Shisong Ma

The paper introduces GPD, a framework using gene co-expression programs to create an organism-wide cell atlas, revealing disease-related gene programs across tissues.

SpacGPA annotates spatial transcriptomes by identifying interpretable gene programs without single-cell data or segmentation.

The paper uses single cell transcriptomes to study how regulatory networks change during the development of Kranz anatomy in C4 grasses.

SingleCellGGM identifies gene expression programs from single-cell transcriptomes and enables cross-study cell-type label transfer.

The paper develops a human gene expression predictor to decode transcriptional regulation by modeling TF-target gene relationships across tissues and conditions.

EXPLICIT-Kinase predicts gene expression in Arabidopsis using kinase genes, identifying key regulators of pathways and showing conservation with maize.

The paper develops a gene expression predictor for Arabidopsis that uses TF activities to accurately predict transcriptomes and infer TF regulators for specific biological processes.

The paper identifies disease-associated gene modules using a co-expression network from GTEx data, revealing molecular pathways for obesity, cardiomyopathy, and other diseases.