Wheat–rye hybrids have a haploid set of 21 wheat chromosomes and seven rye chromosomes. Replication of the rye heterochromatin knobs can be easily visualized in these lines. Previous data showed that in wheat-rye hybrids, either with or without Ph1, DNA replication is initiated in the meiocytes as the tapetal cells are finishing their replication, and all meiocyte replication is completed within a 4 hr period before the telomeres form the bouquet [16]. Therefore, DNA replication in the meiocytes is a good guide for identifying the onset of telomere dynamics and bouquet formation.

In this work, DNA replication in wheat–rye anthers was analyzed by diffusing in 5-ethynyl-2′-deoxyuridine (EdU), a nucleoside analog of thymidine that is incorporated into DNA during active DNA synthesis. In EdU, the terminal methyl group is replaced with an alkyne group, which allows detection using a fluorescent azide compound that covalently binds to the alkyne group in a “click chemistry” reaction [19]. This technology is quick, very specific, and does not require DNA denaturation. It therefore provides good structural preservation and is compatible with dual labelling with telomere probes. After EdU treatment for 4 hr, anthers of wheat-rye hybrids (see Figure 1A), both with and without the Ph1 locus in the wheat genome, were labelled with a telomere probe by fluorescence in situ hybridization (FISH) and chromosomes were counterstained with 4′,6-diamidino-2-phenylindole (DAPI), as described in detail in Materials and Methods. Thus, anthers undergoing or just after DNA replication in the meiocytes were identified via EdU incorporation and labelling, while telomeres in the same meiocytes were labelled by FISH. Anther sections were then imaged using fluorescence microscopy. Our method offers a series of snapshots of in vivo states rather than potentially perturbing the normal progression by in vitro anther culture. These images were taken at essentially random times during (or just after) meiotic DNA replication. Each section gave rise to three stacks of 2D images: one stained with DAPI, one labelled with telomere probes and one labelled with EdU. The images include both meiocytes (which undergo meiosis to form gametes) and tapetal cells (which aid nutrient transportation within the anther and do not undergo meiosis); see Figure 1B. Figures 2A–C show example snapshots of the different stages of bouquet formation, ranging from dispersed telomere clusters to a tight telomere bouquet.

From the raw dataset of images we first extracted the positions of the telomere signals. In each case this involved using the DAPI image to determine the extent of the nucleus and the FISH telomere image to locate the telomeres. For each telomere signal we extracted its 3D position, its size and its intensity. Further, we recorded the point within each nucleus that was furthest from the centre of the anther, i.e. the point on the “outside” of the anther (Figure 1B). For details see Materials and Methods and the Supporting Information. Figure 2D shows a representative example of the cluster positions (extracted from the data in Figure 2A).

Wheat-rye hybrid cells contain 21+7 chromosomes and so, after undergoing DNA replication, a meiocyte nucleus contains 112 telomeres, which, as telomeres at the same end of sister chromatids are close (or attached), would appear as 56 telomere signals. However, it is never possible (at least with our resolution) to even see 56 separate telomere signals. This is due to sister chromatid telomeres being close together (and perhaps even attached), forming sister chromatid telomere clusters. From now on we will often refer to sister chromatid telomeres, namely the pairing of the two telomeres at the same end of sister chromatids. When we refer to pairing/clustering of sister chromatid telomeres, we mean the pairing/clustering of these pairs of telomeres. So, for example, a pair of sister chromatid telomeres would involve a cluster of four telomeres in total.

