Wenhao Cai

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 surveys foundation models for non-invasive brain decoding, reviewing their applications and challenges in visual, language, and auditory domains.

SpatialFuser integrates unpaired spatial multi-omics data using a deep learning framework, improving spatial domain identification and cross-omics integration.

The paper presents uniLUNG, a large single-cell transcriptomic atlas of the human lung, identifying new cell types and subpopulations associated with lung diseases.