Identification of Conserved and Diverse Metabolic Shifts during Rice Grain Development

Abstract

Seed development dedicates to reserve synthesis and accumulation and uncovering its genetic and biochemical mechanisms has been a major research focus. Although proteomic and transcriptomic analyses revealed dynamic changes of genes and enzymes involved, the information regarding concomitant metabolic changes is missing. Here we investigated the dynamic metabolic changes along the rice grain development of two japonica and two indica cultivars using non-targeted metabolomics approach, in which we successfully identified 214 metabolites. Statistical analyses revealed both cultivar and developmental stage dependent metabolic changes in rice grains. Generally, the stage specific metabolic kinetics corresponded well to the physiological status of the developing grains, and metabolic changes in developing rice grain are similar to those of dicot Arabidopsis and tomato at reserve accumulation stage but are different from those of dicots at seed desiccation stage. The remarkable difference in metabolite abundances between japonica and indica rice grain was observed at the reserve accumulation stage. Metabolite-metabolite correlation analysis uncovered potential new pathways for several metabolites. Taken together, this study uncovered both conserved and diverse development associated metabolic kinetics of rice grains, which facilitates further study to explore fundamental questions regarding the evolution of seed metabolic capabilities as well as their potential applications in crop improvement.

Figure 1. A simplified metabolic map of rice grain based on metabolites identified by GC-MS and UHPLC-MS in this study.

Squares and circles denote metabolites detected and undetected in this study, respectively. Full metabolite names refer to Supplementary Table S1.

Figure 2. Principal component (PC) analysis of the metabolomes of developing rice grain.

Red, green, blue, violet and gray colors represent samples at 7, 10, 14, 28 and 42 DAF, respectively. Box, square, open triangle and triangle denote grain metabolomes of 9311, Nongken 58, Nipponbare and Qingfengai, respectively. PC 1 explains 53.3% of variance distinguishing rice grains from different developmental stages.

Figure 3. Result of two-way ANOVA and ASCA.

(a) Venn diagram summary of results from two-way ANOVA. (b) Major pattern associated with Time (developmental stage) (c) ASCA selection of important variables associated with Time (developmental stage) by Leverage/SPE analysis. These analysis was performed in MetATT website (http://metatt.metabolomics.ca/MetATT/).

Figure 4. Heat map of metabolite changes in rice grains at reserve accumulation stage (7, 10 and 14 DAF).

(a) amino acids and dipeptides. (b) lipids. (c) flavonoids. Q, Nip and N are shorted for three rice cultivars, Qingfengai, Nipponbare and Nongken 58, respectively. Ratios of fold changes are given by shades of red or blue colors according to the scale bar. Data represent mean values of four biological replicates for each cultivar and time point. Statistical analysis was performed using t-test (Supplementary Table S4). For full metabolite names, refer to Supplementary Table S1.

Figure 5. Heat map of metabolite changes in rice grains at desiccation stage (28 DAF vs 14 DAF).

(a) amino acids and dipeptides. (b) lipids. (c) flavonoids. Q, Nip and N are shorted for three rice cultivars, Qingfengai, Nipponbare and Nongken 58, respectively. Ratios of fold changes are given by shades of red or blue colors according to the scale bar. Data represent mean values of four biological replicates for each cultivar and time point. Statistical analysis was performed using t-test (Supplementary Table S5). For full metabolite names, refer to Supplementary Table S1.

Figure 6. Heat map of metabolite changes in rice grains at dormancy stage (42 DAF vs 28 DAF).

(a) amino acids and dipeptides. (b) lipids. (c) flavonoids. Q, Nip and N are shorted for three rice cultivars, Qingfengai, Nipponbare and Nongken 58, respectively. Ratios of fold changes are given by shades of red or blue colors according to the scale bar. Data represent mean values of four biological replicates for each cultivar and time point. Statistical analysis was performed using t-test (Supplementary Table S6). For full metabolite names, refer to Supplementary Table S1.