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.
- devtools/scripts/build_cookiecutter_json.py +22 -0
- docs/conf.py +296 -0
- docs/conftest.py +23 -0
- examples/conformer_energies/conformer_energies.py +143 -0
- examples/deprecated/SMIRNOFF_comparison/compare_molecule_energies.py +48 -0
- examples/deprecated/SMIRNOFF_comparison/compare_set_energies.py +58 -0
- examples/deprecated/liquid_box/create_mol2_pdb/create_mol2_pdb.py +193 -0
- examples/deprecated/liquid_box/openff_simulation.py +72 -0
- examples/deprecated/mixedFF_structure/generate_mixedFF_complex.py +56 -0
- examples/deprecated/testing/test_impropers/tleap_tools.py +120 -0
- examples/examples_helper.py +61 -0
- openff/toolkit/__init__.py +101 -0
- openff/toolkit/_tests/__init__.py +0 -0
- openff/toolkit/_tests/_stale_tests.py +146 -0
- openff/toolkit/_tests/conftest.py +108 -0
- openff/toolkit/_tests/create_molecules.py +494 -0
- openff/toolkit/_tests/mocking.py +145 -0
- openff/toolkit/_tests/molecule/__init__.py +1 -0
- openff/toolkit/_tests/molecule/test_state_enumeration.py +302 -0
- openff/toolkit/_tests/test_energies.py +136 -0
- openff/toolkit/_tests/test_examples.py +109 -0
- openff/toolkit/_tests/test_forcefield.py +3864 -0
- openff/toolkit/_tests/test_interchange.py +19 -0
- openff/toolkit/_tests/test_io.py +19 -0
- openff/toolkit/_tests/test_links.py +73 -0
- openff/toolkit/_tests/test_mm_molecule.py +404 -0
- openff/toolkit/_tests/test_molecule.py +4246 -0
- openff/toolkit/_tests/test_nagl.py +169 -0
- openff/toolkit/_tests/test_parameter_plugins.py +89 -0
- openff/toolkit/_tests/test_parameters.py +2898 -0
- openff/toolkit/_tests/test_toolkit_io.py +1088 -0
- openff/toolkit/_tests/test_toolkits.py +4418 -0
- openff/toolkit/_tests/test_topology.py +2485 -0
- openff/toolkit/_tests/test_utils.py +101 -0
- openff/toolkit/_tests/test_utils_callback.py +178 -0
- openff/toolkit/_tests/test_utils_collections.py +263 -0
- openff/toolkit/_tests/test_utils_serialization.py +168 -0
- openff/toolkit/_tests/utils.py +1747 -0
- openff/toolkit/data/README.md +8 -0
- openff/toolkit/data/molecules/AlkEthOH_test_filt1_ff.mol2 +2026 -0
- openff/toolkit/data/molecules/AlkEthOH_test_filt1_tripos.mol2 +2026 -0
- openff/toolkit/data/molecules/AlkEthOH_tripos.tar.gz +0 -0
- openff/toolkit/data/molecules/CID20742535_anion.sdf +50 -0
- openff/toolkit/data/molecules/CID20742535_neutral.sdf +51 -0
- openff/toolkit/data/molecules/FreeSolv.tar.gz +0 -0
- openff/toolkit/data/molecules/MiniDrugBank.sdf +33988 -0
- openff/toolkit/data/molecules/MiniDrugBank_tripos.mol2 +35462 -0
- openff/toolkit/data/molecules/PT2385.sdf +90 -0
- openff/toolkit/data/molecules/QL8.sdf +401 -0
- openff/toolkit/data/molecules/README.md +21 -0
- openff/toolkit/data/molecules/benzene.crd +8 -0
- openff/toolkit/data/molecules/benzene.mol2 +34 -0
- openff/toolkit/data/molecules/benzene.top +166 -0
- openff/toolkit/data/molecules/butane_multi.sdf +231 -0
- openff/toolkit/data/molecules/cyclohexane.mol2 +44 -0
- openff/toolkit/data/molecules/ethanol.mol2 +25 -0
- openff/toolkit/data/molecules/ethanol.sdf +23 -0
- openff/toolkit/data/molecules/ethanol_partial_charges.sdf +26 -0
- openff/toolkit/data/molecules/ethanol_reordered.mol2 +25 -0
- openff/toolkit/data/molecules/ethanol_reordered.sdf +23 -0
- openff/toolkit/data/molecules/ethene_rdkit.sdf +17 -0
- openff/toolkit/data/molecules/laromustine_ff.mol2 +71 -0
- openff/toolkit/data/molecules/laromustine_tripos.mol2 +71 -0
- openff/toolkit/data/molecules/methane_multiconformer.sdf +32 -0
- openff/toolkit/data/molecules/methane_multiconformer_properties.sdf +45 -0
- openff/toolkit/data/molecules/nh4.pdb +7 -0
- openff/toolkit/data/molecules/po4_phenylphosphate.pdb +46 -0
- openff/toolkit/data/molecules/ruxolitinib_conformers.sdf +910 -0
- openff/toolkit/data/molecules/toluene.mol2 +38 -0
- openff/toolkit/data/molecules/toluene.mol2.gz +0 -0
- openff/toolkit/data/molecules/toluene.pdb +30 -0
- openff/toolkit/data/molecules/toluene.sdf +36 -0
- openff/toolkit/data/molecules/toluene_charged.mol2 +38 -0
- openff/toolkit/data/molecules/z_3_hydroxy_propenal.sdf +23 -0
- openff/toolkit/data/proteins/5tbm_complex_solv.pdb +1928 -0
- openff/toolkit/data/proteins/5tbm_complex_solv_box.pdb +19563 -0
- openff/toolkit/data/proteins/CTerminal_ALA.pdb +20 -0
- openff/toolkit/data/proteins/CTerminal_ALA.sdf +43 -0
- openff/toolkit/data/proteins/CTerminal_ALA_ALA.pdb +30 -0
- openff/toolkit/data/proteins/CTerminal_ALA_ALA_misnamedH.pdb +30 -0
- openff/toolkit/data/proteins/CTerminal_ARG.pdb +34 -0
- openff/toolkit/data/proteins/CTerminal_TRP.pdb +34 -0
- openff/toolkit/data/proteins/MainChain_ALA.pdb +25 -0
- openff/toolkit/data/proteins/MainChain_ALA.sdf +52 -0
- openff/toolkit/data/proteins/MainChain_ALA_ALA.pdb +35 -0
- openff/toolkit/data/proteins/MainChain_ALA_ALA.sdf +69 -0
- openff/toolkit/data/proteins/MainChain_ALA_ALA_icodes.pdb +35 -0
- openff/toolkit/data/proteins/MainChain_ALA_ALA_no_hydrogens.pdb +17 -0
- openff/toolkit/data/proteins/MainChain_ARG.pdb +39 -0
