Harnessing Heterotypic 3D Spheroid Culture Method for Pre -clinical Testing of Computationally Identified Biomarkers of Drug Resistance in Breast Cancer

Overview

University Over $10.8 billion is spent each year in oncology clinical trials. However, only 3.4% of those trials succeed. Precise selection of targets could greatly improve the outcome of these trials. I hypothesize that an integrated machine-learning approach with experimental validation using a 3D culture model will be able to predict the drug response and identify markers for drug resistance. I used a breast cancer clinical trial dataset with 998 patients. Feature selection was performed using the ExtraTreesClassif ier. LightGBM predicted patient response for each drug with 94% accuracy after GridSearchCV tuning. SHAP and differential expression analysis prioritized the top 30 out of 16,000 genes. Network and CRISPR dependency analysis further pinpointed the top four functionally significant genes. Interestingly, numerous IGF1R pathway members are upregulated in drug-resistant samples, linked to poor survival in breast cancer patients, suggesting IGF1R is a promising therapeutic target. Next, I tested IGF1R inhibitor synergy with standard-of-care drugs in 147 double and triple combinations, providing better efficacy of triple combinations in 2D culture. Since cancer grows in 3-dimensional form, I established a novel 3-dimensional spheroid method by co-culturing cancer and endothelial cells. Flow cytometry and live cell imaging analyses demonstrated that IGF1R levels are high in drug resistance cells, and combining IGF1R inhibitor with chemotherapy increased cell death and reduced spheroid growth. I validated these resul ts in three breast cancer cell lines. Overall, a machine -learning approach combined with parallel experimental validation identified new targets for clinical trials. My approach could apply to various cancers to improve patients’ outcomes.

Competition history

• JSHS 2024 Category not listed

Resources

• National JSHS abstract book ↗

Related projects

Closest projects by meaning, across every fair and year in the corpus.