Genome-wide association analysis and pathway enrichment provide insights into the genetic basis of photosynthetic responses to drought stress in Persian walnut

Abstract

Uncovering the genetic basis of photosynthetic trait variation under drought stress is essential for breeding climate-resilient walnut cultivars. To this end, we examined photosynthetic capacity in a diverse panel of 150 walnut families (1500 seedlings) from various agro-climatic zones in their habitats and grown in a common garden experiment. Photosynthetic traits were measured under well-watered (WW), water-stressed (WS) and recovery (WR) conditions. We performed genome-wide association studies (GWAS) using three genomic datasets: genotyping by sequencing data (∼43 K SNPs) on both mother trees (MGBS) and progeny (PGBS) and the Axiom™ Juglans regia 700 K SNP array data (∼295 K SNPs) on mother trees (MArray). We identified 578 unique genomic regions linked with at least one trait in a specific treatment, 874 predicted genes that fell within 20 kb of a significant or suggestive SNP in at least two of the three GWAS datasets (MArray, MGBS, and PGBS), and 67 genes that fell within 20 kb of a significant SNP in all three GWAS datasets. Functional annotation identified several candidate pathways and genes that play crucial roles in photosynthesis, amino acid and carbohydrate metabolism, and signal transduction. Further network analysis identified 15 hub genes under WW, WS and WR conditions including GAPB, PSAN, CRR1, NTRC, DGD1, CYP38, and PETC which are involved in the photosynthetic responses. These findings shed light on possible strategies for improving walnut productivity under drought stress.

Figure 1

Distribution of the photosynthetic related traits of 6-month-old plants of walnut under well-watered (blue), severe stress (red) conditions and overlap between them (purple) in the first-year experiment. (a) P_n, (b) C_i, (c) P_n/C_i, (d) C_i/C_a, (e) WUE_i, (f) RWC, (g) F_M/F₀, (h) F_V/F₀, and (i) F_V/F_M in 140 Iranian walnut families. Traits are indicated on the x-axis and number of families on the y-axis. Dashed vertical lines indicate the mean of each distribution.

Figure 2

Correlation plot of photosynthetic traits and principal component analysis (PCA) plots of phenotypic data and SNP markers. (A) Correlation coefficient of plasticity in trait value (DSI), between all gas exchange and chlorophyll fluorescence phenotypes in the 140 walnut families grown in a common garden under severe water stress condition in the first-year experiment. The colour spectrum, bright blue to bright red represents highly positive to highly negative correlations. Stars in circle indicate the significance of correlations (^*P ≤ 0.05, ^**P ≤ 0.01, and ^***P ≤ 0.001). (B) Principal component analysis of photosynthetic traits with the first two components showing variation in plasticity in trait value in the 140 walnut families grown in a common garden under severe water stress condition in the first-year experiment. The traits coloured by red contributed more to the variation explained by PC1 and PC2, than those coloured by blue. (C) PCA of the 140 Persian walnut families using 44 207 GBS-derived SNPs (PGBS). (D) PCA of the 87 Persian walnut mother trees using 40 828 GBS-derived SNPs (MGBS). See Table 1 for the definition of measured traits.

Figure 3

Box plots of the regional differentiation of the gas exchange parameters in the 140 walnut families grown in a common garden under well-water and severe water stress conditions in the first-year experiment. (A) P_n, (B) C_i, (C) T_r and (D) WUE_i. WW: well-water; WS: water-stress. Different letters indicate statistically significant differences at the level of p < 0.01 (Tukey’s test).

Figure 4

Venn diagrams depicting the significant SNPs identified for all the photosynthetic traits across experiments (First and second years) and different conditions through GWAS using different datasets MArray (A), MGBS (B) and PGBS (C) and highlight the concordance between different datasets (D). Well-water: WW, water-stress: WS, water-recovery: WR, drought stress index: DSI, drought recovery index: DRI.

Figure 5

(A) and (B) Circular Manhattan plots (left), and quantile-quantile plots (right) of association analysis using the MGBS dataset and MLMM (Q + K) model for gas-exchange related traits from centre to the outside of plot including; (a) gs_WW21, (b) Pn_WS12, (c) T_r_WS12, (d) WUE_i_WS21, and (e) PC2_WS21. The outermost circle shows SNP density in 1 Mb windows for each chromosome where green to red indicates low to high marker density. Black bold line (Y-axis) represents –Log10 P-value. The circles of red dashed lines represent the Bonferroni-corrected significance threshold. Red stars indicate genome-wide significantly associated SNPs. Vertical grey dashed lines are drawn through GWAS findings to indicate multi-trait associations. For QQ plots, X-axis represents expected − log₁₀ (p-value) and Y-axis is observed − log₁₀ (p-value) of each SNPs. Well-water: WW, water-stress: WS.12: severe drought stress in the first year, 21: severe drought stress in the second year.