- openff/toolkit/data/proteins/MainChain_ARG.sdf +81 -0
- openff/toolkit/data/proteins/MainChain_CYM.pdb +25 -0
- openff/toolkit/data/proteins/MainChain_CYS.pdb +26 -0
- openff/toolkit/data/proteins/MainChain_CYX.pdb +48 -0
- openff/toolkit/data/proteins/MainChain_CYX.sdf +96 -0
- openff/toolkit/data/proteins/MainChain_GLH.sdf +64 -0
- openff/toolkit/data/proteins/MainChain_GLU.sdf +63 -0
- openff/toolkit/data/proteins/MainChain_HID.pdb +32 -0
- openff/toolkit/data/proteins/MainChain_HIE.pdb +32 -0
- openff/toolkit/data/proteins/MainChain_HIE.sdf +67 -0
- openff/toolkit/data/proteins/MainChain_HIP.pdb +33 -0
- openff/toolkit/data/proteins/MainChain_HIP.sdf +70 -0
- openff/toolkit/data/proteins/MainChain_PRO.pdb +29 -0
- openff/toolkit/data/proteins/MainChain_TRP.pdb +39 -0
- openff/toolkit/data/proteins/NTerminal_ALA.pdb +21 -0
- openff/toolkit/data/proteins/NTerminal_ALA.sdf +45 -0
- openff/toolkit/data/proteins/NTerminal_ALA_ALA.pdb +31 -0
- openff/toolkit/data/proteins/NTerminal_ARG.pdb +35 -0
- openff/toolkit/data/proteins/NTerminal_TRP.pdb +35 -0
- openff/toolkit/data/proteins/T4-protein-unprocessed-4w51.pdb +1892 -0
- openff/toolkit/data/proteins/T4-protein.mol2 +5461 -0
- openff/toolkit/data/proteins/T4-protein.pdb +2637 -0
- openff/toolkit/data/proteins/T4-protein.sdf +5318 -0
- openff/toolkit/data/proteins/T4_protein_waters.pdb +2965 -0
- openff/toolkit/data/proteins/TwoMol_SER_CYS.pdb +50 -0
- openff/toolkit/data/proteins/aa_residues_substructures_explicit_bond_orders_with_caps.json +6435 -0
- openff/toolkit/data/proteins/aa_residues_substructures_explicit_bond_orders_with_caps_explicit_connectivity.json +6675 -0
- openff/toolkit/data/proteins/aa_residues_substructures_with_caps.json +6297 -0
- openff/toolkit/data/proteins/ace-ZZZ-gly-nme.pdb +78 -0
- openff/toolkit/data/proteins/ace-ZZZ-gly-nme.sdf +98 -0
- openff/toolkit/data/proteins/ace-a10-nme.sdf +229 -0
- openff/toolkit/data/proteins/ace-ala-nh2.pdb +21 -0
- openff/toolkit/data/proteins/fluoresceine_dyed_helix_capped.pdb +338 -0
- openff/toolkit/data/proteins/neutral_arginine.pdb +31 -0
- openff/toolkit/data/proteins/split_chain.pdb +74 -0
- openff/toolkit/data/proteins/split_chain_reordered.pdb +74 -0
- openff/toolkit/data/reference_energies/README.md +6 -0
- openff/toolkit/data/reference_energies/reference_0.8.0.json +1 -0
- openff/toolkit/data/reference_energies/reference_0.8.0.json.txt +180 -0
- openff/toolkit/data/reference_energies/reference_after_1007.json +1 -0
- openff/toolkit/data/reference_energies/reference_after_1007.json.txt +350 -0
- openff/toolkit/data/reference_energies/reference_after_802.json +1 -0
- openff/toolkit/data/reference_energies/reference_after_802.json.txt +291 -0
- openff/toolkit/data/systems/README.md +3 -0
- openff/toolkit/data/systems/amber/cyclohexane_ethanol_0.4_0.6.inpcrd +1511 -0
- openff/toolkit/data/systems/amber/cyclohexane_ethanol_0.4_0.6.prmtop +13367 -0
- openff/toolkit/data/systems/monomers/butanol.mol2 +38 -0
- openff/toolkit/data/systems/monomers/butanol.sdf +88 -0
- openff/toolkit/data/systems/monomers/cyclohexane.mol2 +45 -0
- openff/toolkit/data/systems/monomers/cyclohexane.sdf +105 -0
- openff/toolkit/data/systems/monomers/ethanol.mol2 +26 -0
- openff/toolkit/data/systems/monomers/ethanol.sdf +58 -0
- openff/toolkit/data/systems/monomers/methane.mol2 +18 -0
- openff/toolkit/data/systems/monomers/methane.sdf +38 -0
- openff/toolkit/data/systems/monomers/propane.mol2 +30 -0
- openff/toolkit/data/systems/monomers/propane.sdf +68 -0
- openff/toolkit/data/systems/monomers/tip3p_water.mol2 +14 -0
- openff/toolkit/data/systems/monomers/water.mol2 +14 -0
- openff/toolkit/data/systems/monomers/water.sdf +28 -0
- openff/toolkit/data/systems/packmol_boxes/cyclohexane_ethanol_0.4_0.6.pdb +6272 -0
- openff/toolkit/data/systems/packmol_boxes/cyclohexane_water.pdb +5524 -0
- openff/toolkit/data/systems/packmol_boxes/ethanol_water.pdb +5174 -0
- openff/toolkit/data/systems/packmol_boxes/propane_methane_butanol_0.2_0.3_0.5.pdb +7959 -0
- openff/toolkit/data/systems/test_systems/1_cyclohexane_1_ethanol.pdb +61 -0
- openff/toolkit/data/systems/test_systems/1_ethanol.pdb +24 -0
- openff/toolkit/data/systems/test_systems/1_ethanol_no_conect.pdb +15 -0
- openff/toolkit/data/systems/test_systems/1_ethanol_reordered.pdb +24 -0
- openff/toolkit/data/systems/test_systems/PE.pdb +67 -0
- openff/toolkit/data/systems/test_systems/README.md +3 -0
- openff/toolkit/data/systems/test_systems/T4_lysozyme_water_ions.pdb +29240 -0
- openff/toolkit/data/test_forcefields/Frosst_AlkEthOH.offxml +61 -0
- openff/toolkit/data/test_forcefields/Frosst_AlkEthOH_GBSA.offxml +78 -0
- openff/toolkit/data/test_forcefields/Frosst_AlkEthOH_MDL.offxml +62 -0
- openff/toolkit/data/test_forcefields/Frosst_AlkEthOH_parmAtFrosst.offxml +64 -0
- openff/toolkit/data/test_forcefields/GBSA_HCT-1.0.offxml +21 -0
- openff/toolkit/data/test_forcefields/GBSA_OBC1-1.0.offxml +18 -0
- openff/toolkit/data/test_forcefields/GBSA_OBC2-1.0.offxml +18 -0
