Files
obikmer/UserDocMD/references.bib
T
Eric Coissac e715528d34 Refactor documentation for kmer indexing and phylogenetic models
This commit updates documentation across the board, introducing definitions for kmer constraints, super-kmers, k-mer set distances, SNP models, and sampling design principles. It also clarifies the index construction pipeline and the underlying mathematical models used for genome pair calibration.
2026-10-13 08:38:49 +02:00

569 lines
29 KiB
BibTeX

%% 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"
}