Integrating Pan-genome, GWAS, and Interpretable Machine Learning to Prioritize Trait-Associated Structural Variations in Setaria italica

Structural variations (SVs), especially presence-absence variations (PAVs), play a crucial role in crop domestication and trait improvement. While pan-genome analysis provides an exhaustive view of PAVs, it is often limited by high costs and restricted sample sizes. Conversely, genome-wide association studies (GWAS) can effectively identify trait-marker associations in large populations but typically overlook PAVs and face challenges in distinguishing causal variants due to linkage disequilibrium. In this study, we performed de novo assembly of eight reference-quality foxtail millet (Setaria italica) genomes and constructed a graph-based pan-genome to systematically explore PAVs. We subsequently conducted GWAS with 344 millet accessions, targeting genomic regions associated with the color of the leaf, leaf sheath, and leaf pulvinus. Through the application of interpretable machine-learning models, we pinpointed large-effect variants within the 26.84-26.94 Mb region on chromosome 7, including a 5002-bp Copia element insertion among other key variants correlated with phenotypic variations in leaf color traits. This integrative approach combines the detailed variant detection capabilities of pan-genome analysis with the large-scale mapping potential of GWAS and enhances variant prioritization using interpretable machine learning, providing a cost-efficient yet effective framework for dissecting agronomic traits in crops.