Mercurial > repos > galaxy-australia > alphafold2

comparison docker/alphafold/alphafold/relax/cleanup_test.py @ 1:6c92e000d684 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/usegalaxy-au/galaxy-local-tools commit a510e97ebd604a5e30b1f16e5031f62074f23e86"
author galaxy-australia
date Tue, 01 Mar 2022 02:53:05 +0000
parents
children
comparison
equal deleted inserted replaced
0:7ae9d78b06f5 1:6c92e000d684
1 # Copyright 2021 DeepMind Technologies Limited
2 #
3 # Licensed under the Apache License, Version 2.0 (the "License");
4 # you may not use this file except in compliance with the License.
5 # You may obtain a copy of the License at
6 #
7 # http://www.apache.org/licenses/LICENSE-2.0
8 #
9 # Unless required by applicable law or agreed to in writing, software
10 # distributed under the License is distributed on an "AS IS" BASIS,
11 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 # See the License for the specific language governing permissions and
13 # limitations under the License.
14
15 """Tests for relax.cleanup."""
16 import io
17
18 from absl.testing import absltest
19 from alphafold.relax import cleanup
20 from simtk.openmm.app.internal import pdbstructure
21
22
23 def _pdb_to_structure(pdb_str):
24 handle = io.StringIO(pdb_str)
25 return pdbstructure.PdbStructure(handle)
26
27
28 def _lines_to_structure(pdb_lines):
29 return _pdb_to_structure('\n'.join(pdb_lines))
30
31
32 class CleanupTest(absltest.TestCase):
33
34 def test_missing_residues(self):
35 pdb_lines = ['SEQRES 1 C 3 CYS GLY LEU',
36 'ATOM 1 N CYS C 1 -12.262 20.115 60.959 1.00 '
37 '19.08 N',
38 'ATOM 2 CA CYS C 1 -11.065 20.934 60.773 1.00 '
39 '17.23 C',
40 'ATOM 3 C CYS C 1 -10.002 20.742 61.844 1.00 '
41 '15.38 C',
42 'ATOM 4 O CYS C 1 -10.284 20.225 62.929 1.00 '
43 '16.04 O',
44 'ATOM 5 N LEU C 3 -7.688 18.700 62.045 1.00 '
45 '14.75 N',
46 'ATOM 6 CA LEU C 3 -7.256 17.320 62.234 1.00 '
47 '16.81 C',
48 'ATOM 7 C LEU C 3 -6.380 16.864 61.070 1.00 '
49 '16.95 C',
50 'ATOM 8 O LEU C 3 -6.551 17.332 59.947 1.00 '
51 '16.97 O']
52 input_handle = io.StringIO('\n'.join(pdb_lines))
53 alterations = {}
54 result = cleanup.fix_pdb(input_handle, alterations)
55 structure = _pdb_to_structure(result)
56 residue_names = [r.get_name() for r in structure.iter_residues()]
57 self.assertCountEqual(residue_names, ['CYS', 'GLY', 'LEU'])
58 self.assertCountEqual(alterations['missing_residues'].values(), [['GLY']])
59
60 def test_missing_atoms(self):
61 pdb_lines = ['SEQRES 1 A 1 PRO',
62 'ATOM 1 CA PRO A 1 1.000 1.000 1.000 1.00 '
63 ' 0.00 C']
64 input_handle = io.StringIO('\n'.join(pdb_lines))
65 alterations = {}
66 result = cleanup.fix_pdb(input_handle, alterations)
67 structure = _pdb_to_structure(result)
68 atom_names = [a.get_name() for a in structure.iter_atoms()]
69 self.assertCountEqual(atom_names, ['N', 'CD', 'HD2', 'HD3', 'CG', 'HG2',
70 'HG3', 'CB', 'HB2', 'HB3', 'CA', 'HA',
71 'C', 'O', 'H2', 'H3', 'OXT'])
72 missing_atoms_by_residue = list(alterations['missing_heavy_atoms'].values())
73 self.assertLen(missing_atoms_by_residue, 1)
74 atoms_added = [a.name for a in missing_atoms_by_residue[0]]
75 self.assertCountEqual(atoms_added, ['N', 'CD', 'CG', 'CB', 'C', 'O'])
76 missing_terminals_by_residue = alterations['missing_terminals']
77 self.assertLen(missing_terminals_by_residue, 1)
78 has_missing_terminal = [r.name for r in missing_terminals_by_residue.keys()]
79 self.assertCountEqual(has_missing_terminal, ['PRO'])
80 self.assertCountEqual([t for t in missing_terminals_by_residue.values()],
81 [['OXT']])
82
83 def test_remove_heterogens(self):
84 pdb_lines = ['SEQRES 1 A 1 GLY',
85 'ATOM 1 CA GLY A 1 0.000 0.000 0.000 1.00 '
86 ' 0.00 C',
87 'ATOM 2 O HOH A 2 0.000 0.000 0.000 1.00 '
88 ' 0.00 O']
89 input_handle = io.StringIO('\n'.join(pdb_lines))
90 alterations = {}
91 result = cleanup.fix_pdb(input_handle, alterations)
92 structure = _pdb_to_structure(result)
93 self.assertCountEqual([res.get_name() for res in structure.iter_residues()],
94 ['GLY'])
95 self.assertEqual(alterations['removed_heterogens'], set(['HOH']))
96
97 def test_fix_nonstandard_residues(self):
98 pdb_lines = ['SEQRES 1 A 1 DAL',
99 'ATOM 1 CA DAL A 1 0.000 0.000 0.000 1.00 '
100 ' 0.00 C']
101 input_handle = io.StringIO('\n'.join(pdb_lines))
102 alterations = {}
103 result = cleanup.fix_pdb(input_handle, alterations)
104 structure = _pdb_to_structure(result)
105 residue_names = [res.get_name() for res in structure.iter_residues()]
106 self.assertCountEqual(residue_names, ['ALA'])
107 self.assertLen(alterations['nonstandard_residues'], 1)
108 original_res, new_name = alterations['nonstandard_residues'][0]
109 self.assertEqual(original_res.id, '1')
110 self.assertEqual(new_name, 'ALA')
111
112 def test_replace_met_se(self):
113 pdb_lines = ['SEQRES 1 A 1 MET',
114 'ATOM 1 SD MET A 1 0.000 0.000 0.000 1.00 '
115 ' 0.00 Se']
116 structure = _lines_to_structure(pdb_lines)
117 alterations = {}
118 cleanup._replace_met_se(structure, alterations)
119 sd = [a for a in structure.iter_atoms() if a.get_name() == 'SD']
120 self.assertLen(sd, 1)
121 self.assertEqual(sd[0].element_symbol, 'S')
122 self.assertCountEqual(alterations['Se_in_MET'], [sd[0].residue_number])
123
124 def test_remove_chains_of_length_one(self):
125 pdb_lines = ['SEQRES 1 A 1 GLY',
126 'ATOM 1 CA GLY A 1 0.000 0.000 0.000 1.00 '
127 ' 0.00 C']
128 structure = _lines_to_structure(pdb_lines)
129 alterations = {}
130 cleanup._remove_chains_of_length_one(structure, alterations)
131 chains = list(structure.iter_chains())
132 self.assertEmpty(chains)
133 self.assertCountEqual(alterations['removed_chains'].values(), [['A']])
134
135
136 if __name__ == '__main__':
137 absltest.main()