bibliography.bib

@ARTICLE{Excoffier1992-pe,
  title    = "Analysis of molecular variance inferred from metric distances
              among {DNA} haplotypes: application to human mitochondrial {DNA}
              restriction data",
  author   = "Excoffier, L and Smouse, P E and Quattro, J M",
  abstract = "We present here a framework for the study of molecular variation
              within a single species. Information on DNA haplotype divergence
              is incorporated into an analysis of variance format, derived from
              a matrix of squared-distances among all pairs of haplotypes. This
              analysis of molecular variance (AMOVA) produces estimates of
              variance components and F-statistic analogs, designated here as
              phi-statistics, reflecting the correlation of haplotypic
              diversity at different levels of hierarchical subdivision. The
              method is flexible enough to accommodate several alternative
              input matrices, corresponding to different types of molecular
              data, as well as different types of evolutionary assumptions,
              without modifying the basic structure of the analysis. The
              significance of the variance components and phi-statistics is
              tested using a permutational approach, eliminating the normality
              assumption that is conventional for analysis of variance but
              inappropriate for molecular data. Application of AMOVA to human
              mitochondrial DNA haplotype data shows that population
              subdivisions are better resolved when some measure of molecular
              differences among haplotypes is introduced into the analysis. At
              the intraspecific level, however, the additional information
              provided by knowing the exact phylogenetic relations among
              haplotypes or by a nonlinear translation of restriction-site
              change into nucleotide diversity does not significantly modify
              the inferred population genetic structure. Monte Carlo studies
              show that site sampling does not fundamentally affect the
              significance of the molecular variance components. The AMOVA
              treatment is easily extended in several different directions and
              it constitutes a coherent and flexible framework for the
              statistical analysis of molecular data.",
  journal  = "Genetics",
  volume   =  131,
  number   =  2,
  pages    = "479--491",
  month    =  jun,
  year     =  1992,
  language = "en"
}


@ARTICLE{Paradis2010-ds,
  title    = "pegas: an {R} package for population genetics with an
              integrated-modular approach",
  author   = "Paradis, Emmanuel",
  abstract = "SUMMARY: pegas (Population and Evolutionary Genetics Analysis
              System) is a new package for the analysis of population genetic
              data. It is written in R and is integrated with two other
              existing R packages (ape and adegenet). pegas provides functions
              for standard population genetic methods, as well as low-level
              functions for developing new methods. The flexible and efficient
              graphical capabilities of R are used for plotting haplotype
              networks as well as for other functionalities. pegas emphasizes
              the need to further develop an integrated-modular approach for
              software dedicated to the analysis of population genetic data.
              AVAILABILITY: pegas is distributed through the Comprehensive R
              Archive Network (CRAN):
              http://cran.r-project.org/web/packages/pegas/index.html. Further
              information may be found at: http://ape.mpl.ird.fr/pegas/.",
  journal  = "Bioinformatics",
  volume   =  26,
  number   =  3,
  pages    = "419--420",
  month    =  feb,
  year     =  2010,
  language = "en"
}


@ARTICLE{Kamvar2014-iv,
  title    = "Poppr: an {R} package for genetic analysis of populations with
              clonal, partially clonal, and/or sexual reproduction",
  author   = "Kamvar, Zhian N and Tabima, Javier F and Gr{\"u}nwald, Niklaus J",
  abstract = "Many microbial, fungal, or oomcyete populations violate
              assumptions for population genetic analysis because these
              populations are clonal, admixed, partially clonal, and/or sexual.
              Furthermore, few tools exist that are specifically designed for
              analyzing data from clonal populations, making analysis difficult
              and haphazard. We developed the R package poppr providing unique
              tools for analysis of data from admixed, clonal, mixed, and/or
              sexual populations. Currently, poppr can be used for
              dominant/codominant and haploid/diploid genetic data. Data can be
              imported from several formats including GenAlEx formatted text
              files and can be analyzed on a user-defined hierarchy that
              includes unlimited levels of subpopulation structure and clone
              censoring. New functions include calculation of Bruvo's distance
              for microsatellites, batch-analysis of the index of association
              with several indices of genotypic diversity, and graphing
              including dendrograms with bootstrap support and minimum spanning
              networks. While functions for genotypic diversity and clone
              censoring are specific for clonal populations, several functions
              found in poppr are also valuable to analysis of any populations.
              A manual with documentation and examples is provided. Poppr is
              open source and major releases are available on CRAN:
              http://cran.r-project.org/package=poppr. More supporting
              documentation and tutorials can be found under 'resources' at:
              http://grunwaldlab.cgrb.oregonstate.edu/.",
  journal  = "PeerJ",
  volume   =  2,
  pages    = "e281",
  month    =  mar,
  year     =  2014,
  keywords = "Bootstrap; Bruvo's distance; Clonality; Clone correction;
              Genotypic diversity; Hierarchy; Index of association; Minimum
              spanning networks; Permutation; Population genetics",
  language = "en"
}


