SmilesCGR (#5)

CGR to SMILES

CGRtools/algorithms/strings.py

@@ -1,6 +1,7 @@
 # -*- coding: utf-8 -*-
 #
 #  Copyright 2017-2019 Ramil Nugmanov <stsouko@live.ru>
+#  Copyright 2019 Timur Gimadiev <timur.gimadiev@gmail.com>
 #  This file is part of CGRtools.
 #
 #  CGRtools is free software; you can redistribute it and/or modify
@@ -19,7 +20,7 @@
 from collections import defaultdict
 from hashlib import sha512
 from itertools import count
-from ..attributes import Atom, DynAtom, QueryAtom, DynQueryAtom
+from ..attributes import Atom, DynAtom, QueryAtom, DynQueryAtom, DynBond
 from ..cache import cached_method, cached_args_method
 
 
@@ -28,6 +29,24 @@
 charge_str = {-3: '-3', -2: '-2', -1: '-', 0: '0', 1: '+', 2: '+2', 3: '+3'}
 order_str = {1: '-', 2: '=', 3: '#', 4: ':', 5: '~', None: '.'}
 stereo_str = {1: '@', -1: '@@'}
+dyn_order_str = {(None, 1): "[.>-]", (None, 2): "[.>=]", (None, 3): "[.>#]", (None, 4): "[.>:]", (None, 5): "[.>~]",
+                 (1, None): "[->.]", (1, 1): "", (1, 2): "[->=]", (1, 3): "[->#]", (1, 4): "[->:]", (1, 5): "[->~]",
+                 (2, None): "[=>.]", (2, 1): "[=>-]", (2, 2): "=", (2, 3): "[=>#]", (2, 4): "[=>:]", (2, 5): "[=>~]",
+                 (3, None): "[#>.]", (3, 1): "[#>-]", (3, 2): "[#>=]", (3, 3): "#", (3, 4): "[#>:]", (3, 5): "[#>~]",
+                 (4, None): "[:>.]", (4, 1): "[:>-]", (4, 2): "[:>=]", (4, 3): "[:>#]", (4, 4): ":", (4, 5): "[:>~]",
+                 (5, None): "[~>.]", (5, 1): "[~>-]", (5, 2): "[~>=]", (5, 3): "[~>#]", (5, 4): "[~>:]", (5, 5): "[~]"}
+dyn_charge_str = {(-3, -3): "-3", (-3, -2): "-3>-2", (-3, -1): "-3>-", (-3, 0): "-3>0", (-3, 1): "-3>+",
+                  (-3, 2): "-3>+2", (-3, 3): "-3>3", (-2, -3): "-2>-3", (-2, -2): "-2", (-2, -1): "-2>-",
+                  (-2, 0): "-2>0", (-2, 1): "-2>+", (-2, 2): "-2>+2", (-2, 3): "-2>+3", (-1, -3): "->-3",
+                  (-1, -2): "->-2", (-1, -1): "-", (-1, 0): "->0", (-1, 1): "->+", (-1, 2): "->+2", (-1, 3): "->+3",
+                  (0, -3): "0>-3", (0, -2): "0>-2", (0, -1): "0>-", (0, 0): "", (0, 1): "0>+", (0, 2): "0>+2",
+                  (0, 3): "0>+3", (1, -3): "+>-3", (1, -2): "+>-2", (1, -1): "+>-", (1, 0): "+>0", (1, 1): "+",
+                  (1, 2): "+>+2", (1, 3): "+>+3", (2, -3): "+2>-3", (2, -2): "+2>-2", (2, -1): "+2>-", (2, 0): "+2>0",
+                  (2, 1): "+2>+", (2, 2): "+2", (2, 3): "+2>+3", (3, -3): "+3>-3", (3, -2): "+3>-2", (3, -1): "+3>-",
+                  (3, 0): "+3>0", (3, 1): "+3>+", (3, 2): "+3>+2", (3, 3): "+3"}
+dyn_multiplicity_str = {(1, 1): "*", (1, 2): "*>*2", (1, 3): "*>*3", (1, None): "*>n", (2, 1): "*2>*", (2, 2): "*2",
+                        (2, 3): "*2>*3", (2, None): "*2>n", (3, 1): "*3>*", (3, 2): "*3>*2", (3, 3): "*3",
+                        (3, None): "*3>n", (None, 1): "n>1", (None, 2): "n>2", (None, 3): "n>3", (None, None): ""}
 
 
 class HashableSmiles:
@@ -224,9 +243,13 @@ def __format__(self, format_spec):
         """
         format CGR as SMIRKS string
 
-        :param format_spec: if == 'n' add neighbors count of atoms. don't forget to call reset query marks before.
-        if == 'h' add hybridizations of atoms. if 'nh' or 'hn' add both.
+        :param format_spec: if 's' in fromat_spec only representation of CGR as smiles will be shown.
+        No hybridization and neighbors count will be used. High priority option.
+        if == 'n' add neighbors count of atoms. don't forget to call reset query marks before.
+        if == 'h' add hybridization of atoms. if 'nh' or 'hn' add both.
         """
+        if format_spec and 's' in format_spec:
+            return self._format_string_cgr(self.atoms_order.__getitem__)
         if not format_spec:
             neighbors = False
             hybridization = False
@@ -319,6 +342,37 @@ def __format_atom(atom, neighbors, hybridization):
 
         return ''.join(smi), ''.join(p_smi)
 
+    def _format_string_cgr(self, order):
+        smiles = []
+        for x in self._flatten(order):
+            if isinstance(x, str):
+                smiles.append(x)
+            elif isinstance(x, list):
+                smiles.append(self.__format_atom_cgr(x[0]))
+                for b, c in sorted(x[1:], key=lambda e: int(e[1])):
+                    smiles.append(dyn_order_str[(b.order, b.p_order)])
+                    smiles.append(str(c))
+            elif isinstance(x, DynAtom):
+                smiles.append(self.__format_atom_cgr(x))
+            else:
+                smiles.append(dyn_order_str[(x.order, x.p_order)])
+        return "".join(smiles)
+
+    @staticmethod
+    def __format_atom_cgr(atom):
+        if atom.isotope != atom.common_isotope:
+            smi = [str(atom.isotope), atom.element]
+        else:
+            smi = [atom.element]
+        if atom.charge or atom.p_charge:
+            smi.append(dyn_charge_str[(atom.charge, atom.p_charge)])
+        if atom.multiplicity or atom.p_multiplicity:
+            smi.append(dyn_multiplicity_str[(atom.multiplicity, atom.p_multiplicity)])
+        if len(smi) != 1 or atom.element not in {'C', 'N', 'O', 'P', 'S', 'F', 'Cl', 'Br', 'I', 'B'}:
+            smi.insert(0, '[')
+            smi.append(']')
+        return ''.join(smi)
+
 
 class SmilesQuery(StringCommon):
     @cached_method