extracting peptide set from txt

image_ref/utils.py

 import fastapy
 import matplotlib.pyplot as plt
 import numpy as np
+import pandas as pd
 from matplotlib_venn import venn2
 from analyse_diann_digestion import load_lib
 import matplotlib.image as mpimg
-
+import re
 
 ALPHABET_UNMOD = {
     "A": 1,
@@ -120,6 +121,35 @@ def fasta_similarity(path_fasta_1, path_fasta_2):
     plt.show()
     plt.savefig('fasta_similarity.png')
 
+def split_string(input_string):
+    # Use regular expression to split the string at underscore followed by uppercase letter
+    return re.split(r'_(?=[A-Zc])', input_string)
+
+def build_database_ref_peptide():
+    l=[]
+    with open('../data/label_raw/250107_FASTA_RP_GroEL_GroES_Tuf_5pct_assemble_peptides_list.txt', 'r') as f:
+        for line in f:
+            if line != '\n':
+                if '>' in line:
+                    #typo ??
+                    line = line.replace('no_family','No_family')
+                    line = line.replace('no_order', 'No_order')
+
+                    split_line = line.split('_')
+                    prot = split_line[0][1:]
+                    err = split_line[1]
+                    prev = split_line[2]
+                    split_line = split_string(line.split(' ')[1])
+                    spe = split_line[0].replace('_',' ')
+                    gen = split_line[1].replace('_',' ')
+                    fam = split_line[2].replace('_',' ')
+                    o = split_line[3].replace('_',' ')
+                else :
+                    seq = line.split(' ')[1]
+                    l.append({'Sequence' : seq,'Protein code' :prot , 'Error treshold':err , 'Prevalance': prev,
+                              'Specie':spe ,'Genus':gen ,'Family':fam ,'Order':o })
+    return pd.DataFrame(l)
+
 def compute_mass(seq, isotop):
     m = 0
     if isotop == 'mono':
@@ -195,6 +225,13 @@ def build_ref_image_from_diann(path_parqet, ms1_end_mz, ms1_start_mz, bin_mz, ma
 
 if __name__ == '__main__':
     # fasta_similarity('fasta/uniparc_proteome_UP000033376_2025_03_14.fasta','fasta/uniparc_proteome_UP000033499_2025_03_14.fasta')
-    im = build_ref_image_from_diann('fasta/steigerwaltii variants/uniparc_proteome_UP000033376_2025_03_14.predicted.parquet', ms1_end_mz=1250, ms1_start_mz=350, bin_mz=1, max_cycle=663, rt_pred=[])
-    plt.clf()
-    mpimg.imsave('test_img.png', im)
+    # im = build_ref_image_from_diann('fasta/steigerwaltii variants/uniparc_proteome_UP000033376_2025_03_14.predicted.parquet', ms1_end_mz=1250, ms1_start_mz=350, bin_mz=1, max_cycle=663, rt_pred=[])
+    # plt.clf()
+    # mpimg.imsave('test_img.png', im)
+
+    df = build_database_ref_peptide()
+    for spe in ['Proteus mirabilis','Klebsiella pneumoniae','Klebsiella oxytoca','Enterobacter hormaechei','Citrobacter freundii']:
+        df_spe = df[df['Specie']==spe]
+        with open(spe+'.fasta','w') as f:
+            for r in df_spe.iterrows():
+                f.write(r[1]['Sequence'])