@ARTICLE{Alexa2006-wf,
  title    = "Improved scoring of functional groups from gene expression data
              by decorrelating {GO} graph structure",
  author   = "Alexa, Adrian and Rahnenf{\"u}hrer, J{\"o}rg and Lengauer, Thomas",
  abstract = "MOTIVATION: The result of a typical microarray experiment is a
              long list of genes with corresponding expression measurements.
              This list is only the starting point for a meaningful biological
              interpretation. Modern methods identify relevant biological
              processes or functions from gene expression data by scoring the
              statistical significance of predefined functional gene groups,
              e.g. based on Gene Ontology (GO). We develop methods that
              increase the explanatory power of this approach by integrating
              knowledge about relationships between the GO terms into the
              calculation of the statistical significance. RESULTS: We present
              two novel algorithms that improve GO group scoring using the
              underlying GO graph topology. The algorithms are evaluated on
              real and simulated gene expression data. We show that both
              methods eliminate local dependencies between GO terms and point
              to relevant areas in the GO graph that remain undetected with
              state-of-the-art algorithms for scoring functional terms. A
              simulation study demonstrates that the new methods exhibit a
              higher level of detecting relevant biological terms than
              competing methods.",
  journal  = "Bioinformatics",
  volume   =  22,
  number   =  13,
  pages    = "1600--1607",
  month    =  jul,
  year     =  2006,
  language = "en"
}


% The entry below contains non-ASCII chars that could not be converted
% to a LaTeX equivalent.
@ARTICLE{Shinzato2011-em,
  title    = "Using the Acropora digitifera genome to understand coral
              responses to environmental change",
  author   = "Shinzato, Chuya and Shoguchi, Eiichi and Kawashima, Takeshi and
              Hamada, Mayuko and Hisata, Kanako and Tanaka, Makiko and Fujie,
              Manabu and Fujiwara, Mayuki and Koyanagi, Ryo and Ikuta, Tetsuro
              and Fujiyama, Asao and Miller, David J and Satoh, Nori",
  abstract = "Despite the enormous ecological and economic importance of coral
              reefs, the keystone organisms in their establishment, the
              scleractinian corals, increasingly face a range of anthropogenic
              challenges including ocean acidification and seawater temperature
              rise. To understand better the molecular mechanisms underlying
              coral biology, here we decoded the approximately 420-megabase
              genome of Acropora digitifera using next-generation sequencing
              technology. This genome contains approximately 23,700 gene
              models. Molecular phylogenetics indicate that the coral and the
              sea anemone Nematostella vectensis diverged approximately 500
              million years ago, considerably earlier than the time over which
              modern corals are represented in the fossil record (∼240 million
              years ago). Despite the long evolutionary history of the
              endosymbiosis, no evidence was found for horizontal transfer of
              genes from symbiont to host. However, unlike several other
              corals, Acropora seems to lack an enzyme essential for cysteine
              biosynthesis, implying dependency of this coral on its symbionts
              for this amino acid. Corals inhabit environments where they are
              frequently exposed to high levels of solar radiation, and
              analysis of the Acropora genome data indicates that the coral
              host can independently carry out de novo synthesis of
              mycosporine-like amino acids, which are potent
              ultraviolet-protective compounds. In addition, the coral innate
              immunity repertoire is notably more complex than that of the sea
              anemone, indicating that some of these genes may have roles in
              symbiosis or coloniality. A number of genes with putative roles
              in calcification were identified, and several of these are
              restricted to corals. The coral genome provides a platform for
              understanding the molecular basis of symbiosis and responses to
              environmental changes.",
  journal  = "Nature",
  volume   =  476,
  number   =  7360,
  pages    = "320--323",
  month    =  jul,
  year     =  2011,
  language = "en"
}


@ARTICLE{Ying2019-qn,
  title    = "The {Whole-Genome} Sequence of the Coral Acropora millepora",
  author   = "Ying, Hua and Hayward, David C and Cooke, Ira and Wang, Weiwen
              and Moya, Aurelie and Siemering, Kirby R and Sprungala, Susanne
              and Ball, Eldon E and For{\^e}t, Sylvain and Miller, David J",
  journal  = "Genome Biol. Evol.",
  volume   =  11,
  number   =  5,
  pages    = "1374--1379",
  month    =  may,
  year     =  2019,
  keywords = " Acropora digitifera ; Acropora millepora ; WGS; genome",
  language = "en"
}


