deletions | additions       diff --git a/README.md b/README.md  index 418ad3b..8488d87 100644  --- a/README.md  +++ b/README.md 
...
This repository has the data, analysis notebooks, and latex files for [Predicting Peptide-MHC Binding Affinities With Imputed Training Data](http://biorxiv.org/content/early/2016/05/22/054775), submitted to the [ICML 2016 Workshop on Computational Biology](https://sites.google.com/site/compbioworkshopicml2016/).  ## Data and notebooks  The predictions on the blind test data generated by the MHCflurry predictors, netMHC, netMHCpan, and SMM are available in [data/validation_predictions_full.csv](blob/master/data/validation_predictions_full.csv). [data/validation_predictions_full.csv](data/validation_predictions_full.csv).  This file has preditions from 64 MHCflurry models, 32 with imputation and 32 without. Descriptions of the models are in [data/validation_models.csv](blob/master/data/validation_models.csv). [data/validation_models.csv](data/validation_models.csv).  The notebook to train the predictors and generate these results took about 20 hours to run on a single TITAN X GPU and is in [notebooks/validation.ipynb](blob/master/notebooks/validation.ipynb). [notebooks/validation.ipynb](notebooks/validation.ipynb).  The analysis of these results, including generating ensemble predictions from the individual predictors and calculating AUC, F1, and tau scores is in [notebooks/validation results analysis.ipynb](blob/master/notebooks/validation%20results%20analysis.ipynb). analysis.ipynb](notebooks/validation%20results%20analysis.ipynb).  The command to generate the data for Figure 1 was: