Kwangsoo Kim

scUnify provides a unified framework for training and inference across multiple single-cell foundation models, enabling comparison and extension of tasks and adaptation strategies.

spHOT identifies phenotype-associated spatial biomarkers in spatial transcriptomics by localizing disease-relevant niches across multiple diseases.

scMILD identifies condition-associated cells using sample-level labels and reveals biological transitions in disease datasets.

CLOVER integrates multi-omics data with whole-slide images to generate molecular-aware slide representations, outperforming existing methods in cancer subtype classification and biomarker prediction.

The paper analyzes hypoxia-related gene expression in cancers from anatomically similar locations using TCGA data to identify prognostic hub genes and functional enrichments.

TGFam-Finder re-annotates eukaryotic genomes to identify previously missed protein-coding genes, improving gene family annotation accuracy across multiple species.