PredictingGeneticvariations

Classification of Genetic Mutations based Clinical text so as to predict their effects on Personalized Medicine

To run this code, you will need:

• Numpy - Version: 1.14.3
• Pandas - Version: 0.22.0
• Seaborn - Version: 0.8.1
• Matplotlib - Version: 2.2.2
• NLTK, Regex, Sklearn, and lightgbm modules

To execute the classifier:

Download the repository and run the Genetic_Variations.py file.
Change the path to the dataset as per your system! The dataset is in the repository:

• Training Variants - Contains the description of the genetic mutations for training
• Training Text - Contains the clinical evidence to classify the mutations.
• Test variants - Contains the description of the genetic mutations for testing. Test Text - Contains the clinical evidence to classify the mutations. The sample submissions file holds the classification results.

Dataset - Personalized Medicine - Redefining Cancer Treatment on Kaggle