Andrew D. B. Leakey

PhenoStream: A Cyberinfrastructure for Automated and AI-Based Crop Trait Extraction from Aerial Imagery

PhenoStream automates crop trait extraction from aerial imagery, enabling high-throughput phenotyping with reduced latency and manual effort.

Nutrient enrichment and herbivore exclusion disrupt the climate-driven balance between C3 and C4 plants in grasslands

The paper shows that nutrient enrichment, especially with nitrogen and phosphorus, reduces C4 plant cover in grasslands, disrupting climate-driven C3-C4 balance globally.

Pi-Ensemble: Sequence-guided generation of interpolated protein conformational ensembles

Pi-Ensemble generates protein conformational ensembles between two structural states using sequence-guided interpolation, producing physically plausible intermediates without additional training.

ROOTQUANT: AUTOMATED ROOT TRAIT QUANTIFICATION FROMMINIRHIZOTRON IMAGES USING DEEP LEARNING

RootQuant uses deep learning to automatically quantify root traits from minirhizotron images, achieving high accuracy across species without pixel-level annotations.

High-resolution microCT reveals relationships between stomata and interior leaf anatomy in Sorghum

This study uses high-resolution microCT and machine learning to analyze the relationship between stomatal distribution and internal leaf anatomy in sorghum, revealing unexpected structural adaptations.

Multi-trait Multi-environment Genomic Prediction Strategies for Miscanthus sacchariflorus Populations

This study evaluates MTME genomic prediction models for Miscanthus sacchariflorus, finding they improve prediction for some traits but not all, depending on the cross-validation scenario.

Optimizing resource allocation in Miscanthus breeding with sparse testing designs for genomic prediction

This study evaluates sparse testing designs for genomic prediction in Miscanthus breeding to reduce phenotyping costs while maintaining predictive accuracy.

Weather Characterization for Optimizing Genomic Prediction in Miscanthus sacchariflorus

This study optimizes genomic prediction in Miscanthus sacchariflorus by incorporating weather data to improve model performance across different locations.

ENHANCING GENOMIC PREDICTION MODELS IN MISCANTHUS POPULATIONS BY INCORPORATING THE GENOTYPE-BY-ENVIRONMENT INTERACTION

The paper evaluates cross-validation schemes for genomic selection in perennial Miscanthus species, showing improved predictive ability by incorporating genotype-by-environment interactions.

Spatial analysis of cell patterning to aid genetic and phenotypic understanding of grass stomatal density: a case study in maize

This study uses a new spatial analysis approach to decompose stomatal density into component traits, revealing specific QTL for lateral and longitudinal patterning in maize.

Improving Multi-Trait Genomic Prediction Efficiency Through The Incorporation Of Synthetic Traits Selected Based on Co-heritability

This paper improves genomic prediction accuracy by using synthetic traits derived from hyperspectral data, showing higher accuracy than single-trait models for leaf traits in sorghum.

Phylogenetic diversity of light dependent phosphorylation of Thr78 in Rca

The paper investigates the phylogenetic distribution and regulation of threonine 78 phosphorylation in Rubisco activase across plant species, finding light-dependent dephosphorylation only in Arabidopsis.

GNC is a regulator of metabolic and productivity responses to elevated CO2 in Arabidopsis thaliana

This study identifies GNC as a GATA transcription factor that modulates metabolic and productivity responses to elevated CO2 in Arabidopsis thaliana.

Breaking the barrier of human-annotated training data for machine-learning-aided plant research using aerial imagery

A machine learning approach accelerates plant phenotyping by reducing the need for large amounts of human-annotated data, enabling faster and more efficient detection of a plant trait using aerial imagery.

A spontaneous mutation in a key C4 pathway gene significantly alters leaf δ13C uncoupling its relationship with WUE and photosynthetic performance in Zea mays

Ozone sensitivity of diverse maize genotypes is associated with differences in gene regulation, not gene content

The paper examines how gene regulation, not gene content, contributes to maize genotypes' sensitivity to ozone stress by analyzing gene expression across diverse inbred lines.

Novel Bayesian Networks for Genomic Prediction of Developmental Traits in Biomass Sorghum

This paper develops Bayesian networks for genomic prediction of developmental traits in biomass sorghum, showing improved accuracy for plant height and biomass yield using multi-time and multi-trait models.

Leveraging mutational burden for complex trait prediction in sorghum

This study estimates deleterious mutation burden in sorghum and assesses its impact on agronomic traits, finding moderate genetic variance explanation but limited improvement in breeding accuracy due to linkage.