Skip to content
Snippets Groups Projects
Unverified Commit 12c0b061 authored by Xavier Robin's avatar Xavier Robin
Browse files

test: reading (or not) of BIRD (PRD) compounds

parent 51a58a0b
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
modules/conop/tests/test_complib.py
+ 26
− 0
View file @ 12c0b061
......@@ -118,6 +118,32 @@ class TestCompLib(unittest.TestCase):
# OX is obsolete
assert complib_no_obsolete.FindCompound("OX") is None
def test_bird(self):
""" the test file in test_compounds.cif contains two entries from
BIRD:
- PRD_900116 is not in a compound format and should not be added
to the compound lib.
- PRDCC_900116 is in a valid format and should be read in
"""
complib = self.complib
# PRD_900116 not added
comp = complib.FindCompound("PRD_900116")
self.assertIsNone(comp)
# PRD_900116 is added
comp = complib.FindCompound("PRDCC_900116")
self.assertIsNotNone(comp)
self.assertEqual(
comp.smiles,
"C1[C@H]([C@@H]([C@H]([C@@H](O1)O[C@@H]2CO[C@H]([C@@H]([C@H]2O)O)O)O)O)O")
# The release flag is REF_ONLY and compound should not be marked as
# obsolete
self.assertFalse(comp.obsolete)
# Contains atoms and bonds
self.assertEqual(len(comp.atom_specs), 37)
self.assertEqual(len(comp.bond_specs), 38)
if __name__ == "__main__":
from ost import testutils
......
modules/conop/tests/testfiles/test_compounds.cif
+ 237
− 0
View file @ 12c0b061
......@@ -2158,3 +2158,240 @@ _chem_comp.pdbx_model_coordinates_db_code ?
_chem_comp.pdbx_subcomponent_list ?
_chem_comp.pdbx_processing_site RCSB
##
# PRDCC_900116 is a BIRD entry in PRDCC format and should read in correctly in
# the compound lib
data_PRDCC_900116
#
_chem_comp.id PRDCC_900116
_chem_comp.name 4-O-beta-D-xylopyranosyl-beta-D-xylopyranose
_chem_comp.type saccharide
_chem_comp.formula "C10 H18 O9"
_chem_comp.pdbx_release_status REF_ONLY
_chem_comp.formula_weight 282.245
_chem_comp.pdbx_type ?
_chem_comp.mon_nstd_parent_comp_id ?
_chem_comp.pdbx_synonyms ?
_chem_comp.pdbx_formal_charge ?
_chem_comp.pdbx_initial_date ?
_chem_comp.pdbx_modified_date ?
_chem_comp.pdbx_ambiguous_flag ?
_chem_comp.pdbx_replaced_by ?
_chem_comp.pdbx_replaces ?
_chem_comp.one_letter_code ?
_chem_comp.three_letter_code ?
_chem_comp.pdbx_model_coordinates_details ?
_chem_comp.pdbx_model_coordinates_missing_flag ?
_chem_comp.pdbx_ideal_coordinates_details ?
_chem_comp.pdbx_ideal_coordinates_missing_flag ?
_chem_comp.pdbx_model_coordinates_db_code ?
_chem_comp.pdbx_subcomponent_list ?
_chem_comp.pdbx_processing_site ?
