Autoregulation of FCA pre-mRNA processing controls Arabidopsis flowering time

Abstract

The timing of the transition to flowering is critical for reproductive success in plants. Arabidopsis FCA encodes an RNA-binding protein that promotes flowering. FCA expression is regulated through alternative processing of its pre-mRNA. We demonstrate here that FCA negatively regulates its own expression by ultimately promoting cleavage and polyadenylation within intron 3. This causes the production of a truncated, inactive transcript at the expense of the full-length FCA mRNA, thus limiting the expression of active FCA protein. We show that this negative autoregulation is under developmental control and requires the FCA WW protein interaction domain. Removal of introns from FCA bypasses the autoregulation, and the resulting increased levels of FCA protein overcomes the repression of flowering normally conferred through the up-regulation of FLC by active FRI alleles. The negative autoregulation of FCA may therefore have evolved to limit FCA activity and hence control flowering time.

Fig. 1. FCA and the control of Arabidopsis flowering time. (A and B) Schematic representation of the principal genetic pathways controlling flowering time in winter annual and rapid cycling accessions of Arabidopsis. Promotive activities are denoted by arrowheads, repressive activities are denoted by T-bars. The photoperiod (PP) and gibberellin signal transduction (GA) pathways are shown activating genes with a floral meristem identity function (FMI), while FLC is shown to repress this. FRI, the FCA-containing autonomous pathway (AUT) and vernalization pathway (VRN) regulate FLC in an antagonistic manner. The most frequently found difference between winter annual (A) and rapid cycling (B) Arabidopsis accessions is allelic variation at FRI, with most rapid cycling accessions carrying inactive, loss-of-function fri alleles. (C) A comparison of the phenotype of wild-type Ler plants and late flowering fca-1 mutant plants. Although grown for the same time and under identical conditions, wild-type plants have already flowered while the fca-1 plants have remained in the vegetative state and continued to produce more leaves as opposed to floral organs. (D) Schematic representation of the alternative processing of Arabidopsis FCA pre-mRNA. Exons are represented as filled boxes and intron by lines.

Fig. 2. FCA negatively autoregulates its expression at the level of poly(A) site choice. (A) Schematic representation illustrating the differences between the endogenous FCA gene and 35S::FCA-γ transgene. The CaMV 35S promoter is inserted at a site upstream of the first in-frame AUG codon, resulting in the deletion of 349 bp of FCA exon 1 from 35S::FCA transgenes. The position of the non-canonical initiation codon from which FCA is translated is denoted with an asterisk. The region used as a probe in northern analysis is denoted by a hatched bar. (B) Immunodetection of FCA protein. Western blot analysis of total soluble protein extracts from seedlings of Ler, fca-1, and the transgenic lines 35S::FCA-γ in Ler and 35S::FCAγ in fca-1 (a 35S fusion to an intronless FCA transgene). Filled and unfilled arrowheads denote endogenous and transgenic FCA proteins respectively. Lower bands are unspecific binding products used as loading controls. (C) Northern blot analysis of poly(A)⁺ RNA isolated from Ler, fca-1, fca-4, and the transgenic lines 35S::FCA-γ in Ler and 35S::FCA-γ in fca-1 [the transgene described in (A)]. The blot was probed first with an FCA 5′ leader probe and later stripped and re-probed with a β-TUBULIN probe as a loading control. Numbers below compare the expression level of each FCA transcript between the different samples analysed. They were calculated as a ratio between a normalized FCA transcript signal (against that for β-TUBULIN) of a given sample and the same FCA transcript signal normalized in the wild type (Ler).

Fig. 3. FCA actively promotes the use of the proximal poly(A) site in its pre-mRNA. Northern blot analysis of poly(A)⁺ RNA isolated from Ler, fca-4 and the transgenic line P_FCA::FCA-γ in fca-4 (an intronless FCA transgene fused to the native FCA promoter). Blot was probed as indicated in Figure 2C. Numbers denote relative expression and were calculated as in Figure 2C. Asterisk denotes the FCA-γ transcript belonging to the P_FCA::FCA-γ transgene.

