Skip to content

L
libcifpp
Commit 80bb24f3 by Maarten L. Hekkelman
Options

- changed Id to ID in all code 

- change ItemReference::as to work with std::optional as well
- changed some DSSP related code
parent 34c7fd3f
Showing with 1797 additions and 634 deletions
include/cif++/Cif++.h
...@@ -249,7 +249,11 @@ namespace detail ...@@ -249,7 +249,11 @@ namespace detail
// ItemReference is a helper class // ItemReference is a helper class
class ItemReference class ItemReference
{ {
public: public:
// some conversion helper classes
template<typename T, typename = void>
struct item_value_as;
template<typename T> template<typename T>
ItemReference& operator=(const T& value) ItemReference& operator=(const T& value)
...@@ -262,12 +266,15 @@ namespace detail ...@@ -262,12 +266,15 @@ namespace detail
// operator string() const { return c_str(); } // operator string() const { return c_str(); }
// template<typename T, typename = void>
// T as() const;
template<typename T> template<typename T>
T as() const T as() const
{ {
return boost::lexical_cast<T>(c_str("0")); return item_value_as<T>::convert(*this);
} }
template<typename T> template<typename T>
int compare(const T& value) const int compare(const T& value) const
{ {
...@@ -292,6 +299,7 @@ namespace detail ...@@ -292,6 +299,7 @@ namespace detail
// empty means either null or unknown // empty means either null or unknown
bool empty() const; bool empty() const;
explicit operator bool() const { return not empty(); }
// is_null means the field contains '.' // is_null means the field contains '.'
bool is_null() const; bool is_null() const;
...@@ -325,20 +333,48 @@ namespace detail ...@@ -325,20 +333,48 @@ namespace detail
bool mConst = false; bool mConst = false;
}; };
template<typename T>
struct ItemReference::item_value_as<T, std::enable_if_t<std::is_arithmetic_v<T>>>
{
static T convert(const ItemReference& ref)
{
T result = {};
if (not ref.empty())
result = boost::lexical_cast<T>(ref.c_str());
return result;
}
};
template<typename T>
struct ItemReference::item_value_as<std::optional<T>>
{
static std::optional<T> convert(const ItemReference& ref)
{
std::optional<T> result;
if (ref)
result = ref.as<T>();
return result;
}
};
template<> template<>
inline struct ItemReference::item_value_as<const char*>
string ItemReference::as<string>() const
{ {
return string(c_str("")); static const char* convert(const ItemReference& ref)
} {
return ref.c_str();
}
};
template<> template<>
inline struct ItemReference::item_value_as<std::string>
const char* ItemReference::as<const char*>() const
{ {
return c_str(""); static std::string convert(const ItemReference& ref)
} {
return ref.c_str();
}
};
template<> template<>
inline inline
int ItemReference::compare<string>(const string& value) const int ItemReference::compare<string>(const string& value) const
......
include/cif++/CifValidator.h
...@@ -112,7 +112,7 @@ struct ValidateCategory ...@@ -112,7 +112,7 @@ struct ValidateCategory
struct ValidateLink struct ValidateLink
{ {
int mLinkGroupId; int mLinkGroupID;
std::string mParentCategory; std::string mParentCategory;
std::vector<std::string> mParentKeys; std::vector<std::string> mParentKeys;
std::string mChildCategory; std::string mChildCategory;
......
include/cif++/Compound.h
...@@ -127,7 +127,7 @@ class Compound ...@@ -127,7 +127,7 @@ class Compound
static void addMonomerLibraryPath(const std::string& dir); static void addMonomerLibraryPath(const std::string& dir);
// accessors // accessors
std::string id() const { return mId; } std::string id() const { return mID; }
std::string name() const { return mName; } std::string name() const { return mName; }
std::string type() const; std::string type() const;
std::string group() const { return mGroup; } std::string group() const { return mGroup; }
...@@ -139,7 +139,7 @@ class Compound ...@@ -139,7 +139,7 @@ class Compound
std::vector<CompoundPlane> planes() const { return mPlanes; } std::vector<CompoundPlane> planes() const { return mPlanes; }
std::vector<CompoundTorsion> torsions() const { return mTorsions; } std::vector<CompoundTorsion> torsions() const { return mTorsions; }
CompoundAtom getAtomById(const std::string& atomId) const; CompoundAtom getAtomByID(const std::string& atomID) const;
bool atomsBonded(const std::string& atomId_1, const std::string& atomId_2) const; bool atomsBonded(const std::string& atomId_1, const std::string& atomId_2) const;
float atomBondValue(const std::string& atomId_1, const std::string& atomId_2) const; float atomBondValue(const std::string& atomId_1, const std::string& atomId_2) const;
...@@ -162,7 +162,7 @@ class Compound ...@@ -162,7 +162,7 @@ class Compound
cif::File mCF; cif::File mCF;
std::string mId; std::string mID;
std::string mName; std::string mName;
std::string mGroup; std::string mGroup;
std::vector<CompoundAtom> mAtoms; std::vector<CompoundAtom> mAtoms;
...@@ -254,7 +254,7 @@ class Link ...@@ -254,7 +254,7 @@ class Link
static const Link& create(const std::string& id); static const Link& create(const std::string& id);
// accessors // accessors
std::string id() const { return mId; } std::string id() const { return mID; }
std::vector<LinkBond> bonds() const { return mBonds; } std::vector<LinkBond> bonds() const { return mBonds; }
std::vector<LinkAngle> angles() const { return mAngles; } std::vector<LinkAngle> angles() const { return mAngles; }
std::vector<LinkChiralCentre> chiralCentres() const { return mChiralCentres; } std::vector<LinkChiralCentre> chiralCentres() const { return mChiralCentres; }
...@@ -269,7 +269,7 @@ class Link ...@@ -269,7 +269,7 @@ class Link
~Link(); ~Link();
std::string mId; std::string mID;
std::vector<LinkBond> mBonds; std::vector<LinkBond> mBonds;
std::vector<LinkAngle> mAngles; std::vector<LinkAngle> mAngles;
std::vector<LinkTorsion> mTorsions; std::vector<LinkTorsion> mTorsions;
......
include/cif++/Config.h
...@@ -5,10 +5,6 @@ ...@@ -5,10 +5,6 @@
#include <string> #include <string>
#include <cstdint> #include <cstdint>
#define HAVE_CPP0X_TEMPLATE_ALIASES 1
#define HAVE_CPP0X_VARIADIC_TEMPLATES 1
#define HAVE_CPP0X_INITIALIZER_LISTS 1
#if defined(_MSC_VER) #if defined(_MSC_VER)
// These are Microsoft Visual C++ special settings // These are Microsoft Visual C++ special settings
......
include/cif++/Structure.h
...@@ -38,27 +38,6 @@ class Polymer; ...@@ -38,27 +38,6 @@ class Polymer;
class Structure; class Structure;
class File; class File;
struct SecondaryStructure;
// --------------------------------------------------------------------
// We do not want to introduce a dependency on cif++ here, we might want
// to change the backend storage in the future.
