Sorghum is often exposed to suboptimal low temperature stress under field conditions, particularly at the seedling establishment stage. Enhancing chilling tolerance will facilitate earlier planting and so minimize the negative impacts of other stresses experienced at later growth stages. Genome-wide association mapping was performed on a sorghum association panel grown under control (30/20 °C; day/night) and chilling (20/10 °C) conditions. Genomic regions on chromosome 7, controlling the emergence index and seedling (root and shoot) vigor, were associated with increased chilling tolerance but they did not co-localize with undesirable tannin content quantitative trait loci (QTLs). Shoot and root samples from highly contrasting haplotype pairs expressing differential responses to chilling stress were used to identify candidate genes. Three candidate genes (an alpha/beta hydrolase domain protein, a DnaJ/Hsp40 motif-containing protein, and a YTH domain-containing RNA-binding protein) were expressed at significantly higher levels under chilling stress in the tolerant haplotype compared with the sensitive haplotype and BTx623. Moreover, two CBF/DREB1A transcription factors on chromosome 2 showed a divergent response to chilling in the contrasting haplotypes. These studies identify haplotype differences on chromosome 7 that modulate chilling tolerance by either regulating CBF or feeding back into this signaling pathway. We have identified new candidate genes that will be useful markers in ongoing efforts to develop tannin-free chilling-tolerant sorghum hybrids.

Stomatal density (SD) and stomatal complex area (SCA) are important traits that regulate gas exchange and abiotic stress response in plants. Despite sorghum (Sorghum bicolor) adaptation to arid conditions, the genetic potential of stomata-related traits remains unexplored due to challenges in available phenotyping methods. Hence, identifying loci that control stomatal traits is fundamental to designing strategies to breed sorghum with optimized stomatal regulation. We implemented both classical and deep-learning methods to characterize genetic diversity in 311 grain sorghum accessions for stomatal traits at two different field environments. Nearly 12,000 images collected from abaxial and adaxial leaf surfaces revealed substantial variation in stomatal traits. Our study demonstrated significant accuracy between manual and deep-learning methods in predicting SD and SCA. In sorghum, SD was 32-39% greater on the abaxial vs. the adaxial surface, while SCA on the abaxial surface was 2-5% lower than on the adaxial surface. GWAS identified 71 genetic loci (38 were environment-specific) with significant genotype to phenotype associations for stomatal traits. Putative causal genes underlying the phenotypic variation were identified. Accessions with similar SCA but carrying contrasting haplotypes for SD were tested for stomatal conductance and carbon assimilation under field conditions. Our findings provide a foundation for further studies on the genetic and molecular mechanisms controlling stomata patterning and regulation in sorghum. An integrated physiological, deep learning, and genomic approach allowed us to clarify the genetic control of natural variation in stomata traits in sorghum, and can be applied to other plants.