-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathreferences.bib
223 lines (213 loc) · 10.2 KB
/
references.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
% Generated by Paperpile. Check out https://paperpile.com for more information.
% BibTeX export options can be customized via Settings -> BibTeX.
@INCOLLECTION{Nordborg2004-xy,
title = "Coalescent Theory",
booktitle = "Handbook of Statistical Genetics",
author = "Nordborg, M",
abstract = "Abstract The coalescent process is a powerful modeling tool for
population genetics. The allelic states of all homologous gene
copies in a population are determined by the genealogical and
mutational history of these copies. The coalescent approach is
based on the realization that the genealogy is usually easier to
model backward in time, and that selectively neutral mutations
can then be superimposed afterwards. A wide range of biological
phenomena can be modeled using this approach. Whereas almost all
of classical population genetics considers the future of a
population given a starting point, the coalescent considers the
present, while taking the past into account. This allows the
calculation of probabilities of sample configurations under the
stationary distribution of various population genetic models,
and makes full likelihood analysis of polymorphism data
possible. It also leads to extremely efficient computer
algorithms for generating simulated data from such
distributions, data which can then be compared with observations
as a form of exploratory data analysis.",
publisher = "John Wiley \& Sons, Ltd",
month = jul,
year = 2004,
address = "Chichester",
keywords = "intro2simulation",
isbn = "9780470022627",
doi = "10.1002/0470022620.bbc21"
}
@INCOLLECTION{Kelleher2020-zf,
title = "Coalescent Simulation with msprime",
booktitle = "Statistical Population Genomics",
author = "Kelleher, Jerome and Lohse, Konrad",
editor = "Dutheil, Julien Y",
abstract = "Coalescent simulation is a fundamental tool in modern population
genetics. The msprime library provides unprecedented scalability
in terms of both the simulations that can be performed and the
efficiency with which the results can be processed. We show how
coalescent models for population structure and demography can be
constructed using a simple Python API, as well as how we can
process the results of such simulations to efficiently calculate
statistics of interest. We illustrate msprime's flexibility by
implementing a simple (but functional) approximate Bayesian
computation inference method in just a few tens of lines of
code.",
publisher = "Springer US",
pages = "191--230",
year = 2020,
address = "New York, NY",
keywords = "intro2simulation;Paula",
isbn = "9781071601990",
doi = "10.1007/978-1-0716-0199-0\_9"
}
@ARTICLE{Rosenberg2002-ac,
title = "Genealogical trees, coalescent theory and the analysis of genetic
polymorphisms",
author = "Rosenberg, Noah A and Nordborg, Magnus",
abstract = "Improvements in genotyping technologies have led to the increased
use of genetic polymorphism for inference about population
phenomena, such as migration and selection. Such inference
presents a challenge, because polymorphism data reflect a unique,
complex, non-repeatable evolutionary history. Traditional
analysis methods do not take this into account. A stochastic
process known as the 'coalescent' presents a coherent statistical
framework for analysis of genetic polymorphisms.",
journal = "Nat. Rev. Genet.",
volume = 3,
number = 5,
pages = "380--390",
month = may,
year = 2002,
keywords = "simbook;intro2simulation;Paula",
language = "en",
issn = "1471-0056",
pmid = "11988763",
doi = "10.1038/nrg795"
}
% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Hudson1990-ff,
title = "Gene genealogies and the coalescent process",
author = "Hudson, Richard R",
abstract = "When a collection of homologous DNA sequences are compared, the
pattern of similarities between the different sequences typically
contains information about the evolutionary history of those
sequences. Under a wide variety of circumstances, sequence data
provide …",
journal = "Oxford surveys in evolutionary biology",
volume = 7,
number = 1,
pages = "44",
year = 1990,
keywords = "polygenic\_inference\_R01;simbook;intro2simulation;Paula"
}
@ARTICLE{Kelleher2016-cb,
title = "Efficient Coalescent Simulation and Genealogical Analysis for
Large Sample Sizes",
author = "Kelleher, Jerome and Etheridge, Alison M and McVean, Gilean",
abstract = "A central challenge in the analysis of genetic variation is to
provide realistic genome simulation across millions of samples.
