df oktoberfest

data/data_processing.py

 import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
-# from loess.loess_1d import loess_1d
+from loess.loess_1d import loess_1d
 import time
 
 ALPHABET_UNMOD = {

data/msp_file_extraction.py

@@ -71,10 +71,31 @@ if __name__ == '__main__':
     # df.to_csv('spectral_lib/df_predicted_library_oktoberfest.csv',index=False)
     #
     #
-    # #write new .msp with new RT
-    #
-    #
-    df= pd.read_csv('spectral_lib/df_predicted_library_oktoberfest.csv')
+    #write new .msp with new RT
+    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'])
 
     predicted_lib=pd.read_csv('../output/out_lib_oktoberfest.csv')
 

diann_lib_processing.py

@@ -5,6 +5,8 @@ import pyarrow.parquet as pq
 import pyarrow as pa
 import torch
 import matplotlib.pyplot as plt
+from loess.loess_1d import loess_1d
+
 from model.model import ModelTransformer
 from config import load_args
 from data.dataset import load_data
@@ -93,34 +95,81 @@ def predict(data_pred, model, output_path):
 
 
 if __name__ =='__main__':
-    # df = load_lib('data/spectral_lib/first_lib.parquet')
-    #
+    df = load_lib('spectral_lib/first_lib.parquet')
+
     # plt.hist(df['RT'])
     # plt.savefig('test.png')
     #
-    # df_2 = pd.read_csv('data/data_prosit/data.csv')
+    # df_2 = pd.read_csv('data_prosit/data.csv')
     #
     # plt.clf()
     # plt.hist(df_2['irt'])
     # plt.savefig('test2.png')
-
+    #
     # df_2 = extract_sequence(df).reset_index(drop=True)
     #
     # pred = pd.read_csv('../output/out_uniprot_base.csv')
-    #
+
     # pred['seq']=pred['seq'].map(numerical_to_alphabetical_str)
     #
     # pred['Modified.Sequence']=pred['seq']
     #
     # result = pd.merge(df,pred[['Modified.Sequence','rt pred']],on='Modified.Sequence',how='left')
     #
-    # result['RT']=result['rt pred']
+    #
+    #
+    # #alignement
+    #
+    # ref = pd.read_csv('data_prosit/data_noc.csv')
+    # df_ISA = pd.read_csv('data_ISA/data_aligned_isa_noc.csv')
+    #
+    # dataset, reference, column_dataset, column_ref, seq_data, seq_ref = df_ISA, ref,  'irt_scaled', 'irt', 'sequence','sequence',
+    #
+    # dataset_ref=dataset[dataset['state']=='train']
+    # dataset_unique = dataset_ref[[seq_data,column_dataset]].groupby(seq_data).mean()
+    # print('unique',len(dataset_unique))
+    # reference_unique = reference[[seq_ref,column_ref]].groupby(seq_ref).mean()
+    # seq_ref = reference_unique.index
+    # seq_common = dataset_unique.index
+    # seq_ref = seq_ref.tolist()
+    # seq_common = seq_common.tolist()
+    #
+    # seq_ref = [tuple(l) for l in seq_ref]
+    # seq_common = [tuple(l) for l in seq_common]
+    #
+    # ind_dict_ref = dict((k, i) for i, k in enumerate(seq_ref))
+    # inter = set(ind_dict_ref).intersection(seq_common)
+    # print(len(inter))
+    #
+    # ind_dict_ref = [ind_dict_ref[x] for x in inter]
+    #
+    # indices_common = dict((k, i) for i, k in enumerate(seq_common))
+    # indices_common = [indices_common[x] for x in inter]
+    #
+    #
+    # rt_ref = reference_unique[column_ref][ind_dict_ref].reset_index()
+    # rt_data = dataset_unique[column_dataset][indices_common].reset_index()
+    #
+    # plt.scatter(rt_data[column_dataset].tolist(),rt_ref[column_ref].tolist(),s=0.1)
+    # plt.savefig('test.png')
+    #
+    # #présence de NAN qui casse le réalignement (solution temporaire : remplacer par 0.
+    # result['rt pred']=result['rt pred'].fillna(value=0)
+    # xout, yout, wout = loess_1d(np.array(rt_data[column_dataset].tolist()), np.array(rt_ref[column_ref].tolist()),
+    #                             xnew=result['rt pred'],
+    #                             degree=1,
+    #                             npoints=None, rotate=False, sigy=None)
+    #
+    #
+    # #writing results
+    #
+    # result['RT'] = yout
     #
     # result = result.drop('rt pred', axis=1)
     #
     # table = pa.Table.from_pandas(result)
     #
-    # pq.write_table(table, 'spectral_lib/custom_first_lib.parquet')
+    # pq.write_table(table, 'spectral_lib/custom_first_lib_prosit_aligned.parquet')