Yi Chang

The paper introduces a GAN-based method to generate high-quality membranes for cells with poor staining in fluorescent microscopy images, improving segmentation accuracy.

The paper introduces a large-scale spatial transcriptomic dataset and a Graph Neural Network-based method for cell type deconvolution in human immuno-oncology.

This paper introduces a causality-inspired feature selection method, CLAND, to improve accuracy and stability in cancer biomarker discovery from imbalanced omics data.

DBPOM is a database that integrates pharmaco-omics data to estimate drug effectiveness and adverse effects for cancer patients by mapping cell lines to individuals based on genetic similarities.