added batch normalization between layers and changed default initialization to divide by sum of fan_in + fan_out instead of just fan_in

split up some of the class1_binding_predictor methods, moved code to training_helpers and Dataset, fixing broken unit tests

adding test to make sure imputation improves predictive accuracy on a small allele, added allow_unknown_amino_acids to from_hyperparameters

fixed neural network test, fixed length filtering of data loading, started on adding imputation to training script