- openff/toolkit/data/test_forcefields/README.md +23 -0
- openff/toolkit/data/test_forcefields/ammonia_minimal.offxml +27 -0
- openff/toolkit/data/test_forcefields/benzene_minimal.offxml +29 -0
- openff/toolkit/data/test_forcefields/chargeincrement-test.offxml +16 -0
- openff/toolkit/data/test_forcefields/frcmod.Frosst_AlkEthOH_withIDs +85 -0
- openff/toolkit/data/test_forcefields/ion_charges.offxml +18 -0
- openff/toolkit/data/test_forcefields/mangled.offxml +9 -0
- openff/toolkit/data/test_forcefields/old/README.md +9 -0
- openff/toolkit/data/test_forcefields/old/hbonds.offxml +11 -0
- openff/toolkit/data/test_forcefields/old/test_ff_0_0_2_spec_0_1.offxml +332 -0
- openff/toolkit/data/test_forcefields/old/test_ff_0_0_2_spec_0_2.offxml +338 -0
- openff/toolkit/data/test_forcefields/old/test_ff_0_0_2_spec_0_3.offxml +329 -0
- openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_fixed_spec_0_1.offxml +342 -0
- openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_fixed_spec_0_2.offxml +348 -0
- openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_fixed_spec_0_3.offxml +337 -0
- openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_spec_0_1.offxml +340 -0
- openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_spec_0_2.offxml +346 -0
- openff/toolkit/data/test_forcefields/old/test_ff_0_0_4_spec_0_3.offxml +337 -0
- openff/toolkit/data/test_forcefields/smirff99Frosst_reference_0_1_spec.offxml +349 -0
- openff/toolkit/data/test_forcefields/smirnoff99Frosst_experimental.offxml +343 -0
- openff/toolkit/data/test_forcefields/smirnoff99Frosst_reference_0_1_spec.offxml +349 -0
- openff/toolkit/data/test_forcefields/smirnoff99Frosst_reference_0_2_spec.offxml +356 -0
- openff/toolkit/data/test_forcefields/test_forcefield.offxml +346 -0
- openff/toolkit/data/test_forcefields/tip3p.offxml +22 -0
- openff/toolkit/data/test_forcefields/unsupported_smirnoff_version.offxml +9 -0
- openff/toolkit/topology/__init__.py +43 -0
- openff/toolkit/topology/_mm_molecule.py +663 -0
- openff/toolkit/topology/molecule.py +6102 -0
- openff/toolkit/topology/topology.py +2555 -0
- openff/toolkit/typing/__init__.py +1 -0
- openff/toolkit/typing/engines/__init__.py +1 -0
- openff/toolkit/typing/engines/smirnoff/__init__.py +31 -0
- openff/toolkit/typing/engines/smirnoff/forcefield.py +1440 -0
- openff/toolkit/typing/engines/smirnoff/io.py +234 -0
- openff/toolkit/typing/engines/smirnoff/parameters.py +3839 -0
- openff/toolkit/typing/engines/smirnoff/plugins.py +91 -0
- openff/toolkit/utils/__init__.py +57 -0
- openff/toolkit/utils/_viz.py +104 -0
- openff/toolkit/utils/ambertools_wrapper.py +507 -0
- openff/toolkit/utils/base_wrapper.py +268 -0
- openff/toolkit/utils/builtin_wrapper.py +136 -0
- openff/toolkit/utils/callback.py +187 -0
- openff/toolkit/utils/collections.py +247 -0
- openff/toolkit/utils/constants.py +18 -0
- openff/toolkit/utils/exceptions.py +766 -0
- openff/toolkit/utils/nagl_wrapper.py +164 -0
- openff/toolkit/utils/openeye_wrapper.py +2750 -0
- openff/toolkit/utils/rdkit_wrapper.py +3302 -0
- openff/toolkit/utils/serialization.py +466 -0
- openff/toolkit/utils/toolkit_registry.py +509 -0
- openff/toolkit/utils/toolkits.py +217 -0
- openff/toolkit/utils/utils.py +805 -0
- openff_toolkit-0.18.0.dist-info/METADATA +109 -0
- openff_toolkit-0.18.0.dist-info/RECORD +231 -0
- openff_toolkit-0.18.0.dist-info/WHEEL +5 -0
- openff_toolkit-0.18.0.dist-info/licenses/LICENSE +21 -0
- openff_toolkit-0.18.0.dist-info/top_level.txt +5 -0
- utilities/deprecated/convert_frosst/convert_frcmod_0.1.py +251 -0
- utilities/deprecated/convert_frosst/convert_frcmod_0.2.py +249 -0
- utilities/deprecated/convert_frosst/convert_frcmod_0.3.py +249 -0
- utilities/make_substructure_dict/_cif_to_substructure_dict.py +955 -0
- utilities/make_substructure_dict/_make_chemical_substructures.py +46 -0
- utilities/make_substructure_dict/_make_metadata_assignment_substructures.py +35 -0
- utilities/test_plugins/custom_plugins/handler_plugins.py +48 -0
- utilities/test_plugins/setup.py +19 -0
|
@@ -0,0 +1,302 @@
|
|
|
1
|
+
import pytest
|
|
2
|
+
|
|
3
|
+
from openff.toolkit import Molecule
|
|
4
|
+
from openff.toolkit._tests.utils import requires_openeye
|
|
5
|
+
from openff.toolkit.utils.toolkits import OpenEyeToolkitWrapper, RDKitToolkitWrapper
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
class TestTautomerEnumeration:
|
|
9
|
+
tautomer_data = [
|
|
10
|
+
{"molecule": "Oc1c(cccc3)c3nc2ccncc12", "tautomers": 2},
|
|
11
|
+
{"molecule": "CN=c1nc[nH]cc1", "tautomers": 2},
|
|
12
|
+
{"molecule": "c1[nH]c2c(=O)[nH]c(nc2n1)N", "tautomers": 14},
|
|
13
|
+
]
|
|
14
|
+
|
|
15
|
+
@pytest.mark.parametrize("toolkit_class", [OpenEyeToolkitWrapper, RDKitToolkitWrapper])
|
|
16
|
+
@pytest.mark.parametrize("molecule_data", tautomer_data)
|
|
17
|
+
def test_enumerating_tautomers(self, molecule_data, toolkit_class):
|
|
18
|
+
"""Test the ability of each toolkit to produce tautomers of an input molecule."""
