diff --git a/modules/io/doc/mmcif.rst b/modules/io/doc/mmcif.rst
index a887323546f8b9687ec9c6e0bde909903261d2d7..df9a948bd44cb5b17c9e3174d97c6cc64fb83e01 100644
--- a/modules/io/doc/mmcif.rst
+++ b/modules/io/doc/mmcif.rst
@@ -130,7 +130,14 @@ of the annotation available.
.. method:: AddBioUnit(biounit)
- Add a bio unit to the bio unit list of an info object.
+ Add a bio unit to the bio unit list of an info object. If the
+ :attr:`id <MMCifInfoBioUnit.id>` of ``biounit`` already exists in the set
+ of assemblies, both will be merged. This means that
+ :attr:`chain <MMCifInfoBioUnit.chains>` and
+ :attr:`operations <MMCifInfoBioUnit.operations>` lists will be concatenated
+ and the interval lists
+ (:attr:`operationsintervalls <MMCifInfoBioUnit.operationsintervalls>`,
+ :attr:`chainintervalls <MMCifInfoBioUnit.chainintervalls>`) will be updated.
:param biounit: Bio unit to be added.
:type biounit: :class:`MMCifInfoBioUnit`
@@ -499,7 +506,17 @@ of the annotation available.
Chains involved in this bio unit. If not provided, resembles an empty list.
Also available as :meth:`GetChainList`. May also be modified by
- :meth:`AddChain`.
+ :meth:`AddChain` or :meth:`SetChainList`.
+
+ .. attribute:: chainintervalls
+
+ List of intervals on the chain list. Needed if there a several sets of
+ chains and transformations to create the bio unit. Comes as a list of
+ tuples. First component is the start, second is the right border of the
+ interval.
+
+ Also available as :meth:`GetChainIntervalList`. Is automatically modified by
+ :meth:`AddChain`, :meth:`SetChainList` and :meth:`MMCifInfo.AddBioUnit`.
.. attribute:: operations
@@ -509,6 +526,16 @@ of the annotation available.
Also available as :meth:`GetOperations`. May be modified by
:meth:`AddOperations`
+ .. attribute:: operationsintervalls
+
+ List of intervals on the operations list. Needed if there a several sets of
+ chains and transformations to create the bio unit. Comes as a list of
+ tuples. First component is the start, second is the right border of the
+ interval.
+
+ Also available as :meth:`GetOperationsIntervalList`. Is automatically
+ modified by :meth:`AddOperations` and :meth:`MMCifInfo.AddBioUnit`.
+
.. method:: GetID()
See :attr:`id`
@@ -529,9 +556,22 @@ of the annotation available.
See :attr:`chains`
+ .. method:: SetChainList(chains)
+
+ See :attr:`chains`, also resets :attr:`chainintervalls` to contain only one
+ interval enclosing the whole chain list.
+
+ :param chains: List of chain names.
+ :type chains: :class:`~ost.StringList`
+
.. method:: AddChain(chain name)
- See :attr:`chains`
+ See :attr:`chains`, also extends the right border of the last entry in
+ :attr:`chainintervalls`.
+
+ .. method:: GetChainIntervalList()
+
+ See :attr:`chainintervalls`
.. method:: GetOperations()
@@ -539,7 +579,12 @@ of the annotation available.
.. method:: AddOperations(list of operations)
- See :attr:`operations`
+ See :attr:`operations`, also extends the right border of the last entry in
+ :attr:`operationsintervalls`.
+
+ .. method:: GetOperationsIntervalList()
+
+ See :attr:`operationsintervalls`
.. function:: PDBize(asu, seqres=None, min_polymer_size=10, transformation=False)
@@ -567,7 +612,7 @@ of the annotation available.
:param asu: Asymmetric unit to work on. Should be created from a mmCIF
file.
- :type asu: :class:`~ost.mol.EntityHandle>`
+ :type asu: :class:`~ost.mol.EntityHandle`
:param seqres: If set to a valid sequence list, the length of the seqres
records will be used to determine if a certain chain has the minimally
required length.
@@ -948,3 +993,8 @@ of the annotation available.
