A new phylogenetic tree sampling method for maximum parsimony bootstrapping and proof-of-concept implementation

摘要

Reconstructing maximum parsimony (MP) trees along with bootstrap for large multiple sequence alignments is a computationally challenging task. In this paper, we present MPBoot, a new method for approximating MP bootstrap based on the idea of a previously introduced method for maximum likelihood bootstrap. MPBoot economizes the computations by only sampling trees on the original alignment and simultaneously calculating exact parsimony scores for all bootstrap alignments. Preliminary experiments on simulated data showed that MPBoot is about 2-3.5 times faster and yields better parsimony scores than a fast bootstrap procedure implemented in TNT. MPBoot also produced less biased support value than TNT for small simulated data sets (=500) MPBoot overestimates the probability that a clade is true, i.e., results in likely high false positive rates. As MPBoot is currently a proof-of-concept implementation, more work is to understand the limitations of the method.