Hyobin Kim

The paper evaluates the reliability of confidence measures from single-cell models on new data and shows that raw confidence scores are unreliable, requiring recalibration with target-specific labels.

CellNeighborEX v2 identifies context-specific cell-cell interaction genes from spatial transcriptomics data without relying on ligand-receptor databases.

PersonaAI generates and validates aging-related hypotheses using literature and single-cell RNA-seq data, identifying novel aging mechanisms.

SC2Spa maps single-cell RNA-seq data to spatial coordinates using deep learning, improving resolution for low-resolution spatial transcriptomics data and identifying spatially variable genes.

This paper introduces an interpretable cell mapping strategy to align and compare heterogeneous spatial data across different scales and contexts, showing spatiotemporal decoupling during development and identifying subpopulations in cancer patient data.

CellNeighborEX identifies gene expression influenced by neighboring cells in spatial transcriptomics data, revealing new insights into cell-cell interactions in mouse embryos, brain, and liver cancer.

Vesalius identifies tissue structures and cell-type-specific gene expression in spatial transcriptomics data by applying image analysis techniques.