R/data.R

#' Thirty datasets with inapplicable data
#' 
#' These are the datasets used to evaluate the behaviour of the inapplicable
#' algorithm in \insertCite{Brazeau2018;textual}{TreeTools}.
#' The name of each item corresponds to the datasets listed below.
#' Datasets are sorted into two subsets, each sorted alphabetically;
#' the first subset comprise simpler datasets with faster processing times.
#' `inapplicable.datasets` provide the data in the matrix format generated by
#' [`read.nexus.data()`]; `inapplicable.phyData` are in \code{phyDat} format.
#' `inapplicable.trees` lists for each dataset a sample of up to 50 trees
#' obtained by tree search under each inapplicable treatment, named accordingly.
#' `inapplicable.citations` is a named character vector specifying the source of
#' each dataset.
#'
#' @source {
#' Subset one (faster processing):
#' 
#'  \describe{
#'    \item{Agnarsson2004}{AGNARSSON, I. 2004. Morphological phylogeny of cobweb spiders and their
#'                      relatives (Araneae, Araneoidea, Theridiidae). Zoological Journal of the
#'                      Linnean Society, 141, 447--626.}
#'    \item{Capa2011}{CAPA, M., HUTCHINGS, P., AGUADO, M. T. and BOTT, N. J. 2011. Phylogeny of 
#'                      Sabellidae (Annelida) and relationships with other taxa inferred from 
#'                      morphology and multiple genes. Cladistics, 27, 449--469.}
#'    \item{DeAssis2011}{ DE ASSIS, J. E. and CHRISTOFFERSEN, M. L. 2011. Phylogenetic relationships
#'                      within Maldanidae (Capitellida, Annelida), based on morphological characters.
#'                       Systematics and Biodiversity, 9, 233--245.}
#'    \item{OLeary1999}{ O'LEARY, M. A. and GEISLER, J. H. 1999. The position of Cetacea within 
#'                      Mammalia: phylogenetic analysis of morphological data from extinct and 
#'                      extant taxa. Systematic Biology, 48, 455--490.}
#'    \item{Rousset2004}{ ROUSSET, V., ROUSE, G. W., SIDDALL, M. E., TILLIER, A. and PLEIJEL, F. 
#'                      2004. The phylogenetic position of Siboglinidae (Annelida) inferred from
#'                       18S rRNA, 28S rRNA and morphological data. Cladistics, 20, 518--533.}
#'    \item{Sano2011}{ SANO, M. and AKIMOTO, S.-I. 2011. Morphological phylogeny of 
#'    gall-forming aphids of the tribe Eriosomatini (Aphididae: Eriosomatinae). 
#'    Systematic Entomology, 36, 607--627.}
#'    \item{Sansom2010}{ SANSOM, R. S., FREEDMAN, K., GABBOTT, S. E., ALDRIDGE, R. J. and
#'                       PURNELL, M. A. 2010. Taphonomy and affinity of an enigmatic Silurian vertebrate,
#'                      \emph{Jamoytius kerwoodi} White. Palaeontology, 53, 1393--1409.}
#'    \item{Schulze2007}{ SCHULZE, A., CUTLER, E. B. and GIRIBET, G. 2007. Phylogeny of sipunculan 
#'                      worms: A combined analysis of four gene regions and morphology. Molecular Phylogenetics and Evolution, 42, 171--92.}
#'    \item{Shultz2007}{ SHULTZ, J. W. 2007. A phylogenetic analysis of the arachnid orders based 
#'                      on morphological characters. Zoological Journal of the Linnean Society, 150, 221--265.}
#'    \item{Wetterer2000}{ WETTERER, A. L., ROCKKMAN, M. V. and SIMMONS, N. B. 2000. Phylogeny of 
#'                      phyllostomid bats (Mammalia: Chiroptera): data from diverse morphological 
#'                      systems, sex chromosomes, and restriction sites. Bulletin of the American Museum of Natural History, 248, 1--200.}
#'    \item{Wills2012}{ WILLS, M. A., GERBER, S., RUTA, M. and HUGHES, M. 2012. The disparity of 
#'                      priapulid, archaeopriapulid and palaeoscolecid worms in the light of new data.
#'                      Journal of Evolutionary Biology, 25, 2056--2076.}
#'  }
#'  
#'  Subset two (longer processing times):
#'  
#'  \describe{                  
#'    \item{Aguado2009}{ AGUADO, M. T. and SAN MARTIN, G. 2009. Phylogeny of Syllidae (Polychaeta) 
#'                      based on morphological data. Zoologica Scripta, 38, 379--402.}
#'    \item{Aria2015}{ ARIA, C., CARON, J. B. and GAINES, R. 2015. A large new leanchoiliid from 
#'                      the Burgess Shale and the influence of inapplicable states on stem arthropod
#'                       phylogeny. Palaeontology, 58, 629--660.}
#'    \item{Asher2005}{ASHER, R. J. and HOFREITER, M. 2006. Tenrec phylogeny and the noninvasive
#'                     extraction of nuclear DNA. Systematic biology, 55, 181--94.}
#'    \item{Baker2009}{ BAKER, W. J., SAVOLAINEN, V., ASMUSSEN-LANGE, C. B., CHASE, M. W., 
#'                      DRANSFIELD, J., FOREST, F., HARLEY, M. M., UHL, N. W. and WILKINSON, M. 2009.
#'                       Complete generic-level phylogenetic analyses of palms (Arecaceae) with 
#'                      comparisons of supertree and supermatrix approaches. 
#'                      Systematic Biology, 58, 240--256.}
#'    \item{Bouchenak2010}{ BOUCHENAK-KHELLADI, Y., VERBOOM, G. A., SAVOLAINEN, V. and HODKINSON, T. R.
#'                      2010. Biogeography of the grasses (Poaceae): a phylogenetic approach to reveal
#'                      evolutionary history in geographical space and geological time. Botanical 
