What I am studying
This project explores COAD (colon adenocarcinoma, a type of colon cancer) through public TCGA and PanCanAtlas data. It brings clinical information, RNA expression, and mutation data into one research workflow.
I use machine learning (training a program to find patterns in data) to study how tumor and normal samples can be distinguished. I also examine frequently mutated genes, connect mutation sites to protein structures, and study related compound information from scientific resources such as AlphaFold, UniProt, NCI, and ChEMBL.
My goal is to learn how biology, data analysis, and computer science can work together in cancer research, while presenting each step clearly enough for other students to follow. This is an educational research project and is not intended for medical diagnosis.