|
|
19
|
+
|
|
20
|
+
if toolkit_class.is_available():
|
|
21
|
+
toolkit = toolkit_class()
|
|
22
|
+
mol = Molecule.from_smiles(
|
|
23
|
+
molecule_data["molecule"],
|
|
24
|
+
allow_undefined_stereo=True,
|
|
25
|
+
toolkit_registry=toolkit,
|
|
26
|
+
)
|
|
27
|
+
|
|
28
|
+
tautomers = mol.enumerate_tautomers(toolkit_registry=toolkit)
|
|
29
|
+
|
|
30
|
+
assert len(tautomers) == molecule_data["tautomers"]
|
|
31
|
+
assert mol not in tautomers
|
|
32
|
+
# check that the molecules are not isomorphic of the input
|
|
33
|
+
for taut in tautomers:
|
|
34
|
+
assert taut.n_conformers == 0
|
|
35
|
+
assert mol.is_isomorphic_with(taut) is False
|
|
36
|
+
|
|
37
|
+
else:
|
|
38
|
+
pytest.skip("Required toolkit is unavailable")
|
|
39
|
+
|
|
40
|
+
@pytest.mark.parametrize("toolkit_class", [OpenEyeToolkitWrapper, RDKitToolkitWrapper])
|
|
41
|
+
def test_enumerating_tautomers_options(self, toolkit_class):
|
|
42
|
+
"""Test the enumeration options"""
|
|
43
|
+
|
|
44
|
+
if toolkit_class.is_available():
|
|
45
|
+
toolkit = toolkit_class()
|
|
46
|
+
# test the max molecules option
|
|
47
|
+
mol = Molecule.from_smiles(
|
|
48
|
+
"c1[nH]c2c(=O)[nH]c(nc2n1)N",
|
|
49
|
+
toolkit_registry=toolkit,
|
|
50
|
+
allow_undefined_stereo=True,
|
|
51
|
+
)
|
|
52
|
+
|
|
53
|
+
tauts_no = 5
|
|
54
|
+
tautomers = mol.enumerate_tautomers(max_states=tauts_no, toolkit_registry=toolkit)
|
|
55
|
+
assert len(tautomers) <= tauts_no
|
|
56
|
+
assert mol not in tautomers
|
|
57
|
+
|
|
58
|
+
@pytest.mark.parametrize("toolkit_class", [RDKitToolkitWrapper, OpenEyeToolkitWrapper])
|
|
59
|
+
def test_enumerating_no_tautomers(self, toolkit_class):
|
|
60
|
+
"""Test that the toolkits return an empty list if there are no tautomers to enumerate."""
|
|
61
|
+
|
|
62
|
+
if toolkit_class.is_available():
|
|
63
|
+
toolkit = toolkit_class()
|
|
64
|
+
mol = Molecule.from_smiles("CC", toolkit_registry=toolkit)
|
|
65
|
+
|
|
66
|
+
tautomers = mol.enumerate_tautomers(toolkit_registry=toolkit)
|
|
67
|
+
assert tautomers == []
|
|
68
|
+
|
|
69
|
+
else:
|
|
70
|
+
pytest.skip("Required toolkit is unavailable")
|
|
71
|
+
|
|
72
|
+
|
|
73
|
+
class TestProtomerEnumeration:
|
|
74
|
+
@requires_openeye
|
|
75
|
+
def test_enumerating_no_protomers(self):
|
|
76
|
+
"""Make sure the input molecule is returned when there is only one protomer."""
|
|
77
|
+
|
|
78
|
+
mol = Molecule.from_smiles("CC")
|
|
79
|
+
|
|
80
|
+
assert len(mol.enumerate_protomers()) == 1
|
|
81
|
+
assert mol.enumerate_protomers()[0] == mol
|
|
82
|
+
|
|
83
|
+
@requires_openeye
|
|
84
|
+
def test_enumerating_protomers(self):
|
|
85
|
+
"""Test enumerating the formal charges."""
