Statistical support for the hypothesis of developmental constraint in marsupial skull evolution

Abstract

Background: In contrast to placental neonates, in which all cranial bones are ossified, marsupial young have only the bones of the oral region and the exoccipital ossified at birth, in order to facilitate suckling at an early stage of development. In this study, we investigated whether this heterochronic shift in the timing of cranial ossification constrains cranial disparity in marsupials relative to placentals.

Methods: We collected three-dimensional (3D) landmark data about the crania of a wide range of extant placentals and marsupials, and from six fossil metatherians (the clade including extant marsupials and their stem relatives), using a laser scanner and a 3D digitizer. Principal components analysis and delta variance tests were used to investigate the distribution and disparity of cranial morphology between different landmark sets (optimizing either number of landmarks or number of taxa) of the whole skull and of individual developmental or functional regions (neurocranium, viscerocranium, oral region) for extant placentals and marsupials. Marsupial and placental data was also compared based on shared ecological aspects including diet, habitat, and time of peak activity.

Results: We found that the extant marsupial taxa investigated here occupy a much smaller area of morphospace than the placental taxa, with a significantly (P<0.01) smaller overall variance. Inclusion of fossil taxa did not significantly increase the variance of metatherian cranial shape. Fossil forms generally plotted close to or within the realm of their extant marsupial relatives. When the disparities of cranial regions were investigated separately, significant differences between placentals and marsupials were seen for the viscerocranial and oral regions, but not for the neurocranial region.

Conclusion: These results support the hypothesis of developmental constraint limiting the evolution of the marsupial skull, and further suggest that the marsupial viscerocranium as a whole, rather than just the early-ossifying oral region, is developmentally constrained.

Figure 1

Principal component (PC)s 1 and PC2 and selected wireframes and line drawings for the ‘maximum landmarks’ dataset. (Top) dorsal and (bottom) lateral views. Letters represent placental taxa, as described in the key; squares represent marsupials. Solid line indicates the range of morphospace occupied by placental taxa; dashed line represents occupied morphospace for marsupials.

Figure 2

Principal components (PC)3 and 4 and selected wireframes and line drawings for the ‘maximum landmarks’ dataset. (Top) dorsal and (bottom) lateral views. Symbols as in Figure 2.

Figure 3

Principal components (PC)1 and 2 for the ‘maximum taxa’ dataset. Symbols as in Figure 2.

Figure 4

Principal components (PC)3 and 4 for the ‘maximum taxa’ dataset. Symbols as in Figure 2.

Figure 5

Principal components (PC)1 and PC2 for the extinct and extant metatherians dataset. Squares represent extant taxa, stars represent fossil taxa, and dashed line indicates the range of morphospace occupied by extant metatherians.

Figure 6

Location of cranial landmarksviews used in the ‘maximum taxa’ (light grey only) and ‘maximum landmarks’ (light and dark grey) datasets. (Left) ventral and (right) lateral. Numbers correspond to Table 1.