A temporal banding approach for consistent taxonomic ranking above the species level

Abstract

Comparable taxonomic ranks within clades can facilitate more consistent classifications and objective comparisons among taxa. Here we use a temporal approach to identify taxonomic ranks. This is an extension of the temporal banding approach including a Temporal Error Score that finds an objective cut-off for each taxonomic rank using information for the current classification. We illustrate this method using a data set of the lichenized fungal family Parmeliaceae. To assess its performance, we simulated the effect of taxon sampling and compared our method with the other temporal banding method. For our sampled phylogeny, 11 of the 12 included families remained intact and 55 genera were confirmed, whereas 32 genera were lumped and 15 genera were split. Taxon sampling impacted the method at the genus level, whereas yielded only insignificant changes at the family level. The other available temporal approach also gives a similar cutoff point to our method. Our approach to identify taxonomic ranks enables taxonomists to revise and propose classifications on an objective basis, changing ranks of clades only when inconsistent with most taxa in a phylogenetic tree. An R script to find the time point with the minimal temporal error is provided.

Figure 1

Distribution of crown ages of currently accepted genera (blue) and families (red) in the studied data set (Parmeliaceae, Ascomycota). The median for both ranks indicated by a dashed line.

Figure 2

Distribution of empirical error score estimated from the tip (time = 0) to the root (the tree depth) for the genus level (A) and family level (B).

Figure 3

Time-calibrated phylogeny of Parmeliaceae and related families based on a multi-locus data set. Temporal bands for family rank (green) and genus level (pink) indicated.

Figure 4

Results of simulations to evaluate sensitivity of temporal banding to taxon sampling. Temporal cut-off indicated as dots (with standard deviation) in relation to amount of removal of taxa from the data set. (A) Temporal cut-off at the genus level. (B) Temporal cut-off at the family level.