.. LocalWords: auth GetMMCifPDBChainTr AddPDBCMMCifhainTr GetPDBMMCifChainTr
.. LocalWords: GetRevisions AddRevision SetRevisionsDateOriginal GetSize
.. LocalWords: GetNum num GetStatus GetLastDate GetFirstRelease storable
+.. LocalWords: SetChainList MMCifInfoTransOp ChainTypes MMCifInfoStructRef
+.. LocalWords: MMCifInfoRevisions bool difs MMCifInfoStructRefSeqDif rnum
+.. LocalWords: SetDateOriginal GetDateOriginal yyyy operationsintervalls
+.. LocalWords: chainintervalls GetChainIntervalList
+.. LocalWords: GetOperationsIntervalList
diff --git a/modules/io/pymod/__init__.py b/modules/io/pymod/__init__.py
index e9e597d726f5d921fb6938f12a13a221610b16b8..2bfe867309289f3daa5bb504ac1c18235c17b009 100644
--- a/modules/io/pymod/__init__.py
+++ b/modules/io/pymod/__init__.py
@@ -380,105 +380,110 @@ def _PDBize(biounit, asu, seqres=None, min_polymer_size=10,
return atom_pos_wrong
chain_names='ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789abcdefghijklmnopqrstuvwxyz'
+ cur_chain_name = 0
+ water_chain = mol.ChainHandle()
+ ligand_chain = mol.ChainHandle()
+ a_pos_wrong = False
+ pdb_bu = mol.CreateEntity()
+ edi = pdb_bu.EditXCS(mol.BUFFERED_EDIT)
+ chains = biounit.GetChainList()
+ c_intvls = biounit.GetChainIntervalList()
+ o_intvls = biounit.GetOperationsIntervalList()
# create list of operations
# for cartesian products, operations are stored in a list, multiplied with
# the next list of operations and re-stored... until all lists of operations
# are multiplied in an all-against-all manner.
operations = biounit.GetOperations()
- trans_matrices = list()
- if len(operations) > 0:
- for op in operations[0]:
- rot = geom.Mat4()
- rot.PasteRotation(op.rotation)
- trans = geom.Mat4()
- trans.PasteTranslation(op.translation)
- tr = geom.Mat4()
- tr = trans * rot
- trans_matrices.append(tr)
- for op_n in range(1, len(operations)):
- tmp_ops = list()
- for o in operations[op_n]:
+ for i in range(0,len(c_intvls)):
+ trans_matrices = list()
+ l_operations = operations[o_intvls[i][0]:o_intvls[i][1]]
+ if len(l_operations) > 0:
+ for op in l_operations[0]:
rot = geom.Mat4()
- rot.PasteRotation(o.rotation)
+ rot.PasteRotation(op.rotation)
trans = geom.Mat4()
- trans.PasteTranslation(o.translation)
+ trans.PasteTranslation(op.translation)
tr = geom.Mat4()
tr = trans * rot
- for t_o in trans_matrices:
- tp = t_o * tr
- tmp_ops.append(tp)
- trans_matrices = tmp_ops
- # select chains into a view as basis for each transformation
- assu = asu.Select('cname=' + ','.join(biounit.GetChainList()))
- # use each transformation on the view, store as entity and transform, PDBize
- # the result while adding everything to one large entity
- pdb_bu = mol.CreateEntity()
- edi = pdb_bu.EditXCS(mol.BUFFERED_EDIT)
- cur_chain_name = 0
- water_chain = mol.ChainHandle()
- ligand_chain = mol.ChainHandle()
- a_pos_wrong = False
- for tr in trans_matrices:
- # do a PDBize, add each new entity to the end product
- for chain in assu.chains:
- residue_count = len(chain.residues)
- if seqres:
- seqres_chain = seqres.FindSequence(chain.name)
- if seqres_chain.IsValid():
- residue_count = len(seqres_chain)
- if chain.is_polymer and residue_count >= min_polymer_size:
- if len(chain_names) == cur_chain_name:
- raise RuntimeError('Running out of chain names')
- new_chain = edi.InsertChain(chain_names[cur_chain_name])
- cur_chain_name += 1
