AFLP-based population structure analysis as a means to validate the complex taxonomy of dogroses (Rosa section Caninae)

Within the genus Rosa numerous species have been described. Circumscription of the dogrose section Caninae is straightforward, but the delineation of species and subsections within this section is less clear, partly due to hybridisation between species. We have investigated the extent to which DNA marker-based information of wild populations corroborates present-day dogrose taxonomy and hypotheses about the origination of taxa. Sampling was conducted in a transect across Europe, collecting over 900 specimens of all encountered dogrose taxa. For comparison, we also included more than 200 samples of species belonging to other sections. Two lines of statistical analyses were used to investigate the genetic structure based on AFLP data: 1) an unstructured model with principal coordinate analysis and hierarchical clustering, and 2) a model with a superimposed taxonomic structure based on analysis of genetic diversity using a novel approach combining assignment tests with canonical discriminant analysis. Support was found for five of the seven subsections, whereas R. balsamica apparently belongs to subsection Caninae thus omitting the need for recognizing subsection Tomentellae. For R. stylosa, a hybridogenic origin with a non-dogrose section member has been suggested, and it can be treated either as a separate subsection or within subsection Caninae. Within the subsection Rubigineae, a species cluster with low support for the taxa R. micrantha, R. rubiginosa and the putatively hybridogenous R. gremlii was identified. Similarly, several species in the subsection Caninae overlapped considerably, and are best regarded as one common species complex. This population genetic approach provides a general method to validate the taxonomic system in complex and polyploid taxa.