Source Code for Module Bio.SCOP.Residues

 1  # Copyright 2000 by Jeffrey Chang.  All rights reserved. 
 2  # This code is part of the Biopython distribution and governed by its 
 3  # license.  Please see the LICENSE file that should have been included 
 4  # as part of this package. 
 5   
 6  # Gavin E. Crooks 2001-11-03 
 7  # Minor extensions, some bug fixes, and major changes to the interface 
 8   
 9  import re 
10   
11  """A collection of residues from a PDB structure.""" 
12   
13  _pdbid_re = re.compile(r"^(\w\w\w\w)(?:$|\s+|_)(.*)") 
14  _fragment_re = re.compile(r"\(?(\w:)?(-?\w*)-?(-?\w*)\)?(.*)") 
15   
16   
17 -class Residues(object): 
18      """A collection of residues from a PDB structure. 
19   
20      This class provides code to work with SCOP domain definitions. These 
21      are concisely expressed as one or more chain fragments. For example, 
22      "(1bba A:10-20,B:)" indicates residue 10 through 20 (inclusive) of 
23      chain A, and every residue of chain B in the pdb structure 1bba. The pdb 
24      id and brackets are optional. In addition "-" indicates every residue of 
25      a pbd structure with one unnamed chain. 
26   
27      Start and end residue ids consist of the residue sequence number and an 
28      optional single letter insertion code. e.g. "12", "-1", "1a", "1000" 
29   
30   
31      pdbid -- An optional PDB id, e.g. "1bba" 
32   
33      fragments -- A sequence of tuples (chainID, startResID, endResID) 
34   
35      """ 
36   
37 -    def __init__(self, str=None): 
38          self.pdbid = '' 
39          self.fragments = () 
40          if str is not None: 
41              self._parse(str) 
42   
43 -    def _parse(self, str): 
44          str = str.strip() 
45   
46          #Is there a pdbid at the front? e.g. 1bba A:1-100 
47          m = _pdbid_re.match(str) 
48          if m is not None: 
49              self.pdbid = m.group(1) 
50              str = m.group(2) # Everything else 
51   
52          if str=='' or str == '-' or str=='(-)':  # no fragments, whole sequence 
53              return 
54   
55          fragments = [] 
56          for l in str.split(","): 
57              m = _fragment_re.match(l) 
58              if m is None: 
59                  raise ValueError("I don't understand the format of %s" % l) 
60              chain, start, end, postfix = m.groups() 
61   
62              if postfix != "": 
63                  raise ValueError("I don't understand the format of %s" % l) 
64   
65              if chain: 
66                  if chain[-1] != ':': 
67                      raise ValueError("I don't understand the chain in %s" % l) 
68                  chain = chain[:-1]   # chop off the ':' 
69              else: 
70                  chain ="" 
71   
72              fragments.append((chain, start, end)) 
73          self.fragments = tuple(fragments) 
74   
75 -    def __str__(self): 
76          prefix ="" 
77          if self.pdbid: 
78              prefix =self.pdbid +' ' 
79   
80          if not self.fragments: 
81              return prefix+'-' 
82          strs = [] 
83          for chain, start, end in self.fragments: 
84              s = [] 
85              if chain: 
86                  s.append("%s:" % chain) 
87              if start: 
88                  s.append("%s-%s" % (start, end)) 
89              strs.append("".join(s)) 
90          return prefix+ ",".join(strs) 
91