// So, in order to access the data we use properties based on boost::any
// Eventually this should be moved to std::variant, but that's only when
// c++17 is acceptable.
struct Property
{
Property() {}
Property(const std::string& name, const boost::any& value)
: name(name), value(value) {}
std::string name;
boost::any value;
};
typedef std::vector<Property> PropertyList;
// -------------------------------------------------------------------- // --------------------------------------------------------------------
class Atom class Atom
...@@ -101,18 +80,18 @@ class Atom ...@@ -101,18 +80,18 @@ class Atom
void property(const std::string& name, const T& value); void property(const std::string& name, const T& value);
// specifications // specifications
std::string labelAtomId() const; std::string labelAtomID() const;
std::string labelCompId() const; std::string labelCompID() const;
std::string labelAsymId() const; std::string labelAsymID() const;
int labelSeqId() const; int labelSeqID() const;
std::string labelAltId() const; std::string labelAltID() const;
std::string authAtomId() const; std::string authAtomID() const;
std::string authCompId() const; std::string authCompID() const;
std::string authAsymId() const; std::string authAsymID() const;
std::string authSeqId() const; std::string authSeqID() const;
std::string pdbxAuthInsCode() const; std::string pdbxAuthInsCode() const;
std::string pdbxAuthAltId() const; std::string pdbxAuthAltID() const;
std::string labelID() const;// label_comp_id + '_' + label_asym_id + '_' + label_seq_id std::string labelID() const;// label_comp_id + '_' + label_asym_id + '_' + label_seq_id
std::string pdbID() const; // auth_comp_id + '_' + auth_asym_id + '_' + auth_seq_id + pdbx_PDB_ins_code std::string pdbID() const; // auth_comp_id + '_' + auth_asym_id + '_' + auth_seq_id + pdbx_PDB_ins_code
...@@ -134,8 +113,8 @@ class Atom ...@@ -134,8 +113,8 @@ class Atom
// convenience routine // convenience routine
bool isBackBone() const bool isBackBone() const
{ {
return labelAtomId() == "N" or labelAtomId() == "O" or return labelAtomID() == "N" or labelAtomID() == "O" or
labelAtomId() == "C" or labelAtomId() == "CA"; labelAtomID() == "C" or labelAtomID() == "CA";
} }
void swap(Atom& b) void swap(Atom& b)
...@@ -199,6 +178,7 @@ class Residue ...@@ -199,6 +178,7 @@ class Residue
const std::string& asymID() const { return mAsymID; } const std::string& asymID() const { return mAsymID; }
int seqID() const { return mSeqID; } int seqID() const { return mSeqID; }
std::string authAsymID() const;
std::string authSeqID() const; std::string authSeqID() const;
std::string authInsCode() const; std::string authInsCode() const;
...@@ -354,10 +334,24 @@ class File : public std::enable_shared_from_this<File> ...@@ -354,10 +334,24 @@ class File : public std::enable_shared_from_this<File>
// -------------------------------------------------------------------- // --------------------------------------------------------------------
enum class StructureOpenOptions
{
SkipHydrogen = 1 << 0
};
inline bool operator&(StructureOpenOptions a, StructureOpenOptions b)
{
return static_cast<int>(a) bitand static_cast<int>(b);
}
// --------------------------------------------------------------------
class Structure class Structure
{ {
public: public:
Structure(File& p, uint32_t modelNr = 1); Structure(File& p, StructureOpenOptions options = {})
: Structure(p, 1, options) {}
Structure(File& p, uint32_t modelNr = 1, StructureOpenOptions options = {});
Structure& operator=(const Structure&) = delete; Structure& operator=(const Structure&) = delete;
~Structure(); ~Structure();
...@@ -372,35 +366,35 @@ class Structure ...@@ -372,35 +366,35 @@ class Structure
const std::list<Polymer>& polymers() const { return mPolymers; } const std::list<Polymer>& polymers() const { return mPolymers; }
const std::vector<Residue>& nonPolymers() const { return mNonPolymers; } const std::vector<Residue>& nonPolymers() const { return mNonPolymers; }
Atom getAtomById(std::string id) const; Atom getAtomByID(std::string id) const;
// Atom getAtomByLocation(Point pt, float maxDistance) const; // Atom getAtomByLocation(Point pt, float maxDistance) const;
Atom getAtomByLabel(const std::string& atomId, const std::string& asymId, Atom getAtomByLabel(const std::string& atomID, const std::string& asymID,
const std::string& compId, int seqId, const std::string& altId = ""); const std::string& compID, int seqID, const std::string& altID = "");
// Atom getAtomByAuth(const std::string& atomId, const std::string& asymId, // Atom getAtomByAuth(const std::string& atomID, const std::string& asymID,
// const std::string& compId, int seqId, const std::string& altId = "", // const std::string& compID, int seqID, const std::string& altID = "",
// const std::string& pdbxAuthInsCode = ""); // const std::string& pdbxAuthInsCode = "");
// map between auth and label locations // map between auth and label locations
std::tuple<std::string,int,std::string> MapAuthToLabel(const std::string& asymId, std::tuple<std::string,int,std::string> MapAuthToLabel(const std::string& asymID,
const std::string& seqId, const std::string& compId, const std::string& insCode = ""); const std::string& seqID, const std::string& compID, const std::string& insCode = "");
std::tuple<std::string,std::string,std::string,std::string> MapLabelToAuth( std::tuple<std::string,std::string,std::string,std::string> MapLabelToAuth(
const std::string& asymId, int seqId, const std::string& compId); const std::string& asymID, int seqID, const std::string& compID);
// returns chain, seqnr, icode // returns chain, seqnr, icode
std::tuple<char,int,char> MapLabelToAuth( std::tuple<char,int,char> MapLabelToAuth(
const std::string& asymId, int seqId) const; const std::string& asymID, int seqID) const;
// returns chain,seqnr,comp,iCode // returns chain,seqnr,comp,iCode
std::tuple<std::string,int,std::string,std::string> MapLabelToPDB( std::tuple<std::string,int,std::string,std::string> MapLabelToPDB(
const std::string& asymId, int seqId, const std::string& compId, const std::string& asymID, int seqID, const std::string& compID,
const std::string& authSeqID) const; const std::string& authSeqID) const;
std::tuple<std::string,int,std::string> MapPDBToLabel( std::tuple<std::string,int,std::string> MapPDBToLabel(
const std::string& asymId, int seqId, const std::string& compId, const std::string& iCode) const; const std::string& asymID, int seqID, const std::string& compID, const std::string& iCode) const;
// Actions // Actions
void removeAtom(Atom& a); void removeAtom(Atom& a);
......
rsrc/dictionaries/mmcif_pdbx.dic
This source diff could not be displayed because it is too large. You can view the blob instead.