From the positions and intensities of the telomere signals, we constructed three measures of the telomere distribution. First, we simply counted the number of telomere clusters in a given nucleus, which we call N. As telomere bouquet formation proceeds, N will gradually decrease as more and more telomeres join the bouquet. Second, we determined which point on the surface of the nucleus lies furthest from the telomere clusters (by maximising the sum of the 3D distances to the telomere clusters weighted by their intensities) and then recorded the average telomere distance from this point (again weighted by intensities). Figure 3A shows a sketch of the definition of d_max. This distance, d_max, always takes values above 1.2R (see Supporting Information) and, as bouquet formation proceeds, telomeres move closer to each other and d_max increases, reaching a maximum after bouquet formation has completed. Finally, we calculated d_out, which is the average 3D distance from the telomere clusters to the “outside” pole of the nucleus weighted by intensity, where the “outside” pole of the nucleus is the point on the nuclear membrane furthest from the anther centre (Figure 1B). Figure 3B shows a sketch of how d_out is defined. Unlike d_max which increases with time, d_out decreases as bouquet formation proceeds, equalling zero only if the bouquet forms exactly on the outside of the nucleus. See Supporting Information for detailed definitions of d_max and d_out.

Since our data are noisy, useful information can only be extracted by analysing many nuclei. We therefore considered the histogram of the number of telomere clusters, N, the histogram of the maximum average telomere cluster distance, d_max, and the histogram of the average telomere cluster distance from the outside pole, d_out. Although we do not have time-lapse images and so cannot track individual telomeres as they move towards the bouquet site, we can still extract information on bouquet formation dynamics by studying these histograms. For example, the cluster number histogram shows the proportion of time that nuclei spend with a given number of clusters, which is directly related to the telomere dynamics.

From the 3D positions of the telomere clusters, we checked that telomeres are attached to the nuclear envelope. To do so we calculated the distance of clusters from the centre of the nucleus as a fraction of the nuclear radius, and found that, in both meiocytes and tapetal cells (both with and without the Ph1 locus), this normalised distance has average 0.9 and standard deviation 0.1. This supports the idea that telomeres are associated with the nuclear envelope, not just in meiocytes, but in tapetal cells and potentially, therefore, in many diverse cell types.

We also examined the position of the final bouquet in Ph1− meiocytes relative to the anther centre. To do this we studied images where the bouquet has completely or very nearly formed. In each case we measured the angle, from the centre of the nucleus, between the bouquet and the “outside” pole and plotted the histogram of these angles (Figure S1). If the bouquet formed at random positions on the nuclear membrane this would give a flat histogram. However, since Figure S1 is heavily weighted to small angles, this shows that, in the majority of cases, the bouquet tends to form close to the outside pole of the nucleus, the point on the nuclear membrane furthest from the centre of the anther (Figure 1B).

During meiosis, meiocytes start with their telomeres attached to the nuclear membrane, and then gradually form the telomere bouquet by moving all telomeres to a small region on the membrane. However, before we study the dynamics of forming the bouquet, it is important to study the initial distribution of telomeres (after telomeres have attached to the nuclear envelope but before bouquet formation has started). This distribution can then be used to inform the initial condition for our mathematical model. Since it is not possible to determine from a still image whether a meiocyte has started bouquet formation, we instead use tapetal cells (both from Ph1+ and Ph1− plants) to study the initial telomere distribution in meiocytes. We also checked, as explained below, that the initial telomere distribution in meiocytes is indeed similar to the telomere distribution in tapetal cells.

As discussed previously, we never observed as many as 56 telomere clusters. In fact combining all our tapetal data we find, on average, only 27±1 telomere clusters (n = 133), where the error is the standard error of the mean number of telomere clusters. This suggests that there is always some association between sister chromatid telomeres. Furthermore, strikingly, 27 is close to half of 56, which suggests that the sister chromatid telomeres may be associating in pairs. We also confirmed this result separately for Ph1+ and Ph1− tapetal cells. There are three possibilities for how telomeres might pair together: sister chromatid telomeres on opposite ends of the same chromosome may pair, homeologous chromosomes may pair, or any two sister chromatid telomeres may pair non-specifically. It would be interesting to label individual chromosome telomeres to determine which of these associations occurs.

