Scientific Intern
CurrentIntegrate Cell-Painting data across batches, using the JUMP data as a test case:1. Developed Snakemake pipelines to automate data integration processes for image-based cell profiling.2. Leveraged containerization to ensure reproducibility and scalability across different computing environments.3. Engineered robust software pipelines to enhance single-cell processing, streamline data integration, and minimize technical variability.4. Captured results for four types of data: single-cell, cell-painting CNN well aggregated, cell profiler well aggregated and Image Net well aggregated data.