openff-toolkit 0.18.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (231) hide show
  1. devtools/scripts/build_cookiecutter_json.py +22 -0
  2. docs/conf.py +296 -0
  3. docs/conftest.py +23 -0
  4. examples/conformer_energies/conformer_energies.py +143 -0
  5. examples/deprecated/SMIRNOFF_comparison/compare_molecule_energies.py +48 -0
  6. examples/deprecated/SMIRNOFF_comparison/compare_set_energies.py +58 -0
  7. examples/deprecated/liquid_box/create_mol2_pdb/create_mol2_pdb.py +193 -0
  8. examples/deprecated/liquid_box/openff_simulation.py +72 -0
  9. examples/deprecated/mixedFF_structure/generate_mixedFF_complex.py +56 -0
  10. examples/deprecated/testing/test_impropers/tleap_tools.py +120 -0
  11. examples/examples_helper.py +61 -0
  12. openff/toolkit/__init__.py +101 -0
  13. openff/toolkit/_tests/__init__.py +0 -0
  14. openff/toolkit/_tests/_stale_tests.py +146 -0
  15. openff/toolkit/_tests/conftest.py +108 -0
  16. openff/toolkit/_tests/create_molecules.py +494 -0
  17. openff/toolkit/_tests/mocking.py +145 -0
  18. openff/toolkit/_tests/molecule/__init__.py +1 -0
  19. openff/toolkit/_tests/molecule/test_state_enumeration.py +302 -0
  20. openff/toolkit/_tests/test_energies.py +136 -0
  21. openff/toolkit/_tests/test_examples.py +109 -0
  22. openff/toolkit/_tests/test_forcefield.py +3864 -0
  23. openff/toolkit/_tests/test_interchange.py +19 -0
  24. openff/toolkit/_tests/test_io.py +19 -0
  25. openff/toolkit/_tests/test_links.py +73 -0
  26. openff/toolkit/_tests/test_mm_molecule.py +404 -0
  27. openff/toolkit/_tests/test_molecule.py +4246 -0
  28. openff/toolkit/_tests/test_nagl.py +169 -0
  29. openff/toolkit/_tests/test_parameter_plugins.py +89 -0
  30. openff/toolkit/_tests/test_parameters.py +2898 -0
  31. openff/toolkit/_tests/test_toolkit_io.py +1088 -0
  32. openff/toolkit/_tests/test_toolkits.py +4418 -0
  33. openff/toolkit/_tests/test_topology.py +2485 -0
  34. openff/toolkit/_tests/test_utils.py +101 -0
  35. openff/toolkit/_tests/test_utils_callback.py +178 -0
  36. openff/toolkit/_tests/test_utils_collections.py +263 -0
  37. openff/toolkit/_tests/test_utils_serialization.py +168 -0
  38. openff/toolkit/_tests/utils.py +1747 -0
  39. openff/toolkit/data/README.md +8 -0
  40. openff/toolkit/data/molecules/AlkEthOH_test_filt1_ff.mol2 +2026 -0
  41. openff/toolkit/data/molecules/AlkEthOH_test_filt1_tripos.mol2 +2026 -0
  42. openff/toolkit/data/molecules/AlkEthOH_tripos.tar.gz +0 -0
  43. openff/toolkit/data/molecules/CID20742535_anion.sdf +50 -0
  44. openff/toolkit/data/molecules/CID20742535_neutral.sdf +51 -0
  45. openff/toolkit/data/molecules/FreeSolv.tar.gz +0 -0
  46. openff/toolkit/data/molecules/MiniDrugBank.sdf +33988 -0
  47. openff/toolkit/data/molecules/MiniDrugBank_tripos.mol2 +35462 -0
  48. openff/toolkit/data/molecules/PT2385.sdf +90 -0
  49. openff/toolkit/data/molecules/QL8.sdf +401 -0
  50. openff/toolkit/data/molecules/README.md +21 -0
  51. openff/toolkit/data/molecules/benzene.crd +8 -0
  52. openff/toolkit/data/molecules/benzene.mol2 +34 -0
  53. openff/toolkit/data/molecules/benzene.top +166 -0
  54. openff/toolkit/data/molecules/butane_multi.sdf +231 -0
  55. openff/toolkit/data/molecules/cyclohexane.mol2 +44 -0
  56. openff/toolkit/data/molecules/ethanol.mol2 +25 -0
  57. openff/toolkit/data/molecules/ethanol.sdf +23 -0
  58. openff/toolkit/data/molecules/ethanol_partial_charges.sdf +26 -0
  59. openff/toolkit/data/molecules/ethanol_reordered.mol2 +25 -0
  60. openff/toolkit/data/molecules/ethanol_reordered.sdf +23 -0
  61. openff/toolkit/data/molecules/ethene_rdkit.sdf +17 -0
  62. openff/toolkit/data/molecules/laromustine_ff.mol2 +71 -0
  63. openff/toolkit/data/molecules/laromustine_tripos.mol2 +71 -0
  64. openff/toolkit/data/molecules/methane_multiconformer.sdf +32 -0
  65. openff/toolkit/data/molecules/methane_multiconformer_properties.sdf +45 -0
  66. openff/toolkit/data/molecules/nh4.pdb +7 -0
  67. openff/toolkit/data/molecules/po4_phenylphosphate.pdb +46 -0
  68. openff/toolkit/data/molecules/ruxolitinib_conformers.sdf +910 -0
  69. openff/toolkit/data/molecules/toluene.mol2 +38 -0
  70. openff/toolkit/data/molecules/toluene.mol2.gz +0 -0
  71. openff/toolkit/data/molecules/toluene.pdb +30 -0
