Unveiling the genetic basis of floral scent formation in roses using weighted gene co-expression and protein-protein interaction network analyses

Abstract

Rosa species hold considerable economic and medicinal importance, used in traditional medicine, essential oils, and landscaping. However, the mechanisms of floral scent formation in roses are not well understood, hindering genetic improvement. To bridge this gap, we conducted a combined transcriptome and metabolome analysis, identifying nine key fragrance compounds. Using Weighted Gene Co-expression Network Analysis (WGCNA), we linked 574 genes to these compounds. From these, we identified candidate genes through differential expression, functional annotations, and protein-protein interaction (PPI) networks. We predicted candidate genes, NUDIX1, NUDIX2, GERD, AFS1, AFS2, CYP82G1, HMG1, NCED2, CCD7, PSY, ICMEL2, MAD1, and MAD2 that might terpenoid-related genes, as well as potential benzenoid/phenylpropanoid-related candidate genes, DET2, DET3, ICS2, PAL1, UGT74B1, MYB330, GST, CAD1, HST, PCBER1, LAC15, CSE, PER25, PER47, PER63, FBA, LNK2, PRE1, and PRE6. Additionally, three function-unknown genes, LOC112167529, LOC112174760, and LOC112183447, were predicted as candidate genes potentially involved in the formation of floral scent.

Keywords: Rosa; Floral scent; Hub gene; PPI; WGCNA.

Fig. 1

Analysis of differential metabolites between the fragrant and scentless roses. (A) Number of differentially accumulated metabolites (DAMs) of GC-MS data (VIP > 1, P < 0.05, log₂|FoldChange| > 1). (B) Venn diagram illustrates the numbers of highly upregulated (log₂FoldChange > 2) DAMs of GC-MS data. (C) Number of DAMs of LC-MS data. (D) Venn diagram illustrates the numbers of highly upregulated DAMs of LC-MS data. (E) Classification of overlapping DAMs of the GC-MS and LC-MS data. (F) Heatmap of overlapping DAMs. (G) Selected floral scent metabolites from overlapping DAMs. GC-MS, GC-TOF/MS; LC-MS, UHPLC-ESI-MS/MS; CK, Iceberg; DM, Damascena; QX, Qin Xiang; CG, Crimson Glory.

Fig. 2

Differentially expressed genes (DEGs) analysis. (A) Volcano plot of RNA-seq data of QX versus CK group. (B) Volcano plot of RNA-seq data of DM versus CK group. (C) Volcano plot of RNA-seq data of CG versus CK group. (D) The Venn diagram illustrates the overlapping DEGs among the comparative groups. (E) The UpSet plot illustrates number of the expressed genes (FPKM > 1.0) from the overlapping DEGs. DEGs were classified as expressed (FPKM > 1.0) and non-expressed (FPKM < 1.0) genes. CK, Iceberg; DM, Damascena; QX, Qin Xiang; CG, Crimson Glory.

Fig. 3

Identification of floral fragrance-related genes by WGCNA. (A) Clustering dendrograms of genes and module detecting. (B) Eigengene dendrogram and adjacency heatmap. (C) Heat map of the correlation between floral fragrant compounds and gene modules. Heatmap colors represent the correlation level, the numbers out and in parentheses are correlation coefficient r and P value, respectively. Numbers in bottom color label represent number of genes within module. (D) Bar plots indicate number of significantly correlated genes of each compound within each module (threshold |GS| ≥ 0.9 & |MM| ≥ 0.8). WGCNA, weighted gene co-expression network analysis.

Fig. 4

Identification of candidate genes from highly expressed genes. (A) Venn diagram of highly expressed genes (FPKM ≥ 100). (B) Upset plot of highly expressed gene. DM, Damascena; QX, Qin Xiang; CG, Crimson Glory. DM_lg2FC, highly expressed gene with log₂FoldChange > 6 in DM compared to Iceberg (CK). QX_lg2FC, highly expressed gene with log₂FoldChange > 6 in QX compared to CK. CG_lg2FC, highly expressed gene with log₂FoldChange > 6 in CG compared to CK.

Fig. 5

GO and KEGG pathway analysis of floral fragrance-related genes. (A) GO analysis. (B) KEGG pathway analysis. GO, gene ontology; KEGG, Kyoto encyclopedia of genes and genomes.

Fig. 6

Identification of candidate genes from floral fragrance-related genes using PPI network analysis. (A) Visualization of entire PPI network. Lines indicate protein-protein interactions and proteins with a degree above three were visualized in detail. (B) Venn diagram shows the overlap of four different algorithms of cytoHubba. MCC, Maximal clique centrality; MNC, Maximum neighborhood component; DMNC, Density of MNC. (C) PPI network maps about 33 overlapping genes. (D) The significant module identified from PPI network via MCODE. (E) Venn diagram shows 21 hub genes obtained by combining cytoHubba and MCODE algorithms. PPI, Protein-protein interaction. MCODE, Molecular Complex Detection.