Su-In Lee

Explainable machine learning prediction of synergistic drug combinations for precision cancer medicine

This study introduces TreeCombo, an XGBoost model predicting synergistic drug combinations using drug properties and gene expression, outperforming DeepSynergy and providing interpretable results.

Identifying Network Perturbation in Cancer

DISCERN identifies gene regulatory network perturbations in cancer by comparing diseased and normal tissues, finding enriched tumor drivers and prognostic genes.

Extracting a low-dimensional description of multiple gene expression datasets reveals a potential driver for tumor-associated stroma in ovarian cancer

The paper introduces INSPIRE, a method to infer gene modules and their dependencies across multiple datasets, identifying HOPX as a potential driver of tumor-associated stroma in ovarian cancer.

Learning the human chromatin network from all ENCODE ChIP-seq data

The paper introduces ChromNet, a method to infer chromatin networks from ChIP-seq data, and applies it to ENCODE data to identify known and novel regulatory interactions.