Integrative genomics and deep learning-based phenotyping reveal the genetic architecture of seed traits in mungbean (Vigna radiata L.)

Improving seed size and weight is a major breeding goal in mungbean (Vigna radiata (L.) R. Wilczek). Improved genomic resources and precision phenotyping may enable more rapid genetic gains. In this study, we integrated a deep learning-based segment anything model (SAM) phenotyping pipeline with genome-wide association studies (GWAS), comparative mapping, and genomic prediction (GP) to dissect the genetic architecture of seed size, shape, and weight traits in the Iowa Mungbean Diversity (IMD) panel. The zero-shot segmentation approach reliably captured seed size traits, which exhibited high heritability (H² > 0.90) and strong correlation with seed weight (r > 0.91). A multi-model GWAS identified 79 unique SNPs across all seven seed traits, including 13 multitrait associations. Furthermore, the analysis revealed 13 major pleiotropic hubs governing multiple seed dimensions, including high-confidence regions on chromosomes 1, 4, and 6 that explained over 20% of the phenotypic variance. Within these hubs, comparative mapping highlighted highly conserved candidate genes with critical putative roles in legume seed development, including an ABC transporter (Virad01G0084400) and an NPGR1-like protein (Virad06G0255600). GP using gBLUP produced moderate to high accuracies for seed size and weight traits (r = 0.81–0.84). Incorporating significant GWAS SNPs (gBLUP+SNPs) yielded slight improvements, suggesting the standard gBLUP model is sufficiently robust for selection. Collectively, this study provides the most comprehensive genomic dissection of seed size and weight traits in mungbean to date, providing candidate loci and genomic prediction models that can accelerate genetic improvement for seed yield and quality.