datasets

alignement.py

@@ -182,15 +182,15 @@ def compare_include_df(df, sub_df, save = True, path = 'temp.png'):
 # dataset_train.to_pickle('database/data_DIA_ISA_55_train.pkl')
 # dataset_train.to_pickle('database/data_DIA_ISA_55_test.pkl')
 
-# data_train_1 = pd.read_pickle('database/data_DIA_ISA_55_test_30_01.pkl').reset_index(drop=True)
-# data_train_2 = pd.read_pickle('database/data_DIA_ISA_55_train_30_01.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_1 = pd.read_pickle('database/data_DIA_ISA_55_test_30_01.pkl').reset_index(drop=True)
+data_train_2 = pd.read_pickle('database/data_DIA_ISA_55_train_30_01.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_2, data_ori)
-#
-# data_align.to_pickle('database/data_ISA_dual_align_train.pkl')
+data_align = align(data_train_1, data_ori)
+
+data_align.to_pickle('database/data_ISA_dual_align_test.pkl')
 
 
 #compare DIANN pred to DIA mesures
@@ -211,32 +211,32 @@ def compare_include_df(df, sub_df, save = True, path = 'temp.png'):
 
 
 # create augmented dataset from ISA data + column invariant prosit peptides
-df_base = pd.read_pickle('database/data_DIA_ISA_55_train.pkl')
+df_base = pd.read_pickle('database/data_ISA_dual_align_train.pkl')
 df_base = df_base[['Sequence','Retention time']]
 
-df_1 = pd.read_pickle('database/data_prosit_threshold_5.pkl')
+df_1 = pd.read_pickle('database/data_prosit_threshold_1.pkl')
 df_1['Sequence']= df_1['Sequence'].map(numerical_to_alphabetical_str)
 
-df_2 = pd.read_pickle('database/data_prosit_threshold_7.pkl')
+df_2 = pd.read_pickle('database/data_prosit_threshold_2.pkl')
 df_2['Sequence']= df_2['Sequence'].map(numerical_to_alphabetical_str)
 
-df_3 = pd.read_pickle('database/data_prosit_threshold_10.pkl')
+df_3 = pd.read_pickle('database/data_prosit_threshold_3.pkl')
 df_3['Sequence']= df_3['Sequence'].map(numerical_to_alphabetical_str)
 
 df_augmented_1 = pd.concat([df_1,df_base],axis=0).reset_index(drop=True)
 df_augmented_1.columns=['sequence','irt']
 df_augmented_1['state']='train'
-df_augmented_1.to_csv('database/data_ISA_augmented_5.csv')
+df_augmented_1.to_csv('database/data_ISA_augmented_1_30_01.csv')
 
 df_augmented_2 = pd.concat([df_2,df_base],axis=0).reset_index(drop=True)
 df_augmented_2.columns=['sequence','irt']
 df_augmented_2['state']='train'
-df_augmented_2.to_csv('database/data_ISA_augmented_7.csv')
+df_augmented_2.to_csv('database/data_ISA_augmented_2_30_01.csv')
 
 df_augmented_3 = pd.concat([df_3,df_base],axis=0).reset_index(drop=True)
 df_augmented_3.columns=['sequence','irt']
 df_augmented_3['state']='train'
-df_augmented_3.to_csv('database/data_ISA_augmented_10.csv')
+df_augmented_3.to_csv('database/data_ISA_augmented_3_30_01.csv')
 
 
 # testing intersection between test and augmented dataset