Data Research Assistant
Current- Cleaned patient and cancer tissue multiplex data for over 800 separate tissues and 200 patients
- Pandas wrangling and data manipulations and transformations
- Used optmized parallel processing calls to speed up data processing by 5x
- Read papers and implemented and adapted models from existing literature
- Logistic regression on clinical variables and biomarkers to predict outcomes
- Wrote multi processor code to speed up analysis on HPC by 2x