  72. openff/toolkit/data/molecules/toluene.sdf +36 -0
  73. openff/toolkit/data/molecules/toluene_charged.mol2 +38 -0
  74. openff/toolkit/data/molecules/z_3_hydroxy_propenal.sdf +23 -0
  75. openff/toolkit/data/proteins/5tbm_complex_solv.pdb +1928 -0
  76. openff/toolkit/data/proteins/5tbm_complex_solv_box.pdb +19563 -0
  77. openff/toolkit/data/proteins/CTerminal_ALA.pdb +20 -0
  78. openff/toolkit/data/proteins/CTerminal_ALA.sdf +43 -0
  79. openff/toolkit/data/proteins/CTerminal_ALA_ALA.pdb +30 -0
  80. openff/toolkit/data/proteins/CTerminal_ALA_ALA_misnamedH.pdb +30 -0
  81. openff/toolkit/data/proteins/CTerminal_ARG.pdb +34 -0
  82. openff/toolkit/data/proteins/CTerminal_TRP.pdb +34 -0
  83. openff/toolkit/data/proteins/MainChain_ALA.pdb +25 -0
  84. openff/toolkit/data/proteins/MainChain_ALA.sdf +52 -0
  85. openff/toolkit/data/proteins/MainChain_ALA_ALA.pdb +35 -0
  86. openff/toolkit/data/proteins/MainChain_ALA_ALA.sdf +69 -0
  87. openff/toolkit/data/proteins/MainChain_ALA_ALA_icodes.pdb +35 -0
  88. openff/toolkit/data/proteins/MainChain_ALA_ALA_no_hydrogens.pdb +17 -0
  89. openff/toolkit/data/proteins/MainChain_ARG.pdb +39 -0
  90. openff/toolkit/data/proteins/MainChain_ARG.sdf +81 -0
  91. openff/toolkit/data/proteins/MainChain_CYM.pdb +25 -0
  92. openff/toolkit/data/proteins/MainChain_CYS.pdb +26 -0
  93. openff/toolkit/data/proteins/MainChain_CYX.pdb +48 -0
  94. openff/toolkit/data/proteins/MainChain_CYX.sdf +96 -0
  95. openff/toolkit/data/proteins/MainChain_GLH.sdf +64 -0
  96. openff/toolkit/data/proteins/MainChain_GLU.sdf +63 -0
  97. openff/toolkit/data/proteins/MainChain_HID.pdb +32 -0
  98. openff/toolkit/data/proteins/MainChain_HIE.pdb +32 -0
  99. openff/toolkit/data/proteins/MainChain_HIE.sdf +67 -0
  100. openff/toolkit/data/proteins/MainChain_HIP.pdb +33 -0
  101. openff/toolkit/data/proteins/MainChain_HIP.sdf +70 -0
  102. openff/toolkit/data/proteins/MainChain_PRO.pdb +29 -0
  103. openff/toolkit/data/proteins/MainChain_TRP.pdb +39 -0
  104. openff/toolkit/data/proteins/NTerminal_ALA.pdb +21 -0
  105. openff/toolkit/data/proteins/NTerminal_ALA.sdf +45 -0
  106. openff/toolkit/data/proteins/NTerminal_ALA_ALA.pdb +31 -0
  107. openff/toolkit/data/proteins/NTerminal_ARG.pdb +35 -0
  108. openff/toolkit/data/proteins/NTerminal_TRP.pdb +35 -0
  109. openff/toolkit/data/proteins/T4-protein-unprocessed-4w51.pdb +1892 -0
  110. openff/toolkit/data/proteins/T4-protein.mol2 +5461 -0
  111. openff/toolkit/data/proteins/T4-protein.pdb +2637 -0
  112. openff/toolkit/data/proteins/T4-protein.sdf +5318 -0
  113. openff/toolkit/data/proteins/T4_protein_waters.pdb +2965 -0
  114. openff/toolkit/data/proteins/TwoMol_SER_CYS.pdb +50 -0
  115. openff/toolkit/data/proteins/aa_residues_substructures_explicit_bond_orders_with_caps.json +6435 -0
  116. openff/toolkit/data/proteins/aa_residues_substructures_explicit_bond_orders_with_caps_explicit_connectivity.json +6675 -0
  117. openff/toolkit/data/proteins/aa_residues_substructures_with_caps.json +6297 -0
  118. openff/toolkit/data/proteins/ace-ZZZ-gly-nme.pdb +78 -0
  119. openff/toolkit/data/proteins/ace-ZZZ-gly-nme.sdf +98 -0
  120. openff/toolkit/data/proteins/ace-a10-nme.sdf +229 -0
  121. openff/toolkit/data/proteins/ace-ala-nh2.pdb +21 -0
  122. openff/toolkit/data/proteins/fluoresceine_dyed_helix_capped.pdb +338 -0
  123. openff/toolkit/data/proteins/neutral_arginine.pdb +31 -0
  124. openff/toolkit/data/proteins/split_chain.pdb +74 -0
  125. openff/toolkit/data/proteins/split_chain_reordered.pdb +74 -0
  126. openff/toolkit/data/reference_energies/README.md +6 -0
  127. openff/toolkit/data/reference_energies/reference_0.8.0.json +1 -0
  128. openff/toolkit/data/reference_energies/reference_0.8.0.json.txt +180 -0
  129. openff/toolkit/data/reference_energies/reference_after_1007.json +1 -0
  130. openff/toolkit/data/reference_energies/reference_after_1007.json.txt +350 -0
  131. openff/toolkit/data/reference_energies/reference_after_802.json +1 -0
  132. openff/toolkit/data/reference_energies/reference_after_802.json.txt +291 -0
  133. openff/toolkit/data/systems/README.md +3 -0
  134. openff/toolkit/data/systems/amber/cyclohexane_ethanol_0.4_0.6.inpcrd +1511 -0