@ARTICLE{Wood2014-qp,
  title    = "Kraken: ultrafast metagenomic sequence classification using exact
              alignments",
  author   = "Wood, Derrick E and Salzberg, Steven L",
  abstract = "Kraken is an ultrafast and highly accurate program for assigning
              taxonomic labels to metagenomic DNA sequences. Previous programs
              designed for this task have been relatively slow and
              computationally expensive, forcing researchers to use faster
              abundance estimation programs, which only classify small subsets
              of metagenomic data. Using exact alignment of k-mers, Kraken
              achieves classification accuracy comparable to the fastest BLAST
              program. In its fastest mode, Kraken classifies 100 base pair
              reads at a rate of over 4.1 million reads per minute, 909 times
              faster than Megablast and 11 times faster than the abundance
              estimation program MetaPhlAn. Kraken is available at
              http://ccb.jhu.edu/software/kraken/.",
  journal  = "Genome Biol.",
  volume   =  15,
  number   =  3,
  pages    = "R46",
  month    =  mar,
  year     =  2014,
  language = "en"
}



@ARTICLE{Korneliussen2014-ah,
  title    = "{ANGSD}: Analysis of Next Generation Sequencing Data",
  author   = "Korneliussen, Thorfinn Sand and Albrechtsen, Anders and Nielsen,
              Rasmus",
  abstract = "BACKGROUND: High-throughput DNA sequencing technologies are
              generating vast amounts of data. Fast, flexible and memory
              efficient implementations are needed in order to facilitate
              analyses of thousands of samples simultaneously. RESULTS: We
              present a multithreaded program suite called ANGSD. This program
              can calculate various summary statistics, and perform association
              mapping and population genetic analyses utilizing the full
              information in next generation sequencing data by working
              directly on the raw sequencing data or by using genotype
              likelihoods. CONCLUSIONS: The open source c/c++ program ANGSD is
              available at http://www.popgen.dk/angsd . The program is tested
              and validated on GNU/Linux systems. The program facilitates
              multiple input formats including BAM and imputed beagle genotype
              probability files. The program allow the user to choose between
              combinations of existing methods and can perform analysis that is
              not implemented elsewhere.",
  journal  = "BMC Bioinformatics",
  volume   =  15,
  pages    = "356",
  month    =  nov,
  year     =  2014,
  language = "en"
}


@ARTICLE{Portik2017-fo,
  title    = "Evaluating mechanisms of diversification in a {Guineo-Congolian}
              tropical forest frog using demographic model selection",
  author   = "Portik, Daniel M and Leach{\'e}, Adam D and Rivera, Danielle and
              Barej, Michael F and Burger, Marius and Hirschfeld, Mareike and
              R{\"o}del, Mark-Oliver and Blackburn, David C and Fujita, Matthew
              K",
  abstract = "The accumulation of biodiversity in tropical forests can occur
              through multiple allopatric and parapatric models of
              diversification, including forest refugia, riverine barriers and
              ecological gradients. Considerable debate surrounds the major
              diversification process, particularly in the West African Lower
              Guinea forests, which contain a complex geographic arrangement of
              topographic features and historical refugia. We used genomic data
              to investigate alternative mechanisms of diversification in the
              Gaboon forest frog, Scotobleps gabonicus, by first identifying
              population structure and then performing demographic model
              selection and spatially explicit analyses. We found that a
              majority of population divergences are best explained by
              allopatric models consistent with the forest refugia hypothesis
              and involve divergence in isolation with subsequent expansion and
              gene flow. These population divergences occurred simultaneously
              and conform to predictions based on climatically stable regions
              inferred through ecological niche modelling. Although forest
              refugia played a prominent role in the intraspecific
              diversification of S. gabonicus, we also find evidence for
              potential interactions between landscape features and historical
              refugia, including major rivers and elevational barriers such as
              the Cameroonian Volcanic Line. We outline the advantages of using
              genomewide variation in a model-testing framework to distinguish
              between alternative allopatric hypotheses, and the pitfalls of
              limited geographic and molecular sampling. Although
              phylogeographic patterns are often species-specific and related
              to life-history traits, additional comparative studies
              incorporating genomic data are necessary for separating shared
              historical processes from idiosyncratic responses to
              environmental, climatic and geological influences on
              diversification.",
  journal  = "Mol. Ecol.",
  volume   =  26,
  number   =  19,
  pages    = "5245--5263",
  month    =  oct,
  year     =  2017,
  keywords = "Africa; Lower Guinea; amphibians; ecological niche model; forest
              refugia; historical demography; phylogeography; riverine barrier",
  language = "en"
}


