df oktoberfest

diann_lib_processing.py

@@ -5,7 +5,7 @@ import pyarrow.parquet as pq
 import pyarrow as pa
 import torch
 import matplotlib.pyplot as plt
-from loess.loess_1d import loess_1d
+# from loess.loess_1d import loess_1d
 
 from model.model import ModelTransformer
 from config import load_args

identification/result_extraction.py

+import numpy as np
+import pandas as pd
+from matplotlib_venn import venn2
+import matplotlib.pyplot as plt
+
+def compare_id(path_1,path_2):
+    df_1 = pd.read_csv(path_1, sep='\t', encoding='latin-1')
+    df_2 = pd.read_csv(path_2, sep='\t', encoding='latin-1')
+    peptides_1 = set(df_1['Stripped.Sequence'].tolist())
+    protein_1 = set(df_1['Protein.Ids'].tolist())
+    peptides_2 = set(df_2['Stripped.Sequence'].tolist())
+    protein_2 = set(df_2['Protein.Ids'].tolist())
+
+    venn2((peptides_1, peptides_2), ('custom lib', 'base lib')) # venn2 works for two sets
+    plt.savefig('venn_diag.png')
+
+compare_id('CITFRE_ANA_69/report_custom.tsv','CITFRE_ANA_69/report_first_lib.tsv')