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 +1,955 @@
1
+ # flake8: noqa
2
+ """
3
+ Tools for generating library of substructures from the Chemical Component
4
+ Dictionary (CCD).
5
+ """
6
+
7
+ import copy
8
+ import json
9
+ from collections import OrderedDict, defaultdict
10
+ from copy import deepcopy
11
+
12
+ import rdkit
13
+ from CifFile import ReadCif
14
+ from openff.units.elements import SYMBOLS
15
+ from rdkit import Chem
16
+
17
+ from openff.toolkit import Molecule
18
+ from openff.toolkit.utils.rdkit_wrapper import RDKitToolkitWrapper
19
+
20
+ _SYMBOL_TO_ATOMIC_NUMBER = {v: k for k, v in SYMBOLS.items()}
21
+
22
+
23
+ # Amber ff porting functions
24
+ def remove_charge_and_bond_order_from_guanidinium(rdmol):
25
+ """
26
+ To correct for chemical perception issues with possible resonance states of arginine,
27
+ remove all charge from the guanidinium group, and set all bond orders to 4. This will
28
+ mark the resonant bonds with a unique "$" character in the SMARTS, which we can later
29
+ replace.
30
+ """
31
+ for atom in rdmol.GetAtoms():
32
+ # print(dir(atom))
33
+ if atom.GetAtomicNum() != 6: # element.symbol != "C":
34
+ continue
35
+ nitrogen_neighbors = 0
36
+ for neighbor in atom.GetNeighbors():
37
+ if neighbor.GetAtomicNum() == 7:
38
+ nitrogen_neighbors += 1
39
+ if nitrogen_neighbors != 3:
40
+ continue
41
+ atom.SetFormalCharge(0)
42
+ for neighbor in atom.GetNeighbors():
43
+ neighbor.SetFormalCharge(0)
44
+ for bond in atom.GetBonds():
45
+ # Set bond order 4, which will produce a "$" character. We later replace this with "~".
46
+ # print(dir(bond))
47
+ bond.SetBondType(rdkit.Chem.BondType.QUADRUPLE)
48
+ # bond.SetBondType(Chem.BondType.AROMATIC)
49
+ # bond.SetBondType(Chem.BondType.OTHER)
50
+
51
+
52
+ def remove_charge_and_bond_order_from_imidazole(rdmol):
53
+ """
54
+ To correct for chemical perception issues with possible resonance states of histidine,
55
+ remove all charge from the imidazole group, and set all bond orders to 4. This will
56
+ mark the resonant bonds with a unique "$" character in the SMARTS, which we can later
57
+ replace.
58
+ """
59
+ # matches = offmol.chemical_environment_matches('[C:1]1~[C:2]~[N:3]~[C:4]~[N:5]1')
60
+ imidazole_substructure = rdkit.Chem.MolFromSmarts("[C:1]1~[C:2]~[N:3]~[C:4]~[N:5]1")
61
+ matches = rdmol.GetSubstructMatches(imidazole_substructure)
62
+ all_imidazole_atoms = set()
63
+ for match in matches:
64
+ for idx in match:
65
+ all_imidazole_atoms.add(idx)
66
+
67
+ for atom in rdmol.GetAtoms():
68
+ if atom.GetIdx() in all_imidazole_atoms:
69
+ atom.SetFormalCharge(0)
70
+
71
+ for bond in rdmol.GetBonds():
72
+ # print(dir(bond))
73
+ if (bond.GetBeginAtomIdx() in all_imidazole_atoms) and (bond.GetEndAtomIdx() in all_imidazole_atoms):
74
+ bond.SetBondType(rdkit.Chem.BondType.QUADRUPLE)
75
+
76
+
77
+ class CifSubstructures:
78
+ """
79
+ Substructure from CIF formatted files.
80
+ """
81
+
82
+ # bond order dictionary translation from mmcif
83
+ bond_order_dict = {"SING": 1, "DOUB": 2, "TRIP": 3, "QUAD": 4}
84
+
85
+ def __init__(self):
86
+ """
87
+ Create object with substructures data from CIF files.
88
+ """
89
+ self.data = defaultdict(defaultdict) # Dictionary where to store substructures data
90
+ self._cif_multi_entry_object = None
91
+
92
+ def from_file(
93
+ self,
94
+ cif_file,
95
+ discard_keyword="FRAGMENT",
96
+ replace_quadruple_bond_with_any: bool = True,
97
+ remove_charge_bond_order_resonant: bool = True,
98
+ ):
99
+ """
100
+ Reads cif formatted file and fills substructure information.
101
+
102
+ Sequential runs combine information from different files.
103
+
104
+ Parameters
105
+ __________
106
+ cif_file : str or file-like object
107
+ File path string, URL or file-like object.
108
+ discard_keyword : str, optional, default='FRAGMENT'
109
+ Keyword in _chem_comp.name for filtering out entries. Default is 'FRAGMENT'.
110
+ remove_charge_bond_order_resonant: bool, optional, default=True
111
+ Removes bond order and charge information from guanidium and imidazole resonant groups.
112
+ replace_quadruple_bond_with_any: bool, optional, default=True:
113
+ Replace expected unique quadruple bond symbol ($) with any order symbol (~) in smarts patterns.
114
+ """
115
+ # read cif file
116
+ self._cif_multi_entry_object = ReadCif(cif_file)
117
+ # fill data dictionary
118
+ self._fill_substructure_data(
119
+ discard_keyword=discard_keyword,
120
+ replace_quadruple_bond_with_any=replace_quadruple_bond_with_any,
121
+ remove_charge_bond_order_resonant=remove_charge_bond_order_resonant,
122
+ )
123
+
124
+ def to_json_file(self, output_file, indent=4):
125
+ """
126
+ Return a JSON serialized representation.
127
+
128
+ Parameters
129
+ __________
130
+ output_file : str
131
+ Path string for output file.
132
+ indent : int, optional, default=4
133
+ If not None, will pretty-print with specified number of spaces for indentation.
134
+
135
+ Returns
136
+ _______
137
+ serialized : str
138
+ A JSON serialized representation of the object.
139
+ """
140
+ with open(output_file, "w") as library_file:
141
+ json.dump(self.data, library_file, indent=indent)
142
+
143
+ def clear_data(self):
144
+ """
145
+ Clears current data structures read from files.
