. A high degree of congruence was found between genome size distribution and the major phylogenetic lineages. Ultrasmall genomes with 1C values of <100 Mbp were almost exclusively found in a derived lineage of South American species. The ancestral haploid chromosome number was inferred to be n = 8. Chromosome numbers in Genlisea ranged from 2n = 2x = 16 to 2n = 4x = 32. Ascendant dysploid series (2n = 36, 38) are documented for three derived taxa. The different ploidy levels corresponded to the two subgenera, but were not directly correlated to differences in genome size; the three different karyotype ranges mirrored the different sections of the genus. The smallest known plant genomes were not found in G. margaretae, as previously reported, but in G. tuberosa (1C ≈ 61 Mbp) and some strains of G. aurea (1C ≈ 64 Mbp). CONCLUSIONS: Genlisea is an ideal candidate model organism for the understanding of genome reduction as the genus includes species with both relatively large (∼1700 Mbp) and ultrasmall (∼61 Mbp) genomes. This comparative, phylogeny-based analysis of genome sizes and karyotypes in Genlisea provides essential data for selection of suitable species for comparative whole-genome analyses, as well as for further studies on both the molecular and cytogenetic basis of genome reduction in plants.", month = dec, year = 2014, url = "http://dx.doi.org/10.1093/aob/mcu189", keywords = "Bladderwort; Genlisea; Lamiales; Lentibulariaceae; carnivorous plant; chromosome number; flow cytometry; genome miniaturization; genome size", doi = "10.1093/aob/mcu189", pmc = "PMC4649684", pmid = 25274549, issn = "0305-7364,1095-8290", language = "en" } @ARTICLE{Fernandez2024-kd, title = "A 160 Gbp fork fern genome shatters size record for eukaryotes", author = "Fernández, Pol and Amice, Rémy and Bruy, David and Christenhusz, Maarten J M and Leitch, Ilia J and Leitch, Andrew L and Pokorny, Lisa and Hidalgo, Oriane and Pellicer, Jaume", journal = "iScience", publisher = "Elsevier BV", volume = 27, number = 6, pages = 109889, abstract = "Vascular plants are exceptional among eukaryotes due to their outstanding genome size diversity which ranges ∼2,400-fold, including the largest genome so far recorded in the angiosperm Paris japonica (148.89 Gbp/1C). Despite available data showing that giant genomes are restricted across the Tree of Life, the biological limits to genome size expansion remain to be established. Here, we report the discovery of an even larger eukaryotic genome in Tmesipteris oblanceolata, a New Caledonian fork fern. At 160.45 Gbp/1C, this record-breaking genome challenges current understanding and opens new avenues to explore the evolutionary dynamics of genomic gigantism.", month = jun, year = 2024, url = "http://dx.doi.org/10.1016/j.isci.2024.109889", keywords = "Plant evolution; Plant genetics", doi = "10.1016/j.isci.2024.109889", pmc = "PMC11270024", pmid = 39055604, issn = "2589-0042", language = "en" } @ARTICLE{Fraser1995-jc, title = "The minimal gene complement of Mycoplasma genitalium", author = "Fraser, C M and Gocayne, J D and White, O and Adams, M D and Clayton, R A and Fleischmann, R D and Bult, C J and Kerlavage, A R and Sutton, G and Kelley, J M and Fritchman, R D and Weidman, J F and Small, K V and Sandusky, M and Fuhrmann, J and Nguyen, D and Utterback, T R and Saudek, D M and Phillips, C A and Merrick, J M and Tomb, J F and Dougherty, B A and Bott, K F and Hu, P C and Lucier, T S and Peterson, S N and Smith, H O and Hutchison, 3rd, C A and Venter, J C", journal = "Science (New York, N.Y.)", publisher = "American Association for the Advancement of Science (AAAS)", volume = 270, number = 5235, pages = "397--403", abstract = "The complete nucleotide sequence (580,070 base pairs) of the Mycoplasma genitalium genome, the smallest known genome of any free-living organism, has been determined by whole-genome random sequencing and assembly. A total of only 470 predicted coding regions were identified that include genes required for DNA replication, transcription and translation, DNA repair, cellular transport, and energy metabolism. Comparison of this genome to that of Haemophilus influenzae suggests that differences in genome content are reflected as profound differences in physiology and metabolic capacity between these two organisms.", month = oct, year = 1995, url = "http://dx.doi.org/10.1126/science.270.5235.397", doi = "10.1126/science.270.5235.397", pmid = 7569993, issn = "0036-8075,1095-9203", language = "en" } @ARTICLE{Schneiker2007-gs, title = "Complete genome sequence of the myxobacterium