diff --git a/modules/conop/doc/cleanup.rst b/modules/conop/doc/cleanup.rst
new file mode 100644
index 0000000000000000000000000000000000000000..35b20e5705b248a995ec61c5e06604c53df0767f
--- /dev/null
+++ b/modules/conop/doc/cleanup.rst
@@ -0,0 +1,8 @@
+:mod:`conop.cleanup <ost.conop.cleanup>` -- Sanitize structures
+================================================================================
+
+.. module:: ost.conop.ceanup
+ :synopsis: Contains functions to sanitize (cleanup) structures by using
+ information from the compound library.
+
+.. autofunction:: ost.conop.cleanup.Cleanup
\ No newline at end of file
diff --git a/modules/conop/doc/conop.rst b/modules/conop/doc/conop.rst
index 8c3f413469872a1d95f9da98e37f4e21ffb24bfc..fb72db2645a92ea70f3db4f686c0f33a35c7e956 100644
--- a/modules/conop/doc/conop.rst
+++ b/modules/conop/doc/conop.rst
@@ -20,3 +20,4 @@ In this module
aminoacid
connectivity
compoundlib
+ cleanup
\ No newline at end of file
diff --git a/modules/conop/pymod/CMakeLists.txt b/modules/conop/pymod/CMakeLists.txt
index 5affa4b457d780b7368b34a097bec832d2c3f36c..97de72d7a52f1a74233a9782e746bd596620ffc7 100644
--- a/modules/conop/pymod/CMakeLists.txt
+++ b/modules/conop/pymod/CMakeLists.txt
@@ -7,4 +7,4 @@ set(OST_CONOP_PYMOD_SOURCES
export_ring_finder.cc
)
-pymod(NAME conop CPP ${OST_CONOP_PYMOD_SOURCES} PY __init__.py)
\ No newline at end of file
+pymod(NAME conop CPP ${OST_CONOP_PYMOD_SOURCES} PY __init__.py cleanup.py)
diff --git a/modules/conop/pymod/cleanup.py b/modules/conop/pymod/cleanup.py
new file mode 100644
index 0000000000000000000000000000000000000000..9ecf9c7ef12b8bb4fce889a5fb8062aab2364eda
--- /dev/null
+++ b/modules/conop/pymod/cleanup.py
@@ -0,0 +1,167 @@
+from ost import conop, mol
+
+def Cleanup(entity, strip_water=True, canonicalize=True, remove_ligands=True):
+ """
+ This function returns a cleaned-up (simplified) version of the protein
+ structure. Different parameters affect the behaviour of the function.
+
+ :param strip_water: Whether to remove water from the structure
+ :param canonicalize: Whether to strip off modifications of amino acids and map
+ them back to their parent standard amino acid, e.g. selenium methionine to
+ methionine.For more complex amino acids, where the relation between the
+ modified and the standard parent amino acid is not known, sidechain atoms
+ are removed. D-peptide-linking residues are completely removed as well.
+ :param remove_ligands: Whether to remove ligands from the structure
+
+ :return: a cleaned version of the entity
+ """
+ #setup
+ builder = conop.GetBuilder()
+ if not hasattr(builder, "compound_lib") :
+ raise RuntimeError( "Cannot cleanup structure, since the default builder doesn't use the compound library")
+ compound_lib = builder.compound_lib
+ clean_entity = entity.Copy()
+ ed = clean_entity.EditXCS()
+ #remove water residues
+ if strip_water:
+ _StripWater(clean_entity, ed)
+ #replace modified residues before removing ligands to avoid removing MSE and others
+ if canonicalize:
+ _CanonicalizeResidues(clean_entity, ed, compound_lib)
+ #remove all hetatoms that are not water
+ if remove_ligands:
+ _RemoveLigands(clean_entity, ed)
+ return clean_entity
+
+
+def _StripWater(clean_entity, ed) :
+ """
+ This function removes water residues from the structure
+ """
+ for res in clean_entity.residues:
+ if res.IsValid():
+ if res.chem_class == mol.WATER:
+ ed.DeleteResidue(res.handle)
+ ed.UpdateICS()
+ return
+
+def _RemoveLigands(clean_entity, ed) :
+ """
+ This function removes ligands from the structure
+ """
+ for res in clean_entity.residues:
+ if res.IsValid():
+ #WHEN mmCIF WILL BE USED, CHANGE IsPeptideLinking() TO IsProtein()
+ if not res.IsPeptideLinking() and res.atoms[0].is_hetatom and res.chem_class != mol.WATER:
+ ed.DeleteResidue(res.handle)
+ ed.UpdateICS()
+ return
+
+def _CanonicalizeResidues(clean_entity, ed, compound_lib) :
+ """
+ This function strips off modifications of amino acids and maps
+ them back to their parent standard amino acid, e.g. selenium methionine to
+ methionine.For more complex amino acids, where the relation between the
+ modified and the standard parent amino acid is not known, sidechain atoms
+ are removed. D-peptide-linking residues are completely removed as well.
