Many diverse systems for sex determination have evolved in plants and animals [1]–[3]. One involves physically distinct sex chromosomes, a system thought to have evolved independently many times by suppression of recombination around the sex determination genes, followed by differentiation and degeneration of the non-recombining chromosome [4]. In the fungal kingdom, there is no dichotomy of individuals into sexes bearing different gametes, but instead mating-type identity is determined by inheritance of alleles at mating-type loci. Nevertheless, chromosomal regions controlling mating-type identity in fungi share features with the more complex sex chromosomes of algae, plants and animals [5]. Although mating-type loci consist of one to a few linked genes, and are thus limited to a small genomic region, alleles at the mating-type loci of fungi often differ to the extent that there is no sequence similarity between them [e.g. 6],[7]. Furthermore, complete recombination cessation in the region around the mating-type loci have been reported from several fungal taxa [7]–[9]. However, fungi generally have much smaller regions of suppressed recombination than animal dimorphic chromosomal regions. For example, in Cryptococcus neoformans recombination is suppressed on only 6% of a 1.8 Mb chromosome, or ca. 100 kb [8].

The filamentous ascomycete Neurospora tetrasperma constitutes an exception in which recombination is blocked over the majority of the chromosome containing the mating-type loci, referred to as the mating-type (mat) chromosome. Moreover, the non-recombining region is flanked by distal regions where obligate crossovers are observed [10],[11]. In this species, the large non-recombining region is associated with a uniquely fungal life cycle, called pseudohomothallism, where self-fertility is enforced by maintenance of a constant state of heterokaryosis, normally only observed post-fertilization in this group of fungi. Modified programs of meiosis and sexual spore development lead to the packaging of two haploid nuclei of opposite mating-type (mat A and mat a) into each N. tetrasperma ascospore progeny [12],[13]. The species maintains its ability to outcross by the occasional production of homokaryotic, self-sterile (mat A or mat a) propagules, both asexual and sexual, which may be isolated to obtain single mating-type component strains. A key feature of meiosis in N. tetrasperma is suppressed crossing over on the mating-type bivalent, ensuring that mat A and mat a will segregate in the first division of meiosis. Although suppressed recombination between mat and the centromere would suffice to provide the mechanism for segregation of mating type, the non-recombining region covers a much larger area of the chromosome [10]. The mating-type chromosomes of N. tetrasperma therefore resemble the sex chromosomes of animals and plants both in failing to recombine over the majority of their length and having obligate crossovers at the flanking “pseudoautosomal” regions. However, the mechanism initiating the divergence of mating-type chromosomes in N. tetrasperma differs from that of animal and plant sex chromosomes, where initiation is suggested to be due to selection for linkage between primary sex-determining alleles and other interacting genes. Such interactions involve alleles with beneficial effects in one sex, but which reduce the fitness of the other sex (e.g. sexually antagonistic genes, [4] and references therein).

Two factors have been suggested to affect recombination between evolving sex chromosomes: the spread of genetic modifiers of recombination rates [14], and chromosomal rearrangements causing chromosome heteromorphism [4]. Both these factors have been suggested to be responsible for the blocked recombination in N. tetrasperma. Reciprocal introgression of the mating-type chromosomes between N. tetrasperma and its close relative N. crassa indicate that both autosomal genes and structural heterozygosity affect recombination in this species [11].

By investigating nucleotide sequence divergence of genes shared between homologous non-recombining chromosomes, insight can be gained into when and how recombination ceased between them, assuming they have been evolving independently since recombination was disrupted. This approach has been used for several systems, including X–Y gametologs of humans [15], mouse [16], dioecious plants [17], W–Z gametologs of chicken [18], and genes located on the mating-type chromosomes of the basidiomycete Cryptococcus [19]. All of these systems exhibit “evolutionary strata”, the term initially introduced by Lahn and Page [15] to represent different sequential steps whereby recombination become arrested between the proto-sex chromosomes.

In this study, we compared the level of divergence between alleles on mat A and mat a-chromosomes from a single wild-type N. tetrasperma heterokaryon and found that evolution of the mating-type chromosome in this lineage involved two successive events. The first suppressed recombination over a very large region-at least 6.6 Mbp, or 75% of the chromosome, and was contemporaneous with the split of N. tetrasperma from a common ancestor with the outcrossing relative N. crassa. The second was confined to a smaller region in which recombination ceased more recently. In spite of the early origin of the first stratum, genealogies of five genes located in this region from strains belonging to an additional N. tetrasperma phylogenetic lineage indicate totally independent initiations of recombination suppression in the two lineages. We hypothesize that pseudohomothallism in N. tetrasperma evolved in a stepwise manner, and that the steps required to block recombination along the mat-chromosome occurred independently in the different lineages in order to facilitate a more efficient first division meiotic segregation of mating type.

Although fungi have no differentiated sexes, i.e. female/male dichotomy of individuals carrying gametes of different sizes, the data presented here confirms that similar mechanisms drive the evolution of sex chromosomes found in the animal and plant kingdoms and the fungal mating-type chromosomes in Neurospora tetrasperma. First, the mating-type chromosomes in the pseudohomothallic N. tetrasperma fail to recombine over the majority of its length; here we establish that in strain P581 the non-recombining region covers almost 7 Mbp, over 75% of the mating-type chromosome. Previous studies, using the same fungal strain, have shown suppressed recombination of a large portion of the mating-type chromosomes of N. tetrasperma [9]–[11]. This study was able to more precisely identify the boundaries and size of the non-recombining region. Notably, the left arm of the non-recombining region is shorter than previously reported [22]; the earlier suggestion that the non-recombining region begins around nit-2 was not supported here. Instead, the left boundary appears located close to mus-42 (Figure 1A).