It is also revealing to study the distribution of the number of clusters. This distribution is approximately normal with a standard deviation of about 8 (see Figure 4A). This implies that, although sister chromatid telomeres on average form pairs, this is not always the case: sometimes fewer than 28 pairs form, and in other cases telomeres form clusters containing more than two sister chromatid telomeres. Potentially this could be because the association between nearby telomeres is transient, with only weak forces holding clusters together, so that telomeres can easily dissociate from existing clusters. It is also possible that the association is not between telomeres but between the chromosomes themselves, perhaps between subtelomeric regions. The exact region of the chromosomes that are associated would impact the distance that telomeres could move from each other, which could also explain the potential movement of telomeres in and out of clusters. Further, the fact that there are clusters containing more than two sister chromatid telomeres disfavours a model where the clusters are solely due to associations between opposite ends of single chromosomes. However, it would still be interesting to know whether pairings between telomeres at opposite ends of a chromatid pair are preferential. Again, labelling individual telomeres would help to answer this question.

In addition to the initial number of telomere clusters, we can also study the initial telomere cluster distribution in space. As before, the initial distribution refers to the distribution once the telomeres are attached to the nuclear envelope, but before bouquet formation has started. When chromosomes are in the Rabl configuration, with centromeres biased towards one side of the nucleus, it is often observed that the telomeres, being the regions on the chromosomes furthest from the centromeres, inhabit regions of the nucleus opposite to the centromeres. In wheat, the Rabl configuration persists through all stages of the cell cycle, and so we expect a bias in the initial distribution of telomeres. To study this we plot the histogram of the maximum average telomere cluster distance, d_max, for tapetal cells (combining both Ph1+ and Ph1− cells; see Figure 4C). If telomere clusters were randomly distributed on the nuclear membrane, a computer simulation (see Supporting Information) shows that we would expect a histogram centred on 1.51R. Conversely if the telomere clusters were confined to a hemisphere the histogram would peak at 1.72R. Since the maximum in Figure 4C occurs at 1.74R, this suggests the telomere clusters are, on average, initially distributed within a region slightly more restricted than a hemisphere (which has an opening angle of 180°). This agrees with the examination of individual images, where it is often obvious that telomere clusters are preferentially grouped within some hemisphere (for example, see Figure 2D). In fact, simulations (see Supporting Information) show that this data fits well with telomere clusters confined to a cap subtending an opening angle that follows a normal distribution with mean <Θ₀> = 170° and standard deviation δΘ₀ = 30°. This result is not changed if Ph1+ or Ph1− tapetal cells are analysed separately.

To determine whether this initial cap has any preferred orientation with respect to the centre of the anther (as suggested in previous models [14]), we calculated the distribution of average distances of telomere clusters from the “outside” pole for tapetal cells, i.e. the distribution of d_out (Figure 4D). If, for example, telomere clusters sit in the “outside” cap, then the average value of d_out will be lower than for other distributions. In fact, computer simulations (see Supporting Information) show the average value of d_out would then be 0.93R. Conversely a random orientation for the telomere cap would give a distribution with an average of 1.31R. The data (combining Ph1+ and Ph1− cells; Figure 4D), with average 1.30R, matches much better with this second case, showing that the initial cap containing the telomeres does not have a preferred orientation. This result is unchanged if we separately analyse Ph1+ and Ph1− cells. This conclusion is important for our mathematical model, as we explain below.

Although the average of d_out matches well between the experimental data and our cap distribution, the full experimental distribution is still somewhat broader (Figure 4D). Nevertheless, the width of the distribution for a randomly-orientated cap is much closer to the experimental value than that for an “outside” cap (see Supporting Information).

The Rabl configuration may also influence the position of telomere clusters within the randomly-orientated cap. For example, chromosomes with similar arm lengths may tend to lie closer to each other than to other chromosomes. This may help explain the spread in initial cluster size, with some sister chromatid telomeres grouped in pairs and others grouped in larger clusters. In principle it would be possible to explicitly model the position of the full length of each chromosome, via a semiflexible polymer model (as in [20] and [12]), in order to determine the initial telomere positions. However, such an analysis is beyond the scope of this work and instead we assume, for simplicity, that the telomere clusters are initially placed randomly within the randomly-orientated cap.