|
|
86
|
+
|
|
87
|
+
# there should be three protomers, in addition to the input state
|
|
88
|
+
mol = Molecule.from_smiles("Oc2ccc(c1ccncc1)cc2")
|
|
89
|
+
|
|
90
|
+
protomers = mol.enumerate_protomers()
|
|
91
|
+
|
|
92
|
+
assert mol in protomers
|
|
93
|
+
assert len(protomers) == 4
|
|
94
|
+
|
|
95
|
+
# make sure generating extra states produces the same result
|
|
96
|
+
assert len(protomers) == len(mol.enumerate_protomers(max_states=10))
|
|
97
|
+
|
|
98
|
+
# make sure each protomer is unique
|
|
99
|
+
assert len(protomers) == len(set(protomers))
|
|
100
|
+
|
|
101
|
+
@requires_openeye
|
|
102
|
+
def test_tetracarboxylic_acid(self):
|
|
103
|
+
acid = Molecule.from_smiles("C(C(=O)O)(C(=O)O)=C(C(=O)O)(C(=O)O)")
|
|
104
|
+
|
|
105
|
+
protomers = acid.enumerate_protomers()
|
|
106
|
+
|
|
107
|
+
assert len(protomers) == 16
|
|
108
|
+
assert acid in protomers
|
|
109
|
+
|
|
110
|
+
@requires_openeye
|
|
111
|
+
def test_bad_state_not_necessarily_in_output(self):
|
|
112
|
+
# Quacpac considers NH4+ and NH3 to be valid states with default charge enumeration settings,
|
|
113
|
+
# but (reasonably enough) does not consider NH2- to be a valid state. Using any of these states
|
|
114
|
+
# as an input, the result should be 2 protomers (cation and neutral) unless `max_states=1`
|
|
115
|
+
cation = Molecule.from_smiles("[NH4+]")
|
|
116
|
+
neutral = Molecule.from_smiles("[NH3]")
|
|
117
|
+
anion = Molecule.from_smiles("[NH2-]")
|
|
118
|
+
|
|
119
|
+
for molecule in [cation, neutral, anion]:
|
|
120
|
+
assert len(molecule.enumerate_protomers(max_states=3)) == 2
|
|
121
|
+
assert len(molecule.enumerate_protomers(max_states=1)) == 1
|
|
122
|
+
|
|
123
|
+
protomers = molecule.enumerate_protomers()
|
|
124
|
+
|
|
125
|
+
assert len(protomers) == 2
|
|
126
|
+
|
|
127
|
+
assert cation in molecule.enumerate_protomers()
|
|
128
|
+
assert neutral in molecule.enumerate_protomers()
|
|
129
|
+
assert anion not in molecule.enumerate_protomers()
|
|
130
|
+
|
|
131
|
+
@pytest.mark.slow
|
|
132
|
+
@requires_openeye
|
|
133
|
+
def test_many_protomers(self):
|
|
134
|
+
acid = Molecule.from_smiles(5 * "C(C(=O)O)(C(=O)O)")
|
|
135
|
+
|
|
136
|
+
protomers = acid.enumerate_protomers()
|
|
137
|
+
|
|
138
|
+
assert acid in protomers
|
|
139
|
+
assert len(protomers) == 1600
|
|
140
|
+
|
|
141
|
+
|
|
142
|
+
class TestStereoisomerEnumeration:
|
|
143
|
+
@pytest.mark.parametrize("toolkit_class", [OpenEyeToolkitWrapper, RDKitToolkitWrapper])
|
|
144
|
+
def test_enumerating_stereobonds(self, toolkit_class):
|
|
145
|
+
"""Test the backend toolkits in enumerating the stereo bonds in a molecule."""
|
|
146
|
+
|
|
147
|
+
if toolkit_class.is_available():
|
|
148
|
+
toolkit = toolkit_class()
|
|
149
|
+
mol = Molecule.from_smiles("ClC=CCl", allow_undefined_stereo=True, toolkit_registry=toolkit)
|
|
150
|
+
|
|
151
|
+
# use the default options
|
|
152
|
+
isomers = mol.enumerate_stereoisomers()
|
|
153
|
+
assert len(isomers) == 2
|
|
154
|
+
|
|
155
|
+
assert mol not in isomers
|
|
156
|
+
# make sure the input molecule is only different by bond stereo
|
|
157
|
+
for ismol in isomers:
|
|
158
|
+
assert (
|
|
159
|
+
Molecule.are_isomorphic(
|
|
160
|
+
mol,
|
|
161
|
+
ismol,
|
|
162
|
+
return_atom_map=False,
|
|
163
|
+
bond_stereochemistry_matching=False,
|
|
164
|
+
)[0]
|
|
165
|
+
is True
|
|
166
|
+
)
|
|
167
|
+
assert mol.is_isomorphic_with(ismol) is False
|
|
168
|
+
|
|
169
|
+
# make sure the isomers are different
|
|
170
|
+
assert isomers[0].is_isomorphic_with(isomers[1]) is False
|
|
171
|
+
|
|
172
|
+
else:
|
|
173
|
+
pytest.skip("Required toolkit is unavailable")
|
|
174
|
+
|
|
175
|
+
@pytest.mark.parametrize("toolkit_class", [OpenEyeToolkitWrapper, RDKitToolkitWrapper])
|
|
176
|
+
def test_enumerating_stereocenters(self, toolkit_class):
|
|
177
|
+
"""Test the backend toolkits in enumerating the stereo centers in a molecule."""
|
|
178
|
+
|
|
179
|
+
if toolkit_class.is_available():
|
|
180
|
+
toolkit = toolkit_class()
|
|
181
|
+
mol = Molecule.from_smiles("NC(Cl)(F)O", toolkit_registry=toolkit, allow_undefined_stereo=True)
