diff --git a/modules/io/src/mol/mmcif_reader.cc b/modules/io/src/mol/mmcif_reader.cc
index 6392ef4b11cc5f3eaff1fbd23536f0ffe03586b5..1b7f9a00382ad94035d2883a7bab0e921fe8c77e 100644
--- a/modules/io/src/mol/mmcif_reader.cc
+++ b/modules/io/src/mol/mmcif_reader.cc
@@ -362,7 +362,13 @@ bool MMCifReader::OnBeginLoop(const StarLoopDesc& header)
indices_[PDS_RECVD_INITIAL_DEPOSITION_DATE]
= header.GetIndex("recvd_initial_deposition_date");
cat_available = true;
- }
+ } else if (header.GetCategory() == "pdbx_entity_branch") {
+ category_ = PDBX_ENTITY_BRANCH;
+ // mandatory
+ this->TryStoreIdx(BR_ENTITY_ID, "entity_id", header);
+ this->TryStoreIdx(BR_ENTITY_TYPE, "type", header);
+ cat_available = true;
+ }
category_counts_[category_]++;
return cat_available;
}
@@ -1541,6 +1547,10 @@ void MMCifReader::OnDataRow(const StarLoopDesc& header,
LOG_TRACE("processing pdbx_database_status entry");
this->ParsePdbxDatabaseStatus(columns);
break;
+ case PDBX_ENTITY_BRANCH:
+ LOG_TRACE("processing pdbx_entity_branch entry");
+ this->ParsePdbxEntityBranch(columns);
+ break;
default:
throw IOException(this->FormatDiagnostic(STAR_DIAG_ERROR,
"Uncatched category '"+ header.GetCategory() +"' found.",
@@ -1679,6 +1689,28 @@ void MMCifReader::ParseStructRefSeqDif(const std::vector<StringRef>& columns)
}
}
+void MMCifReader::ParsePdbxEntityBranch(const std::vector<StringRef>& columns)
+{
+ // we assume that the entity cat. ALWAYS comes before the pdbx_entity_branch
+ // cat.
+ // search entity
+ MMCifEntityDescMap::iterator edm_it =
+ entity_desc_map_.find(columns[indices_[BR_ENTITY_ID]].str());
+
+ if (edm_it == entity_desc_map_.end()) {
+ throw IOException(this->FormatDiagnostic(STAR_DIAG_ERROR,
+ "'pdbx_entity_branch' category defined before 'entity' for id '" +
+ columns[indices_[BR_ENTITY_ID]].str() +
+ "' or missing.",
+ this->GetCurrentLinenum()));
+ }
+
+ // store type
+ if (indices_[BR_ENTITY_TYPE] != -1) {
+ edm_it->second.type = mol::ChainTypeFromString(columns[indices_[EP_TYPE]]);
+ }
+}
+
void MMCifReader::OnEndData()
{
mol::XCSEditor editor=ent_handle_.EditXCS(mol::BUFFERED_EDIT);
diff --git a/modules/io/src/mol/mmcif_reader.hh b/modules/io/src/mol/mmcif_reader.hh
index 9147a234c4f4966b4ac861f45c48f0a2e7bee829..5e1e2204a9da08e6bdfbdd920f5fd1d8af7ccbc9 100644
--- a/modules/io/src/mol/mmcif_reader.hh
+++ b/modules/io/src/mol/mmcif_reader.hh
@@ -56,6 +56,7 @@ namespace ost { namespace io {
/// \li struct_sheet_range
/// \li pdbx_database_PDB_obs_spr
/// \li database_PDB_rev
+/// \li pdbx_entity_branch
class DLLEXPORT_OST_IO MMCifReader : public StarParser {
public:
/// \brief create a MMCifReader
@@ -326,6 +327,11 @@ protected:
/// \param columns data row
void ParsePdbxDatabasePdbObsSpr(const std::vector<StringRef>& columns);
+ /// \brief Fetch mmCIF pdbx_entity_branch information
+ ///
+ /// \param columns data row
+ void ParsePdbxEntityBranch(const std::vector<StringRef>& columns);
+
/// \struct types of secondary structure
typedef enum {
MMCIF_HELIX,
@@ -561,6 +567,12 @@ private:
PDS_RECVD_INITIAL_DEPOSITION_DATE, ///< date of initial deposition
} PdbxDatabaseStatusItems;
+ /// \enum items of the pdbx_entity_branch category (pendant to entity_poly)
+ typedef enum {
+ BR_ENTITY_ID, ///< pointer to entity.id
+ BR_ENTITY_TYPE ///< type of branched molecular entity
+ } EntityBranchItems;
+
/// \enum categories of the mmcif format
typedef enum {
ATOM_SITE,
@@ -584,6 +596,7 @@ private:
PDBX_AUDIT_REVISION_HISTORY,
PDBX_AUDIT_REVISION_DETAILS,
PDBX_DATABASE_STATUS,
+ PDBX_ENTITY_BRANCH,
DONT_KNOW
} MMCifCategory;
diff --git a/modules/mol/base/doc/entity.rst b/modules/mol/base/doc/entity.rst
index ffb82993ce5c368bad66610b2567f7b48d67a390..3a4d0d292748f1c8f7546468d8f8b4657c9d10c2 100644
--- a/modules/mol/base/doc/entity.rst
+++ b/modules/mol/base/doc/entity.rst
@@ -1972,7 +1972,8 @@ here.
