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

Abstract

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 efficient selection for seed trait improvement. In this study, we integrated a deep learning–based segment anything model 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 panel. The zero‐shot segmentation approach reliably captured seed size traits, which exhibited high heritability ( H ²  > 0.90) and strong correlation with seed weight ( r  > 0.91). A multi‐model GWAS identified 82 unique single nucleotide polymorphisms (SNPs) across all seven traits, of which 13 were major pleiotropic SNPs governing multiple seed dimensions, including high‐confidence regions on chromosomes 1, 4, and 6 that explained over 20% of the phenotypic variance. Within these SNP regions, comparative mapping highlighted candidate genes including an ABC transporter ( Virad01G0084400 ) and two colocated candidates, NPGR1 ( Virad06G0255600 ) and a RING‐type E3 ubiquitin‐protein ligase ( Virad06G0255800 ), presented as hypothesis‐generating candidates for seed size regulation. GP using genomic best linear unbiased prediction (gBLUP) produced moderate to high accuracies for seed size and weight traits ( r  = 0.76–0.84). 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.