From dbabcb515f196b60f97c7e949b4edd0c4d9235ac Mon Sep 17 00:00:00 2001
From: Schneider Leo <leo.schneider@etu.ec-lyon.fr>
Date: Thu, 3 Oct 2024 13:18:29 +0200
Subject: [PATCH] filter cysteine
---
alignement.py | 20 ++++++++++++++------
1 file changed, 14 insertions(+), 6 deletions(-)
diff --git a/alignement.py b/alignement.py
index 94b7821..2b88a0c 100644
--- a/alignement.py
+++ b/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')
--
GitLab