146
+
147
+ Useful if you want to start reading cif files from scratch.
148
+ """
149
+ self.data = defaultdict(defaultdict)
150
+ self._cif_multi_entry_object = None
151
+
152
+ @staticmethod
153
+ def _generate_atom_symbol_number_dictionary(cif_entry):
154
+ """
155
+ Generate symbol to atomic number dictionary, given entry information from cif file.
156
+
157
+ Parameters
158
+ __________
159
+ cif_entry : CifFile.StarFile.StarBlock
160
+ Data block entry from cif file.
161
+
162
+ Returns
163
+ _______
164
+ symbol_to_num_dict : dict
165
+ Atom symbol to atomic number (key, value) dictionary.
166
+ """
167
+ # Is this de-duplicated? i.e. can it be ["C", "C", "H"] or only ["C", "H"] ?
168
+ atom_symbol_list: list[str] = cif_entry["_chem_comp_atom.type_symbol"]
169
+
170
+ # Is this dict a de-duplicated mapping between element symbols and atomic numbers
171
+ # for the elements in this cif file? If so, can maybe do it in one step
172
+ """
173
+ symbol_to_num_dict: dict[str, int] = {
174
+ symbol: atomic_number for atomic_number, symbol in SYMBOLS.items() if atomic_number in
175
+ cif_entry["_chem_comp_atom.type_symbol"]
176
+ }
177
+ """
178
+
179
+ symbol_to_num_dict: dict[str, int] = {symbol: _SYMBOL_TO_ATOMIC_NUMBER[symbol] for symbol in atom_symbol_list}
180
+
181
+ return symbol_to_num_dict
182
+
183
+ @staticmethod
184
+ def _get_atom_by_name(molecule, name: str):
185
+ """
186
+ Gets first occurrence of atom object from a molecule by its name.
187
+
188
+ Parameters
189
+ __________
190
+ molecule : Molecule
191
+ Molecule object where to look.
192
+ name : str
193
+ Atom name string to match against molecule atoms.
194
+
195
+ Returns
196
+ _______
197
+ atom_match : Atom or None
198
+ First occurrence of Atom with the given name, in molecule. None if not found.
199
+ """
200
+ for atom in molecule.atoms:
201
+ if atom.name == name:
202
+ match = atom
203
+ break
204
+ else:
205
+ match = None
206
+ return match
207
+
208
+ def _gather_atoms_information(self, cif_entry_data):
209
+ """
210
+ Gather minimum required atom information for creating toolkit Atoms.
211
+
212
+ Returns
213
+ _______
214
+ atom_information_array : tuple
215
+ Multidimensional tuple with atoms information.
216
+ """
217
+ symbol_to_num_dict = self._generate_atom_symbol_number_dictionary(cif_entry_data)
218
+ atom_names = cif_entry_data["_chem_comp_atom.atom_id"]
219
+ atomic_numbers = [symbol_to_num_dict[x] for x in cif_entry_data["_chem_comp_atom.type_symbol"]]
220
+ formal_charges = [int(x) for x in cif_entry_data["_chem_comp_atom.charge"]]
221
+ is_aromatic = [False if x == "N" else True for x in cif_entry_data["_chem_comp_atom.pdbx_aromatic_flag"]]
222
+ stereochemistry = [None if x == "N" else x for x in cif_entry_data["_chem_comp_atom.pdbx_stereo_config"]]
223
+ leaving_atoms_list = cif_entry_data["_chem_comp_atom.pdbx_leaving_atom_flag"]
224
+ return (
225
+ atom_names,
226
+ atomic_numbers,
227
+ formal_charges,
228
+ is_aromatic,
229
+ stereochemistry,
230
+ leaving_atoms_list,
231
+ )
232
+
233
+ def _gather_bonds_information(self, cif_entry_data):
234
+ """
235
+ Gather minimum required bond information for creating toolkit Bonds.
236
+
237
+ Returns
238
+ _______
239
+ bond_information_array : tuple
240
+ Multidimensional tuple with bonds information.
241
+ """
242
+ atom1_name_list = cif_entry_data["_chem_comp_bond.atom_id_1"]
243
+ atom2_name_list = cif_entry_data["_chem_comp_bond.atom_id_2"]
244
+ bond_order_list = [self.bond_order_dict[x] for x in cif_entry_data["_chem_comp_bond.value_order"]]
245
+ is_aromatic_bond_list = [
246
+ False if x == "N" else True for x in cif_entry_data["_chem_comp_bond.pdbx_aromatic_flag"]
247
+ ]
248
+ stereochemistry_bond_list = [
249
+ None if x == "N" else x for x in cif_entry_data["_chem_comp_bond.pdbx_stereo_config"]
250
+ ]
251
+ return (
252
+ atom1_name_list,
253
+ atom2_name_list,
254
+ bond_order_list,
255
+ is_aromatic_bond_list,
256
+ stereochemistry_bond_list,
257
+ )
258
+
259
+ @staticmethod
260
+ def _get_subrdmol(
261
+ rdmol: rdkit.Chem.rdchem.Mol,
262
+ indices: list = [],
263
+ sanitize: bool = False,
264
+ remove_charge_bond_order_resonant: bool = True,
265
+ ):
266
+ """
267
+ Create new sub-molecule from selected atom indices
268
+
269
+ Parameters
270
+ ----------
271
+ rdmol: rdkit.Chem.rdchem.Mol
272
+ Input molecule
273
+ indices: iterable of ints
274
+ atom indices to include from input molecule, indexed from 0
275
+ sanitize: bool
276
+ whether to sanitize the molecule (recommend: no)
277
+
278
+ Returns
279
+ -------
280
+ rdkit.Chem.rdchem.Mol: subset of molecule
281
+ """
282
+ submol = rdkit.Chem.RWMol(rdmol)
283
+ ix = sorted([at.GetIdx() for at in rdmol.GetAtoms() if at.GetIdx() not in indices])
284
+ for i in ix[::-1]:
285
+ submol.RemoveAtom(int(i))
286
+ if sanitize:
287
+ rdkit.Chem.SanitizeMol(submol)
288
+
289
+ for atom in submol.GetAtoms():
290
+ # print(dir(atom))
291
+ atom.SetNoImplicit(True)
292
+
293
+ if remove_charge_bond_order_resonant:
294
+ remove_charge_and_bond_order_from_imidazole(submol)
295
+ remove_charge_and_bond_order_from_guanidinium(submol)
296
+ return submol
297
+
298
+ def _get_smiles(
299
+ self,
300
+ mol: Molecule,
301
+ indices: list = [],
302
+ label_indices: list = [],
303
+ replace_quadruple_bond_with_any: bool = True,
304
+ remove_charge_bond_order_resonant: bool = True,
305
+ ):
306
+ """
307
+ Get SMARTS of selected atoms in molecule
308
+
309
+ Parameters
310
+ ----------
311
+ mol: openff.toolkit.Molecule
312
+ Input molecule
313
+ indices: iterable of ints
314
+ atom indices to include in SMARTS, indexed from 0
315
+ label_indices: iterable of ints
316
+ atom indices to label, indexed from 0. The atoms
317
+ will be labelled in the order specified. Labels
318
+ begin from 1.
