Datasets were obtained from UCSC Xena
GDC Pan-Cancer (PANCAN) cohort:
pip install streamlit
-- For the UI of the applicationpip install pandas
-- For data analysispip install numpy
-- For scientific computingpip install GSVA
-- For the GSVA calculationpip install kaplanmeier
-- For the creation of a Kaplan Meier plotpip install matplotlib
-- For the output of the Kaplan Meier plot
Data was originally transformed from csv
files to parquet
files for faster overall application runtime. In addition to this, Streamlit's @st.cache_data
decorator was used in order to cache the data after the first data read-in.
- Open Terminal and navigate to project folder
- Type
streamlit run SurvivalAnalysisTool.py
to open the streamlit app in the browser - Use preferred editing software to edit the file and see changes reflected in the streamlit app browser