Since the Ph1 locus has been implicated in preventing homeologous pairing, it may well affect the dynamics of telomere bouquet formation. To study this issue we considered telomere data both from a wheat-rye hybrid with the Ph1 locus (Ph1+) and in a mutant where the locus has been deleted (Ph1−). As expected, we found a wide range in the number of telomere clusters in the Ph1− meiocyte images, ranging from many separate clusters to a single large cluster after the bouquet has formed (see below). However, interestingly, when we plotted the histogram of the number of telomere clusters for Ph1+ meiocytes (Figure 4B), we found little evidence of bouquet formation. In fact we found a distribution that is remarkably similar to the distribution for tapetal cells (Figure 4A). The bouquet eventually forms even in Ph1+ meiocytes [16], but since our images (from around the time of meiocyte replication) do not show any noticeable change from the tapetal telomere distribution, we conclude that the onset of bouquet formation is delayed in the presence of Ph1. Since it is not clear whether homologous pairs form before or after formation of the bouquet, perhaps the purpose of this delay in the presence of Ph1 is to facilitate correct pairing of homologues, allowing more time to check potential pairings and dissociate incorrectly-paired homeologous chromosomes.

To further confirm our conclusion that bouquet formation has apparently not started in our Ph1+ meiocyte dataset, we also compared the d_max and d_out distributions from Ph1+ meiocytes with those from the tapetal (both Ph1+ and Ph1−) data. Histograms for d_max and d_out (Figure S2) are, as with tapetal cells, consistent with telomere confinement to a randomly-orientated cap, whose opening angle is slightly less than that of a hemisphere (∼170° on average). Further the average number of telomere clusters is 26±1, again agreeing with the tapetal data (the error is the standard error in the mean). The width of the cluster number histogram, 9, is similar again to that for tapetal cells. The fact that both tapetal cells (with and without Ph1) and Ph1+ meiocytes share the same telomere cluster distribution, both in terms of number and position, buttresses our hypothesis that Ph1− telomeres also start in the same configuration.

In contrast, Ph1− meiocytes do exhibit intricate bouquet-forming telomere dynamics. This is seen in the histogram of the number of telomere clusters (Figure 5), which now has a second peak at the origin, representing nuclei that are close to completing bouquet formation, with only a few remaining clusters. Although the dynamics of bouquet formation is clearly visible in the histogram for small numbers of clusters, the large peak around 28 clusters seen in Ph1+ meiocytes and tapetal cells (in both Ph1+ and Ph1−) is still visible, supporting the idea that telomere clusters in Ph1− meiocytes also start in the same configuration. We believe the presence of two peaks is due to our imaging dataset capturing not only the dynamic formation of the bouquet, but also the period before bouquet-formation onset, when the telomere clusters are arranged in their initial configuration. This leads to the superposition of the initial telomere cluster distribution and the bouquet dynamics distribution (as seen in Figure 5).

It is an interesting question as to how multicellular organisms coordinate meiosis amongst their constituent cells. In wheat, for example, meiosis within different meiocytes could be coordinated at various levels, including that of single meiocytes, locules, anthers, florets or even spikelets (see Figure 1A). Our Ph1− meiocyte data originates from anthers within 12 separate florets and so we were also able to study whether individual florets showed synchrony in the time that bouquet formation started, i.e. whether all meiocytes in a given floret begin to form the bouquet at the same time. In fact it may be that the synchrony is not within florets, but at a lower level, say within anthers. However, since our dataset is only split into florets, we can only test synchrony within florets. To investigate this question we split our data into separate florets and considered the cluster number distribution for each. If florets are synchronous then we would expect a tighter distribution, i.e. smaller variance, for individual florets compared to that for all the florets combined. We found the mean variance in the number of clusters for individual florets was only 66±18 (this error is the standard error in the mean variance), compared to 160 for the whole data set (see Supporting Information). To test whether this was significant we repeatedly randomly partitioned the complete dataset into 12 appropriately-sized sub-datasets, finding that the mean variance followed a distribution with mean 160 and standard deviation 18 (see Supporting Information). Since a mean variance of 66 is far from the randomly-partitioned mean variance of 160, we conclude that individual florets do indeed show synchrony, with meiocytes within many florets starting bouquet formation at similar times.