Sorangium cellulosum", author = "Schneiker, Susanne and Perlova, Olena and Kaiser, Olaf and Gerth, Klaus and Alici, Aysel and Altmeyer, Matthias O and Bartels, Daniela and Bekel, Thomas and Beyer, Stefan and Bode, Edna and Bode, Helge B and Bolten, Christoph J and Choudhuri, Jomuna V and Doss, Sabrina and Elnakady, Yasser A and Frank, Bettina and Gaigalat, Lars and Goesmann, Alexander and Groeger, Carolin and Gross, Frank and Jelsbak, Lars and Jelsbak, Lotte and Kalinowski, Jörn and Kegler, Carsten and Knauber, Tina and Konietzny, Sebastian and Kopp, Maren and Krause, Lutz and Krug, Daniel and Linke, Bukhard and Mahmud, Taifo and Martinez-Arias, Rosa and McHardy, Alice C and Merai, Michelle and Meyer, Folker and Mormann, Sascha and Muñoz-Dorado, Jose and Perez, Juana and Pradella, Silke and Rachid, Shwan and Raddatz, Günter and Rosenau, Frank and Rückert, Christian and Sasse, Florenz and Scharfe, Maren and Schuster, Stephan C and Suen, Garret and Treuner-Lange, Anke and Velicer, Gregory J and Vorhölter, Frank-Jörg and Weissman, Kira J and Welch, Roy D and Wenzel, Silke C and Whitworth, David E and Wilhelm, Susanne and Wittmann, Christoph and Blöcker, Helmut and Pühler, Alfred and Müller, Rolf", journal = "Nature Biotechnology", publisher = "Springer Science and Business Media LLC", volume = 25, number = 11, pages = "1281--1289", abstract = "The genus Sorangium synthesizes approximately half of the secondary metabolites isolated from myxobacteria, including the anti-cancer metabolite epothilone. We report the complete genome sequence of the model Sorangium strain S. cellulosum So ce56, which produces several natural products and has morphological and physiological properties typical of the genus. The circular genome, comprising 13,033,779 base pairs, is the largest bacterial genome sequenced to date. No global synteny with the genome of Myxococcus xanthus is apparent, revealing an unanticipated level of divergence between these myxobacteria. A large percentage of the genome is devoted to regulation, particularly post-translational phosphorylation, which probably supports the strain's complex, social lifestyle. This regulatory network includes the highest number of eukaryotic protein kinase-like kinases discovered in any organism. Seventeen secondary metabolite loci are encoded in the genome, as well as many enzymes with potential utility in industry.", month = nov, year = 2007, url = "http://dx.doi.org/10.1038/nbt1354", doi = "10.1038/nbt1354", pmid = 17965706, issn = "1087-0156,1546-1696", language = "en" } @incollection{Karlin1985, author = {Karlin, Samuel and Ost, Fr{\'e}d{\'e}ric}, title = {Maximal segmental match length among random sequences from a finite alphabet}, booktitle = {Proceedings of the Berkeley Conference in Honor of Jerzy Neyman and Jack Kiefer}, editor = {Le Cam, Lucien M. and Olshen, Richard A.}, volume = {1}, pages = {225--243}, year = {1985}, publisher = {Wadsworth}, address = {Monterey, CA} } @article{Karlin1988, author = {Karlin, Samuel and Ost, Fr{\'e}d{\'e}ric}, title = {Maximal length of common words among random letter sequences}, journal = {The Annals of Probability}, volume = {16}, number = {2}, pages = {535--563}, year = {1988} } @ARTICLE{Le-Cam1960-pe, title = "{An approximation theorem for the Poisson binomial distribution}", author = "Le Cam, Lucien", journal = "Pacific Journal of Mathematics", publisher = "Mathematical Sciences Publishers", volume = 10, number = 4, pages = "1181--1197", month = dec, year = 1960, url = "http://dx.doi.org/10.2140/pjm.1960.10.1181", doi = "10.2140/pjm.1960.10.1181", issn = "0030-8730,1945-5844" } @ARTICLE{Hoeffding1956-bx, title = "{On the distribution of the number of successes in independent trials}", author = "Hoeffding, Wassily", journal = "The Annals of Mathematical Statistics", publisher = "Institute of Mathematical Statistics", volume = 27, number = 3, pages = "713--721", abstract = "Let $S$ be the number of successes in $n$ independent trials, and let $p_j$ denote the probability of success in the $j$th trial, $j = 1, 2, \cdots, n$ (Poisson trials). We consider the problem of finding the maximum and the minimum of $Eg(S),$ the expected value of a given real-valued function of $S,$ when $ES = np$ is fixed. It is well known that the maximum of the variance of $S$ is attained when $p_1 = p_2 = \cdots = p_n = p.