data viz

data/data_exploration.py

@@ -128,11 +128,11 @@ def main():
     # retention_time_distribution(df_unique['irt_scaled'], False, True, '../fig/data_exploration/retention_time_distribution_isa_noc_mox_unique.png')
 
     #prosit outlier_plasma
-    df = pd.read_csv('data_PXD006109/data_prosit_outlier.csv')
+    df = pd.read_csv('data_ISA/data_prosit_outlier.csv')
     df['seq']=df['seq'].map(numerical_to_alphabetical_str)
-    _ = length_distribution(df['seq'],False ,True, '../fig/data_exploration/length_distribution_prosit_outlier.png')
-    _ = aa_distribution(df['seq'], False, True, '../fig/data_exploration/aa_distribution_prosit_outlier.png')
-    retention_time_distribution(df['true rt'], False, True, '../fig/data_exploration/retention_time_distribution_prosit_outlier.png')
+    _ = length_distribution(df['seq'],False ,True, '../fig/data_exploration/length_distribution_ISA_prosit_outlier.png')
+    _ = 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')
 
 
 if __name__ == '__main__':

data/data_viz.py

@@ -7,7 +7,7 @@ import random
 import pandas as pd
 from constant import ALPHABET_UNMOD_REV
 import matplotlib.colors as mcolors
-
+import peptides as pep
 
 def histo_abs_error(dataframe, display=False, save=False, path=None):
     points = dataframe['abs_error']
@@ -266,9 +266,35 @@ def plot_augmented_dataset_size(ref_path,base_path):
 
     plt.savefig('../fig/data_exploration/augmented_dataset_size.png')
 
+def compute_peptide_properties(df, base_name, col='seq', format='alpha'):
+    if format!= 'alpha':
+        df[col] = df[col].map(numerical_to_alphabetical_str)
+    hydro=[]
+    isop=[]
+    molecular_w = []
+    for p in df[col]:
+        pept = pep.Peptide(p)
+        hydro.append(pept.hydrophobicity())
+        isop.append(pept.isoelectric_point())
+        molecular_w.append(pept.molecular_weight())
+    plt.hist(hydro,bins = 50)
+    plt.title("Hydrophobicity")
+    plt.savefig('../fig/data_exploration/hydrophobicity_{}.png'.format(base_name))
+    plt.clf()
+
+    plt.hist(hydro,bins = 50)
+    plt.title("Isoelectric point")
+    plt.savefig('../fig/data_exploration/isoelectric_point_{}.png'.format(base_name))
+    plt.clf()
+
+    plt.hist(hydro,bins = 50)
+    plt.title("Molecular weight")
+    plt.savefig('../fig/data_exploration/molecular_weight_{}.png'.format(base_name))
+    plt.clf()
+
 
 if __name__ == '__main__' :
-    calc_and_plot_res()
+    # calc_and_plot_res()
     # base = ['plasma_plasma','plasma_prosit']
     # # augmented = ['ISA_aug_07_ISA_noc','ISA_aug_1_ISA_noc','ISA_aug_all_ISA_noc']
     # for f_suffix_name in base:
@@ -285,4 +311,22 @@ if __name__ == '__main__' :
     #     error_by_methionine(df)
     # dataframe = pd.read_csv('../output/out_early_stop_plasma_prosit_0.csv')
     # df = filter_outlier_rt(dataframe)
-    # df.to_csv('../data/data_PXD006109/data_prosit_outlier.csv', index=False)
\ No newline at end of file
+    # df.to_csv('../data/data_PXD006109/data_prosit_outlier.csv', index=False)
+    #
+    # 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')
\ No newline at end of file

main.py

@@ -106,7 +106,7 @@ def main(args):
                               embedding_dim=args.embedding_dim, acti=args.activation, norm=args.norm_first)
 
     if args.model_weigh is not None :
-        model.load_state_dict(torch.load(args.model_weigh+'.pt', weights_only=True))
+        model.load_state_dict(torch.load(args.model_weigh, weights_only=True))
 
     if torch.cuda.is_available():
         model = model.cuda()