Present day coalescent simulations do not scale well, or use
approximations that fail to capture important long-range linkage
properties. Analysing the results of simulations also presents a
substantial challenge, as current methods to store genealogies
consume a great deal of space, are slow to parse and do not take
advantage of shared structure in correlated trees. We solve these
problems by introducing sparse trees and coalescence records as
the key units of genealogical analysis. Using these tools, exact
simulation of the coalescent with recombination for
chromosome-sized regions over hundreds of thousands of samples is
possible, and substantially faster than present-day approximate
methods. We can also analyse the results orders of magnitude more
quickly than with existing methods.",
journal = "PLoS Comput. Biol.",
volume = 12,
number = 5,
pages = "e1004842",
month = may,
year = 2016,
keywords = "Optimum shift
paper;pylibseq\_manual;fwdpp\_manual;polygenic\_inference\_R01;simbook;CompSkillsBook;fwdpy11\_manual;intro2simulation;JonathanVo;Paula",
language = "en",
issn = "1553-734X, 1553-7358",
pmid = "27145223",
doi = "10.1371/journal.pcbi.1004842",
pmc = "PMC4856371"
}
@BOOK{Wakeley2008-hd,
title = "Coalescent Theory: An Introduction",
author = "Wakeley, John",
abstract = "Coalescent theory provides the foundation for molecular
population genetics and genomics. It is the conceptual framework
for studies of DNA sequence variation within species, and is the
source of essential tools for making inferences about mutation,
recombination, population structure and natural selection from
DNA sequence data.",
publisher = "W. H. Freeman",
month = jun,
year = 2008,
keywords = "Optimum shift paper;simbook;intro2simulation",
language = "en",
isbn = "9780974707754"
}
@ARTICLE{Hudson1983-lk,
title = "Properties of a Neutral Allele Model with lntragenic
Recombination",
author = "Hudson, Richard R",
journal = "Theor. Popul. Biol.",
volume = 23,
pages = "183--201",
year = 1983,
keywords = "Dec 13 import;simbook;intro2simulation",
issn = "0040-5809"
}
@ARTICLE{Kingman1982-cq,
title = "On the Genealogy of Large Populations",
author = "Kingman, J F C",
abstract = "A new Markov chain is introduced which can be used to describe
the family relationships among n individuals drawn from a
particular generation of a large haploid population. The
properties of this process can be studied, simultaneously for
all n, by coupling techniques. Recent results in neutral
mutation theory are seen as consequences of the genealogy
described by the chain.",
journal = "J. Appl. Probab.",
publisher = "Applied Probability Trust",
volume = 19,
pages = "27--43",
year = 1982,
keywords = "Dec 13 import;simbook;intro2simulation",
issn = "0021-9002",
doi = "10.2307/3213548"
}
@ARTICLE{Hudson1983-kn,
title = "Testing the {Constant-Rate} Neutral Allele Model with Protein
Sequence Data",
author = "Hudson, Richard R",
abstract = "A method of testing the constant-rate neutral allele model of
protein evolution is presented and applied to a large data set.
The method uses the same statistic, $\chi$2 LF, used by Langley
and Fitch (1973, 1974) and Fitch and Langley (1976). The
distribution of $\chi$2 LF, characterized in this study with
Monte Carlo simulations, depends on the parameter $\vartheta$
(=4Nu). The values of $\vartheta$ required to explain the
observed value of $\chi$2 LF are determined and found to be
incompatible with the low levels of heterozygosity observed at
the hemoglobin loci in humans. It is concluded that the
constant-rate neutral model is highly improbable. Other neutral
models and models involving natural selection need to be
considered.",
journal = "Evolution",
publisher = "[Society for the Study of Evolution, Wiley]",
volume = 37,
number = 1,
pages = "203--217",
year = 1983,
keywords = "Dec 13 import;simbook;intro2simulation",
issn = "0014-3820, 1558-5646",
doi = "10.2307/2408186"
}
@ARTICLE{Hudson2002-oo,
title = "Generating samples under a {Wright--Fisher} neutral model of
genetic variation",
author = "Hudson, Richard R",
journal = "Bioinformatics",
volume = 18,
pages = "337--338",
year = 2002,
keywords = "Dec 13 import;polygenic\_inference\_R01;simbook;intro2simulation"
}