Furthermore, in analogy to systems of sex chromosomes representing all three kingdoms [15]–[19], our data revealed that the evolutionary events leading to the suppression of recombination involved two successive events, resulting in two evolutionary strata, 6.6 Mbp and 0.3 Mbp in size, respectively. Thus, the data suggest that in this fungus stepwise cessation of recombination can take place over a vast genomic region up to 6.6Mbp in size. The event(s) that suppressed recombination are unknown. In the absence of a single, large structural change we may expect a more gradual change in divergence along the chromosome. The simplest possible hypothesis is that Stratum 1 correlates with one large inversion. However, when such a pericentric inversion has been observed on the mating-type chromosome of N. crassa, an inversion loop appears to be formed during meiosis, allowing both pairing and crossing over of the inverted region as well as the formation of inviable and unstable progeny [23]. Since such an inversion loop or crossovers do not occur in N. tetrasperma, multiple mechanisms for blocking recombination along the mating-type chromosome are likely to be involved. With the upcoming availability of the genome sequence of N. tetrasperma (http://www.jgi.doe.gov/) we should be able to disentangle what factor resulted in ceased recombination in this region.

Interestingly, the non-recombining region extends over the majority of the chromosome, although a shorter non-recombining region between mat and the centromere would itself be sufficient for the first division meiotic segregation of mating-type that is needed for pseudohomothallism [13]. If one event caused the large Stratum 1, as indicated by our data, it could be the reason for the apparently unnecessary large size. In this context, the reason for the more recent Stratum 2 is obscure. In an earlier study of C. neoformans Fraser and co-workers hypothesized that the accumulation of transposable elements would explain the pattern of a gradually growing non-homologous region between the two mating-type chromosomes [19]. Testing the transposon-mediated chromosomal rearrangement hypothesis in N. tetrasperma would require further investigation, again possible with the sequenced genome.

A small number of genes showed sequence divergence (d_S) that deviated slightly from the other genes located within the same stratum. For example, in Stratum 2, rid and cys-5 showed no sequence divergence in exons between corresponding alleles (d_S = 0). In these two genes, no introns are present to support homogenization or divergence between the alleles. However, the mapping data indicate conserved order of nine markers (including rid and cys-5) located between ro-10 and mat (Supporting Information, Table S1), suggesting that they are not translocated in N. tetrasperma. For eth-1, located in Stratum 1, we found a ds-value of 0.029, which is roughly half the value found for alleles of the other genes in that stratum. As the actual mapping location of eth-1 was not investigated, the possibility should not be excluded that this gene was recently translocated from the younger evolutionary stratum.

Studies from a diverse range of systems have revealed that lack of recombination per se is sufficient for genetic degeneration of a chromosome such as gene loss and null-mutations at protein coding genes, and for transposable element accumulation [4],[24]. The heterokaryotic life-style of N. tetrasperma, in which cells during the whole life-cycle carry two nuclei of separate mating-types, would be expected to further favor the erosion of a gene located on these chromosomes, since maintaining function requires an active counterpart on only one of the chromosomes. However, we found no evidence for relaxed selective constraints, as judged from the d_N/d_S comparisons between genes on the mating-type chromosomes and the autosomes, or gene loss in the mating-type chromosomes of N. tetrasperma. This observation could be due to the very young age of the system. Alternatively, an occasional homokaryotic part of the life cycle [25], would unmask recessive deleterious mutations and purge these from the population. The accumulation of repetitive elements along the mating-type chromosome remains an interesting target for future research, because these are found to be very early colonizers of non-recombining chromosomes of animal and plant systems [26]–[29].

Multiple phylogenetic lineages exist within N. tetrasperma, all of them being pseudohomothallic [20]. The transition from heterothallism to pseudohomothallism in N. tetrasperma is associated with loss of mating-type heterokaryon incompatibility. This loss of heterokaryon incompatibility is required to maintain pseudohomothallism and may explain the sexual dysfunction observed when single mating-type strains are outcrossed in the laboratory [30]. The existence of eight-spored outbreeding sister-species to N. tetrasperma [i.e. (N. crassa (N. tetrasperma, PS1, N.sitophila)) see [31]; Jeremy Dettman and John Taylor, personal communication] indicate that the non-recombining region formed at or after the split of N. tetrasperma from N. crassa. We found that Stratum 1 was contemporaneous with the split of N. tetrasperma from a common ancestor with N. crassa, estimated to be between 3.5 to 5.8 MYA. Assuming that the non-recombining region is a prerequisite for pseudohomothallism would suggest that all lineages of N. tetrasperma should share Stratum 1 of the mat-chromosome. In contrast, the divergence data and genealogies of five genes located in Stratum 1 suggest that the two different N. tetrasperma lineages share a non-recombining region on the mating-type chromosome due to convergent evolutionary events. We hypothesize that pseudohomothallism evolved in a stepwise manner, and that in the early evolution of pseudohomothallism in N. tetrasperma there was no recombination block, but that it evolved independently in the different lineages as a selective response for a more efficient pseudohomothallism with absolute first division meiotic segregation of mating type.

Elucidating mechanisms by which sex chromosomes evolve from autosomes has been accelerated by the revolution in genomic science. Considerable insight into plants and animals can be gained through the study of alternative systems, such as N. tetrasperma, in which the genomic consequences of reduced recombination per se can be disentangled from sex-biased evolutionary forces such as male-biased mutation and dispersal [32],[33]. Thus, the system presented here has the potential to contribute significantly to the general understanding of the forces shaping sex chromosomes, as well as general insights into how levels of polymorphism vary among different regions of the genome.