Merge pull request #1793 from dkoes/master

More robust handling of altloc
prody · Nov 15, 2023 · c55c8a2 · c55c8a2
2 parents 92435c1 + 41d3d8a
commit c55c8a2
Show file tree

Hide file tree

Showing 2 changed files with 18 additions and 15 deletions.
diff --git a/prody/proteins/mmtffile.py b/prody/proteins/mmtffile.py
@@ -41,9 +41,11 @@
 
     :arg altloc: if a location indicator is passed, such as ``'A'`` or ``'B'``,
          only indicated alternate locations will be parsed as the single
-         coordinate set of the AtomGroup, if *altloc* is set **True** all
+         coordinate set of the AtomGroup. If *altloc* is ``'all'`` then all
          alternate locations will be parsed and each will be appended as a
-         distinct coordinate set, default is ``"A"``
+         distinct coordinate set, default is ``"A"``.  In the rare instance
+         where all atoms have a location indicator specified and this does not
+         match altloc, the first location indicator in the file is used.
     :type altloc: str
     """
 
@@ -143,7 +145,7 @@ def _parseMMTF(mmtf_struc, **kwargs):
     chain = kwargs.get('chain')
     header = kwargs.get('header', False)
     get_bonds = kwargs.get('bonds',False) 
-    altloc_sel = kwargs.get('altloc', 'A')
+    altloc_sel = kwargs.get('altloc', None)
 
     assert isinstance(header, bool), 'header must be a boolean'
 
@@ -221,7 +223,7 @@ def _bio_transform(dec):
         ret[t['name']] = L
     return ret
 
-def set_info(atomgroup, mmtf_data,get_bonds=False,altloc_sel='A'):
+def set_info(atomgroup, mmtf_data,get_bonds=False,altloc_sel=None):
 
     mmtfHETATMtypes = set([
         "D-SACCHARIDE",
@@ -322,10 +324,11 @@ def set_info(atomgroup, mmtf_data,get_bonds=False,altloc_sel='A'):
     mask = np.full(asize, True, dtype=bool)
     if altloc_sel != 'all':
         #mask out any unwanted alternative locations
-        mask = (altlocs == '') | (altlocs == altloc_sel)
-
-    if np.all(mask == False):
-        mask = (altlocs == '') | (altlocs == altlocs[0])
+        default_altloc = altloc_sel if altloc_sel != None else 'A'
+        mask = (altlocs == '') | (altlocs == default_altloc)
+        if np.all(mask == False) and altloc_sel == None and len(altlocs):
+            #nothing selected, use first altloc; 6uwi
+            mask = altlocs == altlocs[0]            
 
     atomgroup.setCoords(coords[:,mask])
     atomgroup.setNames(atom_names[mask])

diff --git a/prody/proteins/pdbfile.py b/prody/proteins/pdbfile.py
@@ -1400,9 +1400,9 @@ def writePDBStream(stream, atoms, csets=None, **kwargs):
                 L = helix_resnums[-1] - helix_resnums[0] + 1
 
                 stream.write(HELIXLINE.format(serNum=i, helixID=helix_secids[0], 
-                            initResName=helix_resnames[0][:3], initChainID=helix_chainids[0], 
+                            initResName=helix_resnames[0][:3], initChainID=helix_chainids[0][:1], 
                             initSeqNum=helix_resnums[0], initICode=helix_icodes[0],
-                            endResName=helix_resnames[-1][:3], endChainID=helix_chainids[-1], 
+                            endResName=helix_resnames[-1][:3], endChainID=helix_chainids[-1][:1], 
                             endSeqNum=helix_resnums[-1], endICode=helix_icodes[-1],
                             helixClass=helix_secclasses[0], length=L))
 
@@ -1426,9 +1426,9 @@ def writePDBStream(stream, atoms, csets=None, **kwargs):
                 strand_icodes = icodes[torf_strand]
 
                 stream.write(SHEETLINE.format(strand=i, sheetID=sheet_id, numStrands=numStrands,
-                            initResName=strand_resnames[0][:3], initChainID=strand_chainids[0], 
+                            initResName=strand_resnames[0][:3], initChainID=strand_chainids[0][:1], 
                             initSeqNum=strand_resnums[0], initICode=strand_icodes[0],
-                            endResName=strand_resnames[-1][:3], endChainID=strand_chainids[-1], 
+                            endResName=strand_resnames[-1][:3], endChainID=strand_chainids[-1][:1], 
                             endSeqNum=strand_resnums[-1], endICode=strand_icodes[-1],
                             sense=strand_secclasses[0]))
         pass
@@ -1571,7 +1571,7 @@ def writePDBStream(stream, atoms, csets=None, **kwargs):
 
                 write(anisouline % ("ANISOU", serial,
                                     atomnames[i], altlocs[i],
-                                    resname, chainids[i], resnum,
+                                    resname, chainids[i][:1], resnum,
                                     icodes[i],
                                     anisou[0], anisou[1], anisou[2],
                                     anisou[3], anisou[4], anisou[5],
@@ -1586,7 +1586,7 @@ def writePDBStream(stream, atoms, csets=None, **kwargs):
 
                     false_pdbline = pdbline % ("TER   ", serial,
                                                "", "",
-                                               resname, chainids[i], resnum,
+                                               resname, chainids[i][:1], resnum,
                                                icodes[i],
                                                xyz[0], xyz[1], xyz[2],
                                                occupancies[i], bfactors[i],
@@ -1602,7 +1602,7 @@ def writePDBStream(stream, atoms, csets=None, **kwargs):
 
                     false_pdbline = pdbline % ("TER   ", serial,
                                                "", "",
-                                               resname, chainids[i], resnum,
+                                               resname, chainids[i][:1], resnum,
                                                icodes[i],
                                                xyz[0], xyz[1], xyz[2],
                                                occupancies[i], bfactors[i],