From 491c71b4e8a7290464f8c5f82015ae0b2f2a4fa1 Mon Sep 17 00:00:00 2001
From: Stefan Bienert <stefan.bienert@unibas.ch>
Date: Fri, 20 Jul 2012 15:10:26 +0200
Subject: [PATCH] (cherry-pick) Added PDB chain name to Cif chain name map.
Solved conflicts:
modules/io/doc/mmcif.rst
modules/io/pymod/export_mmcif_io.cc
modules/io/src/mol/mmcif_info.cc
modules/io/src/mol/mmcif_info.hh
modules/io/tests/test_mmcif_info.cc
---
modules/io/doc/mmcif.rst | 39 ++++++++++++++++++-
modules/io/pymod/export_mmcif_io.cc | 4 ++
modules/io/src/mol/mmcif_info.cc | 36 +++++++++++++++++
modules/io/src/mol/mmcif_info.hh | 27 +++++++++++++
modules/io/src/mol/mmcif_reader.cc | 4 ++
modules/io/tests/test_mmcif_info.cc | 12 +++++-
.../io/tests/testfiles/mmcif/atom_site.mmcif | 8 ++--
7 files changed, 124 insertions(+), 6 deletions(-)
diff --git a/modules/io/doc/mmcif.rst b/modules/io/doc/mmcif.rst
index e172b34a3..38934cc79 100644
--- a/modules/io/doc/mmcif.rst
+++ b/modules/io/doc/mmcif.rst
@@ -160,6 +160,42 @@ of the annotation available.
.. method:: GetStructDetails()
+ .. method:: AddMMCifPDBChainTr(cif_chain_id, pdb_chain_id)
+
+ Set up a translation for a certain mmCIF chain name to the traditional PDB
+ chain name.
+
+ :param cif_chain_id: atom_site.label_asym_id
+ :type cif_chain_id: :class:`str`
+ :param pdb_chain_id: atom_site.auth_asym_id
+ :type pdb_chain_id: :class:`str`
+
+ .. method:: GetMMCifPDBChainTr(cif_chain_id)
+
+ Get the translation of a certain mmCIF chain name to the traditional PDB
+ chain name.
+
+ :param cif_chain_id: atom_site.label_asym_id
+ :type cif_chain_id: :class:`str`
+ :returns: atom_site.auth_asym_id as :class:`str`
+
+ .. method:: AddPDBCMMCifhainTr(pdb_chain_id, cif_chain_id)
+
+ Set up a translation for a certain PDB chain name to the mmCIF chain name.
+
+ :param pdb_chain_id: atom_site.label_asym_id
+ :type pdb_chain_id: :class:`str`
+ :param cif_chain_id: atom_site.auth_asym_id
+ :type cif_chain_id: :class:`str`
+
+ .. method:: GetPDBMMCifChainTr(pdb_chain_id)
+
+ Get the translation of a certain PDB chain name to the mmCIF chain name.
+
+ :param pdb_chain_id: atom_site.auth_asym_id
+ :type pdb_chain_id: :class:`str`
+ :returns: atom_site.label_asym_id as :class:`str`
+
.. class:: MMCifInfoCitation
This stores citation information from an input file.
@@ -794,4 +830,5 @@ of the annotation available.
.. LocalWords: cas isbn pubmed asu seqres conop ConnectAll casp COMPND OBSLTE
.. LocalWords: SPRSDE pdb func autofunction exptl attr pdbx oper conf spr dif
-.. LocalWords: biounits biounit uniprot UNP seqs
+.. LocalWords: biounits biounit uniprot UNP seqs AddMMCifPDBChainTr cif asym
+.. LocalWords: auth GetMMCifPDBChainTr AddPDBCMMCifhainTr GetPDBMMCifChainTr
diff --git a/modules/io/pymod/export_mmcif_io.cc b/modules/io/pymod/export_mmcif_io.cc
index 6654393be..18ec3713b 100644
--- a/modules/io/pymod/export_mmcif_io.cc
+++ b/modules/io/pymod/export_mmcif_io.cc
@@ -280,6 +280,10 @@ void export_mmcif_io()
.def("GetStructDetails", &MMCifInfo::GetStructDetails)
.def("SetObsoleteInfo", &MMCifInfo::SetObsoleteInfo)
