Adaptive evolution of the lactose utilization network in experimentally evolved populations of Escherichia coli

Abstract

Adaptation to novel environments is often associated with changes in gene regulation. Nevertheless, few studies have been able both to identify the genetic basis of changes in regulation and to demonstrate why these changes are beneficial. To this end, we have focused on understanding both how and why the lactose utilization network has evolved in replicate populations of Escherichia coli. We found that lac operon regulation became strikingly variable, including changes in the mode of environmental response (bimodal, graded, and constitutive), sensitivity to inducer concentration, and maximum expression level. In addition, some classes of regulatory change were enriched in specific selective environments. Sequencing of evolved clones, combined with reconstruction of individual mutations in the ancestral background, identified mutations within the lac operon that recapitulate many of the evolved regulatory changes. These mutations conferred fitness benefits in environments containing lactose, indicating that the regulatory changes are adaptive. The same mutations conferred different fitness effects when present in an evolved clone, indicating that interactions between the lac operon and other evolved mutations also contribute to fitness. Similarly, changes in lac regulation not explained by lac operon mutations also point to important interactions with other evolved mutations. Together these results underline how dynamic regulatory interactions can be, in this case evolving through mutations both within and external to the canonical lactose utilization network.

Figure 1. Characterization of lac operon regulation.

A) Examples of the range of evolved LacZ activity phenotypes present in the four evolution environments. Degree of blue coloration on TGX plates gives a qualitative measure of LacZ activity. B) Schematic of lac operon and reporters used to measure lac operon regulation. lacZ encodes the β-galactosidase responsible for lactose catabolism and lacY encodes a lactose permease. The expression of lacZYA is directly controlled by LacI and CRP. LacI is a negative regulator, binding to operator sites within the lacZYA promoter (P_lac). LacI binding is inhibited by lactose and gratuitous inducers, such as TMG. CRP is a positive regulator, activating lacZYA expression when cAMP levels are elevated in response to low glucose concentrations. High levels of glucose also repress lac expression by inhibiting import of lactose through LacY. Two reporters were designed to measure LacI and CRP inputs into lac operon regulation. The native lac promoter drives expression of GFP and is subject to regulation by both LacI and CRP. A second reporter utilizes a mutant lac promoter that cannot bind LacI to drive expression of DsRedExpress2. This reporter is only subject to regulation by CRP. Solid lines indicate positive (arrows) and negative (blunt arrow) regulatory interactions; dotted lines indicate the transfer of metabolites; blue lines indicate the production of proteins; open arrows indicate expression start sites. Figure adapted from Ozbudak et al. 2004. C) Ancestral inducer response profile. Shown are flow cytometry histograms for the ancestor grown in a range of TMG concentrations. P_lac-GFP and P_lac(O-)-RFP measurements were taken simultaneously from the same cultures.

Figure 2. Inducer response profiles of evolved clones.

Heat maps show the mean response of the P_lac-GFP reporter (RFU) for evolved clones at different concentrations of inducer (TMG). Black squares indicate the concentration of TMG that gave half maximal expression (TMG_½Max) and red outlines indicate the presence of bimodal expression within the population. Inducer responses for clones with constitutive lac operons were only generated with four TMG concentrations because lac expression was independent of inducer concentration such that finer resolution measurements were redundant.

Figure 3. Inducer response classes and association with evolution environment.

A) Inducer response classes for evolved clones. 1) Bimodal with a higher threshold for lac induction, 2) Constitutive with expression levels that are independent of inducer, 3) Lower threshold for lac induction with graded response to inducer. Inducer response histograms are shown for clones representative of each class (Bimodal, L5-1; Constitutive, G/L5-1; Lower threshold, G+L3-1). B) Distribution of inducer response types by population and evolution environment. Pie charts show the fraction of clones with each inducer response type (Bimodal, Constitutive, Lower threshold) within a given population.

Figure 4. Changes in maximal lac expression for evolved clones.

A) Steady state P_lac-GFP levels (RFU) are shown for evolved clones grown in the presence of 100 µM TMG. Clones are divided into categories by evolution environment: Glu, Lac, G+L and G/L. Markers of the same color denote clones recovered from the same evolved population. Data points are the average of two independent replicates. As a reference, data for six independent ancestral (Anc) samples is also shown. B) Native lac promoter activity for the ancestor, evolved clone G+L3-1 and the ancestor with lacI and lacO1 mutations. Basal promoter activity was measured for strains grown in the absence of inducer, and maximum promoter activity was measured in the presence of saturating levels of inducer.

Figure 5. Identification lac mutations in evolved clones.

Sequence alignments for evolved clones relative to the ancestor are shown for the lacI mutation hotspot region (left) and the primary lacO1 operator (right). Clones were chosen that represent the diversity in lac genotypes within each population. Colored boxes by sequences indicate the inducer response type for each clone. Bimodal is shown as green, constitutive is shown as blue and lower threshold response is shown as purple. No sequence was obtained for the G/L5 clones. Sequence alignments are not shown for Glu clones since all have wt lac regulatory sequences.

Figure 6. Contribution of lac mutations to evolved inducer responses.

A) Inducer response histograms for reconstructed lacI ^ΔTGGC and lacO1 ^G11A mutants. The lacI mutation confers constitutive lac expression, whereas the lacO1 mutation confers a lower induction threshold and a graded response to inducer. B) Effect of the lacO1 mutation on the maximum lac expression level. Mean P_lac-GFP expression levels during growth in saturating levels of inducer (100 µM TMG) are shown for the ancestor, evolved clone G+L3-1, lacO1 ^G11A single mutant and the G+L3-1 clone with lacO1 reverted to the ancestral sequence (G+L3-1 lacO1^anc). Standard error is shown, n = 4.

Figure 7. Effect of lac mutations on fitness.

A) Fitness of lacI and lacO1 mutants in the four evolution environments. Competitions were performed for lacI versus the ancestor, lacO1 versus the ancestor and lacI versus lacO1. As a control, we included the ancestor competed against itself. The red dotted line indicates a relative fitness of 1 (no fitness difference). 95% confidence intervals are shown for each competition (n≥8).

Figure 8. Physiological characterization of lac mutants.

A) Growth curves for the ancestor (green), and reconstructed lacI (blue) and lacO1 (purple) mutants. Conditions used were: Lac→Glu, Glu→Lac and G+L→G+L, where the sugars indicate pre-conditioning and measurement environments, respectively. These transitions correspond to those present in the G/L and G+L evolution environments. OD values are plotted on a log₁₀ scaled axis. B) LacZ expression time course for the ancestor and the ancestor with lacI and lacO1 mutations during growth in the G+L evolution environment. Values are the average of two independent replicates with standard deviation shown.

Figure 9. Fitness effect of lacI and lacO1 mutations depend on genetic background.

The fitness effect of lacO1 and lacI mutations were measured in the ancestor and the G+L3-1 evolved genetic backgrounds when competed in the G+L environment. Gray points indicate fitness effect in competitions against the corresponding progenitor strains that do not have the added lac mutation; black points indicate fitness of lacI and lacO1 mutations competed directly against each other. Lines connect competitions of the same type but in different genetic backgrounds.