However, it is worth noting that the distribution of the variances in cluster number for individual florets, with mean 66, has a relatively large standard deviation of 61, which suggests that, although many florets show synchrony, this may not be true of all florets. This may be because the synchrony is not within florets, but within anthers. It would be interesting to test whether synchrony is only at the anther level by studying images from individual anthers.

To understand better the mechanics of telomere bouquet formation, we constructed a mathematical model incorporating the dynamics of telomere clusters moving along the nuclear membrane. We then used the model to simulate bouquet formation. To do this we idealised the nuclear membrane as a sphere of radius R, with each telomere cluster represented by a position on the surface of the sphere. Although nuclei are never exactly spherical, they are frequently close to this ideal (with the centre-to-edge distance, on average, varying by only about 10%) and so we do not expect a spherical approximation to substantially affect our results.

First, we considered a pure diffusional model, with no drift. Although this can lead to bouquet formation in the correct total time it is unable to capture only an 8% variation in this time. In fact, with D = 0.025 µm² s⁻¹, we found T_bouq = 6.6±2.6 hr, with an approximately 40% variation. Further, such a model cannot capture the cluster number histogram shown in Figure 5, since the minimum around N = 12–16 is too pronounced. Thus a pure diffusion model is unlikely, which agrees with the same conclusion in [14].

Next we considered a pure drift model, without any diffusion. In [14] this was excluded since it could not match the observed variation in T_bouq, producing far too small a variation. However, our initial conditions are different: our telomeres are initially contained in a randomly-orientated cap, rather than in an outwardly-pointing hemisphere as in [14]. This makes a crucial difference since now the dominant source of variation in T_bouq is due to the initial cap orientation. With v = 8.5×10⁻⁴ µms⁻¹ we found that T_bouq = 5.6±1.0 hr. This is in good, although not perfect, agreement with the observed value in [14] (although we note that the standard deviation in [14] is for rye and is based on only four measurements). Thus, by appreciating that the initial cap containing the telomeres is not necessarily on the outside of the anther, a pure drift model can explain the data. Figures 6A and 6B shows examples of the evolution of d_max and d_out for the pure drift model.

Further, the pure drift model appears to match well with the cluster number histogram (Figure 5). To test this more rigorously we performed a chi-squared goodness of fit test, which gave a test statistic of 2.1, a value that is well below that required to doubt the model at the 5% confidence limit (which is 9.5). Thus there is no reason to reject the null hypothesis that our experimental data is well-described by our pure drift model. See Supporting Information for more details. This good match between model and data would not have been the case if the telomere clusters had started in the outside hemisphere rather than a randomly-orientated cap. In this latter case (as in the experimentally measured data) the histogram contains an extra peak at small numbers of clusters that is caused by the few telomere clusters that start on the side of the nucleus opposite to the bouquet and take a relatively long time to move towards the bouquet site. It is these final few telomere clusters that are the last to join the bouquet and, since they are few in number (due to the decreasing area near the poles), there are relatively long gaps between the final few telomere clusters joining the bouquet, leading to the extra peak for small cluster numbers. We also considered the behaviour of d_max and d_out as a function of the number of telomere clusters for Ph1− meiocytes. Despite the noise in the data, the pure drift model still captures the overall telomere dynamics (Figures 6C and 6D).