319
+
320
+ Returns
321
+ -------
322
+ str: SMARTS string
323
+ """
324
+ rdmol = mol.to_rdkit()
325
+ for i, lix in enumerate(label_indices, 1):
326
+ at = rdmol.GetAtomWithIdx(int(lix))
327
+ at.SetAtomMapNum(i)
328
+ indices = sorted(set(indices) | set(label_indices))
329
+ submol = self._get_subrdmol(
330
+ rdmol,
331
+ indices,
332
+ remove_charge_bond_order_resonant=remove_charge_bond_order_resonant,
333
+ )
334
+ smiles = rdkit.Chem.MolToSmiles(submol, allHsExplicit=True)
335
+ # TODO: This doesn't seem to be having an effect. It is replacing bond orders regardless.
336
+ if replace_quadruple_bond_with_any:
337
+ smiles = smiles.replace("$", "~")
338
+ return smiles
339
+
340
+ def _add_substructure_data_entry(
341
+ self,
342
+ atoms_information,
343
+ bonds_information,
344
+ entry_code,
345
+ replace_quadruple_bond_with_any: bool = True,
346
+ remove_charge_bond_order_resonant: bool = True,
347
+ ):
348
+ """
349
+ Read substructure from entry data in cif file and fill data object with smiles.
350
+
351
+ Parameters
352
+ __________
353
+ atoms_information : list[tuple[str,int]]
354
+ Iterable of tuple of atom info.
355
+ Currently [atom_name, element, formal_charge, is_aromatic, stereo, is_leaving]
356
+ bonds_information : list[tuple[str,int]]
357
+ Iterable of tuple of bond info.
358
+ Currently [atom1_name, atom2_name, bond_order, is_aromatic, stereo]
359
+ """
360
+ offmol = Molecule()
361
+
362
+ atom_name_to_idx = dict()
363
+ # add atoms
364
+ for (
365
+ atom_name,
366
+ atomic_number,
367
+ formal_charge,
368
+ is_aromatic,
369
+ stereochemistry,
370
+ is_leaving,
371
+ ) in atoms_information:
372
+ # if include_leaving:
373
+ # Add all atoms
374
+ atom_idx = offmol.add_atom(
375
+ atomic_number,
376
+ formal_charge,
377
+ is_aromatic,
378
+ stereochemistry=stereochemistry,
379
+ name=atom_name,
380
+ )
381
+ atom_name_to_idx[atom_name] = atom_idx
382
+ for (
383
+ atom1_name,
384
+ atom2_name,
385
+ bond_order,
386
+ is_aromatic,
387
+ stereochemistry,
388
+ ) in bonds_information:
389
+ # try:
390
+ atom1_idx = atom_name_to_idx[atom1_name]
391
+ atom2_idx = atom_name_to_idx[atom2_name]
392
+ offmol.add_bond(
393
+ atom1_idx,
394
+ atom2_idx,
395
+ bond_order,
396
+ is_aromatic=is_aromatic,
397
+ stereochemistry=stereochemistry,
398
+ )
399
+ # # TODO: Broad exception. We should raise a specific error.
400
+ # except Exception: # happens when atom is not found, i.e. no leaving atoms.
401
+ # continue
402
+ # Get smiles
403
+ atom_indices = list(range(offmol.n_atoms))
404
+ smiles = self._get_smiles(
405
+ offmol,
406
+ indices=atom_indices,
407
+ label_indices=atom_indices,
408
+ replace_quadruple_bond_with_any=replace_quadruple_bond_with_any,
409
+ remove_charge_bond_order_resonant=remove_charge_bond_order_resonant,
410
+ )
411
+ if smiles not in self.data[entry_code]:
412
+ atom_names = [atom_info[0] for atom_info in atoms_information]
413
+ self.data[entry_code][smiles] = atom_names
414
+
415
+ def _fill_substructure_data(
416
+ self,
417
+ discard_keyword="FRAGMENT",
418
+ replace_quadruple_bond_with_any: bool = True,
419
+ remove_charge_bond_order_resonant: bool = True,
420
+ ):
421
+ """
422
+ Fills data dictionary with the substructure information.
423
+
424
+ Parameters
425
+ __________
426
+ discard_keyword : str, optional, default='FRAGMENT'
427
+ Keyword in _chem_comp.name for filtering out entries. Default is 'FRAGMENT'.
428
+ """
429
+ # override_dict contains atoms that we DO want to treat as leaving, even
430
+ # though the actual entries don't have them flagged as leaving. The "H2" entries
431
+ # in this list are hydrogens attached to the backbone N, which are (for some reason)
432
+ # recorded as NH2, with neither H marked as "leaving", which causes the
433
+ # substructures to be unable to match main-chain appearances of the amino acids.
