diff --git a/diann_lib_processing.py b/diann_lib_processing.py index 770538071d83fc92147ff230d335260e3ef7b51b..9b70b76ba5dff12f22201169688a6904abe55725 100644 --- a/diann_lib_processing.py +++ b/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 diff --git a/identification/result_extraction.py b/identification/result_extraction.py new file mode 100644 index 0000000000000000000000000000000000000000..c936685d3e86d881cd966a6396be340fe4161c35 --- /dev/null +++ b/identification/result_extraction.py @@ -0,0 +1,17 @@ +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')