#
loop_
_chem_comp_atom.comp_id
_chem_comp_atom.atom_id
_chem_comp_atom.alt_atom_id
_chem_comp_atom.type_symbol
_chem_comp_atom.charge
_chem_comp_atom.pdbx_align
_chem_comp_atom.pdbx_aromatic_flag
_chem_comp_atom.pdbx_leaving_atom_flag
_chem_comp_atom.pdbx_stereo_config
_chem_comp_atom.model_Cartn_x
_chem_comp_atom.model_Cartn_y
_chem_comp_atom.model_Cartn_z
_chem_comp_atom.pdbx_model_Cartn_x_ideal
_chem_comp_atom.pdbx_model_Cartn_y_ideal
_chem_comp_atom.pdbx_model_Cartn_z_ideal
_chem_comp_atom.pdbx_component_comp_id
_chem_comp_atom.pdbx_residue_numbering
_chem_comp_atom.pdbx_component_atom_id
_chem_comp_atom.pdbx_polymer_type
_chem_comp_atom.pdbx_ref_id
_chem_comp_atom.pdbx_component_id
_chem_comp_atom.pdbx_ordinal
_chem_comp_atom.pdbx_backbone_atom_flag
_chem_comp_atom.pdbx_n_terminal_atom_flag
_chem_comp_atom.pdbx_c_terminal_atom_flag
PRD_900116 O1A O9 O 0 1 N N N 62.369 63.326 22.057 -5.145 -0.343 1.296 XYP 1 O4A polymer 1 1 1 ? ? ?
PRD_900116 C1A C9 C 0 1 N N R 62.245 64.245 21.048 -3.966 -0.610 0.535 XYP 1 C1B polymer 1 1 2 ? ? ?
PRD_900116 C2A C10 C 0 1 N N R 63.637 64.692 20.579 -3.534 0.662 -0.201 XYP 1 C2B polymer 1 1 3 ? ? ?
PRD_900116 C3A C7 C 0 1 N N R 63.577 65.572 19.393 -2.237 0.384 -0.966 XYP 1 C3B polymer 1 1 4 ? ? ?
PRD_900116 C4A C6 C 0 1 N N R 62.774 65.007 18.298 -1.171 -0.108 0.019 XYP 1 C4B polymer 1 1 5 ? ? ?
PRD_900116 C5A C8 C 0 1 N N N 61.391 64.538 18.774 -1.694 -1.350 0.746 XYP 1 C5B polymer 1 1 6 ? ? ?
PRD_900116 O2A O8 O 0 1 N N N 64.259 65.423 21.647 -4.556 1.052 -1.120 XYP 1 O2B polymer 1 1 7 ? ? ?
PRD_900116 O3A O6 O 0 1 N N N 64.944 65.808 18.894 -1.787 1.585 -1.596 XYP 1 O3B polymer 1 1 8 ? ? ?
PRD_900116 O4A O5 O 0 1 N N N 62.601 66.032 17.300 0.022 -0.440 -0.695 XYP 1 O4B polymer 1 1 9 ? ? ?
PRD_900116 O5A O7 O 0 1 N N N 61.492 63.643 19.942 -2.918 -1.031 1.411 XYP 1 O5B polymer 1 1 10 ? ? ?
PRD_900116 C1B C5 C 0 1 N N S 62.805 65.537 16.116 1.220 -0.261 0.063 XYP 2 C1B polymer 1 1 11 ? ? ?
PRD_900116 C2B C3 C 0 1 N N R 62.263 66.524 15.005 2.417 -0.761 -0.750 XYP 2 C2B polymer 1 1 12 ? ? ?
PRD_900116 C3B C2 C 0 1 N N S 62.560 66.033 13.636 3.703 -0.511 0.043 XYP 2 C3B polymer 1 1 13 ? ? ?
PRD_900116 C4B C1 C 0 1 N N R 63.947 65.755 13.420 3.806 0.981 0.372 XYP 2 C4B polymer 1 1 14 ? ? ?
PRD_900116 C5B C4 C 0 1 N N N 64.542 64.882 14.493 2.556 1.414 1.142 XYP 2 C5B polymer 1 1 15 ? ? ?
PRD_900116 O2B O3 O 0 1 N N N 60.863 66.689 15.161 2.274 -2.161 -1.000 XYP 2 O2B polymer 1 1 16 ? ? ?
PRD_900116 O3B O2 O 0 1 N N N 62.135 67.086 12.661 4.832 -0.907 -0.738 XYP 2 O3B polymer 1 1 17 ? ? ?
PRD_900116 O4B O1 O 0 1 N N N 64.114 65.051 12.120 4.965 1.215 1.174 XYP 2 O4B polymer 1 1 18 ? ? ?