434
+ override_dict = {
435
+ # LYN
436
+ "lys_lfoh_dhz3": ["H2"],
437
+ # GLU
438
+ "glu_lfoh_dhe2": ["H2"],
439
+ # HIE
440
+ "his_lfoh_dhd1": ["H2"],
441
+ # ASP
442
+ "asp_lfoh_dhd2": ["H2"],
443
+ # HID
444
+ "his_lfoh_dhe2": ["H2"],
445
+ # CYX
446
+ "cys": ["HG"],
447
+ # CYM
448
+ "cys_lfoh_dhg": ["H1", "H2"],
449
+ }
450
+
451
+ for entry, entry_data in self._cif_multi_entry_object.items():
452
+ # Skip entries matching discard filtering keyword in comp name
453
+ comp_name = entry_data["_chem_comp.name"]
454
+ if discard_keyword in comp_name:
455
+ continue
456
+ # Gather necessary data for creating/adding atoms
457
+ atoms_information = [*zip(*self._gather_atoms_information(entry_data))]
458
+ # Gather information for bonds
459
+ bonds_information = [*zip(*self._gather_bonds_information(entry_data))]
460
+
461
+ for override_list in override_dict.get(entry, []):
462
+ for idx, atom in enumerate(atoms_information):
463
+ if atom[0] in override_list:
464
+ new_atom_tuple = (
465
+ atom[0],
466
+ atom[1],
467
+ atom[2],
468
+ atom[3],
469
+ atom[4],
470
+ "Y",
471
+ )
472
+ atoms_information[idx] = new_atom_tuple
473
+ # Only take three letter code for key -- Note it uses the new atom_names list
474
+ entry_code = entry_data["_chem_comp.three_letter_code"]
475
+ # Generate structures with permutations of leaving atoms. For example, if a COH
476
+ # motif has -OH group marked as leaving, this will add
477
+ # 1) the O- intermediate where only the H has left, as well as
478
+ # 2) the structure with the entire OH removed.
479
+ # Only atoms marked as "leaving" may have their formal charge changed by
480
+ # this function, so the remaining C when the OH is removed still has a
481
+ # neutral charge.
482
+ info_tuples = self._recursive_prepare_atom_bond_info(
483
+ atoms_information, bonds_information, return_list=list()
484
+ )
485
+
486
+ # Also add a structure with ALL leaving atoms removed
487
+ atoms_info_copy = copy.deepcopy(atoms_information)
488
+ bonds_info_copy = copy.deepcopy(bonds_information)
489
+ atom_idxs_to_remove = [idx for idx, at in enumerate(atoms_info_copy) if at[5] == "Y"]
490
+ atom_names_to_remove = [atoms_info_copy[idx][0] for idx in atom_idxs_to_remove]
491
+ bond_idxs_to_remove = list()
492
+ for bond_idx, bond in enumerate(bonds_info_copy):
493
+ if (bond[0] in atom_names_to_remove) or (bond[1] in atom_names_to_remove):
494
+ bond_idxs_to_remove.append(bond_idx)
495
+
496
+ for atom_idx_to_remove in atom_idxs_to_remove[::-1]:
497
+ atoms_info_copy.pop(atom_idx_to_remove)
498
+ for bond_idx_to_remove in bond_idxs_to_remove[::-1]:
499
+ bonds_info_copy.pop(bond_idx_to_remove)
500
+ info_tuples.append((atoms_info_copy, bonds_info_copy))
501
+
502
+ # Generate substructure entries for all prepared substructures
503
+ for atoms_information, bonds_information in info_tuples:
504
+ self._add_substructure_data_entry(
505
+ atoms_information,
506
+ bonds_information,
507
+ entry_code,
508
+ replace_quadruple_bond_with_any=replace_quadruple_bond_with_any,
509
+ remove_charge_bond_order_resonant=remove_charge_bond_order_resonant,
510
+ )
511
+
512
+ def _recursive_prepare_atom_bond_info(self, atoms_info, bonds_info, return_list=list()):
513
+ """
514
+ This method makes permutations of the substructure with leaving atoms left and removed.
515
+ If some leaving atoms are bound to other leaving atoms, this method produces all permutations
516
+ of the leaving atom chains that are possible without creating a disconnected molecular graph.
517
+
518
+ If multiple leaving atoms form a chain, then this method attempts to keep the graph chemically
519
+ valid by subtracting one from the formal charge of each leaving atom when its neighbor is removed.
520
+ However non-leaving atoms will never have their formal charge changed.
521
+
522
+ Parameters
523
+ ----------
524
+ atoms_info : list[tuple[str,int]]
525
+ Iterable of tuple of atom info.
526
+ Currently [atom_name, element, formal_charge, is_aromatic, stereo, is_leaving]
527
+ bonds_info : list[tuple[str,int]]
528
+ Iterable of tuple of bond info.
529
+ Currently [atom1_name, atom2_name, bond_order, is_aromatic, stereo]
530
+ """
531
+ return_list.append((atoms_info, bonds_info))
532
+ for leaving_atom_idx, leaving_atom_info_tuple in enumerate(atoms_info):
533
+ # If the atom isn't leaving then we don't need to do anything
534
+ if leaving_atom_info_tuple[5] == "N":
535
+ continue
536
+ # If the atom IS leaving, then find any bonds it's involved in
537
+ leaving_atom_name = leaving_atom_info_tuple[0]
538
+ involved_bond_indices = list()
539
+ for bond_idx, bond_info_tuple in enumerate(bonds_info):
540
+ if leaving_atom_name in bond_info_tuple[:2]:
541
+ involved_bond_indices.append(bond_idx)
542
+ # If this leaving atom is involved in more than one bond, then
543
+ # don't remove it, since doing so would disconnect the molecule
544
+ if len(involved_bond_indices) != 1:
545
+ continue
546
+ atoms_info_copy = copy.deepcopy(atoms_info)
547
+ bonds_info_copy = copy.deepcopy(bonds_info)
548
+
549
+ # Determine whether the neighbor of the leaving atom is also leaving
550
+ bond_info_tuple = bonds_info[involved_bond_indices[0]]
551
+ neighbor_atom_name = [name for name in bond_info_tuple[:2] if name != leaving_atom_name][0]
552
+ for neighbor_atom_idx, neighbor_atom_info_tuple in enumerate(atoms_info):
553
+ if neighbor_atom_info_tuple[0] != neighbor_atom_name:
554
+ continue
555
+ neighbor_atom_is_also_leaving = neighbor_atom_info_tuple[5] == "Y"
556
+ # If the neighbor atom is ALSO leaving, then deduct 1 from its formal charge
557
+ if neighbor_atom_is_also_leaving:
558
+ new_atom_tuple = (
559
+ neighbor_atom_info_tuple[0],
560
+ neighbor_atom_info_tuple[1],
561
+ neighbor_atom_info_tuple[2] - 1,
562
+ neighbor_atom_info_tuple[3],
563
+ neighbor_atom_info_tuple[4],
564
+ neighbor_atom_info_tuple[5],
565
+ )
566
+ atoms_info_copy[neighbor_atom_idx] = new_atom_tuple
567
+ atoms_info_copy.pop(leaving_atom_idx)
568
+ bonds_info_copy.pop(involved_bond_indices[0])
569
+ return_list = self._recursive_prepare_atom_bond_info(
570
+ atoms_info_copy, bonds_info_copy, return_list=return_list
571
+ )
572
+
573
+ return return_list
574
+
575
+ def _patch_known_problems(self):
576
+ """
577
+ Monkey-patching known problems with current aa-variants-v1.cif from CCD.
