Converted the tranposed escott output to ranksorted format.

prescott/escott.py

@@ -1415,10 +1415,34 @@ def doit(inAli,mutFile,retMet,bFile,fFile,n,N, jetfile, pdbfile, normWeightMode,
                         colorMap=colormap, offSet=offset, pixelType='square',\
                         sequence=prot+".fasta", interactive=False, isColorBarOn=True)
 
-            #Convert standard combined output to a transposed format to increase
-            #legibility.
+            #Convert standard combined output to (1 minus) ranksorted transposed format to increase
+            #legibility and interpretibility.
             gemmeDF = pd.read_table(prot+"_normPred_evolCombi.txt", sep="\s+")
-            gemmeDFtrans = gemmeDF.T
+            # print(gemmeDF)
+            ######################################################################
+            # Convert the DataFrame to a NumPy matrix
+            from scipy.stats import rankdata
+            import numpy as np
+            #matrix = gemmeDF.to_numpy()
+            maxValue =np.nanmax(gemmeDF.to_numpy())
+            # print(maxValue)
+            matrix = gemmeDF.to_numpy(na_value=maxValue)
+            # Use rankdata to get the ranks for all values in the matrix
+            ranks = 1.0 - rankdata(matrix, method='average')/len(matrix.flatten())
+
+            # Reshape the ranks back to the original matrix shape
+            ranks_matrix = ranks.reshape(matrix.shape)
+
+            # Convert the ranks matrix back to a DataFrame
+            df_ranks = pd.DataFrame(ranks_matrix, columns=gemmeDF.columns, index=gemmeDF.index)
+            # df_ranks.set_index(gemmeDF.index.tolist(), inplace=True)
+            # print(df_ranks)
+
+            gemmeDFtrans = df_ranks.T
+            ######################################################################
+
+            # gemmeDFtrans = gemmeDF.T
+
             # print(gemmeDF)
             gemmeDFtrans.columns = gemmeDFtrans.columns.str.upper()
             aaAndPosition = []
@@ -1431,7 +1455,7 @@ def doit(inAli,mutFile,retMet,bFile,fFile,n,N, jetfile, pdbfile, normWeightMode,
             # gemmeDFtrans.rename(index=aaAndPosition, inplace=True)
             # gemmeDFtrans['pos'] = aaAndPosition
             #print(df['pos'])
-            gemmeDFtrans.to_csv(prot+"_normPred_evolCombiTransposed.txt", sep='\t', float_format='%.2f', na_rep='NaN')
+            gemmeDFtrans.to_csv(prot+"_normPred_evolCombiTransposedRanksorted.txt", sep='\t', float_format='%.2f', na_rep='NaN')
             #sys.exit(-1)
 
         else:
@@ -1443,7 +1467,7 @@ def doit(inAli,mutFile,retMet,bFile,fFile,n,N, jetfile, pdbfile, normWeightMode,
 
 def main():
     """
-    Main function (and yes, I know. The name and the documentation are ingenious :). 
+    Main function (and yes, I know. The name and the function documentation are ingenious :). 
     """
     tic = time.perf_counter()