PRD_900116 O5B O4 O 0 1 N N N 64.275 65.381 15.859 1.394 1.126 0.361 XYP 2 O5B polymer 1 1 19 ? ? ?
PRD_900116 HO1A H18 H 0 0 N N N 62.856 63.709 22.777 -5.476 -1.105 1.790 XYP 1 HO4A polymer 1 1 20 ? ? ?
PRD_900116 H1A1 H15 H 0 0 N N N 61.704 65.134 21.405 -4.172 -1.397 -0.191 XYP 1 H1B polymer 1 1 21 ? ? ?
PRD_900116 H2A H16 H 0 1 N N N 64.231 63.798 20.340 -3.368 1.461 0.521 XYP 1 H2B polymer 1 1 22 ? ? ?
PRD_900116 H3A H11 H 0 1 N N N 63.139 66.536 19.692 -2.415 -0.381 -1.722 XYP 1 H3B polymer 1 1 23 ? ? ?
PRD_900116 H4A H10 H 0 1 N N N 63.304 64.147 17.862 -0.956 0.675 0.745 XYP 1 H4B polymer 1 1 24 ? ? ?
PRD_900116 H5A1 H14 H 0 0 N N N 60.895 63.999 17.953 -0.958 -1.679 1.479 XYP 1 H5B1 polymer 1 1 25 ? ? ?
PRD_900116 H5A2 H13 H 0 0 N N N 60.791 65.418 19.050 -1.870 -2.147 0.023 XYP 1 H5B2 polymer 1 1 26 ? ? ?
PRD_900116 HO2A H17 H 0 0 N N N 64.308 64.874 22.421 -5.408 1.244 -0.704 XYP 1 HO2B polymer 1 1 27 ? ? ?
PRD_900116 HO3A H12 H 0 0 N N N 65.477 66.174 19.590 -2.414 1.953 -2.234 XYP 1 HO3B polymer 1 1 28 ? ? ?
PRD_900116 H1B H9 H 0 1 N N N 62.310 64.564 15.980 1.151 -0.826 0.992 XYP 2 H1B polymer 1 1 29 ? ? ?
PRD_900116 H2B H5 H 0 1 N N N 62.766 67.492 15.149 2.464 -0.225 -1.698 XYP 2 H2B polymer 1 1 30 ? ? ?
PRD_900116 H3B H3 H 0 1 N N N 61.970 65.124 13.450 3.679 -1.087 0.969 XYP 2 H3B polymer 1 1 31 ? ? ?
PRD_900116 H4B H2 H 0 1 N N N 64.510 66.699 13.386 3.882 1.553 -0.553 XYP 2 H4B polymer 1 1 32 ? ? ?
PRD_900116 H5B1 H8 H 0 0 N N N 65.631 64.836 14.343 2.603 2.484 1.341 XYP 2 H5B1 polymer 1 1 33 ? ? ?
PRD_900116 H5B2 H7 H 0 0 N N N 64.116 63.872 14.399 2.503 0.870 2.085 XYP 2 H5B2 polymer 1 1 34 ? ? ?
PRD_900116 HO2B H6 H 0 0 N N N 60.676 67.003 16.038 1.479 -2.392 -1.499 XYP 2 HO2B polymer 1 1 35 ? ? ?
PRD_900116 HO3B H4 H 0 0 N N N 61.215 67.284 12.789 5.682 -0.771 -0.299 XYP 2 HO3B polymer 1 1 36 ? ? ?
PRD_900116 HO4B H1 H 0 0 N N N 65.035 64.866 11.976 5.093 2.141 1.420 XYP 2 HO4B polymer 1 1 37 ? ? ?