  135. openff/toolkit/data/systems/amber/cyclohexane_ethanol_0.4_0.6.prmtop +13367 -0
  136. openff/toolkit/data/systems/monomers/butanol.mol2 +38 -0
  137. openff/toolkit/data/systems/monomers/butanol.sdf +88 -0
  138. openff/toolkit/data/systems/monomers/cyclohexane.mol2 +45 -0
  139. openff/toolkit/data/systems/monomers/cyclohexane.sdf +105 -0
  140. openff/toolkit/data/systems/monomers/ethanol.mol2 +26 -0
  141. openff/toolkit/data/systems/monomers/ethanol.sdf +58 -0
  142. openff/toolkit/data/systems/monomers/methane.mol2 +18 -0
  143. openff/toolkit/data/systems/monomers/methane.sdf +38 -0
  144. openff/toolkit/data/systems/monomers/propane.mol2 +30 -0
  145. openff/toolkit/data/systems/monomers/propane.sdf +68 -0
  146. openff/toolkit/data/systems/monomers/tip3p_water.mol2 +14 -0
  147. openff/toolkit/data/systems/monomers/water.mol2 +14 -0
  148. openff/toolkit/data/systems/monomers/water.sdf +28 -0
  149. openff/toolkit/data/systems/packmol_boxes/cyclohexane_ethanol_0.4_0.6.pdb +6272 -0
  150. openff/toolkit/data/systems/packmol_boxes/cyclohexane_water.pdb +5524 -0
  151. openff/toolkit/data/systems/packmol_boxes/ethanol_water.pdb +5174 -0
  152. openff/toolkit/data/systems/packmol_boxes/propane_methane_butanol_0.2_0.3_0.5.pdb +7959 -0
  153. openff/toolkit/data/systems/test_systems/1_cyclohexane_1_ethanol.pdb +61 -0
  154. openff/toolkit/data/systems/test_systems/1_ethanol.pdb +24 -0
  155. openff/toolkit/data/systems/test_systems/1_ethanol_no_conect.pdb +15 -0
  156. openff/toolkit/data/systems/test_systems/1_ethanol_reordered.pdb +24 -0
  157. openff/toolkit/data/systems/test_systems/PE.pdb +67 -0
  158. openff/toolkit/data/systems/test_systems/README.md +3 -0
  159. openff/toolkit/data/systems/test_systems/T4_lysozyme_water_ions.pdb +29240 -0
  160. openff/toolkit/data/test_forcefields/Frosst_AlkEthOH.offxml +61 -0
  161. openff/toolkit/data/test_forcefields/Frosst_AlkEthOH_GBSA.offxml +78 -0
  162. openff/toolkit/data/test_forcefields/Frosst_AlkEthOH_MDL.offxml +62 -0
  163. openff/toolkit/data/test_forcefields/Frosst_AlkEthOH_parmAtFrosst.offxml +64 -0
  164. openff/toolkit/data/test_forcefields/GBSA_HCT-1.0.offxml +21 -0
  165. openff/toolkit/data/test_forcefields/GBSA_OBC1-1.0.offxml +18 -0
  166. openff/toolkit/data/test_forcefields/GBSA_OBC2-1.0.offxml +18 -0
  167. openff/toolkit/data/test_forcefields/README.md +23 -0
  168. openff/toolkit/data/test_forcefields/ammonia_minimal.offxml +27 -0
  169. openff/toolkit/data/test_forcefields/benzene_minimal.offxml +29 -0
  170. openff/toolkit/data/test_forcefields/chargeincrement-test.offxml +16 -0
  171. openff/toolkit/data/test_forcefields/frcmod.Frosst_AlkEthOH_withIDs +85 -0
  172. openff/toolkit/data/test_forcefields/ion_charges.offxml +18 -0
  173. openff/toolkit/data/test_forcefields/mangled.offxml +9 -0
  174. openff/toolkit/data/test_forcefields/old/README.md +9 -0
  175. openff/toolkit/data/test_forcefields/old/hbonds.offxml +11 -0
  176. openff/toolkit/data/test_forcefields/old/test_ff_0_0_2_spec_0_1.offxml +332 -0
  177. openff/toolkit/data/test_forcefields/old/test_ff_0_0_2_spec_0_2.offxml +338 -0
  178. openff/toolkit/data/test_forcefields/old/test_ff_0_0_2_spec_0_3.offxml +329 -0
  179. openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_fixed_spec_0_1.offxml +342 -0
  180. openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_fixed_spec_0_2.offxml +348 -0
  181. openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_fixed_spec_0_3.offxml +337 -0
  182. openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_spec_0_1.offxml +340 -0
  183. openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_spec_0_2.offxml +346 -0
  184. openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_spec_0_3.offxml +337 -0
  185. openff/toolkit/data/test_forcefields/smirff99Frosst_reference_0_1_spec.offxml +349 -0
  186. openff/toolkit/data/test_forcefields/smirnoff99Frosst_experimental.offxml +343 -0
  187. openff/toolkit/data/test_forcefields/smirnoff99Frosst_reference_0_1_spec.offxml +349 -0
  188. openff/toolkit/data/test_forcefields/smirnoff99Frosst_reference_0_2_spec.offxml +356 -0
  189. openff/toolkit/data/test_forcefields/test_forcefield.offxml +346 -0
  190. openff/toolkit/data/test_forcefields/tip3p.offxml +22 -0
