Kosuke Hamazaki

This paper uses pre-trained LLMs to enhance Bayesian optimization for selecting superior genotypes from germplasm collections, improving efficiency with passport data and genomic information.

The paper develops a multi-kernel mixed model to analyze indirect genetic effects (IGEs) in plant genotypes, finding evidence of intergenotypic competition in aspen and apple trees.

The paper develops a framework that optimizes breeding strategies by updating genomic prediction models during breeding schemes, showing improved performance under moderate to low selection intensities.

The paper develops a method to detect haplotype bias using pedigree-based gene drop simulations in apple cultivars, identifying SNPs associated with fruit traits and potential selection signals.

DiffBreed uses automatic differentiation to optimize breeding strategies, achieving higher genetic gains than equal allocation through gradient-based optimization.

This study proposes a method to select optimal cross pairs in inter-population crosses by considering genetic effects across populations, showing increased genetic gains in multiple traits.

This paper introduces Cross Potential Selection (CPS), a strategy for selecting crossing pairs in plant breeding to accelerate novel variety production, showing higher genetic improvements in early cycles of simulated breeding programs.

This paper develops an AI method using simulation and optimization to improve genetic gain in plant breeding by optimizing progeny allocation strategies for mating pairs.

This paper develops two new GWAS models, SNPxGB and HBxGB, to detect QTLs interacting with discrete and continuous population structures without requiring prior population structure information.

This study uses UAV remote sensing and deep learning to estimate soybean biomass traits and extract latent features for breeding applications.

This study evaluates genomic selection and marker-assisted selection for improving medicinal compound production in red perilla using quantitative trait locus analysis and genomic prediction.

This study evaluates drought tolerance stability in soybean using time-series multispectral data and genomic prediction models, finding higher accuracy with changing irrigation treatments.

The paper proposes a Bayesian optimization method to optimize multivariate genomic prediction models using secondary traits, achieving better accuracy while reducing phenotyping costs.

This study shows that combining target populations with more diverse populations improves GWAS power for detecting QTNs, depending on genetic diversity metrics like FST and He.

RAINBOW is a novel SNP-set GWAS method that improves detection of causal variants and controls false positives, especially for nearby variants with opposite effects.