@article{fdi:010089704,
  title = {{P}hylte{R} : efficient identification of outlier sequences in phylogenomic datasets},
  author = {{C}omte, {A}urore and {T}ricou, {T}. and {T}annier, {E}. and {J}oseph, {J}. and {S}iberchicot, {A}. and {P}enel, {S}. and {A}llio, {R}. and {D}elsuc, {F}. and {D}ray, {S}. and de {V}ienne, {D}. {M}.},
  editor = {},
  language = {{ENG}},
  abstract = {{I}n phylogenomics, incongruences between gene trees, resulting from both artifactual and biological reasons, can decrease the signal-to-noise ratio and complicate species tree inference. {T}he amount of data handled today in classical phylogenomic analyses precludes manual error detection and removal. {H}owever, a simple and efficient way to automate the identification of outliers from a collection of gene trees is still missing. {H}ere, we present {P}hylte{R}, a method that allows rapid and accurate detection of outlier sequences in phylogenomic datasets, i.e. species from individual gene trees that do not follow the general trend. {P}hylte{R} relies on {DISTATIS}, an extension of multidimensional scaling to 3 dimensions to compare multiple distance matrices at once. {I}n {P}hylte{R}, these distance matrices extracted from individual gene phylogenies represent evolutionary distances between species according to each gene. {O}n simulated datasets, we show that {P}hylte{R} identifies outliers with more sensitivity and precision than a comparable existing method. {W}e also show that {P}hylte{R} is not sensitive to {ILS}-induced incongruences, which is a desirable feature. {O}n a biological dataset of 14,463 genes for 53 species previously assembled for {C}arnivora phylogenomics, we show (i) that {P}hylte{R} identifies as outliers sequences that can be considered as such by other means, and (ii) that the removal of these sequences improves the concordance between the gene trees and the species tree. {T}hanks to the generation of numerous graphical outputs, {P}hylte{R} also allows for the rapid and easy visual characterization of the dataset at hand, thus aiding in the precise identification of errors. {P}hylte{R} is distributed as an {R} package on {CRAN} and as containerized versions (docker and singularity).},
  keywords = {phylogenomics ; outliers ; gene tree ; species tree ; {HGT} ; {ILS} ; duplication ; supermatrix ; supertree},
  booktitle = {},
  journal = {{M}olecular {B}iology and {E}volution},
  volume = {40},
  numero = {11},
  pages = {msad234 [16 ]},
  ISSN = {0737-4038},
  year = {2023},
  DOI = {10.1093/molbev/msad234},
  URL = {https://www.documentation.ird.fr/hor/fdi:010089704},
}