+ """
+
+ for res in clean_entity.residues:
+ if res.IsValid() and res.IsPeptideLinking() :
+ parent_olc = res.one_letter_code
+ if parent_olc == "X" :
+ _DeleteSidechain(res, ed)
+ for atom in res.atoms:
+ atom.is_hetatom = False
+ else:
+ parent_tlc = conop.OneLetterCodeToResidueName(parent_olc)
+ parent_res = compound_lib.FindCompound(parent_tlc)
+ if not parent_res:
+ _DeleteSidechain(res, ed)
+ for atom in res.atoms:
+ atom.is_hetatom = False
+ print "Removing sidechain of %s, beacuse it has not been found in the compound library"% parent_tlc
+ else:
+ #collect atom's names
+ modif_atom_names = set([atom.name for atom in res.atoms
+ if atom.element != "H" and atom.element != "D" ])
+ #if the res is the first or last take all the atoms from the parent res
+ if res.FindAtom("OXT").IsValid() :
+ parent_atom_names = set([atom.name for atom in parent_res.atom_specs
+ if atom.element != "H" and atom.element != "D" ])
+ else:
+ parent_atom_names = set([atom.name for atom in parent_res.atom_specs
+ if atom.element != "H" and atom.element != "D" and not atom.is_leaving ])
+ additional_parent_atoms = parent_atom_names - modif_atom_names
+ additional_modif_atoms = modif_atom_names - parent_atom_names
+ #WHEN mmCIF WILL BE USED, CHANGE IsPeptideLinking() TO IsProtein(), TO EXCLUDE LIGANDS FROM CANONICALISATION
+ if res.atoms[0].is_hetatom :
+ old_name = res.name
+ ed.RenameResidue(res, parent_tlc)
+ if additional_parent_atoms:
+ if additional_modif_atoms:
+ #replacement
+ _Replacement(res, ed, old_name)
+ else:
+ #deletion
+ _Deletion(res, ed)
+ elif additional_modif_atoms:
+ #addition
+ _Addition(res, ed, additional_modif_atoms)
+ else:
+ #unchanged, later check stereochemistry or H atoms
+ _Unchanged(res, ed)
+ #the res is a peptide but not a ligand (is a protein res)
+ else:
+ if additional_parent_atoms:# if the sidechain is incomplete
+ _DeleteSidechain(res, ed)
+ ed.UpdateICS()
+ return
+
+def _Replacement(res, ed, old_name) :
+ #TEMP ONLY MSE
+ if old_name == "MSE" :
+ for atom in res.atoms:
+ atom.is_hetatom = False
+ sel = res.FindAtom("SE")
+ if sel.IsValid() :
+ ed.InsertAtom( res, "SD", sel.pos, "S", sel.occupancy, sel.b_factor ) #S radius=~1;SE=~1.2
+ ed.DeleteAtom( sel )
+ else:
+ _DeleteSidechain(res, ed)
+ else:
+ _DeleteSidechain(res, ed)
+ return
+
+def _Deletion(res, ed) :
+ _DeleteSidechain(res, ed)
+ for atom in res.atoms :
+ atom.is_hetatom = False
+ return
+
+def _Addition(res, ed, additional_modif_atoms) :
+ for add_atom_name in additional_modif_atoms:
+ add_atom = res.FindAtom( add_atom_name )
+ if add_atom.IsValid() :
+ ed.DeleteAtom( add_atom )
+ for atom in res.atoms:
+ atom.is_hetatom = False
+ return
+
+def _Unchanged(res, ed) :
+ if res.chem_class == mol.D_PEPTIDE_LINKING:
+ ed.DeleteResidue(res)
+ else:
+ _DeleteSidechain(res, ed)
+ for atom in res.atoms :
+ atom.is_hetatom = False
+ return
+
+def _DeleteSidechain(res, ed) :
+ for atom in res.atoms:
+ if not atom.name in ['CA','CB','C','N','O']:
+ ed.DeleteAtom(atom)
+ return
+
+#visible functions
+__all__ = [Cleanup]
diff --git a/modules/conop/tests/CMakeLists.txt b/modules/conop/tests/CMakeLists.txt
index aa06791bf0be4d64640499010893d9db179f3e33..1af92df10be705d46354506d72df5c0c645be732 100644
--- a/modules/conop/tests/CMakeLists.txt
+++ b/modules/conop/tests/CMakeLists.txt
@@ -4,6 +4,7 @@ set(OST_CONOP_UNIT_TESTS
tests.cc
test_builder.cc
test_compound.py
+ test_cleanup.py
)
ost_unittest(MODULE conop
diff --git a/modules/conop/tests/sample_noligands.pdb b/modules/conop/tests/sample_noligands.pdb
new file mode 100644
index 0000000000000000000000000000000000000000..7fd199276d45124bbe2b2bc6ddf7d47b780d9401
--- /dev/null
