Greg Slabaugh

SHOT-CCR improves classification of genetic perturbations in Cell Painting datasets by reducing batch effects through biologically guided adversarial training.

This paper develops a network-based atlas of human skeletal muscle aging using transcriptomic data from 1,675 biopsies and multiple single-cell technologies, revealing gene modules and interactions associated with aging and load status.

This study uses deep learning to segment osteocyte networks and shows it can distinguish between young and aged mouse bones.

The paper develops a large-scale blood transcriptomic resource for Alzheimer's disease, identifies sex-specific differences, and models insulin resistance biomarkers using machine learning.

This paper develops a Swin Transformer-based model to predict kinase inhibitor mechanisms of action from Cell Painting data, achieving higher accuracy than traditional image-based profile methods.

This paper uses machine learning to predict atrial fibrillation and ischemic stroke risk using UK Biobank data, finding LightGBM outperforms other models for AF and XGBoost for stroke.