``CHAINTYPE_POLY_SAC_L``, ``CHAINTYPE_POLY_DN_RN``,
``CHAINTYPE_UNKNOWN``, ``CHAINTYPE_MACROLIDE``,
``CHAINTYPE_CYCLIC_PSEUDO_PEPTIDE``, ``CHAINTYPE_POLY_PEPTIDE_DN_RN``,
- ``CHAINTYPE_BRANCHED``, ``CHAINTYPE_N_CHAINTYPES``
+ ``CHAINTYPE_BRANCHED``, ``CHAINTYPE_OLIGOSACCHARIDE``,
+ ``CHAINTYPE_N_CHAINTYPES``
Where ``CHAINTYPE_N_CHAINTYPES`` holds the number of different types available.
diff --git a/modules/mol/base/pymod/export_chain.cc b/modules/mol/base/pymod/export_chain.cc
index e81d6e1594171011792023f07ab4b59813d31332..1664c13a33ed03c1fbdc404bbac9b081522c8e4a 100644
--- a/modules/mol/base/pymod/export_chain.cc
+++ b/modules/mol/base/pymod/export_chain.cc
@@ -138,6 +138,7 @@ void export_Chain()
.value("CHAINTYPE_CYCLIC_PSEUDO_PEPTIDE", CHAINTYPE_CYCLIC_PSEUDO_PEPTIDE)
.value("CHAINTYPE_POLY_PEPTIDE_DN_RN", CHAINTYPE_POLY_PEPTIDE_DN_RN)
.value("CHAINTYPE_BRANCHED", CHAINTYPE_BRANCHED)
+ .value("CHAINTYPE_OLIGOSACCHARIDE", CHAINTYPE_OLIGOSACCHARIDE)
.value("CHAINTYPE_N_CHAINTYPES", CHAINTYPE_N_CHAINTYPES)
.export_values()
;
diff --git a/modules/mol/base/src/chain_type.cc b/modules/mol/base/src/chain_type.cc
index 5b2fb1350466b127391dc55d266adbea9713361c..6694aa017ab0c7cf89ba6e8d5cce6d2b495940f2 100644
--- a/modules/mol/base/src/chain_type.cc
+++ b/modules/mol/base/src/chain_type.cc
@@ -34,6 +34,8 @@ ChainType ChainTypeFromString(StringRef identifier)
return CHAINTYPE_WATER;
} else if (StringRef("macrolide", 9) == identifier) {
return CHAINTYPE_MACROLIDE;
+ } else if (StringRef("branched", 8) == identifier) {
+ return CHAINTYPE_BRANCHED;
// chain types as found in the entity_poly category of a mmcif file
} else if (StringRef("polypeptide(D)", 14) == identifier) {
return CHAINTYPE_POLY_PEPTIDE_D;
@@ -54,8 +56,8 @@ ChainType ChainTypeFromString(StringRef identifier)
return CHAINTYPE_CYCLIC_PSEUDO_PEPTIDE;
} else if (StringRef("peptide nucleic acid", 20) == identifier) {
return CHAINTYPE_POLY_PEPTIDE_DN_RN;
- } else if (StringRef("branched", 8) == identifier) {
- return CHAINTYPE_BRANCHED;
+ } else if (StringRef("oligosaccharide", 15) == identifier) {
+ return CHAINTYPE_OLIGOSACCHARIDE;
} else if (StringRef("other", 5) == identifier) {
return CHAINTYPE_UNKNOWN;
}
@@ -81,6 +83,8 @@ String StringFromChainType(ChainType type)
return "water";
} else if (CHAINTYPE_MACROLIDE == type) {
return "macrolide";
+ } else if (CHAINTYPE_BRANCHED == type) {
+ return "branched";
// chain types as found in the entity_poly category of a mmcif file
} else if (CHAINTYPE_POLY_PEPTIDE_D == type) {
return "polypeptide(D)";
