Kun Zhang

scDRP estimates individual treatment effects and predicts single-cell responses to perturbations using disentangled representation learning with a sparsity regularized β-VAE.

This paper introduces scMRDR, a framework for integrating unpaired single-cell and spatial multi-omics data, showing strong performance in batch correction and spatial mapping.

The paper evaluates and introduces new statistical methods for inferring causal feedback networks from fMRI data, finding several methods achieve over 80% orientation precision and the new methods show strong recall.