#
loop_
_chem_comp_bond.comp_id
_chem_comp_bond.atom_id_1
_chem_comp_bond.atom_id_2
_chem_comp_bond.value_order
_chem_comp_bond.pdbx_aromatic_flag
_chem_comp_bond.pdbx_stereo_config
_chem_comp_bond.pdbx_ordinal
PRD_900116 O4B C4B SING N N 1
PRD_900116 O3B C3B SING N N 2
PRD_900116 C4B C3B SING N N 3
PRD_900116 C4B C5B SING N N 4
PRD_900116 C3B C2B SING N N 5
PRD_900116 C5B O5B SING N N 6
PRD_900116 C2B O2B SING N N 7
PRD_900116 C2B C1B SING N N 8
PRD_900116 O5B C1B SING N N 9
PRD_900116 C1B O4A SING N N 10
PRD_900116 O4A C4A SING N N 11
PRD_900116 C4A C5A SING N N 12
PRD_900116 C4A C3A SING N N 13
PRD_900116 C5A O5A SING N N 14
PRD_900116 O3A C3A SING N N 15
PRD_900116 C3A C2A SING N N 16
PRD_900116 O5A C1A SING N N 17
PRD_900116 C2A C1A SING N N 18
PRD_900116 C2A O2A SING N N 19
PRD_900116 C1A O1A SING N N 20
PRD_900116 O4B HO4B SING N N 21
PRD_900116 C4B H4B SING N N 22
PRD_900116 C3B H3B SING N N 23
PRD_900116 O3B HO3B SING N N 24
PRD_900116 C2B H2B SING N N 25
PRD_900116 O2B HO2B SING N N 26
PRD_900116 C5B H5B2 SING N N 27
PRD_900116 C5B H5B1 SING N N 28
PRD_900116 C1B H1B SING N N 29
PRD_900116 C4A H4A SING N N 30
PRD_900116 C3A H3A SING N N 31
PRD_900116 O3A HO3A SING N N 32
PRD_900116 C5A H5A2 SING N N 33
PRD_900116 C5A H5A1 SING N N 34
PRD_900116 C1A H1A1 SING N N 35
PRD_900116 C2A H2A SING N N 36
PRD_900116 O2A HO2A SING N N 37
PRD_900116 O1A HO1A SING N N 38
#
loop_
_pdbx_chem_comp_descriptor.comp_id
_pdbx_chem_comp_descriptor.type
_pdbx_chem_comp_descriptor.program
_pdbx_chem_comp_descriptor.program_version
_pdbx_chem_comp_descriptor.descriptor
PRD_900116 SMILES ACDLabs 12.01 "OC1C(C(O)C(OC1)OC2COC(O)C(C2O)O)O"
PRD_900116 InChI InChI 1.03 "InChI=1S/C10H18O9/c11-3-1-18-10(8(15)5(3)12)19-4-2-17-9(16)7(14)6(4)13/h3-16H,1-2H2/t3-,4-,5+,6+,7-,8-,9-,10+/m1/s1"
PRD_900116 InChIKey InChI 1.03 LGQKSQQRKHFMLI-SJYYZXOBSA-N
PRD_900116 SMILES_CANONICAL CACTVS 3.385 "O[C@@H]1CO[C@@H](O[C@@H]2CO[C@@H](O)[C@H](O)[C@H]2O)[C@H](O)[C@H]1O"
PRD_900116 SMILES CACTVS 3.385 "O[CH]1CO[CH](O[CH]2CO[CH](O)[CH](O)[CH]2O)[CH](O)[CH]1O"
PRD_900116 SMILES_CANONICAL "OpenEye OEToolkits" 2.0.7 "C1[C@H]([C@@H]([C@H]([C@@H](O1)O[C@@H]2CO[C@H]([C@@H]([C@H]2O)O)O)O)O)O"
PRD_900116 SMILES "OpenEye OEToolkits" 2.0.7 "C1C(C(C(C(O1)OC2COC(C(C2O)O)O)O)O)O"
#
loop_
_pdbx_chem_comp_identifier.comp_id
_pdbx_chem_comp_identifier.type
_pdbx_chem_comp_identifier.program
_pdbx_chem_comp_identifier.program_version
_pdbx_chem_comp_identifier.identifier
PRD_900116 "SYSTEMATIC NAME" ACDLabs 12.01 4-O-beta-D-xylopyranosyl-beta-D-xylopyranose
PRD_900116 "SYSTEMATIC NAME" "OpenEye OEToolkits" 2.0.7 "(2~{S},3~{R},4~{S},5~{R})-2-[(3~{R},4~{R},5~{R},6~{R})-4,5,6-tris(oxidanyl)oxan-3-yl]oxyoxane-3,4,5-triol"
#
# PRD_900116 is a BIRD entry in PRD format. It doesn't have _chem_comp or anything useful
# and should not end up in the compound lib
data_PRD_900116
#
_pdbx_reference_molecule.prd_id PRD_900116
_pdbx_reference_molecule.name 4beta-beta-xylobiose
_pdbx_reference_molecule.represent_as branched
_pdbx_reference_molecule.type Oligosaccharide
_pdbx_reference_molecule.type_evidence_code ?
