Zachary R. Miller

This study identifies convergent genomic and gene-level constraints in grasses adapting to extreme environments using phylogenomic data and large language models.

reelGene evaluates gene models using machine learning and evolutionary data, finding 28% of maize gene models are incorrectly annotated or nonfunctional.

The paper introduces PlantCaduceus, a DNA language model for plants, showing high transferability across species and improved performance in mutation prediction and variant identification.

The paper introduces the Practical Haplotype Graph (PHG) platform for storing and using pangenomes, demonstrating its effectiveness in imputing genomes from low-coverage data in crops like maize.

The paper develops a wheat haplotype graph database for efficient genotype storage and imputation, showing improved accuracy over existing methods.

The paper constructs a maize pangenome haplotype graph (PHG) to improve genotype imputation accuracy across diverse germplasm using WGS and GBS data.

This paper introduces a sorghum Practical Haplotype Graph (PHG) that enables accurate SNP calling and imputation from low-coverage sequencing data, improving genomic prediction accuracy and reducing genotyping costs.

This study compares one-stage and two-stage GWAS methods, finding that a weighted two-stage approach reduces bias and improves power, especially in unbalanced data.

This study identifies independent temperate adaptations in maize flowering time across different populations using GWAS and machine learning.