  191. openff/toolkit/data/test_forcefields/unsupported_smirnoff_version.offxml +9 -0
  192. openff/toolkit/topology/__init__.py +43 -0
  193. openff/toolkit/topology/_mm_molecule.py +663 -0
  194. openff/toolkit/topology/molecule.py +6102 -0
  195. openff/toolkit/topology/topology.py +2555 -0
  196. openff/toolkit/typing/__init__.py +1 -0
  197. openff/toolkit/typing/engines/__init__.py +1 -0
  198. openff/toolkit/typing/engines/smirnoff/__init__.py +31 -0
  199. openff/toolkit/typing/engines/smirnoff/forcefield.py +1440 -0
  200. openff/toolkit/typing/engines/smirnoff/io.py +234 -0
  201. openff/toolkit/typing/engines/smirnoff/parameters.py +3839 -0
  202. openff/toolkit/typing/engines/smirnoff/plugins.py +91 -0
  203. openff/toolkit/utils/__init__.py +57 -0
  204. openff/toolkit/utils/_viz.py +104 -0
  205. openff/toolkit/utils/ambertools_wrapper.py +507 -0
  206. openff/toolkit/utils/base_wrapper.py +268 -0
  207. openff/toolkit/utils/builtin_wrapper.py +136 -0
  208. openff/toolkit/utils/callback.py +187 -0
  209. openff/toolkit/utils/collections.py +247 -0
  210. openff/toolkit/utils/constants.py +18 -0
  211. openff/toolkit/utils/exceptions.py +766 -0
  212. openff/toolkit/utils/nagl_wrapper.py +164 -0
  213. openff/toolkit/utils/openeye_wrapper.py +2750 -0
  214. openff/toolkit/utils/rdkit_wrapper.py +3302 -0
  215. openff/toolkit/utils/serialization.py +466 -0
  216. openff/toolkit/utils/toolkit_registry.py +509 -0
  217. openff/toolkit/utils/toolkits.py +217 -0
  218. openff/toolkit/utils/utils.py +805 -0
  219. openff_toolkit-0.18.0.dist-info/METADATA +109 -0
  220. openff_toolkit-0.18.0.dist-info/RECORD +231 -0
  221. openff_toolkit-0.18.0.dist-info/WHEEL +5 -0
  222. openff_toolkit-0.18.0.dist-info/licenses/LICENSE +21 -0
  223. openff_toolkit-0.18.0.dist-info/top_level.txt +5 -0
  224. utilities/deprecated/convert_frosst/convert_frcmod_0.1.py +251 -0
  225. utilities/deprecated/convert_frosst/convert_frcmod_0.2.py +249 -0
  226. utilities/deprecated/convert_frosst/convert_frcmod_0.3.py +249 -0
  227. utilities/make_substructure_dict/_cif_to_substructure_dict.py +955 -0
  228. utilities/make_substructure_dict/_make_chemical_substructures.py +46 -0
  229. utilities/make_substructure_dict/_make_metadata_assignment_substructures.py +35 -0
  230. utilities/test_plugins/custom_plugins/handler_plugins.py +48 -0
  231. utilities/test_plugins/setup.py +19 -0
@@ -0,0 +1,663 @@
1
+ """
2
+ TypedMolecule TODOs
3
+ * Testing
4
+ * Detemine whether atomic numbers are required, or whether a TypedMol could have a mix of
5
+ TypedAtom and TypedParticles, where the latter doesn't need atomic nubmers
6
+ * Determine whether typedmols should have isomorphism operations
7
+ * Should be able to go to hill formula (?), networkx, openmm
8
+ * Topology serialization will have trouble here - Won't know whether it's trying to
9
+ deserialize a Molecule or a TypedMolecule.
10
+
11
+ """
12
+
13
+ import functools
14
+ from collections.abc import Generator, Iterable
15
+ from typing import TYPE_CHECKING, NoReturn, Union
16
+
17
+ from openff.units.elements import MASSES, SYMBOLS
18
+
19
+ from openff.toolkit import unit
20
+ from openff.toolkit.topology.molecule import (
21
+ AtomMetadataDict,
22
+ HierarchyElement,
23
+ HierarchyScheme,
24
+ Molecule,
25
+ _atom_nums_to_hill_formula,
26
+ _has_unique_atom_names,
27
+ )
28
+ from openff.toolkit.utils.exceptions import UnsupportedMoleculeConversionError
29
+ from openff.toolkit.utils.utils import deserialize_numpy, serialize_numpy
30
+
31
+ if TYPE_CHECKING:
32
+ import networkx as nx
33
+
34
+ from openff.toolkit import Quantity, Topology
35
+ from openff.toolkit.topology.molecule import FrozenMolecule
36
+
37
+
38
+ class _SimpleMolecule:
39
+ def __init__(self):
40
+ self.atoms = []
41
+ self.bonds = []
42
+ self._conformers = None
43
+ self._hierarchy_schemes = dict()
44
+
45
+ def add_atom(self, atomic_number: int, **kwargs):
46
+ atom = _SimpleAtom(atomic_number, self, **kwargs)
47
+ self.atoms.append(atom)
48
+
49
+ def add_bond(self, atom1, atom2, **kwargs):
50
+ if isinstance(atom1, int) and isinstance(atom2, int):
51
+ atom1_atom = self.atoms[atom1]
52
+ atom2_atom = self.atoms[atom2]
53