src/BondMap.cpp
...@@ -68,7 +68,7 @@ BondMap::BondMap(const Structure& p) ...@@ -68,7 +68,7 @@ BondMap::BondMap(const Structure& p)
map<tuple<string,int,string>,string> atomMapByAsymSeqAndAtom; map<tuple<string,int,string>,string> atomMapByAsymSeqAndAtom;
for (auto& a: p.atoms()) for (auto& a: p.atoms())
{ {
auto key = make_tuple(a.labelAsymId(), a.labelSeqId(), a.labelAtomId()); auto key = make_tuple(a.labelAsymID(), a.labelSeqID(), a.labelAtomID());
atomMapByAsymSeqAndAtom[key] = a.id(); atomMapByAsymSeqAndAtom[key] = a.id();
} }
...@@ -78,28 +78,28 @@ BondMap::BondMap(const Structure& p) ...@@ -78,28 +78,28 @@ BondMap::BondMap(const Structure& p)
int lastSeqID = 0; int lastSeqID = 0;
for (auto r: db["pdbx_poly_seq_scheme"]) for (auto r: db["pdbx_poly_seq_scheme"])
{ {
string asymId; string asymID;
int seqId; int seqID;
cif::tie(asymId, seqId) = r.get("asym_id", "seq_id"); cif::tie(asymID, seqID) = r.get("asym_id", "seq_id");
if (asymId != lastAsymID) // first in a new sequece if (asymID != lastAsymID) // first in a new sequece
{ {
lastAsymID = asymId; lastAsymID = asymID;
lastSeqID = seqId; lastSeqID = seqID;
continue; continue;
} }
auto c = atomMapByAsymSeqAndAtom[make_tuple(asymId, lastSeqID, "C")]; auto c = atomMapByAsymSeqAndAtom[make_tuple(asymID, lastSeqID, "C")];
auto n = atomMapByAsymSeqAndAtom[make_tuple(asymId, seqId, "N")]; auto n = atomMapByAsymSeqAndAtom[make_tuple(asymID, seqID, "N")];
// auto c = db["atom_site"].find(cif::Key("label_asym_id") == asymId and cif::Key("label_seq_id") == lastSeqID and cif::Key("label_atom_id") == "C"); // auto c = db["atom_site"].find(cif::Key("label_asym_id") == asymID and cif::Key("label_seq_id") == lastSeqID and cif::Key("label_atom_id") == "C");
// if (c.size() != 1 and VERBOSE > 1) // if (c.size() != 1 and VERBOSE > 1)
// cerr << "Unexpected number (" << c.size() << ") of atoms with atom ID C in asym_id " << asymId << " with seq id " << lastSeqID << endl; // cerr << "Unexpected number (" << c.size() << ") of atoms with atom ID C in asym_id " << asymID << " with seq id " << lastSeqID << endl;
// //
// auto n = db["atom_site"].find(cif::Key("label_asym_id") == asymId and cif::Key("label_seq_id") == seqId and cif::Key("label_atom_id") == "N"); // auto n = db["atom_site"].find(cif::Key("label_asym_id") == asymID and cif::Key("label_seq_id") == seqID and cif::Key("label_atom_id") == "N");
// if (n.size() != 1 and VERBOSE > 1) // if (n.size() != 1 and VERBOSE > 1)
// cerr << "Unexpected number (" << n.size() << ") of atoms with atom ID N in asym_id " << asymId << " with seq id " << seqId << endl; // cerr << "Unexpected number (" << n.size() << ") of atoms with atom ID N in asym_id " << asymID << " with seq id " << seqID << endl;
// //
// if (not (c.empty() or n.empty())) // if (not (c.empty() or n.empty()))
// bindAtoms(c.front()["id"].as<string>(), n.front()["id"].as<string>()); // bindAtoms(c.front()["id"].as<string>(), n.front()["id"].as<string>());
...@@ -107,7 +107,7 @@ BondMap::BondMap(const Structure& p) ...@@ -107,7 +107,7 @@ BondMap::BondMap(const Structure& p)
if (not (c.empty() or n.empty())) if (not (c.empty() or n.empty()))
bindAtoms(c, n); bindAtoms(c, n);
lastSeqID = seqId; lastSeqID = seqID;
} }
for (auto l: db["struct_conn"]) for (auto l: db["struct_conn"])
...@@ -166,19 +166,19 @@ BondMap::BondMap(const Structure& p) ...@@ -166,19 +166,19 @@ BondMap::BondMap(const Structure& p)
// loop over poly_seq_scheme // loop over poly_seq_scheme
for (auto r: db["pdbx_poly_seq_scheme"].find(cif::Key("mon_id") == c)) for (auto r: db["pdbx_poly_seq_scheme"].find(cif::Key("mon_id") == c))
{ {
string asymId; string asymID;
int seqId; int seqID;
cif::tie(asymId, seqId) = r.get("asym_id", "seq_id"); cif::tie(asymID, seqID) = r.get("asym_id", "seq_id");
vector<Atom> rAtoms; vector<Atom> rAtoms;
copy_if(atoms.begin(), atoms.end(), back_inserter(rAtoms), copy_if(atoms.begin(), atoms.end(), back_inserter(rAtoms),
[&](auto& a) { return a.labelAsymId() == asymId and a.labelSeqId() == seqId; }); [&](auto& a) { return a.labelAsymID() == asymID and a.labelSeqID() == seqID; });
for (uint32_t i = 0; i + 1 < rAtoms.size(); ++i) for (uint32_t i = 0; i + 1 < rAtoms.size(); ++i)
{ {
for (uint32_t j = i + 1; j < rAtoms.size(); ++j) for (uint32_t j = i + 1; j < rAtoms.size(); ++j)
{ {
if (compound->atomsBonded(rAtoms[i].labelAtomId(), rAtoms[j].labelAtomId())) if (compound->atomsBonded(rAtoms[i].labelAtomID(), rAtoms[j].labelAtomID()))
bindAtoms(rAtoms[i].id(), rAtoms[j].id()); bindAtoms(rAtoms[i].id(), rAtoms[j].id());
} }
} }
...@@ -187,20 +187,20 @@ BondMap::BondMap(const Structure& p) ...@@ -187,20 +187,20 @@ BondMap::BondMap(const Structure& p)
// loop over pdbx_nonpoly_scheme // loop over pdbx_nonpoly_scheme
for (auto r: db["pdbx_nonpoly_scheme"].find(cif::Key("mon_id") == c)) for (auto r: db["pdbx_nonpoly_scheme"].find(cif::Key("mon_id") == c))
{ {
string asymId; string asymID;
cif::tie(asymId) = r.get("asym_id"); cif::tie(asymID) = r.get("asym_id");
vector<Atom> rAtoms; vector<Atom> rAtoms;
copy_if(atoms.begin(), atoms.end(), back_inserter(rAtoms), copy_if(atoms.begin(), atoms.end(), back_inserter(rAtoms),
[&](auto& a) { return a.labelAsymId() == asymId; }); [&](auto& a) { return a.labelAsymID() == asymID; });
// for (auto a: db["atom_site"].find(cif::Key("label_asym_id") == asymId)) // for (auto a: db["atom_site"].find(cif::Key("label_asym_id") == asymID))
// rAtoms.push_back(p.getAtomById(a["id"].as<string>())); // rAtoms.push_back(p.getAtomByID(a["id"].as<string>()));
for (uint32_t i = 0; i + 1 < rAtoms.size(); ++i) for (uint32_t i = 0; i + 1 < rAtoms.size(); ++i)
{ {
for (uint32_t j = i + 1; j < rAtoms.size(); ++j) for (uint32_t j = i + 1; j < rAtoms.size(); ++j)
{ {
if (compound->atomsBonded(rAtoms[i].labelAtomId(), rAtoms[j].labelAtomId())) if (compound->atomsBonded(rAtoms[i].labelAtomID(), rAtoms[j].labelAtomID()))
{ {
uint32_t ixa = index[rAtoms[i].id()]; uint32_t ixa = index[rAtoms[i].id()];
uint32_t ixb = index[rAtoms[j].id()]; uint32_t ixb = index[rAtoms[j].id()];
......
