This project was a part of my MSc. dissertation and used K-means clustering to investigate a protein called FACT in Saccharomyces Cerrevisiae (baker's yeast). The entire project was coded in Python (version 3.9) and the IDE was Microsoft Visual Studio (v. 1.82).
Some of the major results are shared below, and the full annotated code and PDF of the report will be made available in due course. (Meanwhile, the draft code jupyter notebook can be seen here).
We used a range of libraries for data cleaning and modelling (numpy, pandas, scikit-learn), as well data visualisation (matplotlib, seaborn, etc.)
We relied on inertia and silhouette scores to select k = 3 for K-means analysis. The resulting clusters of genes are plotted below