+ elif isinstance(atom1, _SimpleAtom) and isinstance(atom2, _SimpleAtom):
54
+ atom1_atom = atom1
55
+ atom2_atom = atom2
56
+ else:
57
+ raise ValueError(
58
+ "Invalid inputs to molecule._add_bond. Expected ints or Atoms. "
59
+ f"Received {atom1} (type {type(atom1)}) and {atom2} (type {type(atom2)}) "
60
+ )
61
+ bond = _SimpleBond(atom1_atom, atom2_atom, **kwargs)
62
+ self.bonds.append(bond)
63
+
64
+ @property
65
+ def conformers(self) -> list["Quantity"] | None:
66
+ return self._conformers
67
+
68
+ def add_conformer(self, conformer):
69
+ if self._conformers is None:
70
+ self._conformers = list()
71
+ self._conformers.append(conformer)
72
+
73
+ @property
74
+ def n_atoms(self) -> int:
75
+ return len(self.atoms)
76
+
77
+ @property
78
+ def n_bonds(self) -> int:
79
+ return len(self.bonds)
80
+
81
+ @property
82
+ def n_conformers(self) -> int:
83
+ return 0 if self._conformers is None else len(self._conformers)
84
+
85
+ def atom(self, index: int) -> "_SimpleAtom":
86
+ return self.atoms[index]
87
+
88
+ def atom_index(self, atom) -> int:
89
+ return self.atoms.index(atom)
90
+
91
+ def bond(self, index: int) -> "_SimpleBond":
92
+ return self.bonds[index]
93
+
94
+ def get_bond_between(self, atom1_index, atom2_index):
95
+ atom1 = self.atom(atom1_index)
96
+ atom2 = self.atom(atom2_index)
97
+ for bond in atom1.bonds:
98
+ for atom in bond.atoms:
99
+ if atom is atom2:
100
+ return bond
101
+
102
+ @property
103
+ def angles(
104
+ self,
105
+ ) -> Generator[
106
+ tuple[
107
+ "_SimpleAtom",
108
+ "_SimpleAtom",
109
+ "_SimpleAtom",
110
+ ],
111
+ None,
112
+ None,
113
+ ]:
114
+ for atom1 in self.atoms:
115
+ for atom2 in atom1.bonded_atoms:
116
+ for atom3 in atom2.bonded_atoms:
117
+ if atom1 is atom3:
118
+ continue
119
+ if atom1.molecule_atom_index < atom3.molecule_atom_index:
120
+ yield (atom1, atom2, atom3)
121
+ else:
122
+ # Do not return i.e. (2, 1, 0), only (0, 1, 2)
123
+ pass
124
+
125
+ @property
126
+ def propers(
127
+ self,
128
+ ) -> Generator[
129
+ tuple[
130
+ "_SimpleAtom",
131
+ "_SimpleAtom",
132
+ "_SimpleAtom",
133
+ "_SimpleAtom",
134
+ ],
135
+ None,
136
+ None,
137
+ ]:
138
+ for atom1 in self.atoms:
139
+ for atom2 in atom1.bonded_atoms:
140
+ for atom3 in atom2.bonded_atoms:
141
+ if atom1 is atom3:
142
+ continue
143
+ for atom4 in atom3.bonded_atoms:
144
+ if atom4 in (atom1, atom2):
145
+ continue
146
+
147
+ if atom1.molecule_atom_index < atom4.molecule_atom_index:
148
+ yield (atom1, atom2, atom3, atom4)
149
+ else:
150
+ # Do no duplicate
151
+ pass
152
+
153
+ @property
154
+ def impropers(
155
+ self,
156
+ ) -> Generator[
157
+ tuple[
158
+ "_SimpleAtom",
159
+ "_SimpleAtom",
160
+ "_SimpleAtom",
161
+ "_SimpleAtom",
162
+ ],
163
+ None,
164
+ None,
165
+ ]:
166
+ for atom1 in self.atoms:
167
+ for atom2 in atom1.bonded_atoms:
168
+ for atom3 in atom2.bonded_atoms:
169
+ if atom1 is atom3:
170
+ continue
171
+ for atom3i in atom2.bonded_atoms:
172
+ if atom3i == atom3:
173
+ continue
174
+ if atom3i == atom1:
175
+ continue
176
+
177
+ yield (atom1, atom2, atom3, atom3i)
178
+
179
+ @property
180
+ def smirnoff_impropers(
181
+ self,
182
+ ) -> Generator[
183
+ tuple[
184
+ "_SimpleAtom",
185
+ "_SimpleAtom",
186
+ "_SimpleAtom",
187
+ "_SimpleAtom",
188
+ ],
189
+ None,
190
+ None,
191
+ ]:
192
+ for improper in self.impropers:
193
+ if len(list(improper[1].bonded_atoms)) == 3:
194
+ yield improper
195
+
196
+ @property
197
+ def amber_impropers(
198
+ self,
199
+ ) -> Generator[
200
+ tuple[
201
+ "_SimpleAtom",
202
+ "_SimpleAtom",
203
+ "_SimpleAtom",
204
+ "_SimpleAtom",
205
+ ],
206
+ None,
207
+ None,
208
+ ]:
209
+ for improper in self.smirnoff_impropers:
210
+ yield (improper[1], improper[0], improper[2], improper[3])
211
+
212
+ @property
213
+ def n_angles(self) -> int:
214
+ return len(list(self.angles))
215
+
216
+ @property
217
+ def n_propers(self) -> int:
218
+ return len(list(self.propers))
219
+
220
+ @property
221
+ def n_impropers(self) -> int:
222
+ return len(list(self.impropers))
223
+
224
+ @property
225
+ def hill_formula(self) -> str:
226
+ """
227
+ Return the Hill formula of this molecule.
228
+
229
+ If any atoms are non-elemental, defined by having an atomic number of 0,
230
+ return INVALID instead.
