PDF of workflow to predict DLBCL subtype based on chromosome copy number data.
This work is based off my time at the National Institutes of Health and the General Assembly Data Science with Python Coding Bootcamp.
I used traditional machine learning methods including logistic regression, K-nearest neighbors, and random forests to predict lymphona subtype based on DNA sequencing data that was available. The data is anonymized. The jupyter notebook shows the code that went into making the PDF, which is a presentation of my procedure and results.