#'                      Journal of the Linnean Society, 162, 543--557.}
#'    \item{Conrad2008}{ CONRAD, J. L. 2008. Phylogeny And Systematics Of Squamata (Reptilia) Based
#'                      On Morphology. Bulletin of the American Museum of Natural History, 310, 1--182.}
#'    \item{Dikow2009}{ DIKOW, T. 2009. A phylogenetic hypothesis for Asilidae based on a total 
#'                      evidence analysis of morphological and DNA sequence data (Insecta: Diptera:
#'                      Brachycera: Asiloidea). Organisms Diversity and Evolution, 9, 165--188.}
#'    \item{Eklund2004}{ EKLUND, H., DOYLE, J. A. and HERENDEEN, P. S. 2004. Morphological 
#'                      phylogenetic analysis of living and fossil Chloranthaceae. International
#'                      Journal of Plant Sciences, 165, 107--151.}
#'    \item{Geisler2001}{ GEISLER, J. H. 2001. New morphological evidence for the phylogeny of 
#'                      Artiodactyla, Cetacea, and Mesonychidae. American Museum Novitates, 3344, 53.}
#'    \item{Giles2015}{ GILES, S., FRIEDMAN, M. and BRAZEAU, M. D. 2015. Osteichthyan-like cranial
#'                      conditions in an Early Devonian stem gnathostome. Nature, 520, 82--85.}
#'    \item{Griswold1999}{ GRISWOLD, C. E., CODDINGTON, J. A., PLATNICK, N. I. and FORSTER, R. R. 1999.
#'                      Towards a phylogeny of entelegyne spiders (Araneae, Araneomorphae, Entelegynae).
#'                      Journal of Arachnology, 27, 53--63.}
#'    \item{Liljeblad2008}{ LILJEBLAD, J., RONQUIST, F., NIEVES-ALDREY, J. L., FONTAL-CAZALLA, F., 
#'                      ROS-FARRE, P., GAITROS, D. and PUJADE-VILLAR, J. 2008. A fully web-illustrated 
#'                      morphological phylogenetic study of relationships among oak gall wasps and
#'                       their closest relatives (Hymenoptera: Cynipidae).}
#'    \item{Loconte1991}{ LOCONTE, H. and STEVENSON, D. W. 1991. Cladistics of the Magnoliidae. 
#'                      Cladistics, 7, 267--296.}
#'    \item{Longrich2010}{ LONGRICH, N. R., SANKEY, J. and TANKE, D. 2010. \emph{Texacephale langstoni}, 
#'                      a new genus of pachycephalosaurid (Dinosauria: Ornithischia) from the upper
#'                      Campanian Aguja Formation, southern Texas, USA. Cretaceous Research, 31, 274--284.}
#'    \item{OMeara2014}{ O'MEARA, R. N. and THOMPSON, R. S. 2014. Were There Miocene Meridiolestidans?
#'                      Assessing the phylogenetic placement of \emph{Necrolestes patagonensis} and the
#'                       presence of a 40 million year Meridiolestidan ghost lineage. Journal
#'                       of Mammalian Evolution, 21, 271--284.}
#'    \item{Rougier2012}{ ROUGIER, G. W., WIBLE, J. R., BECK, R. M. D. and APESTEGUIA, S. 2012. 
#'                      The Miocene mammal \emph{Necrolestes} demonstrates the survival of a 
#'                      Mesozoic nontherian lineage into the late Cenozoic of South America. 
#'                      Proceedings of the National Academy of Sciences, 109, 20053--8.}
#'    \item{Sharkey2011}{ SHARKEY, M. J., CARPENTER, J. M., VILHELMSEN, L., HERATY, J., LILJEBLAD, J.,
#'                      DOWLING, A. P. G., SCHULMEISTER, S., MURRAY, D., DEANS, A. R., RONQUIST, F.,
#'                       KROGMANN, L. and WHEELER, W. C. 2012. Phylogenetic relationships among 
#'                      superfamilies of Hymenoptera. Cladistics, 28, 80--112.}
#'    \item{Sundue2010}{ SUNDUE, M. A., ISLAM, M. B. and RANKER, T. A. 2010. Systematics of 
#'                      Grammitid Ferns (Polypodiaceae): Using Morphology and Plastid Sequence Data
#'                      to Resolve the Circumscriptions of Melpomene and the Polyphyletic Genera 
#'                      \emph{Lellingeria} and \emph{Terpsichore}. Systematic Botany, 35, 701--715.}
#'    \item{Vinther2008}{ VINTHER, J., VAN ROY, P. and BRIGGS, D. E. G. 2008. Machaeridians are 
#'                      Palaeozoic armoured annelids. Nature, 451, 185--188.}
#'    \item{Wilson2003}{ WILSON, G. D. F. and EDGECOMBE, G. D. 2003. The Triassic isopod 
#'                      \emph{Protamphisopus wianamattensis} (Chilton) and comparison by extant 
#'                      taxa (Crustacea, Phreatoicidea). Journal of Paleontology, 77, 454--470.}
#'    \item{Wortley2006}{ WORTLEY, A. H. and SCOTLAND, R. W. 2006. The effect of combining molecular
#'                      and morphological data in published phylogenetic analyses. 
#'                      Systematic Biology, 55, 677--685.}
#'    \item{Zanol2014}{ ZANOL, J., HALANYCH, K. M. and FAUCHALD, K. 2014. Reconciling taxonomy and
#'                      phylogeny in the bristleworm family Eunicidae (Polychaete, Annelida). 
#'                      Zoologica Scripta, 43, 79--100.}
#'    \item{Zhu2013}{ ZHU, M., YU, X., AHLBERG, P. E., CHOO, B., LU, J., QIAO, T., QU, Q., ZHAO, W.,
#'                      JIA, L., BLOM, H. and ZHU, Y. 2013. A Silurian placoderm with osteichthyan-like
#'                       marginal jaw bones. Nature, 502, 188--193.}
#'   }
#' }
#'
#'
#' @references
#' \insertAllCited{}
#' @examples
#' data("inapplicable.datasets", package = "TreeSearch")
#' names(inapplicable.datasets)
#' @keywords datasets
"inapplicable.datasets"