231
+ """
232
+ return self.to_hill_formula()
233
+
234
+ @property
235
+ def hierarchy_schemes(self) -> dict[str, "HierarchyScheme"]:
236
+ return self._hierarchy_schemes
237
+
238
+ def to_hill_formula(self) -> str:
239
+ atom_nums: list[int] = [atom.atomic_number for atom in self.atoms]
240
+
241
+ if min(atom_nums) < 0:
242
+ return "INVALID"
243
+
244
+ return _atom_nums_to_hill_formula(atom_nums)
245
+
246
+ def to_networkx(self) -> "nx.Graph":
247
+ # TODO: Custom attribtues should probably be attached to the nodes (and possibly also
248
+ # the edges?). See for more:
249
+ # https://github.com/openforcefield/openff-toolkit/pull/1179#discussion_r808549385
250
+ import networkx as nx
251
+
252
+ graph: nx.classes.graph.Graph = nx.Graph()
253
+
254
+ for atom_index, atom in enumerate(self.atoms):
255
+ graph.add_node(
256
+ atom_index,
257
+ atomic_number=atom.atomic_number,
258
+ )
259
+ for bond in self.bonds:
260
+ graph.add_edge(
261
+ bond.atom1_index,
262
+ bond.atom2_index,
263
+ )
264
+
265
+ return graph
266
+
267
+ def to_topology(self) -> "Topology":
268
+ from openff.toolkit.topology import Topology
269
+
270
+ return Topology.from_molecules([self])
271
+
272
+ def nth_degree_neighbors(self, n_degrees):
273
+ from openff.toolkit.topology.molecule import (
274
+ _nth_degree_neighbors_from_graphlike,
275
+ )
276
+
277
+ return _nth_degree_neighbors_from_graphlike(graphlike=self, n_degrees=n_degrees)
278
+
279
+ @classmethod
280
+ def _from_subgraph(cls, subgraph: "nx.Graph"):
281
+ molecule = cls()
282
+
283
+ # The subgraph stores indices that might not start at zero (i.e. topology indices)
284
+ # but we need 0-index indices (like molecule indices) to add bonds
285
+ offset = min(subgraph.nodes())
286
+
287
+ for _, node_data in subgraph.nodes(data=True):
288
+ # Hierarchy metadata like residue name needs to be passed in as a separate argument,
289
+ # so we extract those values from the node data
290
+ metadata = dict()
291
+ for key, val in node_data.items():
292
+ if key in [
293
+ "residue_name",
294
+ "residue_number",
295
+ "insertion_code",
296
+ "chain_id",
297
+ ]:
298
+ metadata[key] = val
299
+ # Then we remove the metadata items that we took from the node data
300
+ for key in metadata.keys():
301
+ del node_data[key]
302
+
303
+ molecule.add_atom(metadata=metadata, **node_data)
304
+
305
+ for topology_index1, topology_index2, _edge_data in subgraph.edges(data=True):
306
+ molecule.add_bond(topology_index1 - offset, topology_index2 - offset)
307
+
308
+ return molecule
309
+
310
+ # TODO: Implement me - shouldn't need to be too different than Molecule.add_hierarchy_scheme
311
+ # since the extra chemical information is unrelated to hierarchy/metadata
312
+ def add_hierarchy_scheme(
313
+ self,
314
+ uniqueness_criteria: Iterable[str],
315
+ iterator_name: str,
316
+ ) -> NoReturn:
317
+ raise NotImplementedError()
318
+
319
+ def to_dict(self) -> dict:
320
+ molecule_dict = dict()
321
+ special_serialization_logic = [
322
+ "atoms",
323
+ "bonds",
324
+ "conformers",
325
+ "hierarchy_schemes",
326
+ "molecule",
327
+ ]
328
+ for attr_name, attr_val in self.__dict__.items():
329
+ if attr_name.startswith("_"):
330
+ continue
331
+ if attr_name in special_serialization_logic:
332
+ continue
333
+ molecule_dict[attr_name] = attr_val
334
+
335
+ molecule_dict["atoms"] = [atom.to_dict() for atom in self.atoms]
336
+
337
+ molecule_dict["bonds"] = [bond.to_dict() for bond in self.bonds]
338
+
339
+ if self._conformers is None:
340
+ molecule_dict["conformers"] = None
341
+ else:
342
+ molecule_dict["conformers"] = []
343
+ molecule_dict["conformers_unit"] = "angstrom" # Have this defined as a class variable?
344
+ for conf in self._conformers:
345
+ conf_unitless = conf.m_as(unit.angstrom)
346
+ conf_serialized, _ = serialize_numpy(conf_unitless)
347
+ molecule_dict["conformers"].append(conf_serialized)
348
+
349
+ molecule_dict["hierarchy_schemes"] = dict()
350
+ for iter_name, hier_scheme in self.hierarchy_schemes.items():
351
+ molecule_dict["hierarchy_schemes"][iter_name] = hier_scheme.to_dict()
352
+
353
+ return molecule_dict
354
+
355
+ @classmethod
356
+ def from_dict(cls, molecule_dict):
357
+ molecule = cls()
358
+
359
+ atom_dicts = molecule_dict.pop("atoms")
360
+ for atom_dict in atom_dicts:
361
+ molecule.atoms.append(_SimpleAtom.from_dict(atom_dict))
362
+ molecule.atoms[-1]._molecule = molecule
363
+
364
+ bond_dicts = molecule_dict.pop("bonds")
365
+
366
+ for bond_dict in bond_dicts:
367
+ atom1_index = bond_dict["atom1_index"]
368
+ atom2_index = bond_dict["atom2_index"]
369
+ molecule.add_bond(atom1=molecule.atom(atom1_index), atom2=molecule.atom(atom2_index))
370
+
371
+ conformers = molecule_dict.pop("conformers")
372
+ if conformers is None:
373
+ molecule._conformers = None
374
+ else:
375
+ conformers_unit = molecule_dict.pop("conformers_unit")
376
+ molecule._conformers = list()
377
+ for ser_conf in conformers:
378
+ conformers_shape = (molecule.n_atoms, 3)
379
+ conformer_unitless = deserialize_numpy(ser_conf, conformers_shape)
380
+ conformer = unit.Quantity(conformer_unitless, conformers_unit)
381
+ molecule._conformers.append(conformer)
382
+
383
+ hier_scheme_dicts = molecule_dict.pop("hierarchy_schemes")
384
+ for iterator_name, hierarchy_scheme_dict in hier_scheme_dicts.items():
385
+ molecule._hierarchy_schemes[iterator_name] = HierarchyScheme(
386
+ parent=molecule,
387
+ uniqueness_criteria=tuple(hierarchy_scheme_dict["uniqueness_criteria"]),
388
+ iterator_name=iterator_name,
389
+ )
390
+
391
+ for element_dict in hierarchy_scheme_dict["hierarchy_elements"]:
392
+ molecule._hierarchy_schemes[iterator_name].add_hierarchy_element(
393
+ identifier=element_dict["identifier"],
394
+ atom_indices=element_dict["atom_indices"],
395
+ )
396
+
397
+ for key, val in molecule_dict.items():
398
+ setattr(molecule, key, val)
399
+
400
+ return molecule
401
+
402
+ @classmethod
403
+ def from_molecule(cls, molecule: Molecule):
404
+ """Generate an MM molecule from an OpenFF Molecule."""
