The genus Rosa has a complex evolutionary history caused by several factors, often in conjunction: extensive hybridization, recent radiation, incomplete lineage sorting, and multiple events of polyploidy. We examined the applicability of AFLP markers for reconstructing (species) relationships in Rosa, using UPGMA clustering, Wagner parsimony, and Bayesian inference. All trees were well resolved, but many of the deeper branches were weakly supported. The cluster analysis showed that the rose cultivars can be separated into a European and an Oriental cluster, each being related to different wild species. The phylogenetic analyses showed that (1) two of the four subgenera (Hulthemia and Platyrhodon) do not deserve subgeneric status; (2) section Carolinae should be merged with sect. Cinnamomeae; (3) subsection Rubigineae is a monophyletic group within sect. Caninae, making sect. Caninae paraphyletic; and (4) there is little support for the distinction of the five other subsections within sect. Caninae. Comparison of the trees with morphological classifications and with previous molecular studies showed that all methods yielded reliable trees. Bayesian inference proved to be a useful alternative to parsimony analysis of AFLP data. Because of their genome-wide sampling, AFLPs are the markers of choice to reconstruct (species) relationships in evolutionary complex groups.

According to previous cytological evidence, the hemisexual dog-rose species, Rosa sect. Caninae, transmit only seven chromosomes (derived from seven bivalents) through their pollen grains, whereas egg cells contain 21, 28 or 35 chromosomes (derived from seven bivalents and 14, 21 or 28 univalents) depending on ploidy level. Two sets of reciprocal pairwise interspecific crosses involving the pentaploid species pair R. dumalis and R. rubiginosa, and the pentaploid/tetraploid species pair R. sherardii and R. villosa, were analysed for 13 and 12 microsatellite DNA loci, respectively. Single loci were represented by a maximum of three simultaneously occurring alleles in R. villosa, and four alleles in the other three parental plants. In the experimentally derived offspring, the theoretical maximum of five alleles was found for only one locus in the pentaploid progenies. Microsatellite DNA allele composition was identical with that of the maternal parent in 10 offspring plants, which were probably derived through apomixis. Almost all microsatellite DNA alleles were shared with the maternal parent also in the remaining offspring, but 1-4 alleles shared only with the paternal parent, indicating sexual seed formation. Analysis of quantitative peak differences allowed a tentative estimation of allelic configuration in the individual plants, and suggested that bivalent formation preferentially takes place between chromosomes that consistently share the same microsatellite alleles and therefore appear to be highly homologous. Moreover, alleles that were shared between the species in each cross combination comparatively often appear to reside on the bivalent-forming chromosomes, whereas species-specific alleles instead occur comparatively often on the univalent-forming chromosomes and are therefore inherited through the maternal parent only. Recombination then takes place between very similar genomes also in interspecific crosses, resulting in a reproduction system that is essentially a mixture between apomixis and selfing.

An allopolyploid complex with high genomic integrity has been studied. Dogroses transmit only seven chromosomes (from seven bivalents) through the pollen, whereas 21, 28 or 35 chromosomes (from seven bivalents and 14, 21 or 28 univalents) come from the egg cells. Seedlings derived from two interspecific crosses were analysed with flow cytometry and molecular markers to determine ploidy level, mode of reproduction and genomic constitution. Evidence was obtained for the formation of unreduced male and female gametes, which can take part in fertilization (producing seedlings with higher ploidy than the parental plants) or in apomictic reproduction. Random amplified polymorphic DNA (RAPD) and microsatellite analyses indicated that three seedlings (5%) were derived through apomixis, whereas the other 49 were hybrids. Bivalent formation appears to involve chromosomes that consistently share the same microsatellite alleles. Allele‐sharing between the maternally transmitted and highly conserved univalent‐forming chromosomes reflected the taxonomic distance between different genotypes. The frequently recombining bivalent‐forming chromosomes were taxonomically less informative.

Low polymorphism in cultivated watermelon has been reported in previous studies, based mainly on US Plant Introductions and watermelon cultivars, most of which were linked to breeding programmes associated with disease resistance. Since germplasm sampled in a putative centre of origin in southern Africa may harbour considerably higher variability, DNA marker-based diversity was estimated among 81 seedlings from eight accessions of watermelon collected in Zimbabwe; five accessions of cow-melons (Citrullus lanatus var. citroides) and three of sweet watermelons (C. lanatus var. lanatus). Two molecular marker methods were used, random amplified polymorphic DNA (RAPD) and simple sequence repeats (SSR) also known as microsatellite DNA. Ten RAPD primers produced 138 markers of which 122 were polymorphic. Nine SSR primer pairs detected a total of 43 alleles with an average of 4.8 alleles per locus. The polymorphic information content (PIC) ranged from 0.47 to 0.77 for the RAPD primers and from 0.39 to 0.97 for the SSR loci. Similarity matrices obtained with SSR and RAPD, respectively, were highly correlated but only RAPD was able to provide each sample with an individual-specific DNA profile. Dendrograms and multidimensional scaling (MDS) produced two major clusters; one with the five cow-melon accessions and the other with the three sweet watermelon accessions. One of the most variable cow-melon accessions took an intermediate position in the MDS analysis, indicating the occurrence of gene flow between the two subspecies. Analysis of molecular variation (AMOVA) attributed most of the variability to within-accessions, and contrary to previous reports, sweet watermelon accessions apparently contain diversity of the same magnitude as the cow-melons.

In Rosa canina (2n ¼ 5x ¼ 35), the pollen and ovular parents contribute, respectively, seven and 28 chromosomes to the zygote. At meiosis I, 14 chromosomes form seven bivalents and 21 chromosomes remain as univalents. Fluorescent in situ hybridization to mitotic and pollen mother cells (PMC) of R. canina showed that 10 chromosomes (two per genome) carry ribosomal DNA (rDNA) loci. Five chromosomes carry terminal 18S-5.8S-26S rDNA loci; three of these also carry paracentric 5S rDNA loci and were designated as marker chromosomes 1. Five chromosomes carry only 5S rDNA loci and three of these were designated as marker chromosomes 2. The remaining four of the 10 chromosomes with rDNA loci were individually identifiable by the type and relative sizes of their rDNA loci and were numbered separately. At PMC meiosis, two marker chromosomes 1 and two marker chromosomes 2 formed bivalents, whereas the others were unpaired. In a gynogenetic haploid of R. canina (n ¼ 4x ¼ 28), obtained after pollination with g-irradiated pollen, chromosomes at meiosis I in PMC remained predominantly unpaired. The data indicate only one pair of truly homologous genomes in R. canina. The 21 unpaired chromosomes probably remain as univalents through multiple generations and do not recombine. The long-term evolutionary consequence for the univalents is likely to be genetic degradation through accumulated mutational change as in the mammalian Y chromosome and chromosomes of asexual species. But there is no indication that univalents carry degenerate 5S rDNA families. This may point to a recent evolution of the R. canina meiotic system. Heredity (2005) 94, 501-506.