src/Cif2PDB.cpp
...@@ -352,9 +352,8 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db) ...@@ -352,9 +352,8 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db)
for (auto r: cat1) for (auto r: cat1)
{ {
keywords = r["keywords"].as<string>(); keywords = r["pdbx_keywords"].as<string>();
if (keywords.empty()) break;
keywords = r["pdbx_keywords"].as<string>();
} }
string date; string date;
...@@ -404,7 +403,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db) ...@@ -404,7 +403,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db)
if (r["type"] != "polymer") if (r["type"] != "polymer")
continue; continue;
string entityId = r["id"].as<string>(); string entityID = r["id"].as<string>();
++molID; ++molID;
cmpnd.push_back("MOL_ID: " + to_string(molID)); cmpnd.push_back("MOL_ID: " + to_string(molID));
...@@ -412,7 +411,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db) ...@@ -412,7 +411,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db)
string molecule = r["pdbx_description"].as<string>(); string molecule = r["pdbx_description"].as<string>();
cmpnd.push_back("MOLECULE: " + molecule); cmpnd.push_back("MOLECULE: " + molecule);
auto poly = db["entity_poly"].find(cif::Key("entity_id") == entityId); auto poly = db["entity_poly"].find(cif::Key("entity_id") == entityID);
if (not poly.empty()) if (not poly.empty())
{ {
string chains = poly.front()["pdbx_strand_id"].as<string>(); string chains = poly.front()["pdbx_strand_id"].as<string>();
...@@ -424,7 +423,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db) ...@@ -424,7 +423,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db)
if (not fragment.empty()) if (not fragment.empty())
cmpnd.push_back("FRAGMENT: " + fragment); cmpnd.push_back("FRAGMENT: " + fragment);
for (auto sr: db["entity_name_com"].find(cif::Key("entity_id") == entityId)) for (auto sr: db["entity_name_com"].find(cif::Key("entity_id") == entityID))
{ {
string syn = sr["name"].as<string>(); string syn = sr["name"].as<string>();
if (not syn.empty()) if (not syn.empty())
...@@ -459,7 +458,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db) ...@@ -459,7 +458,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db)
if (r["type"] != "polymer") if (r["type"] != "polymer")
continue; continue;
string entityId = r["id"].as<string>(); string entityID = r["id"].as<string>();
++molID; ++molID;
source.push_back("MOL_ID: " + to_string(molID)); source.push_back("MOL_ID: " + to_string(molID));
...@@ -489,7 +488,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db) ...@@ -489,7 +488,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db)
{ "details", "OTHER_DETAILS" } { "details", "OTHER_DETAILS" }
}; };
for (auto gr: gen.find(cif::Key("entity_id") == entityId)) for (auto gr: gen.find(cif::Key("entity_id") == entityID))
{ {
for (auto m: kGenSourceMapping) for (auto m: kGenSourceMapping)
{ {
...@@ -514,7 +513,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db) ...@@ -514,7 +513,7 @@ void WriteHeaderLines(ostream& pdbFile, Datablock& db)
{ "details", "OTHER_DETAILS" } { "details", "OTHER_DETAILS" }
}; };
for (auto nr: nat.find(cif::Key("entity_id") == entityId)) for (auto nr: nat.find(cif::Key("entity_id") == entityID))
{ {
for (auto m: kNatSourceMapping) for (auto m: kNatSourceMapping)
{ {
...@@ -3189,7 +3188,7 @@ tuple<int,int> WriteSecondaryStructure(ostream& pdbFile, Datablock& db) ...@@ -3189,7 +3188,7 @@ tuple<int,int> WriteSecondaryStructure(ostream& pdbFile, Datablock& db)
first = false; first = false;
} }
string initResName, initChainID, initICode, endResName, endChainID, endICode, curAtom, curResName, curChainId, curICode, prevAtom, prevResName, prevChainId, prevICode; string initResName, initChainID, initICode, endResName, endChainID, endICode, curAtom, curResName, curChainID, curICode, prevAtom, prevResName, prevChainID, prevICode;
int initSeqNum, endSeqNum, curResSeq, prevResSeq; int initSeqNum, endSeqNum, curResSeq, prevResSeq;
auto r2 = db["struct_sheet_range"][cif::Key("sheet_id") == sheetID and cif::Key("id") == rangeID2]; auto r2 = db["struct_sheet_range"][cif::Key("sheet_id") == sheetID and cif::Key("id") == rangeID2];
...@@ -3223,7 +3222,7 @@ tuple<int,int> WriteSecondaryStructure(ostream& pdbFile, Datablock& db) ...@@ -3223,7 +3222,7 @@ tuple<int,int> WriteSecondaryStructure(ostream& pdbFile, Datablock& db)
string compID[2]; string compID[2];
cif::tie(compID[0], compID[1]) = h.front().get("range_2_label_comp_id", "range_1_label_comp_id"); cif::tie(compID[0], compID[1]) = h.front().get("range_2_label_comp_id", "range_1_label_comp_id");
cif::tie(curAtom, curResName, curResSeq, curChainId, curICode, prevAtom, prevResName, prevResSeq, prevChainId, prevICode) cif::tie(curAtom, curResName, curResSeq, curChainID, curICode, prevAtom, prevResName, prevResSeq, prevChainID, prevICode)
= h.front().get("range_2_auth_atom_id", "range_2_auth_comp_id", "range_2_auth_seq_id", "range_2_auth_asym_id", "range_2_PDB_ins_code", = h.front().get("range_2_auth_atom_id", "range_2_auth_comp_id", "range_2_auth_seq_id", "range_2_auth_asym_id", "range_2_PDB_ins_code",
"range_1_auth_atom_id", "range_1_auth_comp_id", "range_1_auth_seq_id", "range_1_auth_asym_id", "range_1_PDB_ins_code"); "range_1_auth_atom_id", "range_1_auth_comp_id", "range_1_auth_seq_id", "range_1_auth_asym_id", "range_1_PDB_ins_code");
...@@ -3245,12 +3244,12 @@ tuple<int,int> WriteSecondaryStructure(ostream& pdbFile, Datablock& db) ...@@ -3245,12 +3244,12 @@ tuple<int,int> WriteSecondaryStructure(ostream& pdbFile, Datablock& db)
% sense % sense