405
+ mm_molecule = cls()
406
+ for atom in molecule.atoms:
407
+ mm_molecule.add_atom(
408
+ atomic_number=atom.atomic_number,
409
+ metadata=atom.metadata,
410
+ )
411
+
412
+ for bond in molecule.bonds:
413
+ mm_molecule.add_bond(
414
+ atom1=mm_molecule.atom(bond.atom1_index),
415
+ atom2=mm_molecule.atom(bond.atom2_index),
416
+ )
417
+
418
+ if molecule.conformers is not None:
419
+ for conformer in molecule.conformers:
420
+ mm_molecule.add_conformer(conformer)
421
+
422
+ for name, hierarchy_scheme in molecule.hierarchy_schemes.items():
423
+ assert name == hierarchy_scheme.iterator_name
424
+ mm_molecule.add_hierarchy_scheme(
425
+ uniqueness_criteria=hierarchy_scheme.uniqueness_criteria,
426
+ iterator_name=hierarchy_scheme.iterator_name,
427
+ )
428
+
429
+ return mm_molecule
430
+
431
+ def to_molecule(self) -> NoReturn:
432
+ raise UnsupportedMoleculeConversionError(
433
+ "The information content of a _SimpleMolecule is insufficient for creating "
434
+ "an OpenFF Molecule with sufficiently specified chemistry."
435
+ )
436
+
437
+ def is_isomorphic_with(self, other: Union["FrozenMolecule", "_SimpleMolecule", "nx.Graph"], **kwargs) -> bool:
438
+ """
439
+ Check for pseudo-isomorphism.
440
+
441
+ This currently checks that the two molecules have
442
+ * The same number of atoms
443
+ * The same number of bonds
444
+ * Atoms with matching atomic numbers, in order
445
+
446
+ This currently does NOT checks that the two molecules have
447
+ * Topologically identical bond graphs
448
+ """
449
+ return _SimpleMolecule.are_isomorphic(
450
+ self,
451
+ other,
452
+ return_atom_map=False,
453
+ )[0]
454
+
455
+ @staticmethod
456
+ def are_isomorphic(
457
+ mol1: Union["FrozenMolecule", "_SimpleMolecule", "nx.Graph"],
458
+ mol2: Union["FrozenMolecule", "_SimpleMolecule", "nx.Graph"],
459
+ return_atom_map: bool = False,
460
+ ) -> tuple[bool, dict[int, int] | None]:
461
+ import networkx
462
+
463
+ _cls = _SimpleMolecule
464
+
465
+ if isinstance(mol1, networkx.Graph) and isinstance(mol2, networkx.Graph):
466
+ graph1 = _SimpleMolecule._from_subgraph(mol1).to_networkx()
467
+ graph2 = _SimpleMolecule._from_subgraph(mol2).to_networkx()
468
+
469
+ elif isinstance(mol1, networkx.Graph):
470
+ assert isinstance(mol2, _cls)
471
+ graph1 = _SimpleMolecule._from_subgraph(mol1).to_networkx()
472
+ graph2 = mol2.to_networkx()
473
+
474
+ elif isinstance(mol2, networkx.Graph):
475
+ assert isinstance(mol1, _cls)
476
+ graph1 = mol1.to_networkx()
477
+ graph2 = _SimpleMolecule._from_subgraph(mol2).to_networkx()
478
+
479
+ else:
480
+ # static methods (by definition) know nothing about their class,
481
+ # so the class to compare to must be hard-coded here
482
+ if not (isinstance(mol1, _cls) and isinstance(mol2, _cls)):
483
+ return False, None
484
+
485
+ graph1 = mol1.to_networkx()
486
+ graph2 = mol2.to_networkx()
487
+
488
+ def node_match_func(node1, node2):
489
+ return node1["atomic_number"] == node2["atomic_number"]
490
+
491
+ edge_match_func = None
492
+
493
+ matcher = networkx.algorithms.isomorphism.GraphMatcher(
494
+ graph1, graph2, node_match=node_match_func, edge_match=edge_match_func
495
+ )
496
+
497
+ if matcher.is_isomorphic():
498
+ if return_atom_map:
499
+ topology_atom_map = matcher.mapping
500
+
501
+ return True, {key: topology_atom_map[key] for key in sorted(topology_atom_map)}
502
+
503
+ else:
504
+ return True, None
505
+ else:
506
+ return False, None
507
+
508
+ def generate_unique_atom_names(self):
509
+ """Generate unique atom names. See `Molecule.generate_unique_atom_names`."""