578
+
579
+ .. warning: Needed as of Oct-21-2021
580
+ """
581
+
582
+ substructures_to_fix = {
583
+ "PRO": [
584
+ (
585
+ "[N-:1]1[C@@:2]([C-:3]=[O:4])([H:8])[C:5]([H:9])([H:10])[C:6]([H:11])([H:12])[C:7]1([H:13])[H:14]",
586
+ "[N:1]1[C@@:2]([C:3]=[O:4])([H:8])[C:5]([H:9])([H:10])[C:6]([H:11])([H:12])[C:7]1([H:13])[H:14]",
587
+ ),
588
+ ],
589
+ "HIS": [
590
+ (
591
+ "[N:1]([C@:2]([C:3](=[O:4])[O:11][H:18])([C:5]([C:6]1=[C:8]([H:16])[N-:10][C:9]([H:17])=[N+:7]1[H:15])([H:13])[H:14])[H:12])([H:19])[H:20]",
592
+ "[N:1]([C@:2]([C:3](=[O:4])[O:11][H:18])([C:5]([C:6]1=[C:8]([H:16])[N:10]=[C:9]([H:17])[N:7]1[H:15])([H:13])[H:14])[H:12])([H:19])[H:20]",
593
+ ),
594
+ (
595
+ "[N:1]([C@:2]([C:3](=[O:4])[O-:11])([C:5]([C:6]1=[C:8]([H:16])[N-:10][C:9]([H:17])=[N+:7]1[H:15])([H:13])[H:14])[H:12])([H:18])[H:19]",
596
+ "[N:1]([C@:2]([C:3](=[O:4])[O-:11])([C:5]([C:6]1=[C:8]([H:16])[N:10]=[C:9]([H:17])[N:7]1[H:15])([H:13])[H:14])[H:12])([H:18])[H:19]",
597
+ ),
598
+ (
599
+ "[N:1]([C@:2]([C:3]=[O:4])([C:5]([C:6]1=[C:8]([H:15])[N-:10][C:9]([H:16])=[N+:7]1[H:14])([H:12])[H:13])[H:11])([H:17])[H:18]",
600
+ "[N:1]([C@:2]([C:3]=[O:4])([C:5]([C:6]1=[C:8]([H:15])[N:10]=[C:9]([H:16])[N:7]1[H:14])([H:12])[H:13])[H:11])([H:17])[H:18]",
601
+ ),
602
+ (
603
+ "[N:1]([C@:2]([C:3]=[O:4])([C:5]([C:6]1=[C:8]([H:15])[N-:10][C:9]([H:16])=[N+:7]1[H:14])([H:12])[H:13])[H:11])[H:17]",
604
+ "[N:1]([C@:2]([C:3]=[O:4])([C:5]([C:6]1=[C:8]([H:15])[N:10]=[C:9]([H:16])[N:7]1[H:14])([H:12])[H:13])[H:11])[H:17]",
605
+ ),
606
+ (
607
+ "[N:1]([C@:2]([C:3](=[O:4])[O-:11])([C:5]([C:6]1=[C:8]([H:16])[N-:10][C:9]([H:17])=[N+:7]1[H:15])([H:13])[H:14])[H:12])[H:18]",
608
+ "[N:1]([C@:2]([C:3](=[O:4])[O-:11])([C:5]([C:6]1=[C:8]([H:16])[N:10]=[C:9]([H:17])[N:7]1[H:15])([H:13])[H:14])[H:12])[H:18]",
609
+ ),
610
+ (
611
+ "[N:1]([C@:2]([C:3](=[O:4])[O:11][H:18])([C:5]([C:6]1=[C:8]([H:16])[N-:10][C:9]([H:17])=[N+:7]1[H:15])([H:13])[H:14])[H:12])[H:19]",
612
+ "[N:1]([C@:2]([C:3](=[O:4])[O:11][H:18])([C:5]([C:6]1=[C:8]([H:16])[N:10]=[C:9]([H:17])[N:7]1[H:15])([H:13])[H:14])[H:12])[H:19]",
613
+ ),
614
+ (
615
+ "[N+:1]([C@:2]([C:3](=[O:4])[O-:11])([C:5]([C:6]1=[C:8]([H:16])[N-:10][C:9]([H:17])=[N+:7]1[H:15])([H:13])[H:14])[H:12])([H:18])([H:19])[H:20]",
616
+ "[N+:1]([C@:2]([C:3](=[O:4])[O-:11])([C:5]([C:6]1=[C:8]([H:16])[N:10]=[C:9]([H:17])[N:7]1[H:15])([H:13])[H:14])[H:12])([H:18])([H:19])[H:20]",
617
+ ),
618
+ (
619
+ "[N+:1]([C@:2]([C:3]=[O:4])([C:5]([C:6]1=[C:8]([H:15])[N-:10][C:9]([H:16])=[N+:7]1[H:14])([H:12])[H:13])[H:11])([H:17])([H:18])[H:19]",
620
+ "[N+:1]([C@:2]([C:3]=[O:4])([C:5]([C:6]1=[C:8]([H:15])[N:10]=[C:9]([H:16])[N:7]1[H:14])([H:12])[H:13])[H:11])([H:17])([H:18])[H:19]",
621
+ ),
622
+ ],
623
+ "TRP": [
624
+ (
625
+ "[N:1]([C@:2]([C:3](=[O:4])[O:15][H:24])([C:5]([C:6]1=[C:7]([H:19])[N-:9][c:10]2[c:8]1[c:11]([H:20])[c:13]([H:22])[c:14]([H:23])[c:12]2[H:21])([H:17])[H:18])[H:16])([H:25])[H:26]",
626
+ "[N:1]([C@:2]([C:3](=[O:4])[O:15][H:24])([C:5]([C:6]1=[C:7]([H:19])[N:9][c:10]2[c:8]1[c:11]([H:20])[c:13]([H:22])[c:14]([H:23])[c:12]2[H:21])([H:17])[H:18])[H:16])([H:25])[H:26]",
627
+ ),
628
+ (
629
+ "[N:1]([C@:2]([C:3](=[O:4])[O-:15])([C:5]([C:6]1=[C:7]([H:19])[N-:9][c:10]2[c:8]1[c:11]([H:20])[c:13]([H:22])[c:14]([H:23])[c:12]2[H:21])([H:17])[H:18])[H:16])([H:24])[H:25]",
630
+ "[N:1]([C@:2]([C:3](=[O:4])[O-:15])([C:5]([C:6]1=[C:7]([H:19])[N:9][c:10]2[c:8]1[c:11]([H:20])[c:13]([H:22])[c:14]([H:23])[c:12]2[H:21])([H:17])[H:18])[H:16])([H:24])[H:25]",
631
+ ),
632
+ (
633
+ "[N:1]([C@:2]([C:3]=[O:4])([C:5]([C:6]1=[C:7]([H:18])[N-:9][c:10]2[c:8]1[c:11]([H:19])[c:13]([H:21])[c:14]([H:22])[c:12]2[H:20])([H:16])[H:17])[H:15])([H:23])[H:24]",
