Jack R. Leary

genesetGPT is an LLM-based framework that improves gene set annotation by using curated biological context and iterative prompt design to summarize heterogeneous gene sets.

The paper introduces scLANE, an interpretable method for trajectory differential expression in single-cell RNA-seq, validated on simulations and applied to biological datasets.

The paper introduces Escort, a framework to evaluate dataset suitability for trajectory inference and quantify trajectory properties, reducing analysis uncertainty through data-driven assessments.

SCISSORS identifies rare cell types in scRNA-seq data through semi-supervised reclustering and marker gene detection.