Sanguk Kim

A network-based deep learning model integrating subclonal architecture for therapy response prediction in cancer

This paper introduces SubNetDL, a deep learning model that uses subclonal mutation profiles and protein-protein interaction networks to predict cancer therapy response, achieving strong performance across multiple cancer types and treatment modalities.

A Co-essentiality Network of Cancer Driver Genes Better Prioritizes Anticancer Drugs

The paper constructs a co-essentiality network from CRISPR screens to prioritize anticancer targets and predict drug responses, outperforming conventional networks in drug repurposing.

Identification of neuron-glia signaling feedback in human schizophrenia using patient-derived, mix-and-match forebrain assembloids

This study uses patient-derived forebrain assembloids to identify neuron-glia signaling feedback abnormalities in schizophrenia, revealing stage-specific developmental mechanisms.

Link clustering explains non-central essential genes in protein interaction networks

The paper identifies link clustering as a principle explaining non-central essential genes in PPI networks, showing they have distinct functional and evolutionary characteristics compared to central essential genes.

Computational docking reveals evolutionary conservation of a specific interaction between 15d-Prostaglandin-J2 and eIF4A.

The paper uses computational docking to show that 15d-PGJ2 binds to eIF4A, blocking eIF4G interaction and forming stress granules, with conserved binding sites across species.