added parser for PDB (x,y,z) misalignment bug

data_processor_polar.py

@@ -47,7 +47,7 @@ def hydrophobic_acid_patch_interactions(paramlist):
  clean_line[4] = split[0]
  clean_line.insert(5, split[1])
  #check if coordinate data collumns are collided (most likely happens between x and y coor)
- if len(clean_line[6])>=13:
+ while len(clean_line[6])>=13:
  split = [clean_line[6][:-8], clean_line[6][-8:]]
  last_elem = clean_line.pop()
  clean_line[-1] = last_elem
@@ -149,10 +149,10 @@ def hydrophobic_acid_patch_interactions(paramlist):
  complex_files = [f for f in os.listdir(path) if os.path.isfile(os.path.join(path, f))]
  complexes = complex_files
  cutoff = 12
-
+# 
  filename = 'h_a_vec.pkl'
 
- pool = multiprocessing.Pool()
+# pool = multiprocessing.Pool()
 
  #start of the process
  start_time = time.time()
@@ -201,4 +201,42 @@ def hydrophobic_acid_patch_interactions(paramlist):
  data checker
  '''
  data = data_checker.data_load(filename)
- print(data)
+ print(data, len(data))
+
+# id_name = '3s5l.ent.pdb'
+# path_file = path+'/'+id_name
+# l =[]
+# with open(path_file, 'r') as f:
+# for line in f:
+# if line.startswith('ATOM'):
+# clean_line = (line.rstrip()).split()
+# #check for alignment mistakes within data, a row with spacing alignment error has 11 length after splitted by whitespace
+# if len(clean_line) == 11:
+# #split the 2nd last column by the 4th index (this inference is according to PDB file formatting)
+# split = [clean_line[-2][:4], clean_line[-2][4:]]
+# clean_line[-2] = split[1]
+# clean_line.insert(-2, split[0])
+# #check if the chain identifier is misaligned
+# if len(clean_line[4])>1:
+# split = [clean_line[4][0], clean_line[4][1:]]
+# clean_line[4] = split[0]
+# clean_line.insert(5, split[1])
+# #check if coordinate data collumns are collided (most likely happens between x and y coor)
+# while len(clean_line[6])>=13:
+# split = [clean_line[6][:-8], clean_line[6][-8:]]
+# last_elem = clean_line.pop()
+# clean_line[-1] = last_elem
+# clean_line.insert(6, split[0])
+# clean_line[7] = split[1]
+# if len(clean_line[7])>=13:
+# split = [clean_line[7][:-8], clean_line[7][-8:]]
+# last_elem = clean_line.pop()
+# clean_line[-1] = last_elem
+# clean_line.insert(7, split[0])
+# clean_line[8] = split[1]
+# l.append(clean_line)
+# elif line.startswith('TER'):
+# clean_line = (line.rstrip()).split()
+# l.append(clean_line)
+# elif line.startswith('ENDMDL'):
+# break