634
+ "[N:1]([C@:2]([C:3]=[O:4])([C:5]([C:6]1=[C:7]([H:18])[N:9][c:10]2[c:8]1[c:11]([H:19])[c:13]([H:21])[c:14]([H:22])[c:12]2[H:20])([H:16])[H:17])[H:15])([H:23])[H:24]",
635
+ ),
636
+ (
637
+ "[N+:1]([C@:2]([C:3](=[O:4])[O-:15])([C:5]([C:6]1=[C:7]([H:19])[N-:9][c:10]2[c:8]1[c:11]([H:20])[c:13]([H:22])[c:14]([H:23])[c:12]2[H:21])([H:17])[H:18])[H:16])([H:24])([H:25])[H:26]",
638
+ "[N+:1]([C@:2]([C:3](=[O:4])[O-:15])([C:5]([C:6]1=[C:7]([H:19])[N:9][c:10]2[c:8]1[c:11]([H:20])[c:13]([H:22])[c:14]([H:23])[c:12]2[H:21])([H:17])[H:18])[H:16])([H:24])([H:25])[H:26]",
639
+ ),
640
+ (
641
+ "[N+:1]([C@:2]([C:3]=[O:4])([C:5]([C:6]1=[C:7]([H:18])[N-:9][c:10]2[c:8]1[c:11]([H:19])[c:13]([H:21])[c:14]([H:22])[c:12]2[H:20])([H:16])[H:17])[H:15])([H:23])([H:24])[H:25]",
642
+ "[N+:1]([C@:2]([C:3]=[O:4])([C:5]([C:6]1=[C:7]([H:18])[N:9][c:10]2[c:8]1[c:11]([H:19])[c:13]([H:21])[c:14]([H:22])[c:12]2[H:20])([H:16])[H:17])[H:15])([H:23])([H:24])[H:25]",
643
+ ),
644
+ ],
645
+ }
646
+ # Fix PRO smarts substructure
647
+ for aa_name, replacement_list in substructures_to_fix.items():
648
+ for old_smarts, new_smarts in replacement_list:
649
+ self.data[aa_name][new_smarts] = self.data[aa_name][old_smarts]
650
+ self.data[aa_name].pop(old_smarts)
651
+
652
+ def _add_common_substructures(self):
653
+ """
654
+ .. warning: Needed as of Oct-21-2021
655
+ """
656
+
657
+ # Add common caps
658
+ self.data["ACE"] = {"[C:1](=[O:2])[C:3]([H:4])([H:5])[H:6]": ["C", "O", "CH3", "H1", "H2", "H3"]}
659
+ self.data["NME"] = {"[N:1]([C:2]([H:4])([H:5])[H:6])[H:3]": ["N", "C", "H", "H1", "H2", "H3"]}
660
+ self.data["NH2"] = {"[N:1]([H:2])[H:3]": ["N", "HN1", "HN2"]}
661
+
662
+ def _add_common_linkages(self):
663
+ """
664
+ .. warning: Needed as of Oct-21-2021
665
+ """
666
+
667
+ self.data["PEPTIDE_BOND"] = {
668
+ "[C:1](=[O:2])[N:3]": [
669
+ "C",
670
+ "O",
671
+ "N",
672
+ ]
673
+ }
674
+ self.data["DISULFIDE"] = {
675
+ "[S:1][S:2]": [
676
+ "SG",
677
+ "SG",
678
+ ]
679
+ }
680
+
681
+ def _reformat_substructs(self):
682
+ """
683
+ Implemented 7/7/23: add-on to existing substructure library to reformat amino acids
684
+ to a new format. Self contained for now to the following function:
685
+ """
686
+
687
+ def add_atom(
688
+ rdmol,
689
+ begin_atom_idx,
690
+ new_atom_smarts,
691
+ bond_order=Chem.rdchem.BondType.SINGLE,
692
+ ):
693
+ # adds atom with single bond, returns new mol
694
+ emol = Chem.RWMol(deepcopy(rdmol))
695
+ new_atom = Chem.AtomFromSmarts(new_atom_smarts)
696
+ idx = emol.AddAtom(new_atom)
697
+ assert idx == rdmol.GetNumAtoms()
698
+ emol.AddBond(begin_atom_idx, idx, order=bond_order)
699
+ return emol.GetMol()
700
+
701
+ def _get_maximum_map_num(rdmol):
702
+ return max([atom.GetAtomMapNum() for atom in rdmol.GetAtoms()])
703
+
704
+ def _fill_out_query(rdmol):
705
+ params = Chem.SmilesParserParams()
706
+ params.removeHs = False
707
+ params.sanitize = True
708
+ rdmol = Chem.MolFromSmiles(
709
+ Chem.MolToSmiles(
710
+ deepcopy(rdmol),
711
+ isomericSmiles=False,
712
+ kekuleSmiles=True,
713
+ canonical=False,
714
+ ),
715
+ params,
716
+ ) # create non-query version of substruct
717
+ Chem.Kekulize(rdmol, clearAromaticFlags=True) # kekulize using molops (regular molecule required here)
718
+ rdmol = Chem.MolFromSmarts(
719
+ Chem.MolToSmiles(
720
+ deepcopy(rdmol),
721
+ isomericSmiles=False,
722
+ kekuleSmiles=True,
723
+ canonical=False,
724
+ )
725
+ ) # remake into query mol
726
+ current_map_num = 1 + _get_maximum_map_num(rdmol) # do not change existing atom map numbers!