+++ b/modules/conop/tests/sample_noligands.pdb
@@ -0,0 +1,65 @@
+HETATM 1 N MSE A 1 16.152 35.832 19.337 1.00 68.79 N
+ANISOU 1 N MSE A 1 9680 7396 9061 1038 -716 -25 N
+HETATM 2 CA MSE A 1 16.961 36.379 20.419 1.00 66.57 C
+ANISOU 2 CA MSE A 1 9387 7212 8694 1121 -806 40 C
+HETATM 3 C MSE A 1 18.345 36.796 19.931 1.00 62.52 C
+ANISOU 3 C MSE A 1 8685 6846 8225 1266 -870 -107 C
+HETATM 4 O MSE A 1 19.030 36.049 19.227 1.00 60.36 O
+ANISOU 4 O MSE A 1 8358 6511 8064 1396 -922 -219 O
+HETATM 5 CB MSE A 1 17.100 35.372 21.563 1.00 69.52 C
+ANISOU 5 CB MSE A 1 9961 7405 9049 1204 -927 192 C
+HETATM 6 CG MSE A 1 17.608 35.983 22.861 1.00 69.50 C
+ANISOU 6 CG MSE A 1 9977 7515 8914 1239 -1006 292 C
+HETATM 7 SE MSE A 1 16.174 36.321 24.145 0.70149.62 SE
+ANISOU 7 SE MSE A 1 20306 17658 18883 1013 -917 492 SE
+HETATM 8 CE MSE A 1 16.439 38.231 24.424 1.00101.32 C
+ANISOU 8 CE MSE A 1 13992 11855 12651 950 -853 413 C
+ATOM 9 N GLY A 2 21.960 55.913 14.093 1.00 32.26 N
+ANISOU 9 N GLY A 2 3786 4717 3755 -417 -110 -697 N
+ATOM 10 CA GLY A 2 21.067 57.037 14.316 1.00 33.47 C
+ANISOU 10 CA GLY A 2 4071 4728 3919 -478 -95 -611 C
+ATOM 11 C GLY A 2 20.632 57.066 15.769 1.00 28.81 C
+ANISOU 11 C GLY A 2 3536 4062 3349 -382 -126 -599 C
+ATOM 12 O GLY A 2 19.474 57.360 16.089 1.00 26.62 O
+ANISOU 12 O GLY A 2 3358 3653 3104 -343 -120 -528 O
+HETATM 694 N MLY A 3 26.382 48.690 2.460 1.00 30.43 N
+ANISOU 694 N MLY A 3 2388 5919 3254 -646 317 -1852 N
+HETATM 695 CA MLY A 3 27.776 48.333 2.142 1.00 32.62 C
+ANISOU 695 CA MLY A 3 2438 6444 3514 -645 358 -2093 C
+HETATM 696 CB MLY A 3 28.523 49.535 1.556 1.00 34.25 C
+ANISOU 696 CB MLY A 3 2578 6874 3563 -918 442 -2107 C
+HETATM 697 CG MLY A 3 28.053 50.058 0.208 1.00 51.47 C
+ANISOU 697 CG MLY A 3 4819 9152 5586 -1157 527 -2046 C
+HETATM 698 CD MLY A 3 29.170 50.911 -0.420 1.00 65.96 C
+ANISOU 698 CD MLY A 3 6527 11268 7265 -1416 622 -2140 C
+HETATM 699 CE MLY A 3 28.648 51.881 -1.478 1.00 78.91 C
+ANISOU 699 CE MLY A 3 8300 12955 8728 -1697 684 -1985 C
+HETATM 700 NZ MLY A 3 27.996 53.093 -0.885 1.00 83.04 N
+ANISOU 700 NZ MLY A 3 9040 13267 9244 -1780 633 -1724 N
+HETATM 701 CH1 MLY A 3 27.490 53.898 -2.008 1.00 82.17 C
+ANISOU 701 CH1 MLY A 3 9059 13197 8964 -2028 679 -1578 C
+HETATM 702 CH2 MLY A 3 29.059 53.885 -0.248 1.00 83.95 C
+ANISOU 702 CH2 MLY A 3 9084 13473 9342 -1885 652 -1769 C
+HETATM 703 C MLY A 3 28.551 47.875 3.386 1.00 35.38 C
+ANISOU 703 C MLY A 3 2698 6760 3986 -436 275 -2175 C
+HETATM 704 O MLY A 3 29.262 46.867 3.369 1.00 36.09 O
+ANISOU 704 O MLY A 3 2632 6928 4151 -274 255 -2373 O
+HETATM 24 N DHA A 4 26.289 27.329 2.438 1.00 21.02 N
+HETATM 25 CA DHA A 4 26.295 27.688 3.823 1.00 20.17 C
+HETATM 26 CB DHA A 4 27.128 28.481 4.578 1.00 25.40 C
+HETATM 27 C DHA A 4 25.128 27.215 4.536 1.00 14.98 C
+HETATM 28 O DHA A 4 24.918 27.318 5.770 1.00 15.17 O
+ATOM 1454 N CYS A 5 35.381 45.298 39.476 1.00 31.23 N
+ATOM 1455 CA CYS A 5 35.559 43.873 39.703 1.00 26.90 C
+ATOM 1456 C CYS A 5 34.291 43.354 40.319 1.00 28.31 C
+ATOM 1457 OXT CYS A 5 33.569 44.119 40.933 1.00 32.71 O
+ATOM 1458 CB CYS A 5 36.760 43.592 40.596 1.00 27.44 C
+ATOM 1460 H CYS A 5 34.717 45.766 40.024 1.00 0.00 H
+HETATM 1345 N DAL A 6 16.130 53.915 24.417 1.00 8.63 N
+HETATM 1346 CA DAL A 6 16.958 55.083 24.235 1.00 24.17 C
+HETATM 1347 CB DAL A 6 16.321 56.394 24.733 1.00 30.20 C
+HETATM 1348 C DAL A 6 17.335 55.218 22.790 1.00 32.54 C
+HETATM 1349 O DAL A 6 16.693 54.552 21.946 1.00 27.41 O
+HETATM 1350 OXT DAL A 6 18.286 55.960 22.546 1.00 18.81 O
+HETATM 36 O HOH A 19 0.180 48.781 4.764 1.00 23.28 O
+END
diff --git a/modules/conop/tests/sample_nowater.pdb b/modules/conop/tests/sample_nowater.pdb
new file mode 100644
