Mou Yin

CLCNet improves genomic prediction accuracy in plants by integrating contrastive learning and chromosome-aware feature selection, outperforming existing models across four crop species and ten traits.

This study uses RNA-seq on 328 wheat lines to analyze gene expression diversity, identifying introgressed genes and their regulatory impacts on agronomic traits and disease resistance.

This study uses biGWAS to identify 65 Avr loci and 251 R loci in wheat and Blumeria graminis f. sp. tritici, revealing their interactions and implications for durable resistance breeding.

This study identifies genetic modules and epistasis driving wheat yield improvement through GWAS and haplotype analysis across diverse environments.

The paper identifies two divergent haploid genomes in wheat stripe rust, showing their role in generating diversity and virulence through hybridization and recombination.