Heterotic trait locus (HTL) mapping identifies intra-locus interactions that underlie reproductive hybrid vigor in Sorghum bicolor

Abstract

Identifying intra-locus interactions underlying heterotic variation among whole-genome hybrids is a key to understanding mechanisms of heterosis and exploiting it for crop and livestock improvement. In this study, we present the development and first use of the heterotic trait locus (HTL) mapping approach to associate specific intra-locus interactions with an overdominant heterotic mode of inheritance in a diallel population using Sorghum bicolor as the model. This method combines the advantages of ample genetic diversity and the possibility of studying non-additive inheritance. Furthermore, this design enables dissecting the latter to identify specific intra-locus interactions. We identified three HTLs (3.5% of loci tested) with synergistic intra-locus effects on overdominant grain yield heterosis in 2 years of field trials. These loci account for 19.0% of the heterotic variation, including a significant interaction found between two of them. Moreover, analysis of one of these loci (hDPW4.1) in a consecutive F2 population confirmed a significant 21% increase in grain yield of heterozygous vs. homozygous plants in this locus. Notably, two of the three HTLs for grain yield are in synteny with previously reported overdominant quantitative trait loci for grain yield in maize. A mechanism for the reproductive heterosis found in this study is suggested, in which grain yield increase is achieved by releasing the compensatory tradeoffs between biomass and reproductive output, and between seed number and weight. These results highlight the power of analyzing a diverse set of inbreds and their hybrids for unraveling hitherto unknown allelic interactions mediating heterosis.

Figure 1. The Sorghum bicolor lines used for heterosis mapping.

A. Origin of the wide collection of lines includes accessions collected worldwide (see Table S1 for details). B. Phylogenetic tree of the wide Sorghum bicolor ssp. bicolor collection. The external nodes and coding of founder lines (FLs) are indicated.

Figure 2. Genetic analysis of the diallel founder lines.

A. Clustering analysis of the 19 Sorghum bicolor inbreds based on unrooted neighbor joining tree. Color coding representing the four identified clusters. B. Model-based ancestry for each founder line with enforcement of the cluster number (K) to 4 (see Materials and Methods). Distruct plot is shown with color coding representing the four clusters of the STRUCTURE analysis and the name of each founder line is depicted below.

Figure 3. Overdominant heterosis (ODH) in the diallel.

ODH distribution of vegetative (height, H; diameter, D; leaf weight, LW; stem weight, SW) and reproductive (dry panicle weight, DPW) traits. Different letters denote significant difference between ODH distributions (Kruskal-Wallis test, P<0.0001). Quantile boxes show the range between the 25th and 75th percentiles, including the 50th percentile indicated in between. The bottom and upper outer lines depict the 10th and 90th percentiles, respectively.

Figure 4. Hybrid reproductive superiority is induced by release of tradeoff relationship.

Correlations between components of seed number (secondary branching number, SBN; primary branching number, PBN) and seed dry weight (SDW). Analyses of trait values show negative correlations (A, B) while analysis of heterotic values (best parent heterosis; BPH) show either no (C) or positive (D) correlation. E–F. Correlations between vegetative weight (VW) and seed dry weight (SDW). Analysis of trait values (E) shows negative correlation whereas that of heterosis values (F) shows positive correlation.

Figure 5. Illustration of the HTL mapping.

A. Genotyping of the selected FLs is represented by three loci with different shapes (A, B and C), with each harboring 4 different alleles among the FLs of the diallel. B. Projection of the FLs genotype to the derived hybrids and calculation of the mean heterosis values (ODH) for the r replicates of an hybrid. C. Statistical analysis to identify specific hetero combinations with advantageous ODH values (the purple/green hetero-group in this illustration).

Figure 6. The hDPW4.1 grain yield heterotic trait locus (HTL).

A. Chromosomal location of the Dsenhabm39 SSR marker is indicated by star on the physical map of chromosome 4. Black and white coloring indicate pericentric-heterochromatic and telomeric-euchromatic chromosomal regions, respectively. Gray indicates markers within pericentric-heterochromatic chromosomal regions. B. Cumulative distribution function plot showing the ODH values of the significant hetero-genotypic (154/164) and homo-genotypic (H:H) groups for the same marker in the diallel (year 2011). C. Linkage analysis of the hDPW4.1 locus with dry panicle weight (DPW) in the F2 population. Different letters above bars denote significant difference (P<0.05; Hsu’s MCB test) between mean values.

Figure 7. Contribution of heterotic trait loci and their epistatic interactions to heterotic variation in a diallel population.

A. Heterosis least squared means plot. The x axis represents the genotypes of hDPW1.1. The lines represent different genotypes of hDPW1.2. N, neutral non-interacting genotypic allelic combinations; P, positive interacting combination. B. Accumulated variation explained by the model (R²) with each additional factor. C. The factors included in each of the models.