index 0000000000000000000000000000000000000000..0f8c440aa83c10dec2cfffe71cbe524a15d0af15
--- /dev/null
+++ b/modules/conop/tests/sample_nowater.pdb
@@ -0,0 +1,71 @@
+HETATM 1 N MSE A 1 16.152 35.832 19.337 1.00 68.79 N
+ANISOU 1 N MSE A 1 9680 7396 9061 1038 -716 -25 N
+HETATM 2 CA MSE A 1 16.961 36.379 20.419 1.00 66.57 C
+ANISOU 2 CA MSE A 1 9387 7212 8694 1121 -806 40 C
+HETATM 3 C MSE A 1 18.345 36.796 19.931 1.00 62.52 C
+ANISOU 3 C MSE A 1 8685 6846 8225 1266 -870 -107 C
+HETATM 4 O MSE A 1 19.030 36.049 19.227 1.00 60.36 O
+ANISOU 4 O MSE A 1 8358 6511 8064 1396 -922 -219 O
+HETATM 5 CB MSE A 1 17.100 35.372 21.563 1.00 69.52 C
+ANISOU 5 CB MSE A 1 9961 7405 9049 1204 -927 192 C
+HETATM 6 CG MSE A 1 17.608 35.983 22.861 1.00 69.50 C
+ANISOU 6 CG MSE A 1 9977 7515 8914 1239 -1006 292 C
+HETATM 7 SE MSE A 1 16.174 36.321 24.145 0.70149.62 SE
+ANISOU 7 SE MSE A 1 20306 17658 18883 1013 -917 492 SE
+HETATM 8 CE MSE A 1 16.439 38.231 24.424 1.00101.32 C
+ANISOU 8 CE MSE A 1 13992 11855 12651 950 -853 413 C
+ATOM 9 N GLY A 2 21.960 55.913 14.093 1.00 32.26 N
+ANISOU 9 N GLY A 2 3786 4717 3755 -417 -110 -697 N
+ATOM 10 CA GLY A 2 21.067 57.037 14.316 1.00 33.47 C
+ANISOU 10 CA GLY A 2 4071 4728 3919 -478 -95 -611 C
+ATOM 11 C GLY A 2 20.632 57.066 15.769 1.00 28.81 C
+ANISOU 11 C GLY A 2 3536 4062 3349 -382 -126 -599 C
+ATOM 12 O GLY A 2 19.474 57.360 16.089 1.00 26.62 O
+ANISOU 12 O GLY A 2 3358 3653 3104 -343 -120 -528 O
+HETATM 694 N MLY A 3 26.382 48.690 2.460 1.00 30.43 N
+ANISOU 694 N MLY A 3 2388 5919 3254 -646 317 -1852 N
+HETATM 695 CA MLY A 3 27.776 48.333 2.142 1.00 32.62 C
+ANISOU 695 CA MLY A 3 2438 6444 3514 -645 358 -2093 C
+HETATM 696 CB MLY A 3 28.523 49.535 1.556 1.00 34.25 C
+ANISOU 696 CB MLY A 3 2578 6874 3563 -918 442 -2107 C
+HETATM 697 CG MLY A 3 28.053 50.058 0.208 1.00 51.47 C
+ANISOU 697 CG MLY A 3 4819 9152 5586 -1157 527 -2046 C
+HETATM 698 CD MLY A 3 29.170 50.911 -0.420 1.00 65.96 C
+ANISOU 698 CD MLY A 3 6527 11268 7265 -1416 622 -2140 C
+HETATM 699 CE MLY A 3 28.648 51.881 -1.478 1.00 78.91 C
+ANISOU 699 CE MLY A 3 8300 12955 8728 -1697 684 -1985 C
+HETATM 700 NZ MLY A 3 27.996 53.093 -0.885 1.00 83.04 N
+ANISOU 700 NZ MLY A 3 9040 13267 9244 -1780 633 -1724 N
+HETATM 701 CH1 MLY A 3 27.490 53.898 -2.008 1.00 82.17 C
+ANISOU 701 CH1 MLY A 3 9059 13197 8964 -2028 679 -1578 C
+HETATM 702 CH2 MLY A 3 29.059 53.885 -0.248 1.00 83.95 C
+ANISOU 702 CH2 MLY A 3 9084 13473 9342 -1885 652 -1769 C
+HETATM 703 C MLY A 3 28.551 47.875 3.386 1.00 35.38 C
+ANISOU 703 C MLY A 3 2698 6760 3986 -436 275 -2175 C
+HETATM 704 O MLY A 3 29.262 46.867 3.369 1.00 36.09 O
+ANISOU 704 O MLY A 3 2632 6928 4151 -274 255 -2373 O
+HETATM 24 N DHA A 4 26.289 27.329 2.438 1.00 21.02 N
+HETATM 25 CA DHA A 4 26.295 27.688 3.823 1.00 20.17 C
+HETATM 26 CB DHA A 4 27.128 28.481 4.578 1.00 25.40 C
+HETATM 27 C DHA A 4 25.128 27.215 4.536 1.00 14.98 C
+HETATM 28 O DHA A 4 24.918 27.318 5.770 1.00 15.17 O
+ATOM 1454 N CYS A 5 35.381 45.298 39.476 1.00 31.23 N
+ATOM 1455 CA CYS A 5 35.559 43.873 39.703 1.00 26.90 C
+ATOM 1456 C CYS A 5 34.291 43.354 40.319 1.00 28.31 C
+ATOM 1457 OXT CYS A 5 33.569 44.119 40.933 1.00 32.71 O
+ATOM 1458 CB CYS A 5 36.760 43.592 40.596 1.00 27.44 C
+ATOM 1460 H CYS A 5 34.717 45.766 40.024 1.00 0.00 H
+HETATM 1345 N DAL A 6 16.130 53.915 24.417 1.00 8.63 N
+HETATM 1346 CA DAL A 6 16.958 55.083 24.235 1.00 24.17 C
+HETATM 1347 CB DAL A 6 16.321 56.394 24.733 1.00 30.20 C
+HETATM 1348 C DAL A 6 17.335 55.218 22.790 1.00 32.54 C
+HETATM 1349 O DAL A 6 16.693 54.552 21.946 1.00 27.41 O
+HETATM 1350 OXT DAL A 6 18.286 55.960 22.546 1.00 18.81 O
+HETATM 29 C1 GOL A 17 3.793 59.768 8.209 1.00 31.00 C