% curAtom % curAtom
% curResName % curResName
% curChainId % curChainID
% curResSeq % curResSeq
% curICode % curICode
% prevAtom % prevAtom
% prevResName % prevResName
% prevChainId % prevChainID
% prevResSeq % prevResSeq
% prevICode) << endl; % prevICode) << endl;
} }
...@@ -3727,12 +3726,12 @@ void WritePDBFile(ostream& pdbFile, cif::File& cifFile) ...@@ -3727,12 +3726,12 @@ void WritePDBFile(ostream& pdbFile, cif::File& cifFile)
void WritePDBHeaderLines(std::ostream& os, cif::File& cifFile) void WritePDBHeaderLines(std::ostream& os, cif::File& cifFile)
{ {
io::filtering_ostream out; // io::filtering_ostream out;
out.push(FillOutLineFilter()); // out.push(FillOutLineFilter());
out.push(os); // out.push(os);
auto filter = out.component<FillOutLineFilter>(0); // auto filter = out.component<FillOutLineFilter>(0);
assert(filter); // assert(filter);
auto& db = cifFile.firstDatablock(); auto& db = cifFile.firstDatablock();
...@@ -3767,9 +3766,7 @@ std::string GetPDBHEADERLine(cif::File& cifFile, int truncate_at) ...@@ -3767,9 +3766,7 @@ std::string GetPDBHEADERLine(cif::File& cifFile, int truncate_at)
for (auto r: cat1) for (auto r: cat1)
{ {
keywords = r["keywords"].as<string>(); keywords = r["pdbx_keywords"].as<string>();
if (keywords.empty())
keywords = r["pdbx_keywords"].as<string>();
if (keywords.length() > truncate_at - 40) if (keywords.length() > truncate_at - 40)
keywords = keywords.substr(0, truncate_at - 44) + " ..."; keywords = keywords.substr(0, truncate_at - 44) + " ...";
} }
...@@ -3814,7 +3811,7 @@ std::string GetPDBCOMPNDLine(cif::File& cifFile, int truncate_at) ...@@ -3814,7 +3811,7 @@ std::string GetPDBCOMPNDLine(cif::File& cifFile, int truncate_at)
if (r["type"] != "polymer") if (r["type"] != "polymer")
continue; continue;
string entityId = r["id"].as<string>(); string entityID = r["id"].as<string>();
++molID; ++molID;
cmpnd.push_back("MOL_ID: " + to_string(molID)); cmpnd.push_back("MOL_ID: " + to_string(molID));
...@@ -3822,7 +3819,7 @@ std::string GetPDBCOMPNDLine(cif::File& cifFile, int truncate_at) ...@@ -3822,7 +3819,7 @@ std::string GetPDBCOMPNDLine(cif::File& cifFile, int truncate_at)
string molecule = r["pdbx_description"].as<string>(); string molecule = r["pdbx_description"].as<string>();
cmpnd.push_back("MOLECULE: " + molecule); cmpnd.push_back("MOLECULE: " + molecule);
auto poly = db["entity_poly"].find(cif::Key("entity_id") == entityId); auto poly = db["entity_poly"].find(cif::Key("entity_id") == entityID);
if (not poly.empty()) if (not poly.empty())
{ {
string chains = poly.front()["pdbx_strand_id"].as<string>(); string chains = poly.front()["pdbx_strand_id"].as<string>();
...@@ -3834,7 +3831,7 @@ std::string GetPDBCOMPNDLine(cif::File& cifFile, int truncate_at) ...@@ -3834,7 +3831,7 @@ std::string GetPDBCOMPNDLine(cif::File& cifFile, int truncate_at)
if (not fragment.empty()) if (not fragment.empty())
cmpnd.push_back("FRAGMENT: " + fragment); cmpnd.push_back("FRAGMENT: " + fragment);
for (auto sr: db["entity_name_com"].find(cif::Key("entity_id") == entityId)) for (auto sr: db["entity_name_com"].find(cif::Key("entity_id") == entityID))
{ {
string syn = sr["name"].as<string>(); string syn = sr["name"].as<string>();
if (not syn.empty()) if (not syn.empty())
...@@ -3874,7 +3871,7 @@ std::string GetPDBSOURCELine(cif::File& cifFile, int truncate_at) ...@@ -3874,7 +3871,7 @@ std::string GetPDBSOURCELine(cif::File& cifFile, int truncate_at)
if (r["type"] != "polymer") if (r["type"] != "polymer")
continue; continue;
string entityId = r["id"].as<string>(); string entityID = r["id"].as<string>();
++molID; ++molID;
source.push_back("MOL_ID: " + to_string(molID)); source.push_back("MOL_ID: " + to_string(molID));
...@@ -3904,7 +3901,7 @@ std::string GetPDBSOURCELine(cif::File& cifFile, int truncate_at) ...@@ -3904,7 +3901,7 @@ std::string GetPDBSOURCELine(cif::File& cifFile, int truncate_at)
{ "details", "OTHER_DETAILS" } { "details", "OTHER_DETAILS" }
}; };
for (auto gr: gen.find(cif::Key("entity_id") == entityId)) for (auto gr: gen.find(cif::Key("entity_id") == entityID))
{ {
for (auto m: kGenSourceMapping) for (auto m: kGenSourceMapping)
{ {
...@@ -3929,7 +3926,7 @@ std::string GetPDBSOURCELine(cif::File& cifFile, int truncate_at) ...@@ -3929,7 +3926,7 @@ std::string GetPDBSOURCELine(cif::File& cifFile, int truncate_at)
{ "details", "OTHER_DETAILS" } { "details", "OTHER_DETAILS" }
}; };
for (auto nr: nat.find(cif::Key("entity_id") == entityId)) for (auto nr: nat.find(cif::Key("entity_id") == entityID))
{ {
for (auto m: kNatSourceMapping) for (auto m: kNatSourceMapping)
{ {
......
src/CifParser.cpp
...@@ -930,12 +930,12 @@ void DictParser::linkItems() ...@@ -930,12 +930,12 @@ void DictParser::linkItems()
for (auto& kv: linkIndex) for (auto& kv: linkIndex)
{ {
ValidateLink link; ValidateLink link;
std::tie(link.mParentCategory, link.mChildCategory, link.mLinkGroupId) = kv.first; std::tie(link.mParentCategory, link.mChildCategory, link.mLinkGroupID) = kv.first;
std::tie(link.mParentKeys, link.mChildKeys) = linkKeys[kv.second]; std::tie(link.mParentKeys, link.mChildKeys) = linkKeys[kv.second];
// look up the label // look up the label
for (auto r: linkedGroup.find(cif::Key("category_id") == link.mChildCategory and cif::Key("link_group_id") == link.mLinkGroupId)) for (auto r: linkedGroup.find(cif::Key("category_id") == link.mChildCategory and cif::Key("link_group_id") == link.mLinkGroupID))
{ {
link.mLinkGroupLabel = r["label"].as<string>(); link.mLinkGroupLabel = r["label"].as<string>();
break; break;
......