|
|
182
|
+
|
|
183
|
+
isomers = mol.enumerate_stereoisomers(toolkit_registry=toolkit)
|
|
184
|
+
|
|
185
|
+
assert len(isomers) == 2
|
|
186
|
+
# make sure the mol is not in the isomers and that they only differ by stereo chem
|
|
187
|
+
assert mol not in isomers
|
|
188
|
+
for ismol in isomers:
|
|
189
|
+
assert ismol.n_conformers != 0
|
|
190
|
+
assert (
|
|
191
|
+
Molecule.are_isomorphic(
|
|
192
|
+
mol,
|
|
193
|
+
ismol,
|
|
194
|
+
return_atom_map=False,
|
|
195
|
+
atom_stereochemistry_matching=False,
|
|
196
|
+
)[0]
|
|
197
|
+
is True
|
|
198
|
+
)
|
|
199
|
+
assert mol.is_isomorphic_with(ismol) is False
|
|
200
|
+
|
|
201
|
+
# make sure the two isomers are different
|
|
202
|
+
assert isomers[0].is_isomorphic_with(isomers[1]) is False
|
|
203
|
+
|
|
204
|
+
else:
|
|
205
|
+
pytest.skip("Required toolkit is unavailable")
|
|
206
|
+
|
|
207
|
+
@pytest.mark.parametrize("toolkit_class", [OpenEyeToolkitWrapper, RDKitToolkitWrapper])
|
|
208
|
+
def test_enumerating_stereo_options(self, toolkit_class):
|
|
209
|
+
"""Test the enumerating stereo chem options"""
|
|
210
|
+
|
|
211
|
+
if toolkit_class.is_available():
|
|
212
|
+
toolkit = toolkit_class()
|
|
213
|
+
|
|
214
|
+
# test undefined only
|
|
215
|
+
mol = Molecule.from_smiles("ClC=CCl", toolkit_registry=toolkit, allow_undefined_stereo=True)
|
|
216
|
+
isomers = mol.enumerate_stereoisomers(undefined_only=True, rationalise=False)
|
|
217
|
+
|
|
218
|
+
assert len(isomers) == 2
|
|
219
|
+
for isomer in isomers:
|
|
220
|
+
assert isomer.n_conformers == 0
|
|
221
|
+
|
|
222
|
+
mol = Molecule.from_smiles(r"Cl/C=C\Cl", toolkit_registry=toolkit, allow_undefined_stereo=True)
|
|
223
|
+
isomers = mol.enumerate_stereoisomers(undefined_only=True, rationalise=False)
|
|
224
|
+
|
|
225
|
+
assert isomers == []
|
|
226
|
+
|
|
227
|
+
mol = Molecule.from_smiles(r"Cl/C=C\Cl", toolkit_registry=toolkit, allow_undefined_stereo=True)
|
|
228
|
+
isomers = mol.enumerate_stereoisomers(undefined_only=False, rationalise=False)
|
|
229
|
+
|
|
230
|
+
assert len(isomers) == 1
|
|
231
|
+
|
|
232
|
+
# test max isomers
|
|
233
|
+
mol = Molecule.from_smiles(
|
|
234
|
+
"BrC=C[C@H]1OC(C2)(F)C2(Cl)C1",
|
|
235
|
+
toolkit_registry=toolkit,
|
|
236
|
+
allow_undefined_stereo=True,
|
|
237
|
+
)
|
|
238
|
+
isomers = mol.enumerate_stereoisomers(
|
|
239
|
+
max_isomers=5,
|
|
240
|
+
undefined_only=True,
|
|
241
|
+
toolkit_registry=toolkit,
|
|
242
|
+
rationalise=True,
|
|
243
|
+
)
|
|
244
|
+
|
|
245
|
+
assert len(isomers) <= 5
|
|
246
|
+
for isomer in isomers:
|
|
247
|
+
assert isomer.n_conformers == 1
|
|
248
|
+
|
|
249
|
+
else:
|
|
250
|
+
pytest.skip("Required toolkit is unavailable")
|
|
251
|
+
|
|
252
|
+
@pytest.mark.parametrize("toolkit_class", [OpenEyeToolkitWrapper, RDKitToolkitWrapper])
|
|
253
|
+
@pytest.mark.parametrize(
|
|
254
|
+
"smiles, undefined_only, expected",
|
|
255
|
+
[
|
|
256
|
+
(
|
|
257
|
+
"FC(Br)(Cl)[C@@H](Br)(Cl)",
|
|
258
|
+
False,
|
|
259
|
+
[
|
|
260
|
+
"F[C@](Br)(Cl)[C@@H](Br)(Cl)",
|
|
261
|
+
"F[C@](Br)(Cl)[C@H](Br)(Cl)",
|
|
262
|
+
"F[C@@](Br)(Cl)[C@@H](Br)(Cl)",
|
|
263
|
+
"F[C@@](Br)(Cl)[C@H](Br)(Cl)",
|
|
264
|
+
],
|
|
265
|
+
),
|
|
266
|
+
(
|
|
267
|
+
"FC(Br)(Cl)[C@@H](Br)(Cl)",
|
|
268
|
+
True,
|
|
269
|
+
["F[C@](Br)(Cl)[C@@H](Br)(Cl)", "F[C@@](Br)(Cl)[C@@H](Br)(Cl)"],
|
|
270
|
+
),
|
|
271
|
+
("F[C@H](Cl)Br", False, ["F[C@@H](Cl)Br"]),
|
|
272
|
+
("F[C@H](Cl)Br", True, []),
|
|
273
|
+
],
|
|
274
|
+
)
|
|
275
|
+
def test_enumerating_stereo_partially_defined(self, toolkit_class, smiles, undefined_only, expected):
|
|
276
|
+
"""Test the enumerating stereo of molecules with partially defined chirality"""
|
|
277
|
+
|
|
278
|
+
if not toolkit_class.is_available():
|
|
279
|
+
pytest.skip("Required toolkit is unavailable")
|
|
280
|
+
|
|
281
|
+
toolkit = toolkit_class()
|
|
282
|
+
|
|
283
|
+
# test undefined only
|
|
284
|
+
mol = Molecule.from_smiles(smiles, toolkit_registry=toolkit, allow_undefined_stereo=True)
|
|
285
|
+
stereoisomers = mol.enumerate_stereoisomers(undefined_only=undefined_only, rationalise=False)