510
+ from collections import defaultdict
511
+
512
+ element_counts: defaultdict[str, int] = defaultdict(int)
513
+ for atom in self.atoms:
514
+ symbol = SYMBOLS[atom.atomic_number]
515
+ element_counts[symbol] += 1
516
+
517
+ atom.name = symbol + str(element_counts[symbol]) + "x"
518
+
519
+ @property
520
+ def has_unique_atom_names(self) -> bool:
521
+ """``True`` if the molecule has unique atom names, ``False`` otherwise."""
522
+ return _has_unique_atom_names(self)
523
+
524
+ def __getattr__(self, name: str) -> list["HierarchyElement"]:
525
+ """If a requested attribute is not found, check the hierarchy schemes"""
526
+ try:
527
+ return self.__dict__["_hierarchy_schemes"][name].hierarchy_elements
528
+ except KeyError:
529
+ raise AttributeError(f"'{self.__class__.__name__}' object has no attribute {name!r}")
530
+
531
+ def __deepcopy__(self, memo):
532
+ return self.__class__.from_dict(self.to_dict())
533
+
534
+
535
+ _SimpleMolecule.add_hierarchy_scheme = Molecule.add_hierarchy_scheme # type: ignore[assignment]
536
+ _SimpleMolecule.update_hierarchy_schemes = Molecule.update_hierarchy_schemes # type: ignore[attr-defined]
537
+
538
+
539
+ class _SimpleAtom:
540
+ def __init__(
541
+ self,
542
+ atomic_number: int,
543
+ molecule: _SimpleMolecule | None = None,
544
+ metadata: AtomMetadataDict | None = None,
545
+ name: str = "",
546
+ **kwargs,
547
+ ):
548
+ if metadata is None:
549
+ self.metadata = AtomMetadataDict()
550
+ else:
551
+ self.metadata = AtomMetadataDict(metadata)
552
+
553
+ # This _could_ be hidden away into _metadata
554
+ self._name = name
555
+ self._atomic_number = atomic_number
556
+ self._molecule = molecule
557
+ self._bonds: list[_SimpleBond] = list()
558
+ for key, val in kwargs.items():
559
+ setattr(self, key, val)
560
+
561
+ @property
562
+ def name(self) -> str:
563
+ return self._name
564
+
565
+ @name.setter
566
+ def name(self, value: str):
567
+ self._name = value
568
+
569
+ @property
570
+ def atomic_number(self) -> int:
571
+ return self._atomic_number
572
+
573
+ @atomic_number.setter
574
+ def atomic_number(self, value):
575
+ if not isinstance(value, int):
576
+ raise ValueError("atomic_number must be an integer")
577
+ if value < 0:
578
+ raise ValueError("atomic_number must be non-negative. An atomic number of 0 is acceptable.")
579
+ self._atomic_number = value
580
+
581
+ @property
582
+ def symbol(self) -> str:
583
+ return SYMBOLS[self.atomic_number]
584
+
585
+ @property
586
+ def mass(self) -> "Quantity":
587
+ return MASSES[self.atomic_number]
588
+
589
+ @property
590
+ def molecule(self):
591
+ """The ``Molecule`` this atom is part of."""
592
+ return self._molecule
593
+
594
+ @property
595
+ def bonds(self):
596
+ return self._bonds
597
+
598
+ def add_bond(self, bond):
599
+ self._bonds.append(bond)
600
+
601
+ @property
602
+ def bonded_atoms(self):
603
+ for bond in self._bonds:
604
+ for atom in [bond.atom1, bond.atom2]:
605
+ if atom is not self:
606
+ yield atom
607
+
608
+ @functools.cached_property
609
+ def molecule_atom_index(self) -> int:
610
+ return self.molecule.atoms.index(self)
611
+
612
+ def to_dict(self) -> dict[str, dict | str | int]:
613
+ atom_dict: dict[str, dict | str | int] = dict()
614
+ atom_dict["metadata"] = dict(self.metadata)
615
+ atom_dict["atomic_number"] = self._atomic_number
616
+ atom_dict["name"] = self._name
617
+
618
+ keys_to_skip = ["metadata", "molecule", "bonds"]
619
+
620
+ for attr_name, attr_val in self.__dict__.items():
621
+ if attr_name.startswith("_"):
622
+ continue
623
+ if attr_name in keys_to_skip:
624
+ continue
625
+ atom_dict[attr_name] = attr_val
626
+
627
+ return atom_dict
628
+
629
+ @classmethod
630
+ def from_dict(cls, atom_dict: dict):
631
+ atom = cls(**atom_dict)
632
+ return atom
633
+
634
+
635
+ class _SimpleBond:
636
+ def __init__(self, atom1, atom2, **kwargs):
637
+ self.molecule = atom1.molecule
638
+ self.atom1 = atom1
639
+ self.atom2 = atom2
640
+
641
+ atom1.add_bond(self)
642
+ atom2.add_bond(self)
643
+
644
+ for key, val in kwargs.items():
645
+ setattr(self, key, val)
646
+
647
+ @property
648
+ def atoms(self) -> list[_SimpleAtom]:
649
+ return [self.atom1, self.atom2]
650
+
651
+ @property
652
+ def atom1_index(self) -> int:
653
+ return self.atom1.molecule_atom_index
654
+
655
+ @property
656
+ def atom2_index(self) -> int:
657
+ return self.atom2.molecule_atom_index
658
+
659
+ def to_dict(self) -> dict[str, int]:
660
+ return {
661
+ "atom1_index": self.atom1.molecule_atom_index,
662
+ "atom2_index": self.atom2.molecule_atom_index,
663
+ }