Figure 6

(A) Circular Manhattan plots (left), and (B) quantile-quantile plots (right) of association analysis using the MArray dataset and MLMM (Q + K) model for chlorophyll fluorescence related traits from centre to the outside of plot including; (a) DI₀/RC_DSI21, (b) F_V/F₀_WS21, (c) φ_Do_DSI21, (d) TR₀/RC_WS21, and (e) PC3_WR22. The outermost circle shows SNP density in 1 Mb windows for each chromosome where green to red indicates low to high marker density. Black bold line (Y-axis) represents –Log10 P-value. The circles of red dashed lines represent the Bonferroni-corrected significance threshold. Red stars indicate genome-wide significantly associated SNPs. For QQ plots, X-axis represents expected − log₁₀ (p-value) and Y-axis is observed − log₁₀ (p-value) of each SNPs. Water-stress: WS, water-recovery: WR, drought stress index: DSI. 21: severe drought stress in the second year and 22: recovery condition in the second year.

Figure 7

(A) and (B) Circular Manhattan plots (left), and quantile-quantile plots (right) of association analysis using the MGBS dataset and MLMM (Q + K) model for chlorophyll fluorescence related traits from centre to the outside of plot including; (a) ABS/RC_WS21, (b) DI₀/RC_WW21, (c) F_V/F_M_DSI21, (d) V_J_WW21, and (e) PC3_WR22. The outermost circle shows SNP density in 1 Mb windows for each chromosome where green to red indicates low to high marker density. Black bold line (Y-axis) represents –Log10 P-value. The circles of red dashed lines represent the Bonferroni-corrected significance threshold. Red stars indicate genome-wide significantly associated SNPs. Vertical grey dashed lines are drawn through GWAS findings to indicate multi-trait associations. For QQ plots, X-axis represents expected − log₁₀ (p-value) and Y-axis is observed − log₁₀ (p-value) of each SNPs. Well-water: WW, Water-stress: WS, water-recovery: WR, drought stress index: DSI. 21: severe drought stress in the second year and 22: recovery condition in the second year.

Figure 8

(A) and (B) Circular Manhattan plots (left), and quantile-quantile plots (right) of association analysis using the PGBS dataset and MLMM (Q + K) model for chlorophyll fluorescence related traits from centre to the outside of plot including; (a) F_J_DRI22, (b) F_M_DRI22, (c) F_V/F_M_DRI22, (d) PI_ABS_DRI22, and (e) PC2_DRI22. The outermost circle shows SNP density in 1 Mb windows for each chromosome where green to red indicates low to high marker density. Black bold line (Y-axis) represents –Log10 P-value. The circles of red dashed lines represent the Bonferroni-corrected significance threshold. Red stars indicate genome-wide significantly associated SNPs. Vertical grey dashed lines are drawn through GWAS findings to indicate multi-trait associations. For QQ plots, X-axis represents expected − log₁₀ (p-value) and Y-axis is observed − log₁₀ (p-value) of each SNPs. Drought recovery index: DRI. 22: recovery condition in the second year.

Figure 9

Complementarity of the three data sets to detect SNP-trait associations and candidate genes. (A) and (B); the number of specific genomic regions (A) and candidate genes (B) detected by each data set for all the photosynthetic traits across experiments (First and second years) and different conditions. (C) and (D); the number of genomic regions (C) and candidate genes (D) detected by both Array and GBS data sets across experiments (First and second years) under well-watered (WW), water-stressed (WS), and water-recovery (WR) conditions.

Figure 10

Enrichment and network analysis highlighted key pathways and hub genes involved in photosynthetic responses in walnut under drought and recovery conditions. (A) Top KEGG descriptions significantly enriched using genes associated with photosynthetic traits under WW, WS and WR conditions. Different colours in X-axis represent different significant levels of the KEGG pathways. The y-axis represents the KEGG pathways. Sub-networks of the most important hub genes from all the genes associated with photosynthetic traits under (B) well-watered (WW), (C) water-stressed (WS), and (D) water-recovery (WR) conditions are shown.