$ This can be interpreted as showing that the variability in the number of successes is highest when the successes are equally probable (Bernoulli trials). This interpretation is further supported by the following two theorems, proved in this paper. If $b$ and $c$ are two integers, $0 \leqq b \leqq np \leqq c \leqq n,$ the probability $P(b \leqq S \leqq c)$ attains its minimum if and only if $p_1 = p_2 = \cdots = p_n = p,$ unless $b = 0$ and $c = n$ (Theorem 5, a corollary of Theorem 4, which gives the maximum and the minimum of $P(S \leqq c)$). If $g$ is a strictly convex function, $Eg(S)$ attains its maximum if and only if $p_1 = p_2 = \cdots = p_n = p$ (Theorem 3). These results are obtained with the help of two theorems concerning the extrema of the expected value of an arbitrary function $g(S)$ under the condition $ES = np.$ Theorem 1 gives necessary conditions for the maximum and the minimum of $Eg(S).$ Theorem 2 gives a partial characterization of the set of points at which an extremum is attained. Corollary 2.1 states that the maximum and the minimum are attained when $p_1, p_2, \cdots, p_n$ take on, at most, three different values, only one of which is distinct from 0 and 1. Applications of Theorems 3 and 5 to problems of estimation and testing are pointed out in Section 5.", month = sep, year = 1956, url = "http://dx.doi.org/10.1214/aoms/1177728178", doi = "10.1214/aoms/1177728178", issn = "0003-4851,2168-8990", language = "en" } @ARTICLE{Gleser1975-yu, title = "{On the distribution of the number of successes in independent trials}", author = "Gleser, Leon Jay", journal = "Annals of Probability", publisher = "Institute of Mathematical Statistics", volume = 3, number = 1, pages = "182--188", abstract = "Let $S$ be the number of successes in $n$ independent Bernoulli trials, where $p_j$ is the probability of success on the $j$th trial. Let $\mathbf{p} = (p_1, p_2, \cdots, p_n)$, and for any integer $c, 0 \leqq c \leqq n$, let $H(c \mid \mathbf{p}) = P\{S \leqq c\}$. Let $\mathbf{p}^{(1)}$ be one possible choice of $\mathbf{p}$ for which $E(S) = \lambda$. For any $n \times n$ doubly stochastic matrix $\Pi$, let $\mathbf{p}^{(2)} = \mathbf{p}^{(1)}\Pi$. Then in the present paper it is shown that $H(c \mid \mathbf{p}^{(1)}) \leqq H(c \mid \mathbf{p}^{(2)})$ for $0 \leqq c \leqq \lbrack\lambda - 2\rbrack$, and $H(c \mid \mathbf{p}^{(1)}) \geqq H(c \mid \mathbf{p}^{(2)})$ for $\lbrack\lambda + 2\rbrack \leqq c \leqq n$. These results provide a refinement of inequalities for $H(c \mid \mathbf{p})$ obtained by Hoeffding [3]. Their derivation is achieved by applying consequences of the partial ordering of majorization.", month = feb, year = 1975, url = "http://dx.doi.org/10.2307/2959277", doi = "10.1214/aop/1176996461", issn = "0091-1798,2168-894X" } @ARTICLE{Karlin1997-lm, title = "{Compositional differences within and between eukaryotic genomes}", author = "Karlin, S and Mrázek, J", journal = "Proceedings of the National Academy of Sciences of the United States of America", publisher = "Proceedings of the National Academy of Sciences", volume = 94, number = 19, pages = "10227--10232", abstract = "Eukaryotic genome similarity relationships are inferred using sequence information derived from large aggregates of genomic sequences. Comparisons within and between species sample sequences are based on the profile of dinucleotide relative abundance values (The profile is ρ* XY = f * XY / f * X f * Y for all XY , where f * X denotes the frequency of the nucleotide X and f * XY denotes the frequency of the dinucleotide XY , both computed from the sequence concatenated with its inverted complement). Previous studies with respect to prokaryotes and this study document that profiles of different DNA sequence samples (sample size ≥50 kb) from the same organism are generally much more similar to each other than they are to profiles from other organisms, and that closely related organisms generally have more similar profiles than do distantly related organisms. On this basis we refer to the collection {ρ* XY } as the genome signature . This paper identifies ρ* XY extremes and compares genome signature differences for a diverse range of eukaryotic species. Interpretations on the mechanisms maintaining these profile differences center on genome-wide replication, repair, DNA structures, and context-dependent mutational biases. It is also observed that mitochondrial genome signature differences between species parallel the corresponding nuclear genome signature differences despite large differences between corresponding mitochondrial and nuclear signatures. The genome signature differences also have implications for contrasts between rodents and other mammals, and between monocot and dicot plants, as well as providing evidence for