deletions | additions       diff --git a/section_Results_We_evaluated_the__.tex b/section_Results_We_evaluated_the__.tex  index bf35b8a..2bcd682 100644  --- a/section_Results_We_evaluated_the__.tex  +++ b/section_Results_We_evaluated_the__.tex 
...
\end{table}  \section{Discussion}  Imputing training data shows promise in cross-validation as a way to improve performance on alleles with few observations, but only seems to help for very small training sizes ($\leq 100$). Unfortunately, none of the alleles included in the BLIND dataset had fewer than 100 samples in BD2009 (in fact, BD2009, and  only oneallele  had fewer than 200). 200.  Thus, additional work is required to assess the accuracy of MHCflurry and other predictors on alleles with scarce training data. Additionally, we need to further investigate the interaction between imputation parameters, the decay schedule for the weights of imputed samples, and stopping criteria for training individual allele-specific predictors. % These are generated in the 'paper plots' notebook; do not edit by hand.