Another way of quantifying telomere dynamics is via the average telomere cluster distance, d_pairs, which is defined as the mean distance between all pairs of telomere clusters (without intensity-weighting). As the bouquet forms and all telomeres approach a point close to the outside pole, this distance tends to zero. If we plot d_pairs as a function of time for our pure drift model we find two categories of behaviour (Figure S5). Firstly, for cases where the initial cap is mostly facing the outside of the nucleus (nearest where the bouquet forms), d_pairs is monotonically decreasing. Secondly, however, there are cases where the initial cap is partially facing inwards, where we find that d_pairs initially rises before eventually dropping to zero. This initial rise is due to telomere clusters that start near the inside pole of the nucleus and must first diverge from each other as they proceed through the equator, until they form the bouquet near the outside pole. When we average over all initial cap orientations we find, after the initial period of T₀, a slight rise in d_pairs, followed by a relatively gentle decrease, before d_pairs finally drops to zero (Figure S5). This effect was also noted in [14], where its origin was mysterious, and was suggested to be due to a short period between relaxation of the Rabl configuration and directed movement towards the bouquet site, when telomere clusters were able to diffuse freely. Our model, however, provides a natural explanation for this behaviour without the need to postulate an extra period of free diffusion before bouquet formation starts.

As we have seen, a pure directed movement model can fit our data, and hence there is no necessity for diffusive motion. The effect of adding such diffusion is to increase the peak at small cluster numbers (since the final few telomere clusters take a relatively long time to find the bouquet due to partially random rather than directed movement). This effect can be compensated for by increasing the waiting time, T₀, although then the trough at N = 12–16 is more pronounced. Small amounts of diffusion still match the experimental data and so cannot be excluded. However, the important point is that diffusion is not required in our model to fit our data and since, as we discuss below, global diffusion may be negligible, we predict that pure drift is the relevant mechanism in our system.

In the simplest version of the model, telomere clusters move with constant drift speed directly towards the bouquet site. Although we do not know which component of the cytoskeleton is responsible for causing this drift, such a model would require a perfectly ordered cytoskeleton, with all cytoskeletal elements near the nucleus pointing directly towards the bouquet site. Although there is some evidence that microtubules in plants lie tangential to the nucleus during prophase [22], it is not clear to what extent there is variation within this arrangement. In fact, in rye there is evidence that, during bouquet formation, there is significant disorder to the microtubules near the edge of the nucleus [23], with perhaps only the overall average direction pointing towards the bouquet site.

To model this, we introduce a random element to the drift direction in the model. Unless the drift direction varies enormously, we emphasise that this is not the same as simply adding diffusion since telomeres still almost always head roughly towards the bouquet site. Rather this situation is more like constant drift directed towards the bouquet site, with a small amount of transverse diffusion. Telomere clusters are assumed to drift in some direction (not necessarily directly towards the bouquet site) for some distance, L_R, called the run length. Without knowing the details of the cytoskeletal elements involved in telomere movement, it is difficult to estimate the run length. However, motivated by studies of kinesin [24], we use L_R = 1 µm. The drift direction, ψ, is chosen (independently for each telomere cluster) from a truncated normal distribution, with mean centred on the direction towards the bouquet site and with standard deviation, δψ. After a telomere cluster has moved the run length in this drift direction, a new independent drift direction is chosen. The standard deviation of the drift direction, δψ, is thus a measure of the directionality of the cytoskeleton. See Supporting Information for more details. It is worth noting that, even with a random element to the drift direction, a randomly-orientated initial cap is still required to produce a good match with the experimental cluster number histogram.

To fit with the experimental data it is necessary, for each value of δψ, to refit both the drift speed, v, and the waiting time, T₀. After doing this it is notable that a non-zero variation in the drift direction can produce a slightly better match with the experimental cluster number histogram (Figure 5). To quantify this, we use the chi-squared test-statistic as a measure of the goodness-of-fit. As δψ increases from zero the value of the statistic decreases, reaching a minimum of 1.6 at around δψ = 40°, with similar results obtained if the run length is reduced to L_R = 0.5 µm. So although we do not know the relevant run length for telomere movement, for reasonable values we predict that even a relatively large variation in the cytoskeletal directionality does not seem to interfere with bouquet formation.

