Assessing systematic error in the inference of seed plant phylogeny

We used parametric bootstrapping to assess the performance of maximum parsimony and maximum likelihood phylogenetic analyses of a 12-locus seed plant data set. Evidence of biases in maximum parsimony analyses of single-locus data sets may explain some of the locus-specific variation among DNA-based hypotheses of seed plant phylogeny. In particular, there is strong evidence of bias in maximum parsimony analyses, especially of plastid loci, that favors placing Gnetales sister to other seed plants. We concatenated simulated single-locus data sets to examine biases in analyses of a 12-locus data set in which each locus is simulated with different substitution parameters and branch lengths. Maximum parsimony analyses of the simulated 12-locus data set also show evidence of biases in favor of recovering trees with Gnetales sister to other seed plants and against recovering anthophyte, gnepine, and gnetifer trees. These biases are most evident in analyses that include the fastest-evolving characters. In the maximum likelihood analyses of the simulated 12-locus data sets, there is evidence of a bias against recovering the anthophyte hypothesis. Otherwise, there is little evidence that the heterogeneous branch lengths and substitution processes among loci influence the results from maximum likelihood phylogenetic analyses.