Sikta Das Adhikari

SPACE improves spatial domain detection by clustering spatially variable genes while adjusting for cell type effects without requiring prior knowledge of clusters or cell types.

The paper uses Arabidopsis gene expression data to train machine learning models for predicting tissue identity in other flowering plants, finding that gene expression signatures are more predictive than marker genes.

BayesKAT is a Bayesian framework for genetic association studies that identifies joint genetic effects in complex diseases by adaptively selecting optimal kernels.