- edi.SetChainDescription(new_chain, chain.description)
- edi.SetChainType(new_chain, chain.type)
- new_chain.SetStringProp('original_name', chain.name)
- if chain.HasProp("pdb_auth_chain_name"):
- new_chain.SetStringProp("pdb_auth_chain_name",
- chain.GetStringProp("pdb_auth_chain_name"))
- for res in chain.residues:
- new_res = edi.AppendResidue(new_chain, res.name, res.number)
- a_b = _CopyAtoms(res, new_res, edi, tr)
- if not a_pos_wrong:
- a_pos_wrong = a_b
- elif chain.type == mol.CHAINTYPE_WATER:
- if not water_chain.IsValid():
- # water gets '-' as name
- water_chain = edi.InsertChain('-')
- edi.SetChainDescription(water_chain, chain.description)
- edi.SetChainType(water_chain, chain.type)
- for res in chain.residues:
- new_res = edi.AppendResidue(water_chain, res.name)
- new_res.SetStringProp('type', mol.StringFromChainType(chain.type))
- new_res.SetStringProp('description', chain.description)
- a_b = _CopyAtoms(res, new_res, edi, tr)
- if not a_pos_wrong:
- a_pos_wrong = a_b
- else:
- if not ligand_chain.IsValid():
- # all ligands, put in one chain, are named '_'
- ligand_chain = edi.InsertChain('_')
- last_rnum = 0
- else:
- last_rnum = ligand_chain.residues[-1].number.num
- residues=chain.residues
- ins_code='\0'
- if len(residues)>1:
- ins_code='A'
- for res in chain.residues:
- new_res = edi.AppendResidue(ligand_chain, res.name,
- mol.ResNum(last_rnum+1, ins_code))
- new_res.SetStringProp('description', chain.description)
- new_res.SetStringProp('type', mol.StringFromChainType(chain.type))
- new_res.SetStringProp("original_name", chain.name)
+ trans_matrices.append(tr)
+ for op_n in range(1, len(l_operations)):
+ tmp_ops = list()
+ for o in l_operations[op_n]:
+ rot = geom.Mat4()
+ rot.PasteRotation(o.rotation)
+ trans = geom.Mat4()
+ trans.PasteTranslation(o.translation)
+ tr = geom.Mat4()
+ tr = trans * rot
+ for t_o in trans_matrices:
+ tp = t_o * tr
+ tmp_ops.append(tp)
+ trans_matrices = tmp_ops
+ # select chains into a view as basis for each transformation
+ assu = asu.Select('cname='+','.join(chains[c_intvls[i][0]:c_intvls[i][1]]))
+ # use each transformation on the view, store as entity and transform, PDBize
+ # the result while adding everything to one large entity
+ for tr in trans_matrices:
+ # do a PDBize, add each new entity to the end product
+ for chain in assu.chains:
+ residue_count = len(chain.residues)
+ if seqres:
+ seqres_chain = seqres.FindSequence(chain.name)
+ if seqres_chain.IsValid():
+ residue_count = len(seqres_chain)
+ if chain.is_polymer and residue_count >= min_polymer_size:
+ if len(chain_names) == cur_chain_name:
+ raise RuntimeError('Running out of chain names')
+ new_chain = edi.InsertChain(chain_names[cur_chain_name])
+ cur_chain_name += 1
+ edi.SetChainDescription(new_chain, chain.description)
+ edi.SetChainType(new_chain, chain.type)
+ new_chain.SetStringProp('original_name', chain.name)
if chain.HasProp("pdb_auth_chain_name"):
- new_res.SetStringProp("pdb_auth_chain_name",
- chain.GetStringProp("pdb_auth_chain_name"))
- ins_code = chr(ord(ins_code)+1)
- a_b = _CopyAtoms(res, new_res, edi, tr)
- if not a_pos_wrong:
- a_pos_wrong = a_b
+ new_chain.SetStringProp("pdb_auth_chain_name",
+ chain.GetStringProp("pdb_auth_chain_name"))
+ for res in chain.residues:
+ new_res = edi.AppendResidue(new_chain, res.name, res.number)
+ a_b = _CopyAtoms(res, new_res, edi, tr)
+ if not a_pos_wrong:
