diff --git a/diann_lib_processing.py b/diann_lib_processing.py index 9b70b76ba5dff12f22201169688a6904abe55725..abc611083fa62e58a0e59c2005b54588c97d495e 100644 --- a/diann_lib_processing.py +++ b/diann_lib_processing.py @@ -95,7 +95,7 @@ def predict(data_pred, model, output_path): if __name__ =='__main__': - df = load_lib('spectral_lib/first_lib.parquet') + # df = load_lib('spectral_lib/first_lib.parquet') # plt.hist(df['RT']) # plt.savefig('test.png') diff --git a/identification/result_extraction.py b/identification/result_extraction.py index c936685d3e86d881cd966a6396be340fe4161c35..eaac84fd40c33919b26054e36716f7309a3a78f7 100644 --- a/identification/result_extraction.py +++ b/identification/result_extraction.py @@ -3,7 +3,7 @@ import pandas as pd from matplotlib_venn import venn2 import matplotlib.pyplot as plt -def compare_id(path_1,path_2): +def compare_id(path_1,path_2,sample_name): 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()) @@ -11,7 +11,13 @@ def compare_id(path_1,path_2): 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') + venn2((peptides_1, peptides_2), ('custom lib', 'base lib'), set_colors=('g','r')) # venn2 works for two sets + plt.title('Peptide identifications on {} sample'.format(sample_name)) + plt.savefig('venn_diag_pep_{}.png'.format(sample_name)) -compare_id('CITFRE_ANA_69/report_custom.tsv','CITFRE_ANA_69/report_first_lib.tsv') + plt.clf() + venn2((protein_1, protein_2), ('custom lib', 'base lib'), set_colors=('g','r')) # venn2 works for two sets + plt.title('Protein identifications on {} sample'.format(sample_name)) + plt.savefig('venn_diag_prot_{}.png'.format(sample_name)) + +compare_id('CITFRE_ANA_69/report_custom.tsv','CITFRE_ANA_69/report_first_lib.tsv',sample_name='CITFRE_ANA_69')