add threeLetter to pdb header and atomic

prody/atomic/atomic.py

@@ -247,12 +247,20 @@ def getSequence(self, **kwargs):
         residues (e.g. water molecules) in the chain and **X** will be used for
         non-standard residue names."""
 
+        threeLetter = kwargs.get('threeLetter', False)
+
         get = AAMAP.get
         if hasattr(self, 'getResnames'):
-            seq = ''.join([get(res, 'X') for res in self.getResnames()])
+            if threeLetter:
+                seq = ' '.join(self.getResnames())
+            else:
+                seq = ''.join([get(res, 'X') for res in self.getResnames()])
         else:
             res = self.getResname()
-            seq = get(res, 'X')
+            if threeLetter:
+                seq = res
+            else:
+                seq = get(res, 'X')
 
         return seq
 

prody/atomic/chain.py

@@ -8,10 +8,14 @@
 
 __all__ = ['Chain']
 
-def getSequence(resnames):
+def getSequence(resnames, **kwargs):
     """Returns polypeptide sequence as from list of *resnames* (residue
     name abbreviations)."""
 
+    threeLetter = kwargs.get('threeLetter', False)
+    if threeLetter:
+        return ' '.join(resnames)
+
     get = AAMAP.get
     return ''.join([get(rn, 'X') for rn in resnames])
 
@@ -140,7 +144,7 @@ def getSequence(self, **kwargs):
         else:
             calpha = self.calpha
             if calpha:
-                seq = getSequence(calpha.getResnames())
+                seq = getSequence(calpha.getResnames(), **kwargs)
             else:
                 seq = ''
             self._seq = seq

prody/proteins/header.py

@@ -235,7 +235,7 @@ def cleanString(string, nows=False):
         return ' '.join(string.strip().split())
 
 
-def parsePDBHeader(pdb, *keys):
+def parsePDBHeader(pdb, *keys, **kwargs):
     """Returns header data dictionary for *pdb*.  This function is equivalent to
     ``parsePDB(pdb, header=True, model=0, meta=False)``, likewise *pdb* may be
     an identifier or a filename.
@@ -297,12 +297,12 @@ def parsePDBHeader(pdb, *keys):
             raise IOError('{0} is not a valid filename or a valid PDB '
                           'identifier.'.format(pdb))
     pdb = openFile(pdb, 'rt')
-    header, _ = getHeaderDict(pdb, *keys)
+    header, _ = getHeaderDict(pdb, *keys, **kwargs)
     pdb.close()
     return header
 
 
-def getHeaderDict(stream, *keys):
+def getHeaderDict(stream, *keys, **kwargs):
     """Returns header data in a dictionary.  *stream* may be a list of PDB lines
     or a stream."""
 
@@ -325,7 +325,10 @@ def getHeaderDict(stream, *keys):
         keys = list(keys)
         for k, key in enumerate(keys):
             if key in _PDB_HEADER_MAP:
-                value = _PDB_HEADER_MAP[key](lines)
+                if key == 'polymers':
+                    value = _PDB_HEADER_MAP[key](lines, **kwargs)
+                else:
+                    value = _PDB_HEADER_MAP[key](lines)
                 keys[k] = value
             else:
                 raise KeyError('{0} is not a valid header data identifier'
@@ -555,7 +558,7 @@ def _getReference(lines):
     return ref
 
 
-def _getPolymers(lines):
+def _getPolymers(lines, **kwargs):
     """Returns list of polymers (macromolecules)."""
 
     pdbid = lines['pdbid']
@@ -564,7 +567,14 @@ def _getPolymers(lines):
         ch = line[11]
         poly = polymers.get(ch, Polymer(ch))
         polymers[ch] = poly
-        poly.sequence += ''.join(getSequence(line[19:].split()))
+
+        threeLetter = kwargs.get('threeLetter', False)
+        if threeLetter:
+            if poly.sequence != '':
+                poly.sequence += ' '
+            poly.sequence += getSequence(line[19:].split(), **kwargs)
+        else:
+            poly.sequence += ''.join(getSequence(line[19:].split(), **kwargs))
 
     for i, line in lines['DBREF ']:
         i += 1