+ a_pos_wrong = a_b
+ elif chain.type == mol.CHAINTYPE_WATER:
+ if not water_chain.IsValid():
+ # water gets '-' as name
+ water_chain = edi.InsertChain('-')
+ edi.SetChainDescription(water_chain, chain.description)
+ edi.SetChainType(water_chain, chain.type)
+ for res in chain.residues:
+ new_res = edi.AppendResidue(water_chain, res.name)
+ new_res.SetStringProp('type', mol.StringFromChainType(chain.type))
+ new_res.SetStringProp('description', chain.description)
+ a_b = _CopyAtoms(res, new_res, edi, tr)
+ if not a_pos_wrong:
+ a_pos_wrong = a_b
+ else:
+ if not ligand_chain.IsValid():
+ # all ligands, put in one chain, are named '_'
+ ligand_chain = edi.InsertChain('_')
+ last_rnum = 0
+ else:
+ last_rnum = ligand_chain.residues[-1].number.num
+ residues=chain.residues
+ ins_code='\0'
+ if len(residues)>1:
+ ins_code='A'
+ for res in chain.residues:
+ new_res = edi.AppendResidue(ligand_chain, res.name,
+ mol.ResNum(last_rnum+1, ins_code))
+ new_res.SetStringProp('description', chain.description)
+ new_res.SetStringProp('type', mol.StringFromChainType(chain.type))
+ new_res.SetStringProp("original_name", chain.name)
+ if chain.HasProp("pdb_auth_chain_name"):
+ new_res.SetStringProp("pdb_auth_chain_name",
+ chain.GetStringProp("pdb_auth_chain_name"))
+ ins_code = chr(ord(ins_code)+1)
+ a_b = _CopyAtoms(res, new_res, edi, tr)
+ if not a_pos_wrong:
+ a_pos_wrong = a_b
move_to_origin = None
if a_pos_wrong:
start = pdb_bu.bounds.min
diff --git a/modules/io/pymod/export_mmcif_io.cc b/modules/io/pymod/export_mmcif_io.cc
index 78cd7e124f08460009e4f5b98432080e8422ae95..9a21bdb1af003bdaa33406e7f7e98754f8a606ea 100644
--- a/modules/io/pymod/export_mmcif_io.cc
+++ b/modules/io/pymod/export_mmcif_io.cc
@@ -21,6 +21,7 @@
#include <boost/python/suite/indexing/vector_indexing_suite.hpp>
using namespace boost::python;
+#include <ost/export_helper/pair_to_tuple_conv.hh>
#include <ost/io/mol/io_profile.hh>
#include <ost/io/mol/mmcif_reader.hh>
#include <ost/io/mol/mmcif_info.hh>
@@ -172,23 +173,44 @@ void export_mmcif_io()
.add_property("seq_rnum", &MMCifInfoStructRefSeqDif::GetSeqRNum)
.add_property("db_rnum", &MMCifInfoStructRefSeqDif::GetDBRNum)
;
+
+ typedef std::pair<int, int> IntPair;
+ to_python_converter<IntPair, PairToTupleConverter<int, int> >();
+ typedef std::vector<IntPair> VectorIntPair;
+ class_<VectorIntPair>("VectorIntPair", init<>())
+ .def(vector_indexing_suite<VectorIntPair, true>())
+ ;
+
class_<MMCifInfoBioUnit>("MMCifInfoBioUnit", init<>())
.def("SetDetails", &MMCifInfoBioUnit::SetDetails)
.def("GetDetails", &MMCifInfoBioUnit::GetDetails)
.def("AddChain", &MMCifInfoBioUnit::AddChain)
+ .def("SetChainList", &MMCifInfoBioUnit::SetChainList)
.def("GetChainList", make_function(&MMCifInfoBioUnit::GetChainList,
return_value_policy<copy_const_reference>()))
+ .def("GetChainIntervalList",
+ make_function(&MMCifInfoBioUnit::GetChainIntervalList,
+ return_value_policy<copy_const_reference>()))
.def("AddOperations", &MMCifInfoBioUnit::AddOperations)
.def("GetOperations", make_function(&MMCifInfoBioUnit::GetOperations,
return_value_policy<copy_const_reference>()))
+ .def("GetOperationsIntervalList",
+ make_function(&MMCifInfoBioUnit::GetOperationsIntervalList,
+ return_value_policy<copy_const_reference>()))
.def("SetID", &MMCifInfoBioUnit::SetID)
.def("GetID", &MMCifInfoBioUnit::GetID)
.add_property("details", &MMCifInfoBioUnit::GetDetails,