727
+ for atom in rdmol.GetAtoms():
728
+ if atom.GetAtomicNum() > 0:
729
+ if atom.GetAtomMapNum() == 0:
730
+ atom.SetAtomMapNum(current_map_num)
731
+ current_map_num += 1
732
+ atom.SetChiralTag(Chem.rdchem.ChiralType.CHI_UNSPECIFIED)
733
+ a_num = atom.GetAtomicNum()
734
+ D_num = len([0 for _ in atom.GetBonds()])
735
+ F_num = atom.GetFormalCharge()
736
+ query_string = f"[#{a_num}D{D_num}{F_num:+}:{current_map_num}]"
737
+ query = Chem.AtomFromSmarts(query_string)
738
+ atom.SetQuery(query)
739
+ elif atom.GetAtomicNum() == 0:
740
+ atom.SetAtomMapNum(current_map_num)
741
+ current_map_num += 1
742
+ query_string = f"[*:{current_map_num}]"
743
+ query = Chem.AtomFromSmarts(query_string)
744
+ atom.SetQuery(query)
745
+ else:
746
+ raise Exception
747
+ for bond in rdmol.GetBonds():
748
+ if bond.GetBondType() == Chem.rdchem.BondType.AROMATIC:
749
+ raise Exception # there should be no aromatic bonds unless kekulization has failed
750
+ elif bond.GetBondType() == Chem.rdchem.BondType.SINGLE:
751
+ query = Chem.BondFromSmarts("-")
752
+ bond.SetQuery(query)
753
+
754
+ return rdmol
755
+
756
+ def get_atom_with_map_num(rdmol, map_num):
757
+ for atom in rdmol.GetAtoms():
758
+ if atom.GetAtomMapNum() == map_num:
759
+ return atom
760
+ return None
761
+
762
+ def clear_query(rdmol):
763
+ for atom in rdmol.GetAtoms():
764
+ atom.SetAtomMapNum(0)
765
+ n = atom.GetAtomicNum()
766
+ c = atom.GetFormalCharge()
767
+ query_string = f"[#{n}{c:+}]"
768
+ query = Chem.AtomFromSmarts(query_string)
769
+ atom.SetQuery(query)
770
+
771
+ new_subs_dict = OrderedDict()
772
+ # = [(Smarts without terminal groups , [ids to add port to], [ids to add H to], [id of amide bond carbon])]
773
+ amino_acid_subs = [
774
+ (
775
+ Chem.MolFromSmarts(
776
+ "[N+:1](-[H])(-[H])1[C@@:2]([C:3](=[O:4]))([H:9])[C:5]([H:10])([H:11])[C:6]([H:12])([H:13])[C:7]1([H:14])[H:15]"
777
+ ),
778
+ [],
779
+ [],
780
+ 4,
781
+ ),
782
+ (
783
+ Chem.MolFromSmarts(
784
+ "[N+0:1](-[H])1[C@@:2]([C:3](=[O:4]))([H:9])[C:5]([H:10])([H:11])[C:6]([H:12])([H:13])[C:7]1([H:14])[H:15]"
785
+ ),
786
+ [],
787
+ [],
788
+ 3,
789
+ ),
790
+ (
791
+ Chem.MolFromSmarts(
792
+ "[N+1:1](-[H])1[C@@:2]([C:3](=[O:4]))([H:9])[C:5]([H:10])([H:11])[C:6]([H:12])([H:13])[C:7]1([H:14])[H:15]"
793
+ ),
794
+ [0],
795
+ [],
796
+ 3,
797
+ ),
798
+ (
799
+ Chem.MolFromSmarts(
800
+ "[N+0:1]1[C@@:2]([C:3](=[O:4]))([H:9])[C:5]([H:10])([H:11])[C:6]([H:12])([H:13])[C:7]1([H:14])[H:15]"
801
+ ),
802
+ [0],
803
+ [],
804
+ 2,
805
+ ),
806
+ (
807
+ Chem.MolFromSmarts(
808
+ "[N+](-[H])(-[H])(-[H])-[C@:2]([C:3](=[O:4]))([C:5]([S+0:6]([H]))([H:9])[H:10])[H:8]"
809
+ ),
810
+ [],
811
+ [],
812
+ 5,
813
+ ),
814
+ (
815
+ Chem.MolFromSmarts("[N+](-[H])(-[H])(-[H])-[C@:2]([C:3](=[O:4]))([C:5]([S+0:6])([H:9])[H:10])[H:8]"),
816
+ [8],
817
+ [],
818
+ 5,
819
+ ),
820
+ (
821
+ Chem.MolFromSmarts("[N+](-[H])(-[H])(-[H])-[C@:2]([C:3](=[O:4]))([C:5]([S-1:6])([H:9])[H:10])[H:8]"),
822
+ [],
823
+ [],
824
+ 5,
825
+ ),
826
+ (
827
+ Chem.MolFromSmarts("[N](-[H])(-[H])-[C@:2]([C:3](=[O:4]))([C:5]([S+0:6]([H]))([H:9])[H:10])[H:8]"),
828
+ [],
829
+ [],
830
+ 4,
831
+ ),
832
+ (
833
+ Chem.MolFromSmarts("[N](-[H])(-[H])-[C@:2]([C:3](=[O:4]))([C:5]([S+0:6])([H:9])[H:10])[H:8]"),
834
+ [7],
835
+ [],
836
+ 4,
837
+ ),
838
+ (
839
+ Chem.MolFromSmarts("[N](-[H])(-[H])-[C@:2]([C:3](=[O:4]))([C:5]([S-1:6])([H:9])[H:10])[H:8]"),
840
+ [],
841
+ [],
842
+ 4,
843
+ ),
844
+ (
845
+ Chem.MolFromSmarts("[N](-[H])-[C@:2]([C:3](=[O:4]))([C:5]([S+0:6]([H]))([H:9])[H:10])[H:8]"),
846
+ [0],
847
+ [],
848
