Honglin Wang

CLARA infers cell-cell communication by treating it as a natural language processing task using an attention mechanism, improving accuracy over existing methods by considering local gene expression.

The paper introduces vSPACE, a method to create virtual spatial representations of single-cell RNA sequencing data from human articular cartilage, revealing consistent zonal patterns across donors.

CGCom uses a graph neural network to infer cell-cell communication from spatial transcriptomics data, showing improved accuracy over existing methods.