|
|
286
|
+
|
|
287
|
+
# Ensure that the results of the enumeration are what the test expects.
|
|
288
|
+
# This roundtrips the expected output from SMILES --> OFFMol --> SMILES,
|
|
289
|
+
# since the SMILES for stereoisomers generated in this test may change depending
|
|
290
|
+
# on which cheminformatics toolkit is used.
|
|
291
|
+
expected = {
|
|
292
|
+
Molecule.from_smiles(stereoisomer, allow_undefined_stereo=True).to_smiles(
|
|
293
|
+
explicit_hydrogens=True, isomeric=True, mapped=False
|
|
294
|
+
)
|
|
295
|
+
for stereoisomer in expected
|
|
296
|
+
}
|
|
297
|
+
actual = {
|
|
298
|
+
stereoisomer.to_smiles(explicit_hydrogens=True, isomeric=True, mapped=False)
|
|
299
|
+
for stereoisomer in stereoisomers
|
|
300
|
+
}
|
|
301
|
+
|
|
302
|
+
assert expected == actual
|
|
@@ -0,0 +1,136 @@
|
|
|
1
|
+
import json
|
|
2
|
+
|
|
3
|
+
import numpy as np
|
|
4
|
+
import openmm
|
|
5
|
+
import pytest
|
|
6
|
+
from openff.units.openmm import to_openmm
|
|
7
|
+
from openmm import unit as openmm_unit
|
|
8
|
+
|
|
9
|
+
from openff.toolkit._tests.utils import get_data_file_path, requires_rdkit
|
|
10
|
+
from openff.toolkit.topology import Molecule, Topology
|
|
11
|
+
from openff.toolkit.typing.engines.smirnoff import ForceField
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
@requires_rdkit
|
|
15
|
+
@pytest.mark.parametrize("constrained", [True, False])
|
|
16
|
+
@pytest.mark.parametrize(
|
|
17
|
+
"mol",
|
|
18
|
+
[
|
|
19
|
+
"ethanol.sdf",
|
|
20
|
+
"methane_multiconformer.sdf",
|
|
21
|
+
"CID20742535_anion.sdf",
|
|
22
|
+
],
|
|
23
|
+
)
|
|
24
|
+
def test_reference(constrained, mol):
|
|
25
|
+
"""Minimal regression test comparing molecule energies to energies computed
|
|
26
|
+
by version 0.8.0 of the toolkit"""
|
|
27
|
+
# TODO: Also test periodic vs. vacuum
|
|
28
|
+
with open(get_data_file_path("reference_energies/reference_after_1007.json")) as fi:
|
|
29
|
+
reference = json.loads(fi.read())
|
|
30
|
+
|
|
31
|
+
name = mol + "_"
|
|
32
|
+
if not constrained:
|
|
33
|
+
name += "un"
|
|
34
|
+
name += "constrained"
|
|
35
|
+
reference_energy = reference[name]
|
|
36
|
+
|
|
37
|
+
omm_sys, positions, off_top = _build_system(
|
|
38
|
+
mol=mol,
|
|
39
|
+
constrained=constrained,
|
|
40
|
+
)
|
|
41
|
+
|
|
42
|
+
simulation = _build_simulation(omm_sys=omm_sys, off_top=off_top)
|
|
43
|
+
derived_energy = _get_energy(simulation=simulation, positions=positions)
|
|
44
|
+
|
|
45
|
+
np.testing.assert_almost_equal(
|
|
46
|
+
actual=derived_energy.value_in_unit(openmm_unit.kilojoule_per_mole),
|
|
47
|
+
desired=reference_energy,
|
|
48
|
+
decimal=5,
|
|
49
|
+
)
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
def generate_reference():
|
|
53
|
+
"""Function to generate reference files, if this script is called directly by a Python interpreter.
|
|
54
|
+
This is ignored by pytest while running tests."""
|
|
55
|
+
reference = dict()
|
|
56
|
+
for mol in [
|
|
57
|
+
"ethanol.sdf",
|
|
58
|
+
"methane_multiconformer.sdf",
|
|
59
|
+
"CID20742535_anion.sdf",
|
|
60
|
+
]:
|
|
61
|
+
for constrained in [True, False]:
|
|
62
|
+
omm_sys, positions, off_top = _build_system(
|
|
63
|
+
mol=mol,
|
|
64
|
+
constrained=constrained,
|
|
65
|
+
)
|
|
66
|
+
|
|
67
|
+
simulation = _build_simulation(omm_sys=omm_sys, off_top=off_top)
|
|
68
|
+
energy = _get_energy(simulation=simulation, positions=positions)
|
|
69
|
+
|
|
70
|
+
name = mol + "_"
|
|
71
|
+
if not constrained:
|
|
72
|
+
name += "un"
|
|
73
|
+
name += "constrained"
|
|
74
|
+
reference.update({name: energy.value_in_unit(openmm_unit.kilojoule_per_mole)})
|
|
75
|
+
|
|
76
|
+
import openff.toolkit
|
|
77
|
+
|
|
78
|
+
toolkit_version = openff.toolkit.__version__
|
|
79
|
+
|
|
80
|
+
with open(f"reference_{toolkit_version}.json", "w") as json_out:
|
|
81
|
+
json.dump(reference, json_out)
|
|
82
|
+
|
|
83
|
+
|
|
84
|
+
def _build_system(mol, constrained):
|
|
85
|
+
if constrained:
|
|
86
|
+
parsley = ForceField("openff-1.0.0.offxml")
|
|
87
|
+
else:
|
|
88
|
+
parsley = ForceField("openff_unconstrained-1.0.0.offxml")
|
|
89
|
+
|
|
90
|
+
mol = Molecule.from_file(get_data_file_path("molecules/" + mol), file_format="sdf")
|
|
91
|
+
|
|
92
|
+
if type(mol) is Molecule:
|
|
93
|
+
off_top = mol.to_topology()
|
|
94
|
+
positions = mol.conformers[0]
|
|
95
|
+
elif type(mol) is list:
|
|
96
|
+
# methane_multiconformer case is a list of two mols
|
|
97
|
+
off_top = Topology()
|
|
98
|
+
for mol_i in mol:
|
|
99
|
+
off_top.add_molecule(mol_i)
|
|
100
|
+
positions = np.vstack([mol[0].conformers[0], mol[1].conformers[0]])
|
|
101
|
+
|
|
102
|
+
from openff.toolkit.utils.toolkits import (
|
|
103
|
+
AmberToolsToolkitWrapper,
|
|
104
|
+
RDKitToolkitWrapper,
|
|
105
|
+
ToolkitRegistry,
|
|
106
|
+
)
|
|
107
|
+
|
|
108
|
+
toolkit_registry = ToolkitRegistry(toolkit_precedence=[RDKitToolkitWrapper, AmberToolsToolkitWrapper])
|
|
109
|
+
|
|
110
|
+
omm_sys = parsley.create_openmm_system(off_top, toolkit_registry=toolkit_registry)
|
|
111
|
+
|
|
112
|
+
return omm_sys, positions, off_top
|
|
113
|
+
|
|
114
|
+
|
|
115
|
+
def _build_simulation(omm_sys, off_top):
|
|
116
|
+
"""Given an OpenMM System, initialize a barebones OpenMM Simulation."""