&MMCifInfoBioUnit::SetDetails)
.add_property("chains", make_function(&MMCifInfoBioUnit::GetChainList,
return_value_policy<copy_const_reference>()))
+ .add_property("chainintervalls", make_function(
+ &MMCifInfoBioUnit::GetChainIntervalList,
+ return_value_policy<copy_const_reference>()))
.add_property("operations", make_function(&MMCifInfoBioUnit::GetOperations,
return_value_policy<copy_const_reference>()))
+ .add_property("operationsintervalls", make_function(
+ &MMCifInfoBioUnit::GetOperationsIntervalList,
+ return_value_policy<copy_const_reference>()))
.add_property("id", &MMCifInfoBioUnit::GetID, &MMCifInfoBioUnit::SetID)
;
diff --git a/modules/io/src/mol/mmcif_info.cc b/modules/io/src/mol/mmcif_info.cc
index 29f0db7463188068b3584a49457126d7ec1601d0..e7f391894cab4e8ace515de79fa14f6e047fd683 100644
--- a/modules/io/src/mol/mmcif_info.cc
+++ b/modules/io/src/mol/mmcif_info.cc
@@ -72,7 +72,75 @@ void MMCifInfo::AddAuthorsToCitation(StringRef id, std::vector<String> list)
throw IOException("No citation for identifier '" + id.str() + "' found.");
}
+void MMCifInfo::AddBioUnit(MMCifInfoBioUnit bu)
+{
+ std::vector<MMCifInfoBioUnit>::iterator bu_it;
+ for (bu_it = biounits_.begin(); bu_it != biounits_.end(); ++bu_it) {
+ if (bu_it->GetID() == bu.GetID()) {
+ break;
+ }
+ }
+ if (bu_it != biounits_.end()) {
+ bu_it->Merge(bu);
+ return;
+ }
+ biounits_.push_back(bu);
+}
+void MMCifInfoBioUnit::AddChain(String chain)
+{
+ chains_.push_back(chain);
+
+ if (tr_chains_.size()) {
+ tr_chains_.back().second = chains_.size();
+ }
+ else {
+ std::pair<int, int> tr_interval = std::pair<int, int>(0, 1);
+ tr_chains_.push_back(tr_interval);
+ }
+}
+
+void MMCifInfoBioUnit::SetChainList(std::vector<String> chains)
+{
+ chains_ = chains;
+
+ if (tr_chains_.size()) {
+ tr_chains_.clear();
+ }
+ std::pair<int, int> tr_interval = std::pair<int, int>(0, chains_.size());
+ tr_chains_.push_back(tr_interval);
+}
+
+void MMCifInfoBioUnit::AddOperations(std::vector<MMCifInfoTransOpPtr> operations)
+{
+ operations_.push_back(operations);
+
+ if (tr_operations_.size()) {
+ tr_operations_.back().second = operations_.size();
+ }
+ else {
+ std::pair<int, int> tr_interval = std::pair<int, int>(0, 1);
+ tr_operations_.push_back(tr_interval);
+ }
+}
+
+void MMCifInfoBioUnit::Merge(MMCifInfoBioUnit& from)
+{
+ // merge chains
+ int old_size = chains_.size();
+ chains_.insert(chains_.end(), from.chains_.begin(), from.chains_.end());
+ std::pair<int, int> tr_interval = std::pair<int, int>(old_size,
+ chains_.size());
+ tr_chains_.push_back(tr_interval);
+ // merge operations
+ old_size = operations_.size();
+ operations_.insert(operations_.end(),
+ from.operations_.begin(),
+ from.operations_.end());
+ tr_interval.first = old_size;
+ tr_interval.second = operations_.size();
+ tr_operations_.push_back(tr_interval);
+}
MMCifInfoStructRefSeqPtr
MMCifInfoStructRef::AddAlignedSeq(const String& aid, const String& chain_name,
@@ -108,5 +176,4 @@ MMCifInfoStructRefSeq::AddDif(int seq_rnum, int db_rnum, const String& details)
return d;
}
-
}} //ns
diff --git a/modules/io/src/mol/mmcif_info.hh b/modules/io/src/mol/mmcif_info.hh
index f567af0520381f6b726be63046235e2dd0b9a87a..52a44aedc1baf2dcea4255f4a4980eeaec03570f 100644
--- a/modules/io/src/mol/mmcif_info.hh
+++ b/modules/io/src/mol/mmcif_info.hh
@@ -241,6 +241,11 @@ public:
/// \brief Create a biounit.
