deletions | additions       diff --git a/section_Neural_network_architecture_Each__.tex b/section_Neural_network_architecture_Each__.tex  index 3dcedd9..654ce16 100644  --- a/section_Neural_network_architecture_Each__.tex  +++ b/section_Neural_network_architecture_Each__.tex 
...
For each allele, we train a MHCflurry model using the measured peptide affinities for the allele and the values imputed by MICE based on other alleles in the training set. As training progresses, we place quadratically decreasing weight on the imputed values.  A randomly generated peptide is unlikely to bind a given MHC strongly, but a data acquisition bias toward strong binders in the training set can lead models to assign a high affinity to most peptide. peptides.  As a form of regularization, we augment the training set at each epoch to include random peptides with affinity set to be maximally weak. The number of random negative peptides is 20\% of the training size (without imputation). At each training epoch, a fresh set of random peptides is generated.