Deriving structure from evolution: metazoan segmentation

Abstract

Segmentation is a common feature of disparate clades of metazoans, and its evolution is a central problem of evolutionary developmental biology. We evolved in silico regulatory networks by a mutation/selection process that just rewards the number of segment boundaries. For segmentation controlled by a static gradient, as in long-germ band insects, a cascade of adjacent repressors reminiscent of gap genes evolves. For sequential segmentation controlled by a moving gradient, similar to vertebrate somitogenesis, we invariably observe a very constrained evolutionary path or funnel. The evolved state is a cell autonomous 'clock and wavefront' model, with the new attribute of a separate bistable system driven by an autonomous clock. Early stages in the evolution of both modes of segmentation are functionally similar, and simulations suggest a possible path for their interconversion. Our computation illustrates how complex traits can evolve by the incremental addition of new functions on top of pre-existing traits.

Figure 1

Transcriptional regulation of a prototypical gene P. In the example shown, the expression of gene P is activated by proteins A1 and A2 and repressed by protein R. The rate of production of the corresponding protein is described mathematically by Equation (1).

Figure 2

Overview of one generation of the evolution algorithm. At each generation, the algorithm evolves the network collection (A). First, in each embryo, we solve for the expression pattern of a reporter protein E in the presence of a morphogen G as a function of position (B). The fitness, F, is defined as the number of jumps between high and low values of E. Half the networks of lowest fitness are discarded (C) and replaced by mutated copies of the fittest ones (D). This produces the starting network collection for the next generation (dashed arrow).

Figure 3

Evolution of two segmentation networks in a static morphogen gradient. Two different evolutionary pathways are displayed (A–C, D–G). Successive stages run from left to right and show both the network and the spatial profile of the proteins. Note that the first two stages are common to both evolutionary trajectories. The morphogen G is depicted in black, the protein E defining the segments is in blue, and the repressors R1 and R2 are in red (dashed lines represent the last to be added). Concentrations have been normalized by their maximum value for plotting purposes. See the text for details.

Figure 4

Stages in the evolution of sequential segmentation for a morphogen gradient moving to the right. (A) Evolution of the best network fitness as a function of the number of generations. (B–D) The letters correspond to the network topologies and protein profiles in the three subsequent panels following the conventions in Figure 3. (E) Final profile produced by network of (D) for twice as long an embryo showing regular spacing of the stripes. See the text for details and Supplementary Information for other examples.

Figure 5

Binary encoding of the phase of the oscillation by bistability. Creation of high (A) and low (B) values of the segmentation marker E in two cells by the coupled effects of oscillatory and bistable dynamics. The network corresponds to Figure 4D and the colors and scalings are identical. While the morphogen G is high, E is high and oscillates in response to the clock variable R. As time passes, G decreases and at a given moment (black arrow), it can no longer significantly activate gene E. The cell fate is determined by the concentration of E at this particular moment relative to a threshold E⁰ (shown by a dashed line). E⁰ is the (unstable) fixed point (for G=R=0) that separates protein concentrations E>E⁰ converging to the high state of E expression, from smaller values that end in the low state of E expression. In (A), E is high enough at the arrowed time so that G and R can disappear while leaving E>E⁰. In (B), the concentration of E at the arrowed time is under the threshold E⁰.

Figure 6

An alternative pathway from repression to oscillations. This network evolved from the network in Figure 4C and replaces the network in Figure 4D. A triplet of repressors creates oscillations by a mechanism similar to the synthetic network created in Elowitz and Leibler (2000). Two protein expression profiles are shown on the right for the same network at different times with the same conventions as in Figure 4.