diff --git a/Synthetic data creation scripts/main.py b/Synthetic data creation scripts/main.py
index 02c5bc74aa475a71f77899da43bdd7e11055d547..2b158f836f9f60e65ea10c4057c1e92d03d29a53 100644
--- a/Synthetic data creation scripts/main.py	
+++ b/Synthetic data creation scripts/main.py	
@@ -1,4 +1,5 @@
-"""Driver script to create all of the mzML files with the statistially significant peaks.
+"""Driver script to create all of the mzML files with the statistially significant peaks. Running this script creates
+the original dataset used in the MVAPCK paper. 
 
 
 Author: Chris Jurich <cjurich2@huskers.unl.edu>
@@ -26,7 +27,8 @@ def report_significant( mapper  : Dict[str,bool]) -> None:
 	print(f"RNG seed: {RNG_SEED}")
 
 def main():
-    #"""Driver function that reads in idealized files, creates"""
+    #"""Driver function that reads in idealized files, creates all nine versions of the simulated dataset. Values
+    for replicate setup, percent missing and noise are hard-coded but are altered here."""
     np.random.seed( 100 )
     eics = pickle.load(open("data/eics-cpy2.pickle", "rb"))
     rts = eics[0].rts()