src/Compound.cpp
...@@ -313,7 +313,7 @@ bool StructuresAreIsomeric(vector<CompoundAtom> atomsA, const vector<CompoundBon ...@@ -313,7 +313,7 @@ bool StructuresAreIsomeric(vector<CompoundAtom> atomsA, const vector<CompoundBon
Compound::Compound(const std::string& file, const std::string& id, Compound::Compound(const std::string& file, const std::string& id,
const std::string& name, const std::string& group) const std::string& name, const std::string& group)
: mId(id), mName(name), mGroup(group) : mID(id), mName(name), mGroup(group)
{ {
try try
{ {
...@@ -531,7 +531,7 @@ string Compound::type() const ...@@ -531,7 +531,7 @@ string Compound::type() const
// pyranose // pyranose
// saccharide // saccharide
if (cif::iequals(mId, "gly")) if (cif::iequals(mID, "gly"))
result = "peptide linking"; result = "peptide linking";
else if (cif::iequals(mGroup, "l-peptide") or cif::iequals(mGroup, "L-peptide linking") or cif::iequals(mGroup, "peptide")) else if (cif::iequals(mGroup, "l-peptide") or cif::iequals(mGroup, "L-peptide linking") or cif::iequals(mGroup, "peptide"))
result = "L-peptide linking"; result = "L-peptide linking";
...@@ -547,7 +547,7 @@ string Compound::type() const ...@@ -547,7 +547,7 @@ string Compound::type() const
bool Compound::isWater() const bool Compound::isWater() const
{ {
return mId == "HOH" or mId == "H2O"; return mID == "HOH" or mID == "H2O";
} }
bool Compound::isSugar() const bool Compound::isSugar() const
...@@ -555,20 +555,20 @@ bool Compound::isSugar() const ...@@ -555,20 +555,20 @@ bool Compound::isSugar() const
return cif::iequals(mGroup, "furanose") or cif::iequals(mGroup, "pyranose"); return cif::iequals(mGroup, "furanose") or cif::iequals(mGroup, "pyranose");
} }
CompoundAtom Compound::getAtomById(const string& atomId) const CompoundAtom Compound::getAtomByID(const string& atomID) const
{ {
CompoundAtom result = {}; CompoundAtom result = {};
for (auto& a: mAtoms) for (auto& a: mAtoms)
{ {
if (a.id == atomId) if (a.id == atomID)
{ {
result = a; result = a;
break; break;
} }
} }
if (result.id != atomId) if (result.id != atomID)
throw out_of_range("No atom " + atomId + " in Compound " + mId); throw out_of_range("No atom " + atomID + " in Compound " + mID);
return result; return result;
} }
...@@ -612,7 +612,7 @@ bool Compound::isIsomerOf(const Compound& c) const ...@@ -612,7 +612,7 @@ bool Compound::isIsomerOf(const Compound& c) const
for (;;) for (;;)
{ {
// easy tests first // easy tests first
if (mId == c.mId) if (mID == c.mID)
{ {
result = true; result = true;
break; break;
...@@ -694,11 +694,11 @@ vector<string> Compound::isomers() const ...@@ -694,11 +694,11 @@ vector<string> Compound::isomers() const
vector<string> result; vector<string> result;
auto& db = IsomerDB::instance(); auto& db = IsomerDB::instance();
if (db.count(mId)) if (db.count(mID))
{ {
result = db[mId]; result = db[mID];
auto i = find(result.begin(), result.end(), mId); auto i = find(result.begin(), result.end(), mID);
assert(i != result.end()); assert(i != result.end());
result.erase(i); result.erase(i);
...@@ -777,7 +777,7 @@ float Compound::chiralVolume(const string& centreID) const ...@@ -777,7 +777,7 @@ float Compound::chiralVolume(const string& centreID) const
Link::Link(cif::Datablock& db) Link::Link(cif::Datablock& db)
{ {
mId = db.getName(); mID = db.getName();
auto& linkBonds = db["chem_link_bond"]; auto& linkBonds = db["chem_link_bond"];
...@@ -801,7 +801,7 @@ Link::Link(cif::Datablock& db) ...@@ -801,7 +801,7 @@ Link::Link(cif::Datablock& db)
else else
{ {
if (cif::VERBOSE) if (cif::VERBOSE)
cerr << "Unimplemented chem_link_bond.type " << type << " in " << mId << endl; cerr << "Unimplemented chem_link_bond.type " << type << " in " << mID << endl;
b.type = singleBond; b.type = singleBond;
} }
...@@ -863,7 +863,7 @@ Link::Link(cif::Datablock& db) ...@@ -863,7 +863,7 @@ Link::Link(cif::Datablock& db)
else else
{ {
if (cif::VERBOSE) if (cif::VERBOSE)
cerr << "Unimplemented chem_link_chir.volume_sign " << volumeSign << " in " << mId << endl; cerr << "Unimplemented chem_link_chir.volume_sign " << volumeSign << " in " << mID << endl;
continue; continue;
} }
......
src/DistanceMap.cpp
...@@ -19,7 +19,7 @@ namespace mmcif ...@@ -19,7 +19,7 @@ namespace mmcif
inline ostream& operator<<(ostream& os, const Atom& a) inline ostream& operator<<(ostream& os, const Atom& a)
{ {
os << a.labelAsymId() << ':' << a.labelSeqId() << '/' << a.labelAtomId(); os << a.labelAsymID() << ':' << a.labelSeqID() << '/' << a.labelAtomID();
return os; return os;
} }
...@@ -441,7 +441,7 @@ vector<Atom> DistanceMap::near(const Atom& a, float maxDistance) const ...@@ -441,7 +441,7 @@ vector<Atom> DistanceMap::near(const Atom& a, float maxDistance) const
continue; continue;
size_t ixb = mJA[i]; size_t ixb = mJA[i];
Atom b = structure.getAtomById(rIndex.at(ixb)); Atom b = structure.getAtomByID(rIndex.at(ixb));
if (rti > 0) if (rti > 0)
result.emplace_back(b.symmetryCopy(mD, mRtOrth.at(rti))); result.emplace_back(b.symmetryCopy(mD, mRtOrth.at(rti)));
......
src/PDB2Cif.cpp
...@@ -429,7 +429,7 @@ class PDBFileParser ...@@ -429,7 +429,7 @@ class PDBFileParser
char iCode; char iCode;
int numHetAtoms; int numHetAtoms;
string text; string text;
string asymId; string asymID;
set<int> atoms; set<int> atoms;
}; };
...@@ -462,7 +462,7 @@ class PDBFileParser ...@@ -462,7 +462,7 @@ class PDBFileParser
struct PDBCompound struct PDBCompound
{ {
int mMolId; int mMolID;
string mTitle; string mTitle;
set<char> mChains; set<char> mChains;
map<string,string> mInfo; map<string,string> mInfo;
...@@ -472,7 +472,7 @@ class PDBFileParser ...@@ -472,7 +472,7 @@ class PDBFileParser
struct PDBSeqRes struct PDBSeqRes
{ {
string mMonId; string mMonID;
int mSeqNum; int mSeqNum;
char mIcode; char mIcode;
...@@ -482,14 +482,14 @@ class PDBFileParser ...@@ -482,14 +482,14 @@ class PDBFileParser
bool operator==(const PDBSeqRes& rhs) const bool operator==(const PDBSeqRes& rhs) const
{ {
return mSeqNum == rhs.mSeqNum and mMonId == rhs.mMonId and mIcode == rhs.mIcode; return mSeqNum == rhs.mSeqNum and mMonID == rhs.mMonID and mIcode == rhs.mIcode;
} }
}; };
struct PDBChain struct PDBChain
{ {
PDBChain(const string& structureId, char chainId, int molId) PDBChain(const string& structureID, char chainID, int molID)
: mDbref{structureId, chainId}, mWaters(0), mTerIndex(0), mMolId(molId), mNextSeqNum(1), mNextDbSeqNum(1) : mDbref{structureID, chainID}, mWaters(0), mTerIndex(0), mMolID(molID), mNextSeqNum(1), mNextDbSeqNum(1)
{ {
} }
...@@ -498,7 +498,7 @@ class PDBFileParser ...@@ -498,7 +498,7 @@ class PDBFileParser
int mWaters; int mWaters;
int mTerIndex; int mTerIndex;
int mMolId; int mMolID;
// scratch values for reading SEQRES records // scratch values for reading SEQRES records
int mNextSeqNum; int mNextSeqNum;
...@@ -507,7 +507,7 @@ class PDBFileParser ...@@ -507,7 +507,7 @@ class PDBFileParser
// scratch value for aligning // scratch value for aligning
struct AtomRes struct AtomRes
{ {
string mMonId; string mMonID;
int mSeqNum; int mSeqNum;
char mIcode; char mIcode;
...@@ -522,14 +522,14 @@ class PDBFileParser ...@@ -522,14 +522,14 @@ class PDBFileParser
// ---------------------------------------------------------------- // ----------------------------------------------------------------
PDBCompound& GetOrCreateCompound(int molId) PDBCompound& GetOrCreateCompound(int molID)
{ {
auto i = find_if(mCompounds.begin(), mCompounds.end(), [molId](PDBCompound& comp) -> bool { return comp.mMolId == molId; }); auto i = find_if(mCompounds.begin(), mCompounds.end(), [molID](PDBCompound& comp) -> bool { return comp.mMolID == molID; });
if (i == mCompounds.end()) if (i == mCompounds.end())
{ {
mCompounds.push_back(PDBCompound{ molId }); mCompounds.push_back(PDBCompound{ molID });
mMolID2EntityID[molId] = to_string(mNextEntityNr++); mMolID2EntityID[molID] = to_string(mNextEntityNr++);
i = prev(mCompounds.end()); i = prev(mCompounds.end());
} }
...@@ -545,17 +545,17 @@ class PDBFileParser ...@@ -545,17 +545,17 @@ class PDBFileParser
if (i == mChains.end()) if (i == mChains.end())
{ {
// locate the compound for this chain, if any (does that happen?) // locate the compound for this chain, if any (does that happen?)