@@ -100,8 +104,8 @@ String StringFromChainType(ChainType type)
return "cyclic-pseudo-peptide";
} else if (CHAINTYPE_POLY_PEPTIDE_DN_RN == type) {
return "peptide nucleic acid";
- } else if (CHAINTYPE_BRANCHED == type) {
- return "branched";
+ } else if (CHAINTYPE_OLIGOSACCHARIDE == type) {
+ return "oligosaccharide";
} else if (CHAINTYPE_UNKNOWN == type) {
return "other";
}
diff --git a/modules/mol/base/src/chain_type.hh b/modules/mol/base/src/chain_type.hh
index bfc664758b2c2f1c863aa6402bf9322f0ffbf8b4..08ce4dcc6462a726a367eaf34708b789d684dcc0 100644
--- a/modules/mol/base/src/chain_type.hh
+++ b/modules/mol/base/src/chain_type.hh
@@ -45,6 +45,7 @@ typedef enum {
CHAINTYPE_CYCLIC_PSEUDO_PEPTIDE, ///< cyclic-pseudo-peptide
CHAINTYPE_POLY_PEPTIDE_DN_RN, ///< peptide nucleic acid
CHAINTYPE_BRANCHED, ///< carbohydrate
+ CHAINTYPE_OLIGOSACCHARIDE, ///< oligosaccharide (branched carbohydrate)
CHAINTYPE_N_CHAINTYPES ///< no. of chain types
} ChainType;
diff --git a/modules/mol/base/tests/test_chain.cc b/modules/mol/base/tests/test_chain.cc
index 15838c9f0cf9223ba90504c889893ba911bd5765..4c2127670e1a65b67b0230a8a629809462e8712a 100644
--- a/modules/mol/base/tests/test_chain.cc
+++ b/modules/mol/base/tests/test_chain.cc
@@ -319,13 +319,18 @@ BOOST_AUTO_TEST_CASE(chain_type)
BOOST_CHECK(!ch1.IsPolysaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
-
e.SetChainType(ch1, CHAINTYPE_BRANCHED);
BOOST_CHECK(ch1.GetType() == CHAINTYPE_BRANCHED);
BOOST_CHECK(!ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
+ e.SetChainType(ch1, CHAINTYPE_OLIGOSACCHARIDE);
+ BOOST_CHECK(ch1.GetType() == CHAINTYPE_OLIGOSACCHARIDE);
+ BOOST_CHECK(!ch1.IsPolymer());
+ BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsPolypeptide());
+ BOOST_CHECK(!ch1.IsPolynucleotide());
// string -> chain type
BOOST_CHECK(ChainTypeFromString("polymer") == CHAINTYPE_POLY);
@@ -353,6 +358,8 @@ BOOST_AUTO_TEST_CASE(chain_type)
BOOST_CHECK(ChainTypeFromString("peptide nucleic acid") ==
CHAINTYPE_POLY_PEPTIDE_DN_RN);
BOOST_CHECK(ChainTypeFromString("branched") == CHAINTYPE_BRANCHED);
+ BOOST_CHECK(ChainTypeFromString("oligosaccharide") ==
+ CHAINTYPE_OLIGOSACCHARIDE);
BOOST_CHECK_THROW(ChainTypeFromString("supposed to fail"),
Error);
@@ -380,6 +387,8 @@ BOOST_AUTO_TEST_CASE(chain_type)
BOOST_CHECK(StringFromChainType(CHAINTYPE_POLY_PEPTIDE_DN_RN) ==
"peptide nucleic acid");
BOOST_CHECK(StringFromChainType(CHAINTYPE_BRANCHED) == "branched");
+ BOOST_CHECK(StringFromChainType(CHAINTYPE_OLIGOSACCHARIDE) ==
+ "oligosaccharide");
BOOST_CHECK_THROW(StringFromChainType(CHAINTYPE_N_CHAINTYPES),
Error);
}