diff --git a/.idea/LC-MS-RT-prediction.iml b/.idea/LC-MS-RT-prediction.iml
index 81c1f054c8f6682138a3e8066d2e19396c22b814..2a5a0ab367bde49e5adbca0d5136f94cf65e5682 100644
--- a/.idea/LC-MS-RT-prediction.iml
+++ b/.idea/LC-MS-RT-prediction.iml
@@ -8,8 +8,9 @@
       <excludeFolder url="file://$MODULE_DIR$/database" />
       <excludeFolder url="file://$MODULE_DIR$/.venv" />
       <excludeFolder url="file://$MODULE_DIR$/.venv2" />
+      <excludeFolder url="file://$MODULE_DIR$/.venv3_10" />
     </content>
-    <orderEntry type="jdk" jdkName="Python 3.11 (LC-MS-RT-prediction)" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="Python 3.9 (LC-MS-RT-prediction)" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
index cde01ce4f1c28496b5ffbb181b9aa0e7b9db0fda..1b5f6f736536803396a9f042bfdc1981e5153ac8 100644
--- a/.idea/misc.xml
+++ b/.idea/misc.xml
@@ -3,5 +3,5 @@
   <component name="Black">
     <option name="sdkName" value="Python 3.9 (LC-MS-RT-prediction)" />
   </component>
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11 (LC-MS-RT-prediction)" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (LC-MS-RT-prediction)" project-jdk-type="Python SDK" />
 </project>
\ No newline at end of file
diff --git a/alignement.py b/alignement.py
index 58c5969325cab3a60f86e4793584a4ba14f2ed37..1c11a0737517221c5edf939c0991ada89efe594c 100644
--- a/alignement.py
+++ b/alignement.py
@@ -3,9 +3,10 @@ import pandas as pd
 from loess.loess_1d import loess_1d
 
 from dataloader import RT_Dataset
-from common_dataset import Common_Dataset
+from msms_processing import load_data
 import matplotlib.pyplot as plt
 
+
 ALPHABET_UNMOD = {
     "": 0,
     "A": 1,
@@ -70,27 +71,38 @@ def align(dataset, reference):
 data_ori = RT_Dataset(None, 'database/data_train.csv', 'train', 25).data
 data_ori['sequence'] = data_ori['sequence'].map(numerical_to_alphabetical)
 
-data_train = pd.read_pickle('database/data_DIA_16_01.pkl').reset_index(drop=True)
+data_train = load_data('msms/msms16_01.txt').reset_index(drop=True)
+# data_train = pd.read_pickle('database/data_DIA_16_01.pkl').reset_index(drop=True)
 data_align = align(data_train, data_ori)
 data_align.to_pickle('database/data_DIA_16_01_aligned.pkl')
-data_train = pd.read_pickle('database/data_DIA_17_01.pkl').reset_index(drop=True)
+
+data_train = load_data('msms/msms17_01.txt').reset_index(drop=True)
+# data_train = pd.read_pickle('database/data_DIA_17_01.pkl').reset_index(drop=True)
 data_align = align(data_train, data_ori)
 data_align.to_pickle('database/data_DIA_17_01_aligned.pkl')
-data_train = pd.read_pickle('database/data_DIA_20_01.pkl').reset_index(drop=True)
+
+data_train = load_data('msms/msms20_01.txt').reset_index(drop=True)
+# data_train = pd.read_pickle('database/data_DIA_20_01.pkl').reset_index(drop=True)
 data_align = align(data_train, data_ori)
 data_align.to_pickle('database/data_DIA_20_01_aligned.pkl')
-data_train = pd.read_pickle('database/data_DIA_23_01.pkl').reset_index(drop=True)
+
+data_train = load_data('msms/msms23_01.txt').reset_index(drop=True)
+# data_train = pd.read_pickle('database/data_DIA_23_01.pkl').reset_index(drop=True)
 data_align = align(data_train, data_ori)
 data_align.to_pickle('database/data_DIA_23_01_aligned.pkl')
-data_train = pd.read_pickle('database/data_DIA_24_01.pkl').reset_index(drop=True)
+
+data_train = load_data('msms/msms24_01.txt').reset_index(drop=True)
+# data_train = pd.read_pickle('database/data_DIA_24_01.pkl').reset_index(drop=True)
 data_align = align(data_train, data_ori)
 data_align.to_pickle('database/data_DIA_24_01_aligned.pkl')
-data_train = pd.read_pickle('database/data_DIA_30_01.pkl').reset_index(drop=True)
+
+data_train = load_data('msms/msms30_01.txt').reset_index(drop=True)
+# data_train = pd.read_pickle('database/data_DIA_30_01.pkl').reset_index(drop=True)
 data_align = align(data_train, data_ori)
 data_align.to_pickle('database/data_DIA_30_01_aligned.pkl')
 #
-plt.scatter(data_train['Retention time'], data_align['Retention time'], s=1)
-plt.savefig('test_align_2.png')
+# plt.scatter(data_train['Retention time'], data_align['Retention time'], s=1)
+# plt.savefig('test_align_2.png')
 #
 #
 # dataset_ref = pd.read_pickle('database/data_01_16_DIA_ISA_55.pkl')
diff --git a/data_exploration.py b/data_exploration.py
index 019c47127d7b437253c4af8ecf9726a9bc887f62..f74f487de2937bbc31503220c5cdb740671a29a6 100644
--- a/data_exploration.py
+++ b/data_exploration.py
@@ -1,7 +1,6 @@
 import numpy as np
 import matplotlib.pyplot as plt
 import matplotlib
-import pandas as pd
 
 matplotlib.use('agg')
 length = 30
diff --git a/database/data_DIA_ISA_55_test.pkl b/database/data_DIA_ISA_55_test.pkl
index b7186f96f9507a7ce52296e19e8c4b7b6da6a15a..acd3f16f3327a11b7add15c1c0a5521e28a44c46 100644
Binary files a/database/data_DIA_ISA_55_test.pkl and b/database/data_DIA_ISA_55_test.pkl differ
diff --git a/database/data_DIA_ISA_55_train.pkl b/database/data_DIA_ISA_55_train.pkl
index 435b980676ffb348a88160fa92b574236aad8f75..bcdd924040a7188f2cb1a2ca2a0ec99ee2cda6c1 100644
Binary files a/database/data_DIA_ISA_55_train.pkl and b/database/data_DIA_ISA_55_train.pkl differ
diff --git a/layers.py b/layers.py
index 6c3f94f79bfad68a28449e155ff80652bb51287c..b36e1991121556554089d42a4397da7059b09ed1 100644
--- a/layers.py
+++ b/layers.py
@@ -1,5 +1,3 @@
-import math
-
 import torch
 from torch import nn
 
diff --git a/msms_processing.py b/msms_processing.py
index bde575fa0ed43c3f5a374af6d4cbb63c7ddc21ee..5705fc43b573026f3e058d664e12b41bbf6e3213 100644
--- a/msms_processing.py
+++ b/msms_processing.py
@@ -109,6 +109,8 @@ if __name__ == '__main__':
 
     dataset_train = pd.concat(train_set).reset_index(drop=True)
     dataset_test = pd.concat(test_set).reset_index(drop=True)
+    dataset_train.to_pickle('database/data_DIA_ISA_55_train.pkl')
+    dataset_test.to_pickle('database/data_DIA_ISA_55_test.pkl')