data viz

data/data_exploration.py

@@ -2,7 +2,7 @@ import numpy as np
 import matplotlib.pyplot as plt
 import pandas as pd
 from numpy.ma.core import shape
-
+from sklearn.metrics import r2_score
 from constant import ALPHABET_UNMOD, ALPHABET_UNMOD_REV
 
 
@@ -75,6 +75,13 @@ def retention_time_distribution(data, plot=False, save=False, f_name='fig/data_e
     plt.clf()
     plt.close()
 
+def optimal_prediction_r2(df,seq_col,rt_col):
+    df_group_1 = df.groupby([seq_col])[rt_col].mean().to_frame().reset_index()
+    df_group_1['mean rt']=df_group_1[rt_col]
+    df_group_1=df_group_1[[seq_col,'mean rt']]
+    df_merged = df_group_1 .merge(df, how='inner', on=seq_col)
+    return r2_score(df_merged['mean rt'], df_merged[rt_col])
+
 def main():
     #data prosit
     # df = pd.read_csv('data_prosit/data.csv')
@@ -134,6 +141,24 @@ def main():
     _ = aa_distribution(df['seq'], False, True, '../fig/data_exploration/aa_distribution_ISA_prosit_outlier.png')
     retention_time_distribution(df['true rt'], False, True, '../fig/data_exploration/retention_time_distribution_ISA_prosit_outlier.png')
 
+    #compare variance of outliers vs others petides
+    seq_out_list = df['seq'].to_list()
+    df_prosit = pd.read_csv('data_prosit/data_noc.csv')
 
 if __name__ == '__main__':
-    main()
+    df = pd.read_csv('data_PXD006109/plasma/data_prosit_outlier.csv')
+    df['seq'] = df['seq'].map(numerical_to_alphabetical_str)
+
+    # compare variance of outliers vs others petides
+    seq_out_list = df['seq'].to_list()
+    df_prosit = pd.read_csv('data_prosit/data.csv')
+    df_prosit['outlier']=df_prosit['sequence'].map(lambda x : x in seq_out_list)
+    df_prosit_outlier = df_prosit[df_prosit['outlier']==True]
+    df_agg_out = df_prosit_outlier.groupby(pd.Grouper(key='mod_sequence'))['irt_scaled'].agg(['mean', 'median', 'var']).reset_index()
+    df_agg_pro = df_prosit.groupby(pd.Grouper(key='mod_sequence'))['irt_scaled'].agg(['mean', 'median', 'var']).reset_index()
+    # main()
+
+    plt.hist(df_agg_out['var'])
+    plt.savefig('var_outlier.png')
+    plt.hist(df_agg_pro['var'])
+    plt.savefig('var_pro.png')
\ No newline at end of file

data/data_viz.py

@@ -316,17 +316,37 @@ if __name__ == '__main__' :
     # dataframe = pd.read_csv('../archive_output/ISA/out_ISA_noc_prosit_0.csv')
     # df2 = filter_outlier_rt(dataframe)
     # df2.to_csv('../data/data_ISA/data_prosit_outlier.csv', index=False)
-    df = pd.read_csv('../data/data_PXD006109/data_prosit_outlier.csv')
-    compute_peptide_properties(df, 'plasma_prosit_outlier', 'seq', 'num')
-
-    df = pd.read_csv('../data/data_ISA/data_prosit_outlier.csv')
-    compute_peptide_properties(df,'ISA_prosit_outlier','seq', 'num')
-
-    df = pd.read_csv('../data/data_ISA/data_isa.csv')
-    compute_peptide_properties(df,'ISA','sequence')
-
-    df = pd.read_csv('../data/data_prosit/data.csv')
-    compute_peptide_properties(df,'prosit','sequence')
-
-    df = pd.read_csv('../data/data_PXD006109/plasma/data_plasma.csv')
-    compute_peptide_properties(df,'plasma','sequence')
+    # df = pd.read_csv('../data/data_PXD006109/data_prosit_outlier.csv')
+    # compute_peptide_properties(df, 'plasma_prosit_outlier', 'seq', 'num')
+    ## r2_list = []
+    # for index in range(10):
+    #     dataframe = pd.read_csv( '../output/out_tranfert_prosit_isa_mox_'+str(index)+'.csv')
+    #     r2_list.append(r2_score(dataframe['true rt'], dataframe['rt pred']))
+    # r2_arr = np.array(r2_list)
+    # print(r2_arr.mean(),'+/-',r2_arr.std()) #0.979362058986253 +/- 0.004342685753968106
+    # df = pd.read_csv('../data/data_ISA/data_prosit_outlier.csv')
+    # compute_peptide_properties(df,'ISA_prosit_outlier','seq', 'num')
+    #
+    # df = pd.read_csv('../data/data_ISA/data_isa.csv')
+    # compute_peptide_properties(df,'ISA','sequence')
+    #
\ No newline at end of file
+    # df = pd.read_csv('../data/data_prosit/data.csv')
+    # compute_peptide_properties(df,'prosit','sequence')
+    #
+    # df = pd.read_csv('../data/data_PXD006109/plasma/data_plasma.csv')
+    # compute_peptide_properties(df,'plasma','sequence')
+
+    r2_list = []
+    for index in range(10):
+        dataframe = pd.read_csv( '../output/out_tranfert_prosit_ISA_'+str(index)+'.csv')
+        r2_list.append(r2_score(dataframe['true rt'], dataframe['rt pred']))
+    r2_arr = np.array(r2_list)
+    print(r2_arr.mean(),'+/-',r2_arr.std()) #0.979362058986253 +/- 0.004342685753968106 et 0.9775968974701088 +/- 0.0022122290222140123  => moins bon que mélange
+
+    r2_list = []
+    for index in range(10):
+        dataframe = pd.read_csv( '../output/out_tranfert_prosit_plasma_'+str(index)+'.csv')
+        r2_list.append(r2_score(dataframe['true rt'], dataframe['rt pred']))
+    r2_arr = np.array(r2_list)
+    print(r2_arr.mean(),'+/-',r2_arr.std()) #0.977876349023085 +/- 0.0040982548977069695 et 0.982352390283812 +/- 0.00036 => equivalent au mélange
+    pass
\ No newline at end of file