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.
This commit is contained in:
1 parent
9da0876ee6
commit
e715528d34
19 files changed
+582
-712
No files matched your search
@@ -345,3 +345,224 @@
|
||||
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"
|
||||
}
|
||||
Reference in new issue
Block a user