The role of BoFLC2 in cauliflower (Brassica oleracea var. botrytis L.) reproductive development

Abstract

In agricultural species that are sexually propagated or whose marketable organ is a reproductive structure, management of the flowering process is critical. Inflorescence development in cauliflower is particularly complex, presenting unique challenges for those seeking to predict and manage flowering time. In this study, an integrated physiological and molecular approach was used to clarify the environmental control of cauliflower reproductive development at the molecular level. A functional allele of BoFLC2 was identified for the first time in an annual brassica, along with an allele disrupted by a frameshift mutation (boflc2). In a segregating F₂ population derived from a cross between late-flowering (BoFLC2) and early-flowering (boflc2) lines, this gene behaved in a dosage-dependent manner and accounted for up to 65% of flowering time variation. Transcription of BoFLC genes was reduced by vernalization, with the floral integrator BoFT responding inversely. Overall expression of BoFT was significantly higher in early-flowering boflc2 lines, supporting the idea that BoFLC2 plays a key role in maintaining the vegetative state. A homologue of Arabidopsis VIN3 was isolated for the first time in a brassica crop species and was up-regulated by two days of vernalization, in contrast to findings in Arabidopsis where prolonged exposure to cold was required to elicit up-regulation. The correlations observed between gene expression and flowering time in controlled-environment experiments were validated with gene expression analyses of cauliflowers grown outdoors under 'natural' vernalizing conditions, indicating potential for transcript levels of flowering genes to form the basis of predictive assays for curd initiation and flowering time.

Keywords: BoFLC; BoFT; BoVIN3; Brassica oleracea; cauliflower; expression; flowering time; vernalization..

Fig. 1.

Curding and flowering time of BoFLC2 and boflc2 cauliflower parent lines grown under glasshouse and Oyster Cove field conditions. Grey and black columns denote mutant (boflc2) and functional (BoFLC2) lines, respectively. Columns with stripes represent romanesco parent lines, and columns with spots denote boflc2 lines that formed a tightly bunched ‘head’ of leaves before curd formation. The flowering class of each parent lines is shown beside each line number, where E=early; ME=medium early; ML=medium late; L=late; and VL=very late. Error bars denote the standard error of the mean. For plants grown in pots under glasshouse conditions, the average number of days from sowing to curding and anthesis is shown in (A) and (B), respectively. Values are the average of seven replicates. Where plants did not initiate visible curds, they were assigned a maximum value of 378 days, and where plants did not flower, they were assigned a maximum value of 420 days. (C) Average number of days from sowing to curding is shown for plants grown under field conditions. Values are the average of up to 30 plants (three replicates with ten duplicates in each replicate), with dead or missing plants excluded from the analysis. Where plants did not initiate visible curds, they were assigned a maximum value of 300 days.

Fig. 2.

Reproductive behaviour and curd size in segregating F₂ populations. The average number of days from transplanting until curds were visible in parent lines and F₂ populations is shown in (A). Plants that had not produced visible curds after 117 days were given a maximum score of 127 days to differentiate them from those plants for which curds were first recorded on the 117th day. In (B), the average developmental stage (c.f. Supplementary Fig. S1) of curds at a fixed point (117 days after transplanting) is shown for C and D parents and F₂ segregants. Lower developmental stage values represent less-developed curds. In (C) average curd sizes in the C×D segregating F₂ population are displayed. In all graphs, +/+ denotes plants homozygous for BoFLC2, –/– denotes plants homozygous for boflc2, and +/– denotes heterozygotes. Error bars represent the standard error of the mean.

Fig. 3.

Average BoFLC2, BoFLC3, BoFT, and BoVIN3 expression. The timing of vernalization treatment is indicated by a dashed line. Bar (A) shows average gene expression in apex and leaf tissue of late-flowering parent line 1 (c.f. Supplementary Table S1). For each point, n=3. (B) Average gene expression in leaves of BoFLC2 and boflc2 parent lines. Each series represents the average expression of four different parent lines (one replicate per line) within the BoFLC2 or boflc2 genotype. Panel (C) shows average gene expression in apical tissue of cauliflower line 1 plants vernalized at different ages for different durations. Data is plotted against plant age at the time of vernalization treatment, or simply against plant age in the case of unvernalized controls. For each point, n=3 except for BoFLC2 week 10 and BoVIN3 weeks 4 and 9 where n=2. In all graphs, error bars represent the standard error of the mean.

Fig. 4.

Gene expression throughout autumn, winter, and spring in apical tissue of cauliflower parent lines 51 (BoFLC2) and 48 (boflc2). Inset: detail of BoFT expression during early growth. Values are based on one replicate only. The developmental stage of both parent lines is shown above each set of graphs, where V=vegetative; F=fat, expanded apex without any discernible curd structure; and 1–5=developmental stages according to Supplementary Fig. S1. Parent line details are provided in Supplementary Table S1.

Fig. 5.

Reproductive behaviour of BFLC2 cauliflower parent lines grown under field conditions, and relative expression of apical BoFLC2 and BoFT at a fixed time point. In (A), black bars represent the average number of days to visible curd formation. Striped bars indicate romanesco varieties. White bars indicate the average number of days to anthesis. Values for the average number of days to both curding and anthesis are counted from the 13 June and are the average of up to 30 plants (three replicates with ten duplicates in each replicate), with dead or missing plants excluded from the analysis. Plants that had not curded or flowered by the end of the observation period were assigned a maximum score of 180 days. Error bars represent the standard error of the mean. (B) BoFLC2 and BoFT gene expression at a fixed point before curd induction (13 June). Striped bars indicate romanesco varieties. Parent line details are provided in Supplementary Table S1.