_pdbx_reference_molecule.class metabolism
_pdbx_reference_molecule.class_evidence_code ?
_pdbx_reference_molecule.formula "C10 H18 O9"
_pdbx_reference_molecule.formula_weight 282.245
_pdbx_reference_molecule.chem_comp_id ?
_pdbx_reference_molecule.release_status REL
_pdbx_reference_molecule.replaces ?
_pdbx_reference_molecule.replaced_by ?
_pdbx_reference_molecule.compound_details ?
_pdbx_reference_molecule.description oligosaccharide
_pdbx_reference_molecule.representative_PDB_id_code 6RV8
#
_pdbx_reference_entity_list.prd_id PRD_900116
_pdbx_reference_entity_list.ref_entity_id 1
_pdbx_reference_entity_list.component_id 1
_pdbx_reference_entity_list.type branched
_pdbx_reference_entity_list.details ?
#
_pdbx_reference_entity_poly.prd_id PRD_900116
_pdbx_reference_entity_poly.ref_entity_id 1
_pdbx_reference_entity_poly.type oligosaccharide
_pdbx_reference_entity_poly.db_code ?
_pdbx_reference_entity_poly.db_name ?
#
_pdbx_reference_entity_sequence.prd_id PRD_900116
_pdbx_reference_entity_sequence.ref_entity_id 1
_pdbx_reference_entity_sequence.type saccharide
_pdbx_reference_entity_sequence.NRP_flag N
#
loop_
_pdbx_reference_entity_poly_seq.prd_id
_pdbx_reference_entity_poly_seq.ref_entity_id
_pdbx_reference_entity_poly_seq.num
_pdbx_reference_entity_poly_seq.mon_id
_pdbx_reference_entity_poly_seq.parent_mon_id
_pdbx_reference_entity_poly_seq.hetero
_pdbx_reference_entity_poly_seq.observed
PRD_900116 1 1 XYP ? N Y
PRD_900116 1 2 XYP ? N Y
#
_pdbx_reference_entity_poly_link.prd_id PRD_900116
_pdbx_reference_entity_poly_link.ref_entity_id 1
_pdbx_reference_entity_poly_link.component_id 1
_pdbx_reference_entity_poly_link.link_id 1
_pdbx_reference_entity_poly_link.atom_id_1 O4
_pdbx_reference_entity_poly_link.comp_id_1 XYP
_pdbx_reference_entity_poly_link.entity_seq_num_1 1
_pdbx_reference_entity_poly_link.atom_id_2 C1
_pdbx_reference_entity_poly_link.comp_id_2 XYP
_pdbx_reference_entity_poly_link.entity_seq_num_2 2
_pdbx_reference_entity_poly_link.value_order SING
_pdbx_reference_entity_poly_link.details ?
_pdbx_reference_entity_poly_link.insert_code_1 ?
_pdbx_reference_entity_poly_link.insert_code_2 ?
#
loop_
_pdbx_prd_audit.prd_id
_pdbx_prd_audit.date
_pdbx_prd_audit.processing_site
_pdbx_prd_audit.action_type
PRD_900116 2020-05-08 RCSB "Create molecule"
PRD_900116 2020-07-29 RCSB "Initial release"
#
\ No newline at end of file
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment