Foraging Trait (Co)variances in Stickleback Evolve Deterministically and Do Not Predict Trajectories of Adaptive Diversification

Abstract

How does natural selection shape the structure of variance and covariance among multiple traits, and how do (co)variances influence trajectories of adaptive diversification? We investigate these pivotal but open questions by comparing phenotypic (co)variances among multiple morphological traits across 18 derived lake-dwelling populations of threespine stickleback, and their marine ancestor. Divergence in (co)variance structure among populations is striking and primarily attributable to shifts in the variance of a single key foraging trait (gill raker length). We then relate this divergence to an ecological selection proxy, to population divergence in trait means, and to the magnitude of sexual dimorphism within populations. This allows us to infer that evolution in (co)variances is linked to variation among habitats in the strength of resource-mediated disruptive selection. We further find that adaptive diversification in trait means among populations has primarily involved shifts in gill raker length. The direction of evolutionary trajectories is unrelated to the major axes of ancestral trait (co)variance. Our study demonstrates that natural selection drives both means and (co)variances deterministically in stickleback, and strongly challenges the view that the (co)variance structure biases the direction of adaptive diversification predictably even over moderate time spans.K E Y W O R D S : Adaptive landscape, disruptive selection, evolutionary divergence, P matrix, sexual dimorphism, trophic morphology.

Size correction in biology: how reliable are approaches based on (common) principal component analysis?

“…As the present analysis of stickleback traits using ISMSC methodology indicates, this negative correlation between gill raker length and gape width (and other traits) is an artifact. If anything, these traits appear weakly positively correlated (see Berner et al 2010, for a similar conclusion from an analysis across 17 additional stickleback populations). The particularly high size-independent variance in gill raker length, however, is real and strongly drives bias in the estimation of (co)variances and correlations when using PCSC.…”

“…In addition, body mass was available as an independent size metric. Sample size was 300 individuals (details on the population, traits, and measurements are provided in Bolnick 2004;Bolnick and Lau 2008;Berner et al 2010). In a first step, each trait was divided by its mean to decouple variances from measurement scales and means (Houle 1992;Hansen and Houle 2008; log-transformation instead of mean-scaling produced very similar results in all analyses).…”

“…To compare results from PCSC and ISMSC applied to multiple populations, measurements (n = 300 individuals) from the stickleback population from Gray Lake (Bolnick and Lau 2008;Berner et al 2010) were added to the above dataset. Mean-scaling of each trait followed, but this time based on the grand mean in order to preserve differences in population means.…”

“…When studying a single population, this approach typically involves linear regression of each focal trait separately on the body size metric. The residuals of the regressions are retained and treated as size-independent morphology (Reist 1985), for instance to estimate the (co)variance or correlation structure (e.g., Losos et al 1998;Hulsey et al 2007;Berner et al 2010). The extension to situations where mean trait differences between two or more populations are the focus involves adding population as a factor in the general linear model (GLM) (i.e., using an ANCOVA design ;Reist 1986;Darlington and Smulders 2001;Garcia-Berthou 2001).…”

Covarying variances: more morphologically variable populations also exhibit more diet variation

“…It is also known that stickleback populations differ in the magnitude of within-population morphological variance (Berner et al 2010). Some of this variation in morphological variation can be ascribed to lake size.…”