int molId = 0; int molID = 0;
for (auto& cmp: mCompounds) for (auto& cmp: mCompounds)
{ {
if (cmp.mChains.count(chainID) > 0) if (cmp.mChains.count(chainID) > 0)
{ {
molId = cmp.mMolId; molID = cmp.mMolID;
break; break;
} }
} }
mChains.emplace_back(mStructureId, chainID, molId); mChains.emplace_back(mStructureID, chainID, molID);
i = prev(mChains.end()); i = prev(mChains.end());
} }
...@@ -846,12 +846,12 @@ class PDBFileParser ...@@ -846,12 +846,12 @@ class PDBFileParser
PDBRecord* mRec; PDBRecord* mRec;
cif::Datablock* mDatablock = nullptr; cif::Datablock* mDatablock = nullptr;
string mStructureId; string mStructureID;
string mModelTypeDetails; string mModelTypeDetails;
string mOriginalDate; string mOriginalDate;
string mExpMethod = "X-RAY DIFFRACTION"; string mExpMethod = "X-RAY DIFFRACTION";
int mCitationAuthorNr = 1, mCitationEditorNr = 1; int mCitationAuthorNr = 1, mCitationEditorNr = 1;
int mNextMolId = 1, mNextEntityNr = 1; int mNextMolID = 1, mNextEntityNr = 1;
int mNextSoftwareOrd = 1; int mNextSoftwareOrd = 1;
struct SEQADV struct SEQADV
...@@ -875,12 +875,12 @@ class PDBFileParser ...@@ -875,12 +875,12 @@ class PDBFileParser
map<string,string> mHetnams; map<string,string> mHetnams;
map<string,string> mHetsyns; map<string,string> mHetsyns;
map<string,string> mFormuls; map<string,string> mFormuls;
string mWaterHetId; string mWaterHetID;
vector<string> mChemComp, mAtomTypes; vector<string> mChemComp, mAtomTypes;
map<string,string> mRemark200; map<string,string> mRemark200;
string mRefinementSoftware; string mRefinementSoftware;
int mAtomId = 0; int mAtomID = 0;
int mPdbxDifOrdinal = 0; int mPdbxDifOrdinal = 0;
vector<UNOBS> mUnobs; vector<UNOBS> mUnobs;
...@@ -1096,7 +1096,9 @@ void PDBFileParser::PreParseInput(istream& is) ...@@ -1096,7 +1096,9 @@ void PDBFileParser::PreParseInput(istream& is)
} }
catch (const exception& ex) catch (const exception& ex)
{ {
throw_with_nested(runtime_error("Invalid component number '" + value.substr(1, 3) + '\'')); std::cerr << "Dropping FORMUL line (" << (lineNr - 1) << ") with invalid component number '" << value.substr(1, 3) << '\'' << std::endl;
continue;
// throw_with_nested(runtime_error("Invalid component number '" + value.substr(1, 3) + '\''));
} }
int n = 2; int n = 2;
...@@ -1114,7 +1116,8 @@ void PDBFileParser::PreParseInput(istream& is) ...@@ -1114,7 +1116,8 @@ void PDBFileParser::PreParseInput(istream& is)
} }
catch (const invalid_argument& ex) catch (const invalid_argument& ex)
{ {
throw_with_nested(runtime_error("Invalid component number '" + lookahead.substr(7, 3) + '\'')); continue;
// throw_with_nested(runtime_error("Invalid component number '" + lookahead.substr(7, 3) + '\''));
} }
} }
catch (const exception& ex) catch (const exception& ex)
...@@ -1254,7 +1257,7 @@ void PDBFileParser::ParseTitle() ...@@ -1254,7 +1257,7 @@ void PDBFileParser::ParseTitle()
if (mRec->is("HEADER")) if (mRec->is("HEADER"))
{ {
mStructureId = vS(63, 66); mStructureID = vS(63, 66);
keywords = vS(11, 50); keywords = vS(11, 50);
mOriginalDate = pdb2cifDate(vS(51, 59)); mOriginalDate = pdb2cifDate(vS(51, 59));
...@@ -1263,15 +1266,15 @@ void PDBFileParser::ParseTitle() ...@@ -1263,15 +1266,15 @@ void PDBFileParser::ParseTitle()
GetNextRecord(); GetNextRecord();
} }
ba::trim(mStructureId); ba::trim(mStructureID);
if (mStructureId.empty()) if (mStructureID.empty())
mStructureId = "nohd"; mStructureID = "nohd";
mDatablock = new cif::Datablock(mStructureId); mDatablock = new cif::Datablock(mStructureID);
auto cat = getCategory("entry"); auto cat = getCategory("entry");
// cat->addColumn("id"); // cat->addColumn("id");
cat->emplace({ {"id", mStructureId} }); cat->emplace({ {"id", mStructureID} });
// OBSLTE // OBSLTE
if (mRec->is("OBSLTE")) if (mRec->is("OBSLTE"))
...@@ -1429,7 +1432,7 @@ void PDBFileParser::ParseTitle() ...@@ -1429,7 +1432,7 @@ void PDBFileParser::ParseTitle()
{ {
for (auto& c: mCompounds) for (auto& c: mCompounds)
{ {
if (c.mMolId == stoi(value)) if (c.mMolID == stoi(value))
{ {
source = &c.mSource; source = &c.mSource;
break; break;
...@@ -1462,7 +1465,7 @@ void PDBFileParser::ParseTitle() ...@@ -1462,7 +1465,7 @@ void PDBFileParser::ParseTitle()
if (not (keywords.empty() and pdbxKeywords.empty())) if (not (keywords.empty() and pdbxKeywords.empty()))
{ {
getCategory("struct_keywords")->emplace({ getCategory("struct_keywords")->emplace({
{ "entry_id", mStructureId }, { "entry_id", mStructureID },
{ "pdbx_keywords", keywords }, { "pdbx_keywords", keywords },
{ "text", pdbxKeywords } { "text", pdbxKeywords }
}); });
...@@ -1491,7 +1494,7 @@ void PDBFileParser::ParseTitle() ...@@ -1491,7 +1494,7 @@ void PDBFileParser::ParseTitle()
continue; continue;
cat->emplace({ cat->emplace({
{ "entry_id", mStructureId }, { "entry_id", mStructureID },
{ "method", expMethod }, { "method", expMethod },
{ "crystals_number", ci != crystals.end() ? *ci : "" } { "crystals_number", ci != crystals.end() ? *ci : "" }
}); });
...@@ -1557,7 +1560,7 @@ void PDBFileParser::ParseTitle() ...@@ -1557,7 +1560,7 @@ void PDBFileParser::ParseTitle()
string date = pdb2cifDate(vS(14, 22)); // 14 - 22 Date modDate Date of modification (or release for string date = pdb2cifDate(vS(14, 22)); // 14 - 22 Date modDate Date of modification (or release for
// new entries) in DD-MMM-YY format. This is // new entries) in DD-MMM-YY format. This is
// not repeated on continued lines. // not repeated on continued lines.
string modId = vS(24, 27); // 24 - 27 IDCode modId ID code of this datablock. This is not repeated on string modID = vS(24, 27); // 24 - 27 IDCode modID ID code of this datablock. This is not repeated on
// continuation lines. // continuation lines.
int modType = vI(32, 32); // 32 Integer modType An integer identifying the type of int modType = vI(32, 32); // 32 Integer modType An integer identifying the type of
// modification. For all revisions, the // modification. For all revisions, the
...@@ -1567,7 +1570,7 @@ void PDBFileParser::ParseTitle() ...@@ -1567,7 +1570,7 @@ void PDBFileParser::ParseTitle()
// 54 - 59 LString(6) record Modification detail. // 54 - 59 LString(6) record Modification detail.