Fig. 4. FCA autoregulation requires an intact WW domain. (A) Immunodetection of FCA protein. Western blot analysis of total soluble protein extracts from seedlings of Ler and the transgenic line 35S::FCA-δ in Ler (a 35S fusion to an intronless FCA-δ transgene). Lower bands are unspecific binding products used as loading controls. Filled and unfilled arrowheads denote endogenous and transgenic FCA proteins, respectively. (B) Northern blot analysis of poly(A)⁺ RNA isolated from Ler and the transgenic line 35S::FCA-δ in Ler [the same transgenic line as reported in (A)]. The blot was probed as indicated in Figure 2C. Numbers denote relative expression and were calculated as in Figure 2C. (C) Northern blot analysis of poly(A)⁺ RNA isolated from Ler, fca-1, and the transgenic lines P_FCA::FCA-γ in fca-1 (the same transgene reported in Figure 3) and P_FCA::FCA-WF in fca-1 (an intronless FCA transgene fused to the endogenous promoter carrying a mutation resulting in a tryptophan to phenylalanine substitution in the WW domain). The blot was probed as indicated in Figure 2C. Numbers denote relative expression and were calculated as in Figure 2C.

Fig. 5. Nuclear localization of FCA protein. (A) Histochemical staining for GUS activity (dark staining) of transiently transfected onion epidermal cells. (B) DAPI counter staining of same cells as in (A), revealing location of nuclei.

Fig. 6. FCA autoregulation controls the level of functional transcript γ. (A) Immunodetection of FCA protein. Western blot analysis of total soluble protein extracts from seedlings of Ler and the transgenic line 35S::FCA-gene (a 35S fusion to the FCA gene) in Ler. Filled and unfilled arrowheads denote endogenous and transgenic FCA proteins, respectively. Lower bands are unspecific binding products used as loading controls. (B) Northern blot analysis of poly(A)⁺ RNA isolated from Ler and the transgenic line 35S::FCA-gene in Ler [the same transgene as in (A)]. The blot was probed as indicated in Figure 2C. Numbers denote relative expression and were calculated as in Figure 2C. (C) Quantification of the FCA transcripts levels in the fca-1 mutant. Data are the average of six different experiments and the FCA transcript signals obtained by northern analysis were normalized against that for β-TUBULIN. (D) Northern blot analysis of poly(A)⁺ RNA isolated from Ler, fca-1, and the transgenic lines P_FCA::FCA_{to exon 5}:GUS in Ler and P_FCA::FCA_{to exon 5}:GUS in fca-1. The blot was probed as indicated in Figure 2C. Numbers denote relative expression and were calculated as in Figure 2C.

Fig. 7. Histochemical assay for GUS activity in seedlings expressing P_FCA::FCA_{to exon 5}:GUS in a Ler or fca-1 background. (A–D) P_FCA:: FCA_{to exon 5}:GUS (Ler) at 2 (A), 4 (B), 6 (C) and 10 (D) days after germination. (E–H) P_FCA::FCA_{to exon 5}:GUS (fca-1) at 2 (E), 4 (F), 6 (G) and 10 (H) days after germination. All panels show seedlings incubated with X-Gluc for 16 h.

Fig. 8. High overexpression of FCA is detrimental for Arabidopsis development. (A) Wild-type Ler plants grown in long day photoperiod (16 h light) and (B) close-up of rosette leaves. (C) A transgenic plant expressing the 35S::cab-FCA-γ transgene, grown under the same conditions as the wild-type plant shown in (A). (D) A close-up of the rosette leaves of the plants shown in (C). (E) Wild-type Ler seedlings. (F) 35S::cab-FCA-γ plants that gave a more severe phenotype, shown at the same magnification as (E). (G) The 35S::cab-FCA-γ plants that gave a more severe phenotype, shown at a higher magnification.

Fig. 9. Model of the interplay of flowering time control pathways. (A) FRI represses flowering in the absence of vernalization by up- regulating the floral repressor, FLC, which antagonizes the promotive effects of the photoperiod (PP) and gibberellin (GA) signal transduction pathways on the activation of floral meristem identity genes (FMI). (B) When FCA autoregulation is removed, increased FCA activity perturbs the quantitative interaction of these pathways. Increased FCA activity down-regulates FLC, enabling the FMI genes to respond to the promotive pathways and accelerate flowering. Promotive activities are denoted by arrowheads, repressive activities are denoted by T-bars.