Distinct gene networks modulate floral induction of autonomous maize and photoperiod-dependent teosinte

Abstract

Temperate maize was domesticated from its tropical ancestor, teosinte. Whereas temperate maize is an autonomous day-neutral plant, teosinte is an obligate short-day plant that requires uninterrupted long nights to induce flowering. Leaf-derived florigenic signals trigger reproductive growth in both teosinte and temperate maize. To study the genetic mechanisms underlying floral inductive pathways in maize and teosinte, mRNA and small RNA genome-wide expression analyses were conducted on leaf tissue from plants that were induced or not induced to flower. Transcriptome profiles reveal common differentially expressed genes during floral induction, but a comparison of candidate flowering time genes indicates that photoperiod and autonomous pathways act independently. Expression differences in teosinte are consistent with the current paradigm for photoperiod-induced flowering, where changes in circadian clock output trigger florigen production. Conversely, differentially expressed genes in temperate maize link carbon partitioning and flowering, but also show altered expression of circadian clock genes that are distinct from those altered upon photoperiodic induction in teosinte. Altered miRNA399 levels in both teosinte and maize suggest a novel common connection between flowering and phosphorus perception. These findings provide insights into the molecular mechanisms underlying a strengthened autonomous pathway that enabled maize growth throughout temperate regions.

Fig. 1.

Tissue sampling scheme of reproductive and vegetative teosinte and B73. Teosinte was grown under inductive short-day (SD) conditions (A) and uninductive night-break (NB) conditions (B). B73 inbreds were grown under long-day conditions with either homozygous for (WT) Id1 (C) or homozygous for mutant id1 (D) to induce and repress the floral transition, respectively. RNA profiling was conducted on mature leaf (blue box) and the immature leaf whorl above the meristem (red box). Reproductive and vegetative expression changes were first compared (A versus B; C versus D) within subspecies, followed by a comparison of expression changes between teosinte and B73.

Fig. 2.

The floral transition in teosinte and B73 results in transcriptional changes enriched in many Gene Ontology (GO) terms and contains candidate floral regulators. (A) Enriched GO terms up- and down-regulated in immature leaves (ILs; left) and mature leaves (MLs; right) in vegetative/reproductive teosinte (night-break; NB versus short-days; SD) and B73 (id1 versus WT). (B) Proportions of candidate floral regulators that were expressed (grey), differentially expressed (red), or not expressed (white) in vegetative/reproductive teosinte and B73. Shared GO terms are outlined in red, and P-values for each ontology term are displayed with a colour reflecting its level of significance.

Fig. 3.

Comparison of immature leaf (IL) and mature leaf (ML) transcriptomes from induced and uninduced teosinte and B73. (A) Venn diagram displaying the number of transcripts differentially expressed in both reproductive/vegetative B73 (WT versus id1) and teosinte (short-days versus night-break). Principal component analysis (PCA) of B73 (blue) and teosinte (green) mRNA mature leaf (ML; light shades) and immature leaf (IL; dark shades) transcriptomes in three (B) and two (C) dimensions, capturing 86.3% and 78.4% of the variance, respectively. Reproductive treatments are depicted as triangles, and vegetative treatments as circles.

Fig. 4.

qPCR confirmation of miRNA and miRNA target gene expression changes upon floral induction. (A) Stem–loop qPCR quantification of miR399 isoforms and its target ZmPHO2 from immature (IL) and mature (ML) leaves of maize B73 WT and id1 plants. (B) Stem–loop qPCR quantification of miR399 isoforms in teosinte plants grown under inductive short days (SD) and inhibitory night breaks (NB). (C) Stem–loop qPCR quantification of miR156 expression in ILs and MLs from B73 WT and id1 plants. The primers used are not specific for a unique miRNA isoform, and a group of isoforms detected is reported. These graphs are representative of data obtained for one of the three biological replicates analysed. An asterisk indicates a statistically significant change (P≤0.05) when it was achieved across biological replicates.

Fig. 5.

Model: parallel clocks in maize leaf regulate autonomous and photoperiod pathways that converge at the shoot apical meristem (SAM) to cause flowering. Diurnal cycles of light and dark (top) are perceived by photoreceptors to entrain the circadian clock and induce flowering under short-day (SD) photoperiods (blue box, right). Similarly, in growing plants, daily fluctuations of fixed carbon levels (starch and Suc) attain a critical threshold and feed into a proposed ‘sugar clock’ to activate autonomous induction (red box, left). Output from each clock affects expression of distinct CCT-like genes that produce florigens, such as the ZCN genes. For autonomous flowering, ID1 modulates input from carbon sensors to signal expression of CCT-like regulators and other possible florigens (indicated by ‘?’). Crosstalk between clocks integrates environmental and endogenous signals to balance plant growth and determine the relative contribution of each flowering pathway (illustrated by the red and blue triangle graphic, lower left). Genes found to have altered expression in this study are shown in purple; key genes implicated in flowering from other studies are shown in grey. Dotted lines indicate movement of florigens from leaves. The green boxed area represents activity in leaf.