|
|
117
|
+
# Use OpenMM to compute initial and minimized energy for all conformers
|
|
118
|
+
integrator = openmm.VerletIntegrator(1 * openmm_unit.femtoseconds)
|
|
119
|
+
platform = openmm.Platform.getPlatformByName("Reference")
|
|
120
|
+
omm_top = off_top.to_openmm()
|
|
121
|
+
simulation = openmm.app.Simulation(omm_top, omm_sys, integrator, platform)
|
|
122
|
+
|
|
123
|
+
return simulation
|
|
124
|
+
|
|
125
|
+
|
|
126
|
+
def _get_energy(simulation, positions):
|
|
127
|
+
"""Given an OpenMM simulation and position, return its energy"""
|
|
128
|
+
simulation.context.setPositions(to_openmm(positions))
|
|
129
|
+
state = simulation.context.getState(getEnergy=True, getPositions=True)
|
|
130
|
+
energy = state.getPotentialEnergy()
|
|
131
|
+
|
|
132
|
+
return energy
|
|
133
|
+
|
|
134
|
+
|
|
135
|
+
if __name__ == "__main__":
|
|
136
|
+
generate_reference()
|
|
@@ -0,0 +1,109 @@
|
|
|
1
|
+
"""
|
|
2
|
+
Test that the examples in the repo run without errors.
|
|
3
|
+
"""
|
|
4
|
+
|
|
5
|
+
import pathlib
|
|
6
|
+
import re
|
|
7
|
+
import subprocess
|
|
8
|
+
import tempfile
|
|
9
|
+
import textwrap
|
|
10
|
+
|
|
11
|
+
import pytest
|
|
12
|
+
|
|
13
|
+
from openff.toolkit._tests.utils import _get_readme_path
|
|
14
|
+
from openff.toolkit.utils import RDKIT_AVAILABLE, get_data_file_path, temporary_cd
|
|
15
|
+
|
|
16
|
+
|
|
17
|
+
def run_script_file(file_path):
|
|
18
|
+
"""Run through the shell a python script."""
|
|
19
|
+
with tempfile.TemporaryDirectory() as tmp_dir:
|
|
20
|
+
with temporary_cd(tmp_dir):
|
|
21
|
+
cmd = ["python", file_path]
|
|
22
|
+
if "conformer_energies.py" in file_path:
|
|
23
|
+
cmd.append("--filename")
|
|
24
|
+
mol_file = get_data_file_path("molecules/ruxolitinib_conformers.sdf")
|
|
25
|
+
cmd.append(mol_file)
|
|
26
|
+
try:
|
|
27
|
+
subprocess.check_call(cmd)
|
|
28
|
+
except subprocess.CalledProcessError:
|
|
29
|
+
raise Exception(f"Example {file_path} failed")
|
|
30
|
+
|
|
31
|
+
|
|
32
|
+
def run_script_str(script_str):
|
|
33
|
+
"""Execute a Python string through the shell in a temporary directory.
|
|
34
|
+
|
|
35
|
+
With respect to eval, this has the advantage of catching all import errors.
|
|
36
|
+
|
|
37
|
+
"""
|
|
38
|
+
with tempfile.TemporaryDirectory() as tmp_dir:
|
|
39
|
+
temp_file_path = (pathlib.Path(tmp_dir) / "temp.py").as_posix()
|
|
40
|
+
# Create temporary python script.
|
|
41
|
+
with open(temp_file_path, "w") as f:
|
|
42
|
+
f.write(script_str)
|
|
43
|
+
# Run the Python script.
|
|
44
|
+
try:
|
|
45
|
+
run_script_file(temp_file_path)
|
|
46
|
+
except Exception as error:
|
|
47
|
+
script_str = textwrap.indent(script_str, " ")
|
|
48
|
+
raise Exception(f"The following script failed:\n{script_str}") from error
|
|
49
|
+
|
|
50
|
+
|
|
51
|
+
def find_example_scripts() -> list[str]:
|
|
52
|
+
"""Find all Python scripts, excluding Jupyter notebooks, in the examples folder.
|
|
53
|
+
|
|
54
|
+
Returns
|
|
55
|
+
-------
|
|
56
|
+
example_file_paths : list[str]
|
|
57
|
+
List of full paths to python scripts to execute.
|
|
58
|
+
"""
|
|
59
|
+
if "site-packages" in __file__:
|
|
60
|
+
# This test file is being collected from the installed package, which
|
|
61
|
+
# does not provide the examples folder in the same location
|
|
62
|
+
return list()
|
|
63
|
+
|
|
64
|
+
examples_dir_path = pathlib.Path(__file__).parents[3] / "examples"
|
|
65
|
+
|
|
66
|
+
# Examples that require RDKit
|
|
67
|
+
rdkit_examples = {
|
|
68
|
+
examples_dir_path / "conformer_energies/conformer_energies.py",
|
|
69
|
+
}
|
|
70
|
+
|
|
71
|
+
example_file_paths = []
|
|
72
|
+
for example_file_path in examples_dir_path.glob("*/*.py"):
|
|
73
|
+
if not RDKIT_AVAILABLE:
|
|
74
|
+
if example_file_path in rdkit_examples:
|
|
75
|
+
continue
|
|
76
|
+
example_file_paths.append(example_file_path.as_posix())
|
|
77
|
+
|
|
78
|
+
return example_file_paths
|
|
79
|
+
|
|
80
|
+
|
|
81
|
+
def find_readme_examples() -> list[str]:
|
|
82
|
+
"""Yield the Python scripts in the main README.md file.
|
|
83
|
+
|
|
84
|
+
Returns
|
|
85
|
+
-------
|
|
86
|
+
readme_examples : list[str]
|
|
87
|
+
The list of Python scripts included in the README.md files.
|
|
88
|
+
"""
|
|
89
|
+
readme_file_path = _get_readme_path()
|
|
90
|
+
|
|
91
|
+
if readme_file_path is None:
|
|
92
|
+
return list()
|
|
93
|
+
|
|
94
|
+
with open(readme_file_path) as f:
|
|
95
|
+
readme_content = f.read()
|
|
96
|
+
|
|
97
|
+
return re.findall("```python(.*?)```", readme_content, flags=re.DOTALL)
|
|
98
|
+
|
|
99
|
+
|
|
100
|
+
@pytest.mark.parametrize("readme_example_str", find_readme_examples())
|
|
101
|
+
def test_readme_examples(readme_example_str):
|
|
102
|
+
"""Test the example"""
|
|
103
|
+
run_script_str(readme_example_str)
|
|
104
|
+
|
|
105
|
+
|
|
106
|
+
@pytest.mark.parametrize("example_file_path", find_example_scripts())
|
|
107
|
+
def test_examples(example_file_path):
|
|
108
|
+
"""Test that the example run without errors."""
|
|
109
|
+
run_script_file(example_file_path)
|