@article {Darriba023978, author = {Diego Darriba and David Posada}, title = {The impact of partitioning on phylogenomic accuracy}, elocation-id = {023978}, year = {2015}, doi = {10.1101/023978}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Several strategies have been proposed to assign substitution models in phylogenomic datasets, or partitioning. The accuracy of these methods, and most importantly, their impact on phylogenetic estimation has not been thoroughly assessed using computer simulations. We simulated multiple partitioning scenarios to benchmark two a priori partitioning schemes (one model for the whole alignment, one model for each data block), and two statistical approaches (hierarchical clustering and greedy) implemented in PartitionFinder and in our new program, PartitionTest. Most methods were able to identify optimal partitioning schemes closely related to the true one. Greedy algorithms identified the true partitioning scheme more frequently than the clustering algorithms, but selected slightly less accurate partitioning schemes and tended to underestimate the number of partitions. PartitionTest was several times faster than PartitionFinder, with equal or better accuracy. Importantly, maximum likelihood phylogenetic inference was very robust to the partitioning scheme. Best-fit partitioning schemes resulted in optimal phylogenetic performance, without appreciable differences compared to the use of the true partitioning scheme. However, accurate trees were also obtained by a {\textquotedblleft}simple{\textquotedblright} strategy consisting of assigning independent GTR+G models to each data block. On the contrary, leaving the data unpartitioned always diminished the quality of the trees inferred, to a greater or lesser extent depending on the simulated scenario. The analysis of empirical data confirmed these trends, although suggesting a stronger influence of the partitioning scheme. Overall, our results suggests that statistical partitioning, but also the a priori assignment of independent GTR+G models, maximize phylogenomic performance.}, URL = {https://www.biorxiv.org/content/early/2015/08/19/023978}, eprint = {https://www.biorxiv.org/content/early/2015/08/19/023978.full.pdf}, journal = {bioRxiv} }