df oktoberfest

data/msp_file_extraction.py

@@ -40,39 +40,42 @@ def numerical_to_alphabetical_str(s):
     return seq
 
 if __name__ == '__main__':
-    seq=[]
-    file = open("spectral_lib/predicted_library.msp", "r")
-    content=file.readlines()
-    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 :
-                pass
-
-        if 'Name:'in content[i]:
-            s=content[i].split(': ')[1].split('/')[0]
-            if 'C' in s or len(s)>30:
-                remove=True
-            else :
-                seq.append(s)
-
-    df = pd.DataFrame(seq,columns=['sequence'])
-    df = df.drop_duplicates()
-    df['irt_scaled']=0
-    df['state'] = 'holdout'
-    df.to_csv('spectral_lib/df_predicted_library_oktoberfest.csv',index=False)
+    #extract seq from .msp
+    # seq=[]
+    # file = open("spectral_lib/predicted_library.msp", "r")
+    # content=file.readlines()
+    # file.close()
+    # remove = False
+    # 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 :
+    #             pass
+    #
+    #     if 'Name:'in content[i]:
+    #         s=content[i].split(': ')[1].split('/')[0]
+    #         if 'C' in s or len(s)>30:
+    #             remove=True
+    #         else :
+    #             seq.append(s)
+    #
+    # df = pd.DataFrame(seq,columns=['sequence'])
+    # df = df.drop_duplicates()
+    # df['irt_scaled']=0
+    # df['state'] = 'holdout'
+    # df.to_csv('spectral_lib/df_predicted_library_oktoberfest.csv',index=False)
+    #
+    #
+    # #write new .msp with new RT
     #
-    updated_content=[]
-    ind=0
+    #
+    df= pd.read_csv('spectral_lib/df_predicted_library_oktoberfest.csv')
+
     predicted_lib=pd.read_csv('../output/out_lib_oktoberfest.csv')
 
     predicted_lib['seq'] = predicted_lib['seq'].map(numerical_to_alphabetical_str)
@@ -82,6 +85,42 @@ if __name__ == '__main__':
     pred_rt=predicted_lib['rt pred']
 
     df_joined = pd.merge(df,predicted_lib[['rt pred','sequence']],on='sequence',how='left')
+    #
+
+    file = open("spectral_lib/predicted_library.msp", "r")
+    content=file.readlines()
+    file.close()
+
+    remove = False
+
+    with open('spectral_lib/new_lib.msp', 'w') as f:
+        i=0
+        j=0
+        k=-1
+        for i in range(len(content)) :
+            k-=1
+            if remove:
+                if 'Name:' in content[i]:
+                    remove = False
+                else :
+                    pass
+
+            elif 'Name:'in content[i]:
+                s=content[i].split(': ')[1].split('/')[0]
+                k=2
+                if 'C' in s or len(s)>30:
+                    remove=True
+                else :
+                    f.write(f"{content[i]}")
+                    i += 1
+            elif k==0:
+                rt = content[i].split('iRT=')[1]
+                f.write(f"{content[i].replace(rt, str(df_joined['rt pred'][j]))}\n")
+                i+=1
+                j+=1
 
+            else:
+                f.write(f"{content[i]}")
+                i+=1
 
     #1787661 avec C , 15104040 sans
\ No newline at end of file