@ARTICLE{TreeBASE2Ref20490,
author = {Michael Woodhams and Dorothy A. Steane and Rebecca C Jones and Dean Nicolle and Vincent Moulton and Barbara R Holland},
title = {Novel distances for Dollo data},
year = {2012},
keywords = {Additive Dollo Distance, Dollo process, LogDet/paralinear distances, Diversity Arrays Technology, Eucalyptus phylogeny, Adnataria phylogeny, gene content phylogeny, conditioning genomes. },
doi = {},
url = {http://},
pmid = {},
journal = {Systematic Biology},
volume = {},
number = {},
pages = {},
abstract = {We investigate distances on binary (presence/absence) data in the context of a Dollo process, where a trait can only arise once on a phylogenetic tree but may be lost many times. We introduce a novel distance, the Additive Dollo Distance (ADD), which is consistent for data generated under a Dollo model, and show that it has some useful theoretical properties including an intriguing link to the LogDet distance. Simulations of Dollo data are used to compare a number of binary distances including ADD, LogDet, Nei Li and some simple, but to our knowledge previously unstudied, variations on common binary distances. The simulations suggest that ADD outperforms other distances on Dollo data. Interestingly, we found that the LogDet distance performs poorly in the context of a Dollo process, which may have implications for its use in connection with conditioned genome reconstruction. We apply the ADD to two Diversity Arrays Technology (DArT) datasets, one that broadly covers Eucalyptus species and one that focuses on the Eucalyptus series Adnataria. We also reanalyse gene family presence/absence data on bacteria from the COG database and compare the results to previous phylogenies estimated using the conditioned genome reconstruction approach.}
}
Citation for Study 12439
Citation title:
"Novel distances for Dollo data".
Study name:
"Novel distances for Dollo data".
This study is part of submission 12439
(Status: Published).
Citation
Woodhams M., Steane D., Jones R.C., Nicolle D., Moulton V., & Holland B.R. 2012. Novel distances for Dollo data. Systematic Biology, .
Authors
-
Woodhams M.
(submitter)
-
Steane D.
-
Jones R.C.
-
Nicolle D.
-
Moulton V.
-
Holland B.R.
Abstract
We investigate distances on binary (presence/absence) data in the context of a Dollo process, where a trait can only arise once on a phylogenetic tree but may be lost many times. We introduce a novel distance, the Additive Dollo Distance (ADD), which is consistent for data generated under a Dollo model, and show that it has some useful theoretical properties including an intriguing link to the LogDet distance. Simulations of Dollo data are used to compare a number of binary distances including ADD, LogDet, Nei Li and some simple, but to our knowledge previously unstudied, variations on common binary distances. The simulations suggest that ADD outperforms other distances on Dollo data. Interestingly, we found that the LogDet distance performs poorly in the context of a Dollo process, which may have implications for its use in connection with conditioned genome reconstruction. We apply the ADD to two Diversity Arrays Technology (DArT) datasets, one that broadly covers Eucalyptus species and one that focuses on the Eucalyptus series Adnataria. We also reanalyse gene family presence/absence data on bacteria from the COG database and compare the results to previous phylogenies estimated using the conditioned genome reconstruction approach.
Keywords
Additive Dollo Distance, Dollo process, LogDet/paralinear distances, Diversity Arrays Technology, Eucalyptus phylogeny, Adnataria phylogeny, gene content phylogeny, conditioning genomes.
External links
About this resource
- Canonical resource URI:
http://purl.org/phylo/treebase/phylows/study/TB2:S12439
- Other versions:
Nexus
NeXML
- Show BibTeX reference
@ARTICLE{TreeBASE2Ref20490,
author = {Michael Woodhams and Dorothy A. Steane and Rebecca C Jones and Dean Nicolle and Vincent Moulton and Barbara R Holland},
title = {Novel distances for Dollo data},
year = {2012},
keywords = {Additive Dollo Distance, Dollo process, LogDet/paralinear distances, Diversity Arrays Technology, Eucalyptus phylogeny, Adnataria phylogeny, gene content phylogeny, conditioning genomes. },
doi = {},
url = {http://},
pmid = {},
journal = {Systematic Biology},
volume = {},
number = {},
pages = {},
abstract = {We investigate distances on binary (presence/absence) data in the context of a Dollo process, where a trait can only arise once on a phylogenetic tree but may be lost many times. We introduce a novel distance, the Additive Dollo Distance (ADD), which is consistent for data generated under a Dollo model, and show that it has some useful theoretical properties including an intriguing link to the LogDet distance. Simulations of Dollo data are used to compare a number of binary distances including ADD, LogDet, Nei Li and some simple, but to our knowledge previously unstudied, variations on common binary distances. The simulations suggest that ADD outperforms other distances on Dollo data. Interestingly, we found that the LogDet distance performs poorly in the context of a Dollo process, which may have implications for its use in connection with conditioned genome reconstruction. We apply the ADD to two Diversity Arrays Technology (DArT) datasets, one that broadly covers Eucalyptus species and one that focuses on the Eucalyptus series Adnataria. We also reanalyse gene family presence/absence data on bacteria from the COG database and compare the results to previous phylogenies estimated using the conditioned genome reconstruction approach.}
}
- Show RIS reference
TY - JOUR
ID - 20490
AU - Woodhams,Michael
AU - Steane,Dorothy A.
AU - Jones,Rebecca C
AU - Nicolle,Dean
AU - Moulton,Vincent
AU - Holland,Barbara R
T1 - Novel distances for Dollo data
PY - 2012
KW - Additive Dollo Distance
KW - Dollo process
KW - LogDet/paralinear distances
KW - Diversity Arrays Technology
KW - Eucalyptus phylogeny
KW - Adnataria phylogeny
KW - gene content phylogeny
KW - conditioning genomes.
UR - http://dx.doi.org/
N2 - We investigate distances on binary (presence/absence) data in the context of a Dollo process, where a trait can only arise once on a phylogenetic tree but may be lost many times. We introduce a novel distance, the Additive Dollo Distance (ADD), which is consistent for data generated under a Dollo model, and show that it has some useful theoretical properties including an intriguing link to the LogDet distance. Simulations of Dollo data are used to compare a number of binary distances including ADD, LogDet, Nei Li and some simple, but to our knowledge previously unstudied, variations on common binary distances. The simulations suggest that ADD outperforms other distances on Dollo data. Interestingly, we found that the LogDet distance performs poorly in the context of a Dollo process, which may have implications for its use in connection with conditioned genome reconstruction. We apply the ADD to two Diversity Arrays Technology (DArT) datasets, one that broadly covers Eucalyptus species and one that focuses on the Eucalyptus series Adnataria. We also reanalyse gene family presence/absence data on bacteria from the COG database and compare the results to previous phylogenies estimated using the conditioned genome reconstruction approach.
L3 -
JF - Systematic Biology
VL -
IS -
ER -
Go to search
Citation
Taxa
Matrices
Trees
Analyses