MMCifInfoBioUnit(): id_(""), details_("") {};
+ /// \brief Merge chains & operations, set intervals
+ ///
+ /// \param from biounit to read data from
+ void Merge(MMCifInfoBioUnit& from);
+
/// \brief Set id
///
/// \param id id
@@ -262,19 +267,39 @@ public:
/// \brief Add a chain name
///
/// \param chain chain name
- void AddChain(String chain) { chains_.push_back(chain); }
+ void AddChain(String chain);
+
+ /// \brief Set a vector of chain names
+ ///
+ /// \param chains chain name
+ void SetChainList(std::vector<String> chains);
+
/// \brief Get vector of chain names
///
/// \return chains
const std::vector<String>& GetChainList() const { return chains_; }
+ /// \brief Get the list of intervals of chains
+ ///
+ /// \return pair-intervals
+ const std::vector<std::pair<int, int> >& GetChainIntervalList()
+ {
+ return tr_chains_;
+ }
+
/// \brief Add a set of operations
///
/// \param operations vector of operations to be added
- void AddOperations(std::vector<MMCifInfoTransOpPtr> operations)
+ void AddOperations(std::vector<MMCifInfoTransOpPtr> operations);
+
+ /// \brief Get the list of intervals of operations
+ ///
+ /// \return pair-intervals
+ const std::vector<std::pair<int, int> >& GetOperationsIntervalList()
{
- operations_.push_back(operations);
+ return tr_operations_;
}
+
/// \brief Get the list of operations
///
/// \return vector of vectors of iterators.
@@ -293,6 +318,12 @@ public:
if (this->chains_ != bu.chains_) {
return false;
}
+ if (this->tr_chains_ != bu.tr_chains_) {
+ return false;
+ }
+ if (this->tr_operations_ != bu.tr_operations_) {
+ return false;
+ }
if (this->operations_.size() == bu.operations_.size()) {
std::vector<std::vector<MMCifInfoTransOpPtr> >::const_iterator th_ops_it;
std::vector<std::vector<MMCifInfoTransOpPtr> >::const_iterator bu_ops_it;
@@ -329,8 +360,10 @@ public:
private:
String id_; ///< pdbx_struct_assembly.id
String details_; ///< pdbx_struct_assembly.details
- std::vector<String> chains_; ///< chains involved in this assembly
+ std::vector<String> chains_; ///< all chains of this this assembly
+ std::vector<std::pair<int, int> > tr_chains_; //< chains of a transformation
std::vector<std::vector<MMCifInfoTransOpPtr> > operations_;
+ std::vector<std::pair<int, int> > tr_operations_; //< ops. of a transformation
};
class DLLEXPORT_OST_IO MMCifInfoCitation {
@@ -888,10 +921,7 @@ public:
/// \brief Add a biounit
///
/// \param bu biounit to be added
- void AddBioUnit(MMCifInfoBioUnit bu) // unit test
- {
- biounits_.push_back(bu);
- }
+ void AddBioUnit(MMCifInfoBioUnit bu);
/// \brief Get the list of biounits stored in an info object.