+HETATM 30 O1 GOL A 17 3.244 58.473 8.337 1.00 27.42 O
+HETATM 31 C2 GOL A 17 4.701 60.020 9.406 1.00 26.81 C
+HETATM 32 O2 GOL A 17 5.573 58.919 9.512 1.00 26.44 O
+HETATM 33 C3 GOL A 17 5.505 61.287 9.156 1.00 24.74 C
+HETATM 34 O3 GOL A 17 6.429 61.468 10.222 1.00 31.06 O
+HETATM 35 CL CL A 18 11.844 59.221 16.755 0.79 32.84 CL
+END
diff --git a/modules/conop/tests/sample_test_cleanup.pdb b/modules/conop/tests/sample_test_cleanup.pdb
new file mode 100644
index 0000000000000000000000000000000000000000..cce7fe04d4fe753d68c9e73620fea8617ce07059
--- /dev/null
+++ b/modules/conop/tests/sample_test_cleanup.pdb
@@ -0,0 +1,72 @@
+HETATM 1 N MSE A 1 16.152 35.832 19.337 1.00 68.79 N
+ANISOU 1 N MSE A 1 9680 7396 9061 1038 -716 -25 N
+HETATM 2 CA MSE A 1 16.961 36.379 20.419 1.00 66.57 C
+ANISOU 2 CA MSE A 1 9387 7212 8694 1121 -806 40 C
+HETATM 3 C MSE A 1 18.345 36.796 19.931 1.00 62.52 C
+ANISOU 3 C MSE A 1 8685 6846 8225 1266 -870 -107 C
+HETATM 4 O MSE A 1 19.030 36.049 19.227 1.00 60.36 O
+ANISOU 4 O MSE A 1 8358 6511 8064 1396 -922 -219 O
+HETATM 5 CB MSE A 1 17.100 35.372 21.563 1.00 69.52 C
+ANISOU 5 CB MSE A 1 9961 7405 9049 1204 -927 192 C
+HETATM 6 CG MSE A 1 17.608 35.983 22.861 1.00 69.50 C
+ANISOU 6 CG MSE A 1 9977 7515 8914 1239 -1006 292 C
+HETATM 7 SE MSE A 1 16.174 36.321 24.145 0.70149.62 SE
+ANISOU 7 SE MSE A 1 20306 17658 18883 1013 -917 492 SE
+HETATM 8 CE MSE A 1 16.439 38.231 24.424 1.00101.32 C
+ANISOU 8 CE MSE A 1 13992 11855 12651 950 -853 413 C
+ATOM 9 N GLY A 2 21.960 55.913 14.093 1.00 32.26 N
+ANISOU 9 N GLY A 2 3786 4717 3755 -417 -110 -697 N
+ATOM 10 CA GLY A 2 21.067 57.037 14.316 1.00 33.47 C
+ANISOU 10 CA GLY A 2 4071 4728 3919 -478 -95 -611 C
+ATOM 11 C GLY A 2 20.632 57.066 15.769 1.00 28.81 C
+ANISOU 11 C GLY A 2 3536 4062 3349 -382 -126 -599 C
+ATOM 12 O GLY A 2 19.474 57.360 16.089 1.00 26.62 O
+ANISOU 12 O GLY A 2 3358 3653 3104 -343 -120 -528 O
+HETATM 694 N MLY A 3 26.382 48.690 2.460 1.00 30.43 N
+ANISOU 694 N MLY A 3 2388 5919 3254 -646 317 -1852 N
+HETATM 695 CA MLY A 3 27.776 48.333 2.142 1.00 32.62 C
+ANISOU 695 CA MLY A 3 2438 6444 3514 -645 358 -2093 C
+HETATM 696 CB MLY A 3 28.523 49.535 1.556 1.00 34.25 C
+ANISOU 696 CB MLY A 3 2578 6874 3563 -918 442 -2107 C
+HETATM 697 CG MLY A 3 28.053 50.058 0.208 1.00 51.47 C
+ANISOU 697 CG MLY A 3 4819 9152 5586 -1157 527 -2046 C
+HETATM 698 CD MLY A 3 29.170 50.911 -0.420 1.00 65.96 C
+ANISOU 698 CD MLY A 3 6527 11268 7265 -1416 622 -2140 C
+HETATM 699 CE MLY A 3 28.648 51.881 -1.478 1.00 78.91 C
+ANISOU 699 CE MLY A 3 8300 12955 8728 -1697 684 -1985 C
+HETATM 700 NZ MLY A 3 27.996 53.093 -0.885 1.00 83.04 N
+ANISOU 700 NZ MLY A 3 9040 13267 9244 -1780 633 -1724 N
+HETATM 701 CH1 MLY A 3 27.490 53.898 -2.008 1.00 82.17 C
+ANISOU 701 CH1 MLY A 3 9059 13197 8964 -2028 679 -1578 C
+HETATM 702 CH2 MLY A 3 29.059 53.885 -0.248 1.00 83.95 C
+ANISOU 702 CH2 MLY A 3 9084 13473 9342 -1885 652 -1769 C
+HETATM 703 C MLY A 3 28.551 47.875 3.386 1.00 35.38 C
+ANISOU 703 C MLY A 3 2698 6760 3986 -436 275 -2175 C
+HETATM 704 O MLY A 3 29.262 46.867 3.369 1.00 36.09 O
+ANISOU 704 O MLY A 3 2632 6928 4151 -274 255 -2373 O
+HETATM 24 N DHA A 4 26.289 27.329 2.438 1.00 21.02 N
+HETATM 25 CA DHA A 4 26.295 27.688 3.823 1.00 20.17 C
+HETATM 26 CB DHA A 4 27.128 28.481 4.578 1.00 25.40 C
+HETATM 27 C DHA A 4 25.128 27.215 4.536 1.00 14.98 C
+HETATM 28 O DHA A 4 24.918 27.318 5.770 1.00 15.17 O
+ATOM 1454 N CYS A 5 35.381 45.298 39.476 1.00 31.23 N
+ATOM 1455 CA CYS A 5 35.559 43.873 39.703 1.00 26.90 C
+ATOM 1456 C CYS A 5 34.291 43.354 40.319 1.00 28.31 C
+ATOM 1457 OXT CYS A 5 33.569 44.119 40.933 1.00 32.71 O
+ATOM 1458 CB CYS A 5 36.760 43.592 40.596 1.00 27.44 C
