Added auto-generation of mol names if they are absent in sdf file. Mo…

…l order in output text file is the same as in input sdf file for single compounds. License years were updated.

canon.py

@@ -146,7 +146,9 @@ def GetSirmsType(bonds):
 
 def GetSirmsType2(mol, atoms):
     b = []
+    # atoms = set(atoms)
     for a in atoms:
+        # b.append(len(set(mol.bonds[a].keys()).intersection(atoms)))
         tmp = 0
         for a1 in mol.bonds[a].keys():
             if a1 in atoms:

files.py

@@ -5,7 +5,7 @@
 # Author:      Pavel Polishchuk
 #
 # Created:     06.06.2013
-# Copyright:   (c) Pavel Polishchuk 2013
+# Copyright:   (c) Pavel Polishchuk 2013-2015
 # Licence:     GPLv3
 #-------------------------------------------------------------------------------
 

mols.py

@@ -5,7 +5,7 @@
 # Author:      Pavel Polishchuk
 #
 # Created:     11.01.2013
-# Copyright:   (c) Pavel Polishchuk 2013
+# Copyright:   (c) Pavel Polishchuk 2013-2015
 # Licence:     GPLv3
 #-------------------------------------------------------------------------------
 

ppgfunctions.py

@@ -5,7 +5,7 @@
 # Author:      Pavel Polishchuk
 #
 # Created:     11.01.2013
-# Copyright:   (c) Pavel Polishchuk 2013
+# Copyright:   (c) Pavel Polishchuk 2013-2015
 # Licence:     GPLv3
 #-------------------------------------------------------------------------------
 

sdf.py

@@ -5,11 +5,15 @@
 # Author:      Pavel Polishchuk
 #
 # Created:     11.01.2013
-# Copyright:   (c) Pavel Polishchuk 2013
+# Copyright:   (c) Pavel Polishchuk 2013-2015
 # Licence:     GPLv3
 #-------------------------------------------------------------------------------
 
 
+import string
+import random
+from collections import OrderedDict
+
 from mols import Mol3 as Mol
 from files import ReadPropertyRange, RangedLetter
 
@@ -30,11 +34,16 @@ def ReadSDF(fname, opt_diff, fsetup, parse_stereo):
     OUTPUT: dict of molecules, where key is the title of the moleculae taken from the first line of mol-record
     """
 
-    def MolstrToMol(molstr, opt_diff, parse_stereo):
+    def MolstrToMol(molstr, opt_diff, parse_stereo, num_mol):
 
         mol = Mol()
         mol.stereo = parse_stereo
-        mol.title = molstr[0]
+
+        if molstr[0] == '':
+            mol.title = 'autogenerated_mol_id_' + str(num_mol)
+        else:
+            mol.title = molstr[0]
+
         natoms = int(molstr[3][0:3])
         nbonds = int(molstr[3][3:6])
 
@@ -117,14 +126,14 @@ def MolstrToMol(molstr, opt_diff, parse_stereo):
 
         return mol
 
-    mols = {}
+    mols = OrderedDict()
     molstr = []
-    f = open(fname)
-    for line in f:
-        if line.find("$$$$") < 0:
-            molstr.append(line.rstrip())
-        else:
-            m = MolstrToMol(molstr, opt_diff, parse_stereo)
-            mols[m.title] = m
-            molstr = []
+    with open(fname) as f:
+        for line in f:
+            if line.find("$$$$") < 0:
+                molstr.append(line.rstrip())
+            else:
+                m = MolstrToMol(molstr, opt_diff, parse_stereo, len(mols) + 1)
+                mols[m.title] = m
+                molstr = []
     return mols

sirms.py

@@ -8,7 +8,7 @@
 # Author:      Pavel Polishchuk
 #
 # Created:     01.01.2013
-# Copyright:   (c) Pavel Polishchuk 2013
+# Copyright:   (c) Pavel Polishchuk 2013-2015
 # Licence:     GPLv3
 # Python Version: 3.2
 #-------------------------------------------------------------------------------
@@ -18,6 +18,8 @@
 import time
 import files
 from itertools import combinations, chain, product
+from collections import OrderedDict
+
 from sdf import ReadSDF
 from ppgfunctions import *
 from canon import LoadSirmsDict, GetCanonNameByDict, GenCanonName, GetSirmsType2, GetSirmsType
@@ -37,10 +39,10 @@ def SaveSimplexes(fname, sirms, ndigits=5):
     f_out = open(fname, 'wt')
     # get sorted unique simplex names
     sirms_names = sorted(list(set(list(chain.from_iterable([list(s.keys()) for s in sirms.values()])))))
-    compound_names = sorted([k for k in sirms.keys()])
+    # compound_names = sorted([k for k in sirms.keys()])
     f_out.write("Compounds\t" + "\t".join(sirms_names) + "\n")
     s = "{:." + str(ndigits) + "f}"
-    for n in compound_names:
+    for n in sirms.keys():
         line = []
         for m in sirms_names:
             value = sirms[n].get(m, 0)
@@ -324,7 +326,7 @@ def CalcSingleCompSirmsMP(mol_list, sirms_dict, opt_diff, opt_types, opt_noH, nc
     """
     if opt_verbose:
         print(' Single compounds calculation '.center(79, '-'))
-    d = {}
+    d = OrderedDict()
     if abs(ncores) > 1:
         p = Pool(processes=min(len(mol_list), abs(ncores)))
         res = [p.apply_async(CalcSingleCompSirms, [mol, sirms_dict, opt_diff, opt_types, opt_noH, opt_verbose, frags])