Single-Cell Analysis and Deep Learning for
Cancer Precision Medicine
Cellular heterogeneity is crucial for diverse functions in multicellular organisms, influencing normal physiology and disease development, including cancer. However, current biological understanding often overlooks individual cell variability due to population-averaged measurements. Leveraging single-cell technology, we focus on high-throughput multi-omics analysis and machine learning to track cell dynamics and profile heterogeneity. Microfluidic technology offers superior single-cell tracking but lacks integration with automated systems. Our research integrates user-friendly microfluidics, robotic liquid handling, and advanced computer vision for efficient single-cell migration assays. Automation enhances speed, accuracy, and reproducibility while reducing error, bias, and human intervention, driving scientific discovery. Harnessing data from high-throughput single-cell experiments, we aim to predict cellular responses to stimuli using deep learning, enabling iterative refinement of treatments. The integrated approach will change how we understand and treat cancer and ultimately improve outcomes for patients.
Robotic Operation of a Microfluidic Cell Migration Platform
Yu-Chih Chen, Ph.D.