This repo contains the source code for Cancer Drug Prediction based on Genetic Mutations
-
Download the .py file and open in a Python IDE, using Python 3.6
-
Dowload Ananconda, specifically scikit-learn 0.19.1, pandas 0.20.3, and pydot 1.2.3
-
Download the given datafiles, with data from Glioma, Bladder Urothelial Carcinoma, Breast Invasive Carcinoma, Lung Adenocarcinoma, Colorectal Adenocarcinoma, Colon Adenocarcinoma, Head and Neck Squamous Cell Carcinoma, Ovarian Serous Cystadenocarcinoma, Brain Lower Grade Glioma.
a. patient_to_depletion_category_df contains miRNA depletion data and drug data from patients from all cancer types except for Glioma and Bladder Urothelial Carcinoma.
b. GBMLLC_patient_to_depletion_category_df miRNA depletion data and drug data from patients from the Glioma cohort
c. BLCA_patient_to_depletion_category_df miRNA depletion data and drug data from patients from the Bladder Urothelial Carcinoma cohort
d. mirna_and_mutation_with_target_df includes miRNA depeltion data, drug data, and mutational data for patients from all 9 cancer types.
-
Run the program.
-
Output should be a drug prediction.