.def("GetObsoleteInfo", &MMCifInfo::GetObsoleteInfo)
+.def("AddMMCifPDBChainTr", &MMCifInfo::AddMMCifPDBChainTr)
+ .def("GetMMCifPDBChainTr", &MMCifInfo::GetMMCifPDBChainTr)
+ .def("AddPDBMMCifChainTr", &MMCifInfo::AddPDBMMCifChainTr)
+ .def("GetPDBMMCifChainTr", &MMCifInfo::GetPDBMMCifChainTr)
.add_property("citations", make_function(&MMCifInfo::GetCitations,
return_value_policy<copy_const_reference>()))
.add_property("biounits", make_function(&MMCifInfo::GetBioUnits,
diff --git a/modules/io/src/mol/mmcif_info.cc b/modules/io/src/mol/mmcif_info.cc
index c8565a2e8..29f0db746 100644
--- a/modules/io/src/mol/mmcif_info.cc
+++ b/modules/io/src/mol/mmcif_info.cc
@@ -22,6 +22,42 @@
namespace ost { namespace io {
+void MMCifInfo::AddMMCifPDBChainTr(String cif, String pdb)
+{
+ std::map<String, String>::iterator tr_it = cif_2_pdb_chain_id_.find(cif);
+ if (tr_it != cif_2_pdb_chain_id_.end()) {
+ throw IOException("mmCIF chain id '"+ cif +"' is already mapped to '"+
+ tr_it->second+"'.");
+ }
+ cif_2_pdb_chain_id_.insert(std::pair<String, String>(cif, pdb));
+}
+
+String MMCifInfo::GetMMCifPDBChainTr(String cif) const
+{
+ std::map<String, String>::const_iterator tr_it =
+ cif_2_pdb_chain_id_.find(cif);
+ if (tr_it == cif_2_pdb_chain_id_.end()) { return ""; }
+ return tr_it->second;
+}
+
+void MMCifInfo::AddPDBMMCifChainTr(String pdb, String cif)
+{
+ std::map<String, String>::iterator tr_it = pdb_2_cif_chain_id_.find(pdb);
+ if (tr_it != pdb_2_cif_chain_id_.end()) {
+ throw IOException("PDB chain id '"+ pdb +"' is already mapped to '"+
+ tr_it->second+"'.");
+ }
+ pdb_2_cif_chain_id_.insert(std::pair<String, String>(pdb, cif));
+}
+
+String MMCifInfo::GetPDBMMCifChainTr(String pdb) const
+{
+ std::map<String, String>::const_iterator tr_it =
+ pdb_2_cif_chain_id_.find(pdb);
+ if (tr_it == pdb_2_cif_chain_id_.end()) { return ""; }
+ return tr_it->second;
+}
+
void MMCifInfo::AddAuthorsToCitation(StringRef id, std::vector<String> list)
{
// find citation
diff --git a/modules/io/src/mol/mmcif_info.hh b/modules/io/src/mol/mmcif_info.hh
index b240e5a1c..3eebf54b2 100644
--- a/modules/io/src/mol/mmcif_info.hh
+++ b/modules/io/src/mol/mmcif_info.hh
@@ -22,6 +22,7 @@
#include <vector>
#include <map>
#include <boost/shared_ptr.hpp>
+#include <ost/seq/sequence_list.hh>
#include <ost/geom/geom.hh>
#include <ost/string_ref.hh>
#include <ost/io/module_config.hh>
@@ -771,6 +772,30 @@ public:
/// \return experiment resolution
Real GetResolution() const { return resolution_; }
+ /// \brief Add a new mmCIF/ PDB chain name tuple.
+ ///
+ /// \param cif chain name as used by the mmCIF file (label_asym_id)
+ /// \param pdb chain name as used in the PDB file (auth_asym_id)
+ void AddMMCifPDBChainTr(String cif, String pdb);
+
+ /// \brief Get a PDB chain name for a CIF chain name
+ ///
+ /// \param cif chain name as used by the mmCIF file (label_asym_id)
+ /// \return chain name as used in the PDB file (auth_asym_id)
+ String GetMMCifPDBChainTr(String cif) const;
+
+ /// \brief Add a new PDB/ mmCIF chain name tuple.