+ATOM 1460 H CYS A 5 34.717 45.766 40.024 1.00 0.00 H
+HETATM 1345 N DAL A 6 16.130 53.915 24.417 1.00 8.63 N
+HETATM 1346 CA DAL A 6 16.958 55.083 24.235 1.00 24.17 C
+HETATM 1347 CB DAL A 6 16.321 56.394 24.733 1.00 30.20 C
+HETATM 1348 C DAL A 6 17.335 55.218 22.790 1.00 32.54 C
+HETATM 1349 O DAL A 6 16.693 54.552 21.946 1.00 27.41 O
+HETATM 1350 OXT DAL A 6 18.286 55.960 22.546 1.00 18.81 O
+HETATM 29 C1 GOL A 17 3.793 59.768 8.209 1.00 31.00 C
+HETATM 30 O1 GOL A 17 3.244 58.473 8.337 1.00 27.42 O
+HETATM 31 C2 GOL A 17 4.701 60.020 9.406 1.00 26.81 C
+HETATM 32 O2 GOL A 17 5.573 58.919 9.512 1.00 26.44 O
+HETATM 33 C3 GOL A 17 5.505 61.287 9.156 1.00 24.74 C
+HETATM 34 O3 GOL A 17 6.429 61.468 10.222 1.00 31.06 O
+HETATM 35 CL CL A 18 11.844 59.221 16.755 0.79 32.84 CL
+HETATM 36 O HOH A 19 0.180 48.781 4.764 1.00 23.28 O
+END
diff --git a/modules/conop/tests/test_cleanup.py b/modules/conop/tests/test_cleanup.py
new file mode 100644
index 0000000000000000000000000000000000000000..ee6ab57cae413a550e1cc6abdbc7875a1d7d3210
--- /dev/null
+++ b/modules/conop/tests/test_cleanup.py
@@ -0,0 +1,162 @@
+import unittest
+from ost import geom, conop
+from ost.conop import cleanup
+
+class TestCleanUp(unittest.TestCase):
+
+ def setUp(self):
+ self.comp_lib=conop.GetBuilder().compound_lib
+ self.ent = io.LoadPDB("sample_test_cleanup.pdb")
+ self.ent_no_wat = io.LoadPDB("sample_nowater.pdb")
+ self.ent_no_lig = io.LoadPDB("sample_noligands.pdb")
+
+ def testStripWater(self):
+ self.new_ent = cleanup.Cleanup(self.ent, strip_water=True, canonicalize=False, remove_ligands=False)
+ self.assertEqual( self.new_ent.residue_count, self.ent_no_wat.residue_count )
+ self.assertTrue( self.new_ent.residues[0].IsValid() )
+ self.assertEqual( self.new_ent.residues[0].qualified_name, self.ent_no_wat.residues[0].qualified_name)
+ self.assertTrue( self.new_ent.residues[1].IsValid() )
+ self.assertEqual( self.new_ent.residues[1].qualified_name, self.ent_no_wat.residues[1].qualified_name)
+ self.assertTrue( self.new_ent.residues[2].IsValid() )
+ self.assertEqual( self.new_ent.residues[2].qualified_name, self.ent_no_wat.residues[2].qualified_name)
+ self.assertTrue( self.new_ent.residues[3].IsValid() )
+ self.assertEqual( self.new_ent.residues[3].qualified_name, self.ent_no_wat.residues[3].qualified_name)
+ self.assertTrue( self.new_ent.residues[4].IsValid() )
+ self.assertEqual( self.new_ent.residues[4].qualified_name, self.ent_no_wat.residues[4].qualified_name)
+ self.assertTrue( self.new_ent.residues[5].IsValid() )
+ self.assertEqual( self.new_ent.residues[5].qualified_name, self.ent_no_wat.residues[5].qualified_name)
+ self.assertTrue( self.new_ent.residues[6].IsValid() )
+ self.assertEqual( self.new_ent.residues[6].qualified_name, self.ent_no_wat.residues[6].qualified_name)
+ self.assertTrue( self.new_ent.residues[7].IsValid() )
+ self.assertEqual( self.new_ent.residues[7].qualified_name, self.ent_no_wat.residues[7].qualified_name)
+
+ def testCanonicalize(self):
+ self.new_ent = cleanup.Cleanup(self.ent, strip_water=False, canonicalize=True, remove_ligands=False)
+ #standard residue must be the same
+ self.gly = self.ent.residues[1]
+ self.new_gly = self.new_ent.residues[1]
+ self.assertTrue(self.new_gly.IsValid())
+ self.assertTrue(self.new_gly.IsPeptideLinking())
+ self.assertEqual(self.gly.atom_count, self.new_gly.atom_count)
+ #TEMP del sidechain of incomplete residue and OXT if present
+ self.new_cys = self.new_ent.residues[4]
+ self.new_cys_atoms = set([atm.name for atm in self.new_cys.atoms])
+ self.assertEqual( len(self.new_cys_atoms), 4, msg = repr(self.new_cys_atoms))
+ self.assertTrue( "CB" in self.new_cys_atoms)