///
diff --git a/modules/io/src/mol/mmcif_reader.cc b/modules/io/src/mol/mmcif_reader.cc
index 33e71d4e3daeced0ddf26484cdfb4c0dfe9bbccf..91d46cb9b86646add1832a8ea972b6c316a3cba7 100644
--- a/modules/io/src/mol/mmcif_reader.cc
+++ b/modules/io/src/mol/mmcif_reader.cc
@@ -981,14 +981,13 @@ std::vector<std::vector<String> > MMCifReader::UnPackOperExperession(StringRef e
void MMCifReader::ParsePdbxStructAssemblyGen(const std::vector<StringRef>& columns)
{
MMCifBioUAssembly assembly;
- assembly.biounit = MMCifInfoBioUnit();
- assembly.biounit.SetID(columns[indices_[ASSEMBLY_ID]].str());
+ assembly.biounit_id = columns[indices_[ASSEMBLY_ID]].str();
std::vector<StringRef> tmp_chains=columns[indices_[ASYM_ID_LIST]].split(',');
std::vector<StringRef>::const_iterator tc_it;
for (tc_it = tmp_chains.begin(); tc_it != tmp_chains.end(); ++tc_it) {
- assembly.biounit.AddChain(tc_it->str());
+ assembly.chains.push_back(tc_it->str());
}
assembly.operations =
@@ -1620,19 +1619,22 @@ void MMCifReader::OnEndData()
std::vector<MMCifInfoTransOpPtr> operations = info_.GetOperations();
info_.SetStructRefs(struct_refs_);
std::vector<MMCifInfoTransOpPtr>::const_iterator buop_it;
+ MMCifInfoBioUnit biounit;
for (bua_it = bu_assemblies_.begin();
bua_it != bu_assemblies_.end();
++bua_it) {
+ biounit = MMCifInfoBioUnit();
// pair with pdbx_struct_assembly entry
- buom_it = bu_origin_map_.find(bua_it->biounit.GetID());
+ buom_it = bu_origin_map_.find(bua_it->biounit_id);
if (buom_it == bu_origin_map_.end()) {
throw IOException(this->FormatDiagnostic(STAR_DIAG_ERROR,
"No pdbx_struct_assembly.id '"+
- bua_it->biounit.GetID() +
+ bua_it->biounit_id +
"' found as requested by pdbx_struct_assembly_gen."));
}
- bua_it->biounit.SetDetails(buom_it->second);
- bua_it->biounit.SetID(buom_it->first);
+ biounit.SetDetails(buom_it->second);
+ biounit.SetID(buom_it->first);
+ biounit.SetChainList(bua_it->chains);
// pair with pdbx_struct_oper_list
for (aol_it = bua_it->operations.begin();
@@ -1657,9 +1659,9 @@ void MMCifReader::OnEndData()
"' found as requested by pdbx_struct_assembly_gen."));
}
}
- bua_it->biounit.AddOperations(operation_list);
+ biounit.AddOperations(operation_list);
}
- info_.AddBioUnit(bua_it->biounit);
+ info_.AddBioUnit(biounit);
}
bu_assemblies_.clear();
diff --git a/modules/io/src/mol/mmcif_reader.hh b/modules/io/src/mol/mmcif_reader.hh
index b8f6daed068fd5c96293d4d8e6442d24a74b3e0b..d91cf340355be48f58664a4ada5e02966365e931 100644
--- a/modules/io/src/mol/mmcif_reader.hh
+++ b/modules/io/src/mol/mmcif_reader.hh
@@ -559,9 +559,11 @@ private:
/// \struct assembly information
typedef struct {
- MMCifInfoBioUnit biounit;
+ String biounit_id; ///< identifier for the bu
+ std::vector<String> chains; ///< chains affected by
+ /// this operations
std::vector<std::vector<String> > operations; ///< list of links to
- /// MMCifBioUOperation
+ /// MMCifBioUOperation
} MMCifBioUAssembly;
typedef std::vector<MMCifBioUAssembly> MMCifBioUAssemblyVector;
diff --git a/modules/io/tests/test_io_mmcif.py b/modules/io/tests/test_io_mmcif.py
index 9b5481d6d821ccc54c133961d4128fa2654ed915..be7594314f103c127f2c6297066daf45f24e7d21 100644
--- a/modules/io/tests/test_io_mmcif.py
+++ b/modules/io/tests/test_io_mmcif.py
@@ -69,14 +69,38 @@ class TestMMCifInfo(unittest.TestCase):
