Lijing Lin A

NexuST is a hierarchical foundation model for spatial transcriptomics that improves cell-type annotation and spatial prediction by integrating gene-level and cell-level modeling.

This paper introduces UVAE to integrate unpaired clinical flow cytometry data, improving cell type signal and clustering by correcting batch effects.

This study identifies lymphocyte alterations and elevated complement signaling as key features of refractory myasthenia gravis, with implications for treatment strategies.

TriTan is a triple non-negative matrix factorisation method for single-cell multiomics data integration, offering efficient computation and improved interpretability.