similarities among fungi and the diversity of protists.", month = sep, year = 1997, url = "http://dx.doi.org/10.1073/pnas.94.19.10227", doi = "10.1073/pnas.94.19.10227", pmc = "PMC23344", pmid = 9294192, issn = "0027-8424,1091-6490", language = "en" } @ARTICLE{Karlin1997-vm, title = "{Compositional biases of bacterial genomes and evolutionary implications}", author = "Karlin, S and Mrázek, J and Campbell, A M", journal = "Journal of Bacteriology", publisher = "American Society for Microbiology", volume = 179, number = 12, pages = "3899--3913", abstract = "We compare and contrast genome-wide compositional biases and distributions of short oligonucleotides across 15 diverse prokaryotes that have substantial genomic sequence collections. These include seven complete genomes (Escherichia coli, Haemophilus influenzae, Mycoplasma genitalium, Mycoplasma pneumoniae, Synechocystis sp. strain PCC6803, Methanococcus jannaschii, and Pyrobaculum aerophilum). A key observation concerns the constancy of the dinucleotide relative abundance profiles over multiple 50-kb disjoint contigs within the same genome. (The profile is rhoXY* = fXY*/fX*fY* for all XY, where fX* denotes the frequency of the nucleotide X and fY* denotes the frequency of the dinucleotide XY, both computed from the sequence concatenated with its inverted complementary sequence.) On the basis of this constancy, we refer to the collection [rhoXY*] as the genome signature. We establish that the differences between [rhoXY*] vectors of 50-kb sample contigs of different genomes virtually always exceed the differences between those of the same genomes. Various di- and tetranucleotide biases are identified. In particular, we find that the dinucleotide CpG=CG is underrepresented in many thermophiles (e.g., M. jannaschii, Sulfolobus sp., and M. thermoautotrophicum) but overrepresented in halobacteria. TA is broadly underrepresented in prokaryotes and eukaryotes, but normal counts appear in Sulfolobus and P. aerophilum sequences. More than for any other bacterial genome, palindromic tetranucleotides are underrepresented in H. influenzae. The M. jannaschii sequence is unprecedented in its extreme underrepresentation of CTAG tetranucleotides and in the anomalous distribution of CTAG sites around the genome. Comparative analysis of numbers of long tetranucleotide microsatellites distinguishes H. influenzae. Dinucleotide relative abundance differences between bacterial sequences are compared. For example, in these assessments of differences, the cyanobacteria Synechocystis, Synechococcus, and Anabaena do not form a coherent group and are as far from each other as general gram-negative sequences are from general gram-positive sequences. The difference of M. jannaschii from low-G+C gram-positive proteobacteria is one-half of the difference from gram-negative proteobacteria. Interpretations and hypotheses center on the role of the genome signature in highlighting similarities and dissimilarities across different classes of prokaryotic species, possible mechanisms underlying the genome signature, the form and level of genome compositional flux, the use of the genome signature as a chronometer of molecular phylogeny, and implications with respect to the three putative eubacterial, archaeal, and eukaryote domains of life and to the origin and early evolution of eukaryotes.", month = jun, year = 1997, url = "http://dx.doi.org/10.1128/jb.179.12.3899-3913.1997", doi = "10.1128/jb.179.12.3899-3913.1997", pmc = "PMC179198", pmid = 9190805, issn = "0021-9193,1098-5530", language = "en" } @ARTICLE{Karlin1995-lt, title = "{Dinucleotide relative abundance extremes: a genomic signature}", author = "Karlin, S and Burge, C", journal = "Trends in Genetics: TIG", publisher = "Elsevier BV", volume = 11, number = 7, pages = "283--290", abstract = "Early biochemical experiments established that the set of dinucleotide odds ratios or 'general design' is a remarkably stable property of the DNA of an organism, which is essentially the same in protein-coding DNA, bulk genomic DNA, and in different renaturation rate and density gradient fractions of genomic DNA in many organisms. Analysis of currently available genomic sequence data has extended these earlier results, showing that the general designs of disjoint samples of a genome are substantially more similar to each other than to those of sequences from other organisms and that closely related organisms have similar general designs. From this perspective, the set of dinucleotide odds ratio (relative abundance) values constitute a