b.SetDetails('Details')
self.assertEquals(b.GetDetails(), 'Details')
b.AddChain('A')
+ b.AddChain('B')
cl = b.GetChainList()
+ il = b.GetChainIntervalList()
self.assertEquals(cl[0], 'A')
+ self.assertEquals(il[0][0], 0)
+ self.assertEquals(il[0][1], 2)
+ s = ost.StringList()
+ s.append('B')
+ s.append('C')
+ s.append('D')
+ b.SetChainList(s)
+ cl = b.GetChainList()
+ il = b.GetChainIntervalList()
+ self.assertEquals(il[0][0], 0)
+ self.assertEquals(il[0][1], 3)
+ self.assertEquals(cl[0], 'B')
+ self.assertEquals(cl[1], 'C')
+ self.assertEquals(cl[2], 'D')
i = io.MMCifInfo()
i.AddBioUnit(b)
+ i.AddBioUnit(b)
+ b.SetID("2")
+ i.AddBioUnit(b)
bl = i.GetBioUnits()
- self.assertEquals(len(bl), 1)
+ il = bl[0].GetChainIntervalList()
+ self.assertEquals(il[0][0], 0)
+ self.assertEquals(il[0][1], 3)
+ self.assertEquals(il[1][0], 3)
+ self.assertEquals(il[1][1], 6)
+ self.assertEquals(len(bl), 2)
def test_mmcifinfo_transoperation(self):
@@ -102,6 +126,10 @@ class TestMMCifInfo(unittest.TestCase):
b.AddOperations(ol)
oll = b.GetOperations()
self.assertEquals(oll[0][0].GetID(), '1')
+ tr_ol = b.GetOperationsIntervalList()
+ self.assertEquals(len(tr_ol), 1)
+ self.assertEquals(tr_ol[0][0], 0)
+ self.assertEquals(tr_ol[0][1], 1)
def test_mmcifinfo_biounit_pdbize(self):
ent, seqres, info = io.LoadMMCIF("testfiles/mmcif/3T6C.cif.gz",
diff --git a/modules/io/tests/test_mmcif_info.cc b/modules/io/tests/test_mmcif_info.cc
index 3f3e21baf4b8a9e3f10b8f65380338668015bfd3..71dc2ddf40d7433c60629497288cf6e989528a5d 100644
--- a/modules/io/tests/test_mmcif_info.cc
+++ b/modules/io/tests/test_mmcif_info.cc
@@ -109,10 +109,23 @@ BOOST_AUTO_TEST_CASE(mmcif_info_biounit)
MMCifInfoBioUnit bu = MMCifInfoBioUnit();
bu.SetDetails("author_defined_assembly");
+ bu.SetID("1");
+ bu.AddChain("B");
bu.AddChain("A");
BOOST_CHECK(bu.GetDetails() == "author_defined_assembly");
BOOST_CHECK(bu.GetChainList().back() == "A");
+ std::vector<std::pair<int, int> > tr = bu.GetChainIntervalList();
+ BOOST_CHECK(tr[0].first == 0);
+ BOOST_CHECK(tr[0].second == 2);
+
+ std::vector<String> chains;
+ chains.push_back("B");
+ bu.SetChainList(chains);
+ BOOST_CHECK(bu.GetChainList().back() == "B");
+ tr = bu.GetChainIntervalList();
+ BOOST_CHECK(tr[0].first == 0);
+ BOOST_CHECK(tr[0].second == 1);
MMCifInfo info = MMCifInfo();
info.AddBioUnit(bu);
@@ -120,6 +133,18 @@ BOOST_AUTO_TEST_CASE(mmcif_info_biounit)
BOOST_CHECK(biounits.size() == 1);
BOOST_CHECK(biounits.back() == bu);
+ info.AddBioUnit(bu);
+ bu.SetID("2");
+ info.AddBioUnit(bu);
+ biounits = info.GetBioUnits();
+ BOOST_CHECK(biounits.size() == 2);
+ tr = biounits.front().GetChainIntervalList();
+ BOOST_CHECK(tr.size() == 2);
+ BOOST_CHECK(tr[0].first == 0);
+ BOOST_CHECK(tr[0].second == 1);
+ BOOST_CHECK(tr[1].first == 1);
+ BOOST_CHECK(tr[1].second == 2);
+
BOOST_MESSAGE(" done.");
}
@@ -148,6 +173,10 @@ BOOST_AUTO_TEST_CASE(mmcif_info_transoperation)
MMCifInfoBioUnit bu = MMCifInfoBioUnit();
bu.AddOperations(ops);
BOOST_CHECK((*(bu.GetOperations().begin()->begin())) == op);
+ std::vector<std::pair<int, int> > tr = bu.GetOperationsIntervalList();
+ BOOST_CHECK(tr.size() == 1);
+ BOOST_CHECK(tr.back().first == 0);
+ BOOST_CHECK(tr.back().second == 1);
BOOST_MESSAGE(" done.");
}