Dataset 1. Epitopes / non-epitopes
Dataset 2. Whole proteome

Task 1: contains the whole proteome data
Task 2: contains the code of the Protein Unet to predict secondary structure
Task 3: contains code for BERT
Task 4: contains the Epitopes/non-epitopes dataset 
Task 5: contains the code to run and train the classifier
Task 6: contains code to predict over new data and the pipeline needed to follow in the README.