+ 3,
849
+ ),
850
+ (
851
+ Chem.MolFromSmarts("[N](-[H])-[C@:2]([C:3](=[O:4]))([C:5]([S+0:6])([H:9])[H:10])[H:8]"),
852
+ [0, 6],
853
+ [],
854
+ 3,
855
+ ),
856
+ (
857
+ Chem.MolFromSmarts("[N](-[H])-[C@:2]([C:3](=[O:4]))([C:5]([S-1:6])([H:9])[H:10])[H:8]"),
858
+ [0],
859
+ [],
860
+ 3,
861
+ ),
862
+ (
863
+ Chem.MolFromSmarts("[N:1][C@:2]([C:3](=[O:4]))([C:5]([S+0:6]([H]))([H:9])[H:10])[H:8]"),
864
+ [0, 0],
865
+ [],
866
+ 2,
867
+ ),
868
+ (
869
+ Chem.MolFromSmarts("[N:1][C@:2]([C:3](=[O:4]))([C:5]([S+0:6])([H:9])[H:10])[H:8]"),
870
+ [0, 0, 5],
871
+ [],
872
+ 2,
873
+ ),
874
+ (
875
+ Chem.MolFromSmarts("[N:1][C@:2]([C:3](=[O:4]))([C:5]([S-1:6])([H:9])[H:10])[H:8]"),
876
+ [0, 0],
877
+ [],
878
+ 2,
879
+ ),
880
+ (
881
+ Chem.MolFromSmarts("[N+](-[H])(-[H])(-[H])-[C@](-[H])(-[*])-[C](=[O])"),
882
+ [],
883
+ [],
884
+ 7,
885
+ ),
886
+ (
887
+ Chem.MolFromSmarts("[N](-[H])(-[H])-[C@](-[H])(-[*])-[C](=[O])"),
888
+ [],
889
+ [],
890
+ 6,
891
+ ),
892
+ (Chem.MolFromSmarts("[N](-[H])-[C@](-[H])(-[*])-[C](=[O])"), [0], [], 5),
893
+ ]
894
+ special_cases = {
895
+ "[C:1](=[O:2])[C:3]([H:4])([H:5])[H:6]": "[*]-[C:1](=[O:2])[C:3]([H:4])([H:5])[H:6]",
896
+ "[N:1]([C:2]([H:4])([H:5])[H:6])[H:3]": "[*]-[N:1]([C:2]([H:4])([H:5])[H:6])[H:3]",
897
+ "[N:1]([H:2])[H:3]": "[*]-C(=O)[N:1]([H:2])[H:3]",
898
+ "[C:1](=[O:2])[N:3]": "[*]-[C:1](=[O:2])[N:3](-[H])[C:4](-[*])(-[*])(-[*])",
899
+ "[S:1][S:2]": "[*]-[S:1]-[S:2]-[*]",
900
+ }
901
+ for res_name, subs in self.data.items():
902
+ res_dict = OrderedDict()
903
+ res_num = 0
904
+ for substruct, atom_names in subs.items():
905
+ rdmol = Chem.MolFromSmarts(substruct)
906
+ old_rdmol = deepcopy(rdmol)
907
+ query = tuple()
908
+ add_port = []
909
+ add_Hs = []
910
+ carboxyl_C = -1
911
+ for query, add_port, add_Hs, carboxyl_C in amino_acid_subs:
912
+ aa_match = rdmol.GetSubstructMatch(query)
913
+ if aa_match:
914
+ break
915
+ if not aa_match and substruct not in special_cases.keys():
916
+ raise Exception(f"{res_name}, {substruct} has no match")
917
+ if substruct in special_cases.keys():
918
+ if special_cases[substruct]:
919
+ rdmol = Chem.MolFromSmarts(special_cases[substruct])
920
+ else: # empty, discard
921
+ continue
922
+ else:
923
+ # add * where appropriate
924
+ for port_idx in add_port:
925
+ rdmol = add_atom(rdmol, aa_match[port_idx], "[*]")
926
+ # add H where appropriate
927
+ for H_idx in add_Hs:
928
+ rdmol = add_atom(rdmol, aa_match[H_idx], "[H]")
929
+ # add port to carboxyl atom if needed
930
+ carb = rdmol.GetAtomWithIdx(aa_match[carboxyl_C])
931
+ if carb.GetDegree() == 2:
932
+ rdmol = add_atom(rdmol, aa_match[carboxyl_C], "[*]")
933
+ formated_rdmol = _fill_out_query(rdmol)
934
+ # In this document, the only new atoms I add are *, so edit the atom names
935
+ num_new_atoms = formated_rdmol.GetNumAtoms() - len(atom_names)
936
+ atom_names = atom_names + ["*"] * num_new_atoms
937
+ sub_smarts = Chem.MolToSmarts(formated_rdmol)
938
+ res_num += 1
939
+
940
+ sub_smarts = sub_smarts.replace("&", "")
941
+ res_dict[sub_smarts] = atom_names
942
+
943
+ new_subs_dict[res_name] = res_dict
944
+
945
+ # validate using toolkit validator to check
946
+ check_dict = dict()
947
+ for res_name, subs in new_subs_dict.items():
948
+ res_num = 0
949
+ for substruct, atom_names in subs.items():
950
+ check_dict[f"{res_name}_{res_num}"] = [substruct]
951
+ res_num += 1
952
+ RDKitToolkitWrapper()._validate_custom_substructures(
953
+ custom_substructures=check_dict, forbidden_keys=[]
954
+ ) # errors if any are invalid
955
+ self.data = new_subs_dict