signature of each DNA genome, which can discriminate between sequences from different organisms. Dinucleotide-odds ratio values appear to reflect not only the chemistry of dinucleotide stacking energies and base-step conformational preferences, but also the species-specific properties of DNA modification, replication and repair mechanisms.", month = jul, year = 1995, url = "http://dx.doi.org/10.1016/s0168-9525(00)89076-9", doi = "10.1016/s0168-9525(00)89076-9", pmid = 7482779, issn = "0168-9525,1362-4555", language = "en" } @ARTICLE{Karlin1994-on, title = "{Heterogeneity of genomes: measures and values}", author = "Karlin, S and Ladunga, I and Blaisdell, B E", journal = "Proceedings of the National Academy of Sciences of the United States of America", publisher = "Proceedings of the National Academy of Sciences", volume = 91, number = 26, pages = "12837--12841", abstract = "Genomic homogeneity is investigated for a broad base of DNA sequences in terms of dinucleotide relative abundance distances (abbreviated delta-distances) and of oligonucleotide compositional extremes. It is shown that delta-distances between different genomic sequences in the same species are low, only about 2 or 3 times the distance found in random DNA, and are generally smaller than the between-species delta-distances. Extremes in short oligonucleotides include underrepresentation of TpA and overrepresentation of GpC in most temperate bacteriophage sequences; underrepresentation of CTAG in most eubacterial genomes; underrepresentation of GATC in most bacteriophage; CpG suppression in vertebrates, in all animal mitochondrial genomes, and in many thermophilic bacterial sequences; and overrepresentation of GpG/CpC in all animal mitochondrial sets and chloroplast genomes. Interpretations center on DNA structures (dinucleotide stacking energies, DNA curvature and superhelicity, nucleosome organization), context-dependent mutational events, methylation effects, and processes of replication and repair.", month = dec, year = 1994, url = "http://dx.doi.org/10.1073/pnas.91.26.12837", doi = "10.1073/pnas.91.26.12837", pmc = "PMC45535", pmid = 7809131, issn = "0027-8424,1091-6490", language = "en" } @ARTICLE{Bennett2013-cl, title = "{Small, smaller, smallest: the origins and evolution of ancient dual symbioses in a Phloem-feeding insect}", author = "Bennett, Gordon M and Moran, Nancy A", journal = "Genome Biology and Evolution", publisher = "Oxford University Press (OUP)", volume = 5, number = 9, pages = "1675--1688", abstract = "Many insects rely on bacterial symbionts with tiny genomes specialized for provisioning nutrients lacking in host diets. Xylem sap and phloem sap are both deficient as insect diets, but differ dramatically in nutrient content, potentially affecting symbiont genome evolution. For sap-feeding insects, sequenced symbiont genomes are available only for phloem-feeding examples from the suborder Sternorrhyncha and xylem-feeding examples from the suborder Auchenorrhyncha, confounding comparisons. We sequenced genomes of the obligate symbionts, Sulcia muelleri and Nasuia deltocephalinicola, of the phloem-feeding pest insect, Macrosteles quadrilineatus (Auchenorrhyncha: Cicadellidae). Our results reveal that Nasuia-ALF has the smallest bacterial genome yet sequenced (112 kb), and that the Sulcia-ALF genome (190 kb) is smaller than that of Sulcia in other insect lineages. Together, these symbionts retain the capability to synthesize the 10 essential amino acids, as observed for several symbiont pairs from xylem-feeding Auchenorrhyncha. Nasuia retains genes enabling synthesis of two amino acids, DNA replication, transcription, and translation. Both symbionts have lost genes underlying ATP synthesis through oxidative phosphorylation, possibly as a consequence of the enriched sugar content of phloem. Shared genomic features, including reassignment of the UGA codon from Stop to tryptophan, and phylogenetic results suggest that Nasuia-ALF is most closely related to Zinderia, the betaproteobacterial symbiont of spittlebugs. Thus, Nasuia/Zinderia and Sulcia likely represent ancient associates that have co-resided in hosts since the divergence of leafhoppers and spittlebugs >200 Ma, and possibly since the origin of the Auchenorrhyncha, >260 Ma.", month = aug, year = 2013, url = "http://dx.doi.org/10.1093/gbe/evt118", keywords = "Nasuia deltocephalinicola; Sulcia muelleri; gene loss; genome evolution; leafhopper; nutritional symbioses", doi = "10.1093/gbe/evt118", pmc = "PMC3787670", pmid = 23918810, issn = "1759-6653", language = "en" }