+ self.assertTrue( "CA" in self.new_cys_atoms)
+ self.assertTrue( "C" in self.new_cys_atoms)
+ self.assertFalse( "OXT" in self.new_cys_atoms)
+ self.assertTrue( "N" in self.new_cys_atoms)
+ #test replacement of atoms
+ self.mse = self.ent.residues[0]
+# self.assertTrue( self.mse.IsValid())
+# self.assertTrue( self.mse.IsPeptideLinking())
+ self.sel = self.mse.FindAtom("SE")
+# self.assertTrue( self.sel.IsValid())
+ self.met = self.new_ent.residues[0]
+ self.assertTrue(self.met.IsValid())
+ self.assertEqual(self.mse.atom_count, self.met.atom_count)
+ self.assertEqual(self.met.name, "MET")
+ self.assertEqual(self.met.one_letter_code, "M")
+ self.assertTrue(self.met.IsPeptideLinking())
+ self.sul = self.met.FindAtom("SD")
+ self.assertTrue(self.sul.IsValid())
+ self.assertTrue(geom.Equal(self.sul.pos,self.sel.pos), msg = "sul:%s sel:%s"%(str(self.sul.pos), str(self.sel.pos)) )
+ self.assertEqual(self.sul.element, "S")
+# self.AssertTrue( sul.mass == conop.Conopology.Instance().GetDefaultAtomMass("S"))
+# self.AssertTrue( sul.radius == conop.Conopology.Instance().GetDefaultAtomRadius("S"))
+ for atm in self.met.atoms:
+ self.assertFalse( atm.is_hetatom)
+ #test addition
+ self.mly = self.ent.residues[2]
+# self.assertTrue( self.mly.IsValid())
+# self.assertTrue( self.mly.IsPeptideLinking())
+ self.new_lys = self.new_ent.residues[2]
+ self.assertTrue(self.new_lys.IsValid())
+ self.assertTrue(self.new_lys.IsPeptideLinking())
+ self.assertEqual(self.new_lys.name, "LYS")
+ self.assertEqual(self.new_lys.one_letter_code, "K")
+ self.new_lys_atoms = set([atm.name for atm in self.new_lys.atoms])
+ self.canon_lys = self.comp_lib.FindCompound("LYS")
+ self.canon_lys_atoms = set([atom.name for atom in self.canon_lys.atom_specs
+ if atom.element != "H" and atom.element != "D" and not atom.is_leaving ])
+ self.assertEqual(self.canon_lys_atoms, self.new_lys_atoms)
+ self.assertFalse(self.canon_lys_atoms - self.new_lys_atoms)
+ self.assertFalse(self.new_lys_atoms - self.canon_lys_atoms) #test the reverse
+ for atm in self.new_lys.atoms:
+ self.assertFalse( atm.is_hetatom)
+ #deletions
+ self.dha = self.ent.residues[3]
+# self.assertTrue( self.dha.IsValid())
+# self.assertTrue( self.dha.IsPeptideLinking())
+ self.new_ser = self.new_ent.residues[3]
+ self.assertTrue(self.new_ser.IsValid())
+ self.assertTrue(self.new_ser.IsPeptideLinking())
+ self.assertEqual(self.new_ser.name, "SER")
+ self.assertEqual(self.new_ser.one_letter_code, "S")
+ self.new_ser_atoms = set([atm.name for atm in self.new_ser.atoms])
+ self.canon_ser = self.comp_lib.FindCompound("SER")
+ self.canon_ser_atoms = set([atom.name for atom in self.canon_ser.atom_specs
+ if atom.element != "H" and atom.element != "D" and not atom.is_leaving ])
+ #TEMP
+ self.assertEqual( len(self.new_ser_atoms), 5)
+ self.assertTrue( "CB" in self.new_ser_atoms)
+ self.assertTrue( "CA" in self.new_ser_atoms)
+ self.assertTrue( "C" in self.new_ser_atoms)
+ self.assertTrue( "O" in self.new_ser_atoms)
+ self.assertTrue( "N" in self.new_ser_atoms)
+ #AFTER TEMP
+ #self.assertEqual( self.canon_ser_atoms, self.new_ser_atoms)
+ #self.assertFalse(self.canon_ser_atoms - self.new_ser_atoms)
+ #self.assertFalse(self.new_ser_atoms - self.canon_ser_atoms) #test the reverse
+ for atm in self.new_ser.atoms:
+ self.assertFalse( atm.is_hetatom)
+ #test deletion of whole residue
+ self.assertEqual(self.ent.residues[5].chem_class, "D_PEPTIDE_LINKING")
+ self.assertNotEqual(self.new_ent.residues[5].name, "DAL")
+ self.assertNotEqual(self.ent.residue_count, self.new_ent.residue_count)
+
+ def testRemoveLigands(self):
+ self.new_ent = cleanup.Cleanup(self.ent, strip_water=False, canonicalize=False, remove_ligands=True)
