filter cysteine

alignement.py

@@ -68,6 +68,12 @@ def align(dataset, reference):
     dataset['Retention time'] = yout
     return dataset
 
+def filter_cysteine(df, col):
+    def map_cys(str):
+        return not('C' in str)
+    df['cys'] = df[col].map(map_cys)
+    data = df[df['cys']].reset_index(drop=True)
+    return data
 
 # data_ori = load_data('msms/msms30_01.txt').reset_index(drop=True)
 # # data_ori['sequence'] = data_ori['sequence'].map(numerical_to_alphabetical)
@@ -141,9 +147,11 @@ def align(dataset, reference):
 # dataset_train.to_pickle('database/data_DIA_ISA_55_test.pkl')
 
 data_train_1 = pd.read_pickle('database/data_DIA_ISA_55_train.pkl').reset_index(drop=True)
-data_train_2 = pd.read_pickle('database/data_DIA_ISA_55_test.pkl').reset_index(drop=True)
-data_ori = pd.read_csv('database/data_train.csv').reset_index(drop=True)
-data_ori['Sequence']=data_ori['sequence']
-data_ori['Retention time']=data_ori['irt']
-data_train = pd.concat([data_train_2,data_train_1]).reset_index(drop=True)
-data_align = align(data_train, data_ori)
+# data_train_2 = pd.read_pickle('database/data_DIA_ISA_55_test.pkl').reset_index(drop=True)
+# data_ori = pd.read_csv('database/data_train.csv').reset_index(drop=True)
+# data_ori['Sequence']=data_ori['sequence']
+# data_ori['Retention time']=data_ori['irt']
+# data_train = pd.concat([data_train_2,data_train_1]).reset_index(drop=True)
+# data_align = align(data_train, data_ori)
+
+df = filter_cysteine(data_train_1,'Sequence')