Understanding how cancer cells develop resistance to chemotherapy is central to our work. We investigate the molecular mechanisms by which leukemia and ovarian cancer cells survive extensive chemotherapy, with particular focus on the PI3K/mTOR pathway, BCL2 family proteins, and receptor tyrosine kinase signaling. Our research has revealed that aberrant activation of the PI3K/mTOR pathway promotes resistance to sorafenib in AML, and we continue to explore how targeting components of this pathway can overcome resistance.

We develop machine learning models to predict drug sensitivity in cancer, enabling personalized treatment strategies. Our published work on machine learning in cancer therapy prediction has been widely cited, demonstrating the potential of computational approaches to guide clinical decision-making. We integrate genomic, transcriptomic, and proteomic data to build predictive models that can identify which patients will respond to specific therapies.

While single-agent therapies often display poor responses in resistant cancers, drug combinations can overcome resistance mechanisms. We investigate synergistic drug combinations, particularly in relapsed T-cell acute lymphoblastic leukemia (T-ALL) and ovarian cancer. Our work includes the development of novel tools to predict therapy resistance and the identification of effective combination strategies using CDK inhibitors, PI3K/mTOR inhibitors, and ALK inhibitors.