+ ///
+ /// \param pdb chain name as used by the PDB file (auth_asym_id)
+ /// \param cif chain name as used in the mmCIF file (label_asym_id)
+ void AddPDBMMCifChainTr(String pdb, String cif);
+
+ /// \brief Get a CIF chain name for a PDB chain name
+ ///
+ /// \param pdb chain name as used by the mmCIF file (auth_asym_id)
+ /// \return chain name as used in the PDB file (label_asym_id)
+ String GetPDBMMCifChainTr(String pdb) const;
+
/// \brief Add a biounit
///
/// \param bu biounit to be added
@@ -848,6 +873,8 @@ private:
std::vector<MMCifInfoBioUnit> biounits_; ///< list of biounits
std::vector<MMCifInfoTransOpPtr> transops_;
MMCifInfoStructRefs struct_refs_;
+ std::map<String, String> cif_2_pdb_chain_id_;
+ std::map<String, String> pdb_2_cif_chain_id_;
};
diff --git a/modules/io/src/mol/mmcif_reader.cc b/modules/io/src/mol/mmcif_reader.cc
index 2bcdee810..762939ca8 100644
--- a/modules/io/src/mol/mmcif_reader.cc
+++ b/modules/io/src/mol/mmcif_reader.cc
@@ -1539,6 +1539,7 @@ void MMCifReader::OnEndData()
// process chain types
std::vector<std::pair<mol::ChainHandle, String> >::const_iterator css;
MMCifEntityDescMap::const_iterator edm_it;
+ String pdb_auth_chain_name;
for (css = chain_id_pairs_.begin(); css != chain_id_pairs_.end(); ++css) {
edm_it = entity_desc_map_.find(css->second);
@@ -1548,6 +1549,9 @@ void MMCifReader::OnEndData()
if (edm_it->second.seqres.length() > 0) {
seqres_.AddSequence(seq::CreateSequence(css->first.GetName(),
edm_it->second.seqres));
+ pdb_auth_chain_name = css->first.GetStringProp("pdb_auth_chain_name");
+ info_.AddMMCifPDBChainTr(css->first.GetName(), pdb_auth_chain_name);
+ info_.AddPDBMMCifChainTr(pdb_auth_chain_name, css->first.GetName());
} else if (edm_it->second.type!=mol::CHAINTYPE_WATER) {
// mark everything that doesn't have SEQRES as ligand and isn't of type
// water as ligand
diff --git a/modules/io/tests/test_mmcif_info.cc b/modules/io/tests/test_mmcif_info.cc
index 3d2674797..65e4fdaec 100644
--- a/modules/io/tests/test_mmcif_info.cc
+++ b/modules/io/tests/test_mmcif_info.cc
@@ -202,7 +202,17 @@ BOOST_AUTO_TEST_CASE(mmcif_info)
#else
BOOST_CHECK_CLOSE(info.GetResolution(), 1.9f, 0.001f);
#endif
-
+
+ info.AddMMCifPDBChainTr("A", "B");
+ BOOST_CHECK_THROW(info.AddMMCifPDBChainTr("A", "B"), IOException);
+ BOOST_CHECK("B" == info.GetMMCifPDBChainTr("A"));
+ BOOST_CHECK("" == info.GetMMCifPDBChainTr("C"));
+
+ info.AddPDBMMCifChainTr("A", "B");
+ BOOST_CHECK_THROW(info.AddPDBMMCifChainTr("A", "B"), IOException);
+ BOOST_CHECK("B" == info.GetPDBMMCifChainTr("A"));
+ BOOST_CHECK("" == info.GetPDBMMCifChainTr("C"));
+
BOOST_MESSAGE(" done.");
}
diff --git a/modules/io/tests/testfiles/mmcif/atom_site.mmcif b/modules/io/tests/testfiles/mmcif/atom_site.mmcif
index ce890cf9d..68b2fbb57 100644
--- a/modules/io/tests/testfiles/mmcif/atom_site.mmcif
+++ b/modules/io/tests/testfiles/mmcif/atom_site.mmcif
@@ -168,10 +168,10 @@ ATOM C CB ILE A 13 . 1 21.236 34.463 16.492 1.00 22.67 . 13 21 ? A
ATOM C CG1 ILE A 13 . 1 20.478 33.469 17.371 1.00 22.14 . 13 22 ? A
ATOM C CG2 ILE A 13 . 1 21.357 33.986 15.016 1.00 21.75 . 13 23 ? A
# - - - - data truncated for brevity - - - -
-HETATM C C1 APS C 1 1 1 4.171 29.012 7.116 0.58 17.27 1 300 101 ? A
-HETATM C C2 APS C 1 1 1 4.949 27.758 6.793 0.58 16.95 1 300 102 ? A
-HETATM O O3 APS C 1 1 1 4.800 26.678 7.393 0.58 16.85 1 300 103 ? A
-HETATM N N4 APS C 1 1 1 5.930 27.841 5.869 0.58 16.43 1 300 104 ? A
+HETATM C C1 APS C 1 1 1 4.171 29.012 7.116 0.58 17.27 1 300 101 ? C
+HETATM C C2 APS C 1 1 1 4.949 27.758 6.793 0.58 16.95 1 300 102 ? C
+HETATM O O3 APS C 1 1 1 4.800 26.678 7.393 0.58 16.85 1 300 103 ? C
+HETATM N N4 APS C 1 1 1 5.930 27.841 5.869 0.58 16.43 1 300 104 ? C
# - - - - data truncated for brevity - - - -
# chain to be ignored by 'restrict_chains' feature
ATOM N N ILE Z 1 . 1 23.664 33.855 16.884 1.00 22.08 . 1 17 ? Z
--
GitLab