Seoyeon Kim

The paper introduces distributed AI agents to analyze large-scale biological datasets, demonstrating their ability to rapidly extract insights and predict outcomes across a Perturb-seq atlas.

The paper develops Perturb-CLEAR to study dendritic morphogenesis in the developing mouse cortex, revealing gene-specific multimodal phenotypes linked to NDD risk genes.

The paper maps gene expression responses to loss of 1,947 disease-associated genes across the mouse brain using Perturb-seq, revealing cell-type-specific essentiality and transcriptional programs.

The paper constructs a single-cell atlas of developing human brains to analyze the temporal and cellular specificity of neurological disorder genes across 393,060 cells.