+ self.assertEqual(self.new_ent.residue_count, self.ent_no_lig.residue_count )
+ #MSE
+ self.assertTrue(self.new_ent.residues[0].IsValid() )
+ self.assertEqual(self.new_ent.residues[0].qualified_name, self.ent_no_lig.residues[0].qualified_name)
+ self.assertTrue(self.new_ent.residues[0].IsPeptideLinking())
+ self.assertTrue(self.new_ent.residues[0].atoms[0].is_hetatom)
+ #GLY
+ self.assertTrue(self.new_ent.residues[1].IsValid() )
+ self.assertEqual(self.new_ent.residues[1].qualified_name, self.ent_no_lig.residues[1].qualified_name)
+ self.assertTrue(self.new_ent.residues[1].IsPeptideLinking())
+ self.assertFalse(self.new_ent.residues[1].atoms[0].is_hetatom)
+ #MLY
+ self.assertTrue(self.new_ent.residues[2].IsValid() )
+ self.assertEqual(self.new_ent.residues[2].qualified_name, self.ent_no_lig.residues[2].qualified_name)
+ self.assertTrue(self.new_ent.residues[2].IsPeptideLinking())
+ self.assertTrue(self.new_ent.residues[2].atoms[0].is_hetatom)
+ #DHA
+ self.assertTrue(self.new_ent.residues[3].IsValid() )
+ self.assertEqual(self.new_ent.residues[3].qualified_name, self.ent_no_lig.residues[3].qualified_name)
+ self.assertTrue(self.new_ent.residues[3].IsPeptideLinking())
+ self.assertTrue(self.new_ent.residues[3].atoms[0].is_hetatom)
+ #CYS
+ self.assertTrue(self.new_ent.residues[4].IsValid() )
+ self.assertEqual(self.new_ent.residues[4].qualified_name, self.ent_no_lig.residues[4].qualified_name)
+ self.assertTrue(self.new_ent.residues[4].IsPeptideLinking())
+ self.assertFalse(self.new_ent.residues[4].atoms[0].is_hetatom)
+ #DAL
+ self.assertTrue(self.new_ent.residues[5].IsValid() )
+ self.assertEqual(self.new_ent.residues[5].qualified_name, self.ent_no_lig.residues[5].qualified_name)
+ self.assertTrue(self.new_ent.residues[5].IsPeptideLinking())
+ self.assertTrue(self.new_ent.residues[5].atoms[0].is_hetatom)
+ #HOH
+ self.assertTrue(self.new_ent.residues[6].IsValid() )
+ self.assertEqual(self.new_ent.residues[6].qualified_name, self.ent_no_lig.residues[6].qualified_name)
+ self.assertFalse(self.new_ent.residues[6].IsPeptideLinking()) # here assertFalse instead of assertTrue
+ self.assertTrue(self.new_ent.residues[6].atoms[0].is_hetatom)
+
+if not hasattr(conop.GetBuilder(), 'compound_lib'):
+ print 'Default builder without compound lib. Ignoring test_cleanup.py tests'
+ sys.exit()
+suite = unittest.TestLoader().loadTestsFromTestCase(TestCleanUp)
+unittest.TextTestRunner().run(suite)
diff --git a/modules/mol/base/pymod/export_residue.cc b/modules/mol/base/pymod/export_residue.cc
index 1e1b9f74a60d94c224b9aad51153a9e873b2a4a7..75d74bdb577c618094ee18223102dfa56f932abe 100644
--- a/modules/mol/base/pymod/export_residue.cc
+++ b/modules/mol/base/pymod/export_residue.cc
@@ -64,6 +64,13 @@ namespace {
void export_Residue()
{
+ class_<ChemClass>("ChemClass", init<char>(args("chem_class")))
+ .def(self!=self)
+ .def(self==self)
+ .def("IsPeptideLinking", &ChemClass::IsPeptideLinking)
+ .def("IsNucleotideLinking", &ChemClass::IsNucleotideLinking)
+ ;
+ implicitly_convertible<char, ChemClass>();
class_<ResNum>("ResNum", init<int>(args("num")))
.def(init<int,char>(args("num", "ins_code")))
@@ -149,8 +156,8 @@ void export_Residue()
.def("GetNumber", &ResidueBase::GetNumber,
return_value_policy<copy_const_reference>())
.def("GetChemClass", &ResidueBase::GetChemClass)
+ .add_property("chem_class", &ResidueBase::GetChemClass, set_chemclass)
.def("SetChemClass", set_chemclass)
- .add_property("chem_class",&ResidueBase::GetChemClass,set_chemclass)
.add_property("is_ligand", &ResidueBase::IsLigand, &ResidueBase::SetIsLigand)
.def("IsLigand", &ResidueBase::IsLigand)
.def("SetIsLigand", &ResidueBase::SetIsLigand)