Inference of large phylogenetic trees with statistical methods is computationally intensive. We recently introduced simple heuristics which yield accurate trees for synthetic as well as real data and are implemented in a sequential program called RAxML. We have demonstrated that RAxML outperforms the currently fastest statistical phylogeny programs (MrBayes, PHYML) in terms of speed and likelihood values on real data. In this paper we present a non-deterministic parallel implementation of our algorithm which in some cases yields super-linear speedups for an analysis of 1.000 organisms on a LINUX cluster. In addition, we use RAxML to infer a 10.000-taxon phylogenetic tree containing representative organisms from the three domains: Eukarya, Bacteria and Archaea. Finally, we compare the sequential speed and accuracy of RAxML and PHYML on 8 synthetic alignments comprising 4.000 sequences.

@inproceedings{PIOAPWMLSL04,
	author	 = {Alexandros P. Stamatakis and Thomas Ludwig and Harald Meier},
	title	 = {{Parallel Inference of a 10.000-taxon Phylogeny with Maximum Likelihood}},
	year	 = {2004},
	booktitle	 = {{Euro-Par 2004 Parallel Processing}},
	editor	 = {Marco Danelutto and Marco Vanneschi and Domenico Laforenza},
	publisher	 = {Springer},
	address	 = {Berlin / Heidelberg, Germany},
	series	 = {Lecture Notes in Computer Science},
	number	 = {3149},
	pages	 = {997--1004},
	conference	 = {Euro-Par-04},
	organization	 = {University of Pisa and Institute of Information Science and Technologies (ISTI-CNR)},
	location	 = {Pisa, Italy},
	doi	 = {http://dx.doi.org/10.1007/978-3-540-27866-5_134},
	abstract	 = {Inference of large phylogenetic trees with statistical methods is computationally intensive. We recently introduced simple heuristics which yield accurate trees for synthetic as well as real data and are implemented in a sequential program called RAxML. We have demonstrated that RAxML outperforms the currently fastest statistical phylogeny programs (MrBayes, PHYML) in terms of speed and likelihood values on real data. In this paper we present a non-deterministic parallel implementation of our algorithm which in some cases yields super-linear speedups for an analysis of 1.000 organisms on a LINUX cluster. In addition, we use RAxML to infer a 10.000-taxon phylogenetic tree containing representative organisms from the three domains: Eukarya, Bacteria and Archaea. Finally, we compare the sequential speed and accuracy of RAxML and PHYML on 8 synthetic alignments comprising 4.000 sequences.},
	url	 = {http://www.springerlink.com/content/xr0qv7gjqg8wkqut/fulltext.pdf},
}