The plants used came from crosses between rye (Secale cereale cv. Petkus) and hexaploid wheat (Triticum aestivum cv. Chinese Spring). Two crosses were used: one from wild-type wheat and one with the wheat lacking the Ph1 locus [36]. Seeds from both genotypes were germinated on petri dishes for 3–4 days. The seedlings were vernalized for 3 weeks at 4°C and then transferred to a controlled environmental room with the following growth conditions: 16 hours at 20°C (day) and 8 hours at 15°C (night) with 85% humidity. Plants were collected after 6–7 weeks.

EdU treatment was carried out as described previously [16]. Briefly, tillers containing immature pre-meiotic spikes were detached after an 8 hr period in the dark and immediately transferred to a solution of 100 mM sucrose and 1 mM EdU (Invitrogen: A10044). The cut tillers in individual tubes were left in the light for four hours, after which the spike was dissected out and fixed in 4% formaldehyde solution, freshly made from paraformaldehyde [37]. The fixed samples were placed in biopsy cassettes and embedded in wax using a Tissue-tek vacuum infiltrator processor (VIP) machine [38]. They were then sectioned using a microtome [25] to produce sections of 10 µm thickness.

EdU detection was carried out using a Click-iT EdU Alexa Fluor 488 Imaging Kit, according to the manufacturer's instructions (Invitrogen: C10337).

Fluorescence in situ hybridization was carried out as previously described [39]. Telomeric probes were labelled with biotin-16-dUTP by nick translation of PCR-amplified products using the oligomer primers (5′-TTTAGGG-3′)₅ and (5′-CCCTAAA-3′)₅ in the absence of template DNA [40], and detected using streptavidin-Cy3 conjugate. Chromosomes were counterstained with DAPI (4′,6-diamidino-2-phenylindole) and mounted in Vectashield (H-1000) medium.

To carry out dual labelling with both EdU and telomere probes, samples (sections) were first digested in 2% cellulose, 2% pectolyase in 1×TBS for 3 hours at 37°C. Then, the telomere probe was hybridised to the sample, incubated overnight at 37°C and washed according to the usual protocol [39]. Samples were then blocked in 3% BSA and followed by the EdU detection protocol. Before staining with DAPI, samples were incubated with the required antibodies for the telomere probe, and then finally mounted in Vectashield.

Images were acquired with a Nikon Eclipse E600 epifluorescence microscope equipped with a Hamamatsu Orca-ER cooled CCD camera and a Prior Proscan x,y,z stage. Stack images of individual cells were collected by using MetaMorph (Universal Imaging) software. Deconvolutions of images were processed with AutoDeblur (AutoQuant Imaging). Projections of 3D pictures were performed with ImageJ. These images were also used in [16] to study the possible Cdk2-type activity of the Ph1 locus. However, the work described here is the first detailed analysis of this data, where the actual telomere cluster positions are determined and analysed.

From each DAPI image we first identified the nucleus by generating ellipses that fit around the DAPI stain. Then, from the equivalent telomere FISH image, we identified telomeres within the nucleus by searching for discrete pixels with an elevated FISH signal. Pixels were only counted as part of a telomere if their intensity was greater than some threshold, which, for each image, was chosen as 0.12 of the maximum pixel intensity. This value was chosen since it gave consistently-sized clusters: larger values missed some telomere clusters and smaller values sometimes led to large regions being incorrectly identified as a single cluster. After imposing the threshold, clusters were defined such that adjacent pixels (including diagonally adjacent) were considered part of the same cluster. In order to remove spurious background signals, clusters were only counted if their total intensity was greater than 2 (where each pixel had a maximum intensity of 1). We tried various other values for the minimum total intensity, although this did not affect our results. See Supporting Information for more details.