Starch as a major integrator in the regulation of plant growth

Abstract

Rising demand for food and bioenergy makes it imperative to breed for increased crop yield. Vegetative plant growth could be driven by resource acquisition or developmental programs. Metabolite profiling in 94 Arabidopsis accessions revealed that biomass correlates negatively with many metabolites, especially starch. Starch accumulates in the light and is degraded at night to provide a sustained supply of carbon for growth. Multivariate analysis revealed that starch is an integrator of the overall metabolic response. We hypothesized that this reflects variation in a regulatory network that balances growth with the carbon supply. Transcript profiling in 21 accessions revealed coordinated changes of transcripts of more than 70 carbon-regulated genes and identified 2 genes (myo-inositol-1-phosphate synthase, a Kelch-domain protein) whose transcripts correlate with biomass. The impact of allelic variation at these 2 loci was shown by association mapping, identifying them as candidate lead genes with the potential to increase biomass production.

Fig. 1.

Multivariate analysis of the relations between biomass and metabolic traits. (A) Graphical Gaussian Model. Partial correlation was used to identify direct association between 2 metabolites and/or traits with the influence of all other ones removed. For clarity, the different classes of traits have been colored: green, biomass; gray, chlorophylls; yellow, sugars and sugar alcohols; orange, organic acids; red, amino acids; pink, other metabolites. (B) PLS regression analysis of the relation between 5 inputs. These include 3 univariate inputs (biomass, starch, total protein) and 1 multivariate input (all other metabolites). Linear regression was used to compare the univariate inputs, and PLS regression was used to predict each univariate class from the multivariate class. Cross-validation was used to determine regression coefficients (R_pls = regression coefficient obtained by PLS, R_u = regression coefficient obtained by univariate correlation with cross-validation) and their P values (values in italics are nonsignificant), with red and blue arrows indicating negative and positive relationships between inputs. (C–D) VIP values of metabolites in the PLS regression. Metabolites with high VIP values are indicated by numbers: 1, amino acids; 2, Arg; 3, l-alanine; 4, DHA; 5, Asn; 6, Glc; 7, Gln; 8, Glu; 9, Gly; 10, guanidine; 11, fumarate; 12, OHPro; 13, Pro; 14, raffinose; 15, red sugars; 16, sucrose; 17, total sugars; 18, threonate; 19, serine. (C) Comparison of loadings for the PLS prediction of starch and biomass (blue) or protein and biomass (green). (D) Comparison of loadings for the PLS prediction of starch and protein.

Fig. 2.

Cartographic representation of the sugar-responsive gene network. Correlations were considered as significant for Rs >0.7 and P < 0.01 for gene–gene interactions and Rs >0.6 and P < 0.01 for gene–metabolites and metabolite–metabolite interactions, respectively. Genes are depicted as circles, with green and orange distinguishing between sugar-induced and sugar-repressed genes, respectively. Blue and red lines are for positive and negative correlations, respectively. Metabolic traits are depicted as squares. ED, end of the day; EN, end of the night.

Fig. 3.

Sequence polymorphisms in Kelch/At1g23390 (A) and IPS1/At4g39800 (B) that are significantly associated with the traits FW, starch, protein, sucrose or total amino acids. Full information about sequence polymorphisms and associations are given in Table S6. This display summarizes polymorphisms that show significant trait associations and is based on TAIR gene models At4g23390.1 and At4g39800. Gene regions are distinguished by coloring (orange, upstream sequence; green, exons; yellow, introns; salmon, downstream region). Significant (corrected P values <5%) polymorphisms are identified by their distance from the start codon, the locus number, and, for the ORF, the effect on the protein sequence. LD (expressed as R² values) is classified in 6 classes (R² < 0.1; 0.1 < R² < 0.2; 0.2 < R² < 0.4; 0.4 < R² < 0.6; 0.6 < R² < 0.8; 0.8 < R²) that are shaded from light to dark gray. For each polymorphism, the allele frequency is summed. The proportion of the genetic variance of the 5 traits explained by the marker main effect (R_M²) are shaded to indicate the significance of the association (dark, P < 0.01; light, 0.01 < P < 0.05), with blue or red signifying a negative or positive effect of the Col0 allele, respectively.