Exploring tomato gene functions based on coexpression modules using graph clustering and differential coexpression approaches

Abstract

Gene-to-gene coexpression analysis provides fundamental information and is a promising approach for predicting unknown gene functions in plants. We investigated various associations in the gene expression of tomato (Solanum lycopersicum) to predict unknown gene functions in an unbiased manner. We obtained more than 300 microarrays from publicly available databases and our own hybridizations, and here, we present tomato coexpression networks and coexpression modules. The topological characteristics of the networks were highly heterogenous. We extracted 465 total coexpression modules from the data set by graph clustering, which allows users to divide a graph effectively into a set of clusters. Of these, 88% were assigned systematically by Gene Ontology terms. Our approaches revealed functional modules in the tomato transcriptome data; the predominant functions of coexpression modules were biologically relevant. We also investigated differential coexpression among data sets consisting of leaf, fruit, and root samples to gain further insights into the tomato transcriptome. We now demonstrate that (1) duplicated genes, as well as metabolic genes, exhibit a small but significant number of differential coexpressions, and (2) a reversal of gene coexpression occurred in two metabolic pathways involved in lycopene and flavonoid biosynthesis. Independent experimental verification of the findings for six selected genes was done using quantitative real-time polymerase chain reaction. Our findings suggest that differential coexpression may assist in the investigation of key regulatory steps in metabolic pathways. The approaches and results reported here will be useful to prioritize candidate genes for further functional genomics studies of tomato metabolism.

Figure 1.

Work flow for extracting coexpression modules and for differential coexpression analyses among organs. Coexpression modules for each gene were generated by graph clustering without regard to functional properties. 1, Quality checks of microarrays were performed with robust regression techniques and the Kolmogorov-Smirnov goodness-of-fit statistic D (see “Materials and Methods”). We discarded 20 arrays with low-quality scores (D ≥ 0.15). Probe sets with the prefix AFFX and RPTR were excluded. 2, We rejected 220 probes with the detection call “absent” across all samples.

Figure 2.

Pie charts with a classification of the experiments and organs collected in this study. GeneChips (n = 327) were from publicly available databases including the GEO, ArrayExpress, TFGD, and our own data (see “Materials and Methods”). The 17 experiments contained in the data set were classified into nine experimental (A) and 10 organ (B) categories. [See online article for color version of this figure.]

Figure 3.

Topological overview of the tomato coexpression network. A, Degree distribution of the network P(k) at various correlation thresholds (r ranging from 0.5 to 0.95); k indicates connectivity, and P(k) indicates the connectivity distribution. B, Partial coexpression network (r ≥ 0.6, P < 2.1e-31) in all data. The network shows how genes neighboring LeMADS-Rin (orange circle) correlate with each other. This undirected graph consists of nodes (black circles) and links (gray edges), indicating genes and positive correlations between genes.

Figure 4.

Distribution of the number of unknown genes within a module.

Figure 5.

Topological overview of organ-specific coexpression networks. A, Degree distribution of the coexpression network (r ≥ 0.6) for three organs: leaves, fruits, and roots. B, Relationship between the average of the Jaccard coefficient and the correlation coefficient. The former can measure the degree overlap between two networks as the ratio of the intersection to the union of the networks.

Figure 6.

A typical example of differentially coexpressed genes in different data sets. The correlation between the expression levels of two genes was significantly different in leaves and fruits (FDR = 9.27e-14). The axes represent relative gene expression. Note that differential coexpression was completely different from differential expression, and the mean level of given genes was significantly different between the two organs (see “Materials and Methods”). [See online article for color version of this figure.]

Figure 7.

Distribution of significantly differentially coexpressed genes between leaves and fruits (A), leaves and roots (B), and fruits and roots (C). This calculation was based on Fisher’s Z-transformation (see “Materials and Methods”). Thresholds correspond to Pearson’s correlation coefficient (PCC). Black and gray bars show the number of transitions from positive to negative correlations and from negative to positive correlations, respectively.

Figure 8.

Differential coexpressions mapped onto the lycopene biosynthesis pathway. Solid arrows show the reaction steps. Orange dashed lines and green broken lines represent intensified correlations in fruits (F) and leaves (L), respectively.

Figure 9.

Differential coexpression mapping to the flavonoid biosynthesis pathway. Solid arrows represent reaction steps. Orange dashed lines and green broken lines indicate intensified correlations in fruits (F) and roots (R), respectively. CHS, Chalcone synthase; CHI, chalcone isomerase; F3H, flavanone-3-hydroxylase.

Figure 10.

qRT-PCR assessment of microarray results. A, Box plots of expression values measured by qRT-PCR across seven experimental conditions, including leaf (L) and fruit (F) samples. Six genes associated with biosynthetic pathways were involved in photosynthesis, photosystem 1 reaction center protein subunit 2 (psaD; SGN-U580167) and zeaxanthin epoxidase (ZEP; SGN-U569421); flavonoids, flavanone 3-hydroxylase (F3H; SGN-U563669) and chalcone synthase 2 (CHS2; SGN−U580856); and carotenoids, phytoene synthase 1 (PSY1; SGN−U590947) and ζ-carotene desaturase (ZDS; SGN-U568537). B, Coexpression patterns between the genes, as determined by qRT-PCR (blue circles). Correlation between qRT-PCR and microarray analyses was also verified as shown in Supplemental Figure S3. w, Week. [See online article for color version of this figure.]