@ARTICLE{Mao2018-bu,
  title    = "The Roles of Introgression and Climate Change in the Rise to
              Dominance of Acropora Corals",
  author   = "Mao, Yafei and Economo, Evan P and Satoh, Noriyuki",
  abstract = "Reef-building corals provide the structural basis for one of
              Earth's most spectacular and diverse-but increasingly
              threatened-ecosystems. Modern Indo-Pacific reefs are dominated by
              species of the staghorn coral genus Acropora, but the
              evolutionary and ecological factors associated with their
              diversification and rise to dominance are unclear. Recent work on
              evolutionary radiations has demonstrated the importance of
              introgression and ecological opportunity in promoting
              diversification and ecological success. Here, we analyze the
              genomes of five staghorn coral species to examine the roles of
              introgression and ecological opportunity in the rise to dominance
              of Acropora. We found evidence for a history marked by a major
              introgression event as well as recurrent gene flow across
              species. In addition, we found that genes with topologies
              mismatching the species tree are evolving faster, which is
              suggestive of a role for introgression in spreading adaptive
              genetic variation. Demographic analysis showed that Acropora
              lineages profited from climate-driven mass extinctions in the
              Plio-Pleistocene, indicating that Acropora exploited ecological
              opportunity opened by a new climatic regime favoring species that
              could cope with rapid sea-level changes. Collectively, the
              genomes of reef-building corals have recorded an evolutionary
              history shaped by introgression and climate change, suggesting
              that Acropora-among most vulnerable corals to stressors-may be
              critical for understanding how reefs track the impending rapid
              sea-level changes of the Anthropocene.",
  journal  = "Curr. Biol.",
  volume   =  28,
  number   =  21,
  pages    = "3373--3382.e5",
  month    =  nov,
  year     =  2018,
  keywords = "Acropora; adaptive radiation; climate change; corals; ecological
              opportunity; hybridization; introgression; mass extinction; sea
              level",
  language = "en"
}

@ARTICLE{Kimura1962-dy,
  title    = "On the probability of fixation of mutant genes in a population",
  author   = "Kimura, M",
  journal  = "Genetics",
  volume   =  47,
  pages    = "713--719",
  month    =  jun,
  year     =  1962,
  keywords = "CHROMOSOMES",
  language = "en"
}


@ARTICLE{Hedrick2015-gl,
  title    = "Measuring relatedness between inbred individuals",
  author   = "Hedrick, Philip W and Lacy, Robert C",
  abstract = "Genetic relatedness between individuals is an important measure
              in many areas of biology. However, some relatedness measures for
              use with molecular (allele) data assume that the individuals
              themselves are not inbred. Here, we present a new measure of
              relatedness based on the different modes of identity-by-descent
              for alleles that has an upper bound of 1 even when the
              individuals being compared are themselves inbred. This new
              measure is compared to several other measures of relatedness
              using several simple examples and pedigree data from the wolf
              population in Isle Royale National Park.",
  journal  = "J. Hered.",
  volume   =  106,
  number   =  1,
  pages    = "20--25",
  month    =  jan,
  year     =  2015,
  keywords = "coefficient of relationship; inbreeding; pedigree; wolves",
  language = "en"
}


@ARTICLE{Hanghoj2019-sl,
  title    = "Fast and accurate relatedness estimation from high-throughput
              sequencing data in the presence of inbreeding",
  author   = "Hangh{\o}j, Kristian and Moltke, Ida and Andersen, Philip Alstrup
              and Manica, Andrea and Korneliussen, Thorfinn Sand",
  abstract = "BACKGROUND: The estimation of relatedness between pairs of
              possibly inbred individuals from high-throughput sequencing (HTS)
              data has previously not been possible for samples where we cannot
              obtain reliable genotype calls, as in the case of low-coverage
              data. RESULTS: We introduce ngsRelateV2, a major revision of
              ngsRelateV1, a program that originally allowed for estimation of
              relatedness from HTS data among non-inbred individuals only. The
              new revised version takes into account the possibility of
              individuals being inbred by estimating the 9 condensed Jacquard
              coefficients along with various other relatedness statistics. The
              program is threaded and scales linearly with the number of cores
              allocated to the process. CONCLUSION: The program is available as
              an open source C/C++ program under the GPL license and hosted at
              https://github.com/ANGSD/ngsRelate. To facilitate easy analysis,
              the program is able to work directly on the most commonly used
              container formats for raw sequence (BAM/CRAM) and summary data
              (VCF/BCF).",
  journal  = "Gigascience",
  volume   =  8,
  number   =  5,
  month    =  may,
  year     =  2019,
  keywords = "Jacquard coefficients; genotype likelihood; high-throughput
              sequencing data; inbreeding; next-generation sequencing;
              population genetics; relatedness estimation; threading",
  language = "en"
}