#' @rdname inapplicable.datasets
"inapplicable.phyData"

#' @rdname inapplicable.datasets
"inapplicable.trees"

#' @rdname inapplicable.datasets
"inapplicable.citations"

#' 100 simulated data matrices 
#'
#' Contains the 100 simulated matrices generated by
#' \insertCite{Congreve2016}{TreeSearch} using a heterogeneous Markov-k model,
#' generated from the \link{referenceTree} topology, with 
#' all branches sharing an equal length.
#'
#' @format A list with 100 entries, each comprising a `phyDat` object of 55
#' characters for 22 taxa
#'
#' @references 
#'  \insertAllCited{}
#' 
#' @examples 
#' data("referenceTree")
#' data("congreveLamsdellMatrices")
#' TreeLength(referenceTree, congreveLamsdellMatrices[[17]], "profile")
#'
#' @source \doi{10.5061/dryad.7dq0j}
#' 
#' @keywords datasets
"congreveLamsdellMatrices"

#' Tree topology for matrix simulation
#'
#' The tree topology used to generate the matrices in 
#' \code{\link{congreveLamsdellMatrices}} 
#'
#' @format A single phylogenetic tree saved as an object of class \code{phylo}
#'
#' @references 
#'  \insertRef{Congreve2016}{TreeSearch}
#'  \insertRef{Congreve2016dd}{TreeSearch}
#' 
#' @examples 
#' data(referenceTree)
#' plot(referenceTree)
#' 
#' @source Congreve & Lamsdell (2016); \doi{10.1111/pala.12236}
#' 
#' @keywords datasets
"referenceTree"

#' Empirically counted profiles for small trees
#' 
#' The base 2 logarithm of the number of trees containing _s_ steps, calculated
#' by scoring a character on each _n_-leaf tree.
#' 
#' @format A list with the structure 
#' `profiles[[number of leaves]][[number of tokens]][[tokens in smallest split]]`
#' The list entry returns a named numeric vector; each entry lists 
#' log2(proportion of _n_-leaf trees with _s_ or fewer steps for this character).
#' 
#' @examples 
#' data(profiles)
#' 
#' # Load profile for a character of the structure 0 0 0 1 1 1 1 1
#' profile3.5 <- profiles[[8]][[2]][[3]]
#' 
#' # Number of trees with _s_ or fewer steps on that character
#' TreeTools::NUnrooted(8) * 2 ^ profile3.5
#' @family profile parsimony functions
"profiles"
ms609/TreeSearch documentation built on April 7, 2024, 7:06 p.m.