df oktoberfest

data/msp_file_extraction.py

 import pandas as pd
+from sympy import false
 
+ALPHABET_UNMOD = {
+    "": 0,
+    "A": 1,
+    "C": 2,
+    "D": 3,
+    "E": 4,
+    "F": 5,
+    "G": 6,
+    "H": 7,
+    "I": 8,
+    "K": 9,
+    "L": 10,
+    "M": 11,
+    "N": 12,
+    "P": 13,
+    "Q": 14,
+    "R": 15,
+    "S": 16,
+    "T": 17,
+    "V": 18,
+    "W": 19,
+    "Y": 20,
+    "M(UniMod:35)": 21,
+    "CaC": 22
+}
+
+ALPHABET_UNMOD_REV = {v: k for k, v in ALPHABET_UNMOD.items()}
+
+def numerical_to_alphabetical_str(s):
+    seq = ''
+    s = s.replace('[','')
+    s = s.replace(']', '')
+    arr = s.split(',')
+    arr = list(map(int, arr))
+    for i in range(len(arr)):
+        seq+=ALPHABET_UNMOD_REV[arr[i]]
+    return seq
 
 if __name__ == '__main__':
     seq=[]
@@ -8,12 +46,17 @@ if __name__ == '__main__':
     file.close()
     remove = False
     index_to_remove=[]
+    updated_content=[]
+    ind=0
+    predicted_lib=pd.read_csv('../output/out_lib_oktoberfest.csv')
+    pred_rt=predicted_lib['rt pred']
+
     for i in range(len(content)) :
         if remove:
             if 'Name:' in content[i]:
                 remove = False
             else :
-                index_to_remove.append(i)
+                pass
 
         if 'Name:'in content[i]:
             s=content[i].split(':')[1].split('/')[0]
@@ -27,4 +70,16 @@ if __name__ == '__main__':
     df['state'] = 'holdout'
     df.to_csv('spectral_lib/df_predicted_library_oktoberfest.csv',index=False)
 
+    updated_content=[]
+    ind=0
+    predicted_lib=pd.read_csv('../output/out_lib_oktoberfest.csv')
+
+    predicted_lib['seq'] = predicted_lib['seq'].map(numerical_to_alphabetical_str)
+
+    predicted_lib['sequence']=predicted_lib['seq']
+    pred_rt=predicted_lib['rt pred']
+
+    df_joined = pd.merge(df,predicted_lib[['rt pred','sequence']],on='sequence',how='left')
+
+
     #1787661 avec C , 15104040 sans
\ No newline at end of file

diann_lib_processing.py

@@ -136,8 +136,7 @@ if __name__ =='__main__':
 
     model.load_state_dict(torch.load(args.model_weigh, weights_only=True))
 
-    print(args.dataset_test)
-    data_test = load_data(data_source='data/spectral_lib/data_uniprot_base.csv', batch_size=args.batch_size, length=30, mode=args.split_test,
+    data_test = load_data(data_source=args.dataset_test, batch_size=args.batch_size, length=30, mode=args.split_test,
                           seq_col=args.seq_test)
 
     predict(data_test, model, args.output)