Colorectal cancer (CRC) is among the most common and fatal cancers in the world; its tumor heterogeneity, therapy resistance, and complex tumor-immune microenvironment make treatment very difficult. Currently available preclinical models, such as two-dimensional cell cultures and animal models, do not adequately recapitulate the in vivo tumor immune microenvironment (TIME), including immune interactions, tissue architecture, and drug pharmacokinetics, making it difficult to translate findings into clinical outcomes. The goal of this project is to design an AI-powered 3D CRC-on-chip system that accurately replicates essential features of CRC TIME and supports predictive drug testing.

A CRC-on-a-chip will be designed, fabricated, and optimized for 3D coculture of colorectal cancer cells, endothelial cells, human mesenchymal stem cells, and immune cells within physiologically relevant extracellular matrix components. The chip will be evaluated by clinically relevant drugs and novel compounds.

The datasets for pharmacokinetic, pharmacodynamic, molecular, and immunological studies will be generated using confocal imaging, qPCR, ELISA, flow cytometry, and HPLC techniques. The efficacy and clearance of drugs will be estimated based on the PK-PD modeling method. AI-based technology will be utilized to predict the responses to treatment and to recognize resistance-associated patterns.

The project will evaluate the effectiveness of this platform using preclinical and clinical data to support its translation into precision oncology. It is anticipated that the project will produce a working CRC-on-a-chip prototype, an AI-based prediction model for predicting the response of drugs in patients with CRC, reduce the need for animal testing, accelerate the process of screening drugs to identify new potential treatments and provide a greater understanding of how CRC becomes resistant to chemotherapy.