Genomes contain mosaics of discordant evolutionary histories, challenging the accurate inference of the tree of life. While genome-wide data are routinely used for discordance-aware phylogenomic analyses, due to modeling and scalability limitations, the current practice leaves out large chunks of genomes. As more high-quality genomes become available, we urgently need discordance-aware methods to infer the tree directly from a multiple genome alignment. Here, we introduce CASTER, a theoretically justified site-based method that eliminates the need to predefine recombination-free loci. CASTER is scalable to hundreds of mammalian whole genomes. We demonstrate the accuracy and scalability of CASTER in simulations that include recombination and apply CASTER to several biological datasets, showing that its per-site scores can reveal both biological and artefactual patterns of discordance across the genome.
%0 Journal Article
%1 doi:10.1126/science.adk9688
%A Zhang, Chao
%A Nielsen, Rasmus
%A Mirarab, Siavash
%D 2025
%J Science
%K incomplete_lineage_sorting methods pyhlogenetics
%N 0
%P eadk9688
%R 10.1126/science.adk9688
%T CASTER: Direct species tree inference from whole-genome alignments
%U https://www.science.org/doi/abs/10.1126/science.adk9688
%V 0
%X Genomes contain mosaics of discordant evolutionary histories, challenging the accurate inference of the tree of life. While genome-wide data are routinely used for discordance-aware phylogenomic analyses, due to modeling and scalability limitations, the current practice leaves out large chunks of genomes. As more high-quality genomes become available, we urgently need discordance-aware methods to infer the tree directly from a multiple genome alignment. Here, we introduce CASTER, a theoretically justified site-based method that eliminates the need to predefine recombination-free loci. CASTER is scalable to hundreds of mammalian whole genomes. We demonstrate the accuracy and scalability of CASTER in simulations that include recombination and apply CASTER to several biological datasets, showing that its per-site scores can reveal both biological and artefactual patterns of discordance across the genome.
@article{doi:10.1126/science.adk9688,
abstract = { Genomes contain mosaics of discordant evolutionary histories, challenging the accurate inference of the tree of life. While genome-wide data are routinely used for discordance-aware phylogenomic analyses, due to modeling and scalability limitations, the current practice leaves out large chunks of genomes. As more high-quality genomes become available, we urgently need discordance-aware methods to infer the tree directly from a multiple genome alignment. Here, we introduce CASTER, a theoretically justified site-based method that eliminates the need to predefine recombination-free loci. CASTER is scalable to hundreds of mammalian whole genomes. We demonstrate the accuracy and scalability of CASTER in simulations that include recombination and apply CASTER to several biological datasets, showing that its per-site scores can reveal both biological and artefactual patterns of discordance across the genome.},
added-at = {2025-01-27T17:59:15.000+0100},
author = {Zhang, Chao and Nielsen, Rasmus and Mirarab, Siavash},
biburl = {https://www.bibsonomy.org/bibtex/258d49a4ab779cefc929216be61e31767/peter.ralph},
doi = {10.1126/science.adk9688},
eprint = {https://www.science.org/doi/pdf/10.1126/science.adk9688},
interhash = {95d2ce0e1c52f6f6eebf0f8770727642},
intrahash = {58d49a4ab779cefc929216be61e31767},
journal = {Science},
keywords = {incomplete_lineage_sorting methods pyhlogenetics},
number = 0,
pages = {eadk9688},
timestamp = {2025-01-27T17:59:15.000+0100},
title = { {CASTER}: Direct species tree inference from whole-genome alignments},
url = {https://www.science.org/doi/abs/10.1126/science.adk9688},
volume = 0,
year = 2025
}