// 61 - 66 LString(6) record Modification detail. // 61 - 66 LString(6) record Modification detail.
revdats.push_back({revNum, date, modType == 0 ? mOriginalDate : "", modId, modType}); revdats.push_back({revNum, date, modType == 0 ? mOriginalDate : "", modID, modType});
ba::split(revdats.back().types, value, ba::is_any_of(" ")); ba::split(revdats.back().types, value, ba::is_any_of(" "));
...@@ -1576,7 +1579,7 @@ void PDBFileParser::ParseTitle() ...@@ -1576,7 +1579,7 @@ void PDBFileParser::ParseTitle()
cat = getCategory("database_2"); cat = getCategory("database_2");
cat->emplace({ cat->emplace({
{ "database_id", "PDB" }, { "database_id", "PDB" },
{ "database_code", modId } { "database_code", modID }
}); });
} }
...@@ -2430,10 +2433,10 @@ void PDBFileParser::ParseRemarks() ...@@ -2430,10 +2433,10 @@ void PDBFileParser::ParseRemarks()
rx3(R"(SITE_DESCRIPTION: (binding site for residue ([[:alnum:]]{1,3}) ([[:alnum:]]) (\d+)|.+))", regex_constants::icase); rx3(R"(SITE_DESCRIPTION: (binding site for residue ([[:alnum:]]{1,3}) ([[:alnum:]]) (\d+)|.+))", regex_constants::icase);
string id, evidence, desc; string id, evidence, desc;
string pdbxAuthAsymId, pdbxAuthCompId, pdbxAuthSeqId, pdbxAuthInsCode; string pdbxAuthAsymID, pdbxAuthCompID, pdbxAuthSeqID, pdbxAuthInsCode;
smatch m; smatch m;
enum State { sStart, sId, sEvidence, sDesc, sDesc2 } state = sStart; enum State { sStart, sID, sEvidence, sDesc, sDesc2 } state = sStart;
auto store = [&]() auto store = [&]()
{ {
...@@ -2450,9 +2453,9 @@ void PDBFileParser::ParseRemarks() ...@@ -2450,9 +2453,9 @@ void PDBFileParser::ParseRemarks()
getCategory("struct_site")->emplace({ getCategory("struct_site")->emplace({
{ "id", id }, { "id", id },
{ "details", desc }, { "details", desc },
{ "pdbx_auth_asym_id", pdbxAuthAsymId }, { "pdbx_auth_asym_id", pdbxAuthAsymID },
{ "pdbx_auth_comp_id", pdbxAuthCompId }, { "pdbx_auth_comp_id", pdbxAuthCompID },
{ "pdbx_auth_seq_id", pdbxAuthSeqId }, { "pdbx_auth_seq_id", pdbxAuthSeqID },
{ "pdbx_num_residues", site->vI(16, 17) }, { "pdbx_num_residues", site->vI(16, 17) },
{ "pdbx_evidence_code", evidence } { "pdbx_evidence_code", evidence }
}); });
...@@ -2468,12 +2471,12 @@ void PDBFileParser::ParseRemarks() ...@@ -2468,12 +2471,12 @@ void PDBFileParser::ParseRemarks()
{ {
case sStart: case sStart:
if (s == "SITE") if (s == "SITE")
state = sId; state = sID;
else if (cif::VERBOSE) else if (cif::VERBOSE)
throw runtime_error("Invalid REMARK 800 record, expected SITE"); throw runtime_error("Invalid REMARK 800 record, expected SITE");
break; break;
case sId: case sID:
if (regex_match(s, m, rx1)) if (regex_match(s, m, rx1))
{ {
id = m[1].str(); id = m[1].str();
...@@ -2497,9 +2500,9 @@ void PDBFileParser::ParseRemarks() ...@@ -2497,9 +2500,9 @@ void PDBFileParser::ParseRemarks()
if (regex_match(s, m, rx3)) if (regex_match(s, m, rx3))
{ {
desc = m[1].str(); desc = m[1].str();
pdbxAuthCompId = m[2].str(); pdbxAuthCompID = m[2].str();
pdbxAuthAsymId = m[3].str(); pdbxAuthAsymID = m[3].str();
pdbxAuthSeqId = m[4].str(); pdbxAuthSeqID = m[4].str();
state = sDesc2; state = sDesc2;
} }
...@@ -2588,7 +2591,7 @@ void PDBFileParser::ParseRemarks() ...@@ -2588,7 +2591,7 @@ void PDBFileParser::ParseRemarks()
if (not (compoundDetails.empty() and sequenceDetails.empty() and sourceDetails.empty())) if (not (compoundDetails.empty() and sequenceDetails.empty() and sourceDetails.empty()))
{ {
getCategory("pdbx_entry_details")->emplace({ getCategory("pdbx_entry_details")->emplace({
{ "entry_id", mStructureId }, { "entry_id", mStructureID },
{ "compound_details", compoundDetails }, { "compound_details", compoundDetails },
{ "sequence_details", sequenceDetails }, { "sequence_details", sequenceDetails },
{ "source_details", sourceDetails } { "source_details", sourceDetails }
...@@ -2647,7 +2650,7 @@ void PDBFileParser::ParseRemark200() ...@@ -2647,7 +2650,7 @@ void PDBFileParser::ParseRemark200()
if (inRM200({"INTENSITY-INTEGRATION SOFTWARE", "DATA SCALING SOFTWARE", "SOFTWARE USED"}) or if (inRM200({"INTENSITY-INTEGRATION SOFTWARE", "DATA SCALING SOFTWARE", "SOFTWARE USED"}) or
not mRefinementSoftware.empty()) not mRefinementSoftware.empty())
getCategory("computing")->emplace({ getCategory("computing")->emplace({
{ "entry_id", mStructureId }, { "entry_id", mStructureID },
{ "pdbx_data_reduction_ii", mRemark200["INTENSITY-INTEGRATION SOFTWARE"] }, { "pdbx_data_reduction_ii", mRemark200["INTENSITY-INTEGRATION SOFTWARE"] },
{ "pdbx_data_reduction_ds", mRemark200["DATA SCALING SOFTWARE"] }, { "pdbx_data_reduction_ds", mRemark200["DATA SCALING SOFTWARE"] },
{ "structure_solution", mRemark200["SOFTWARE USED"] }, { "structure_solution", mRemark200["SOFTWARE USED"] },
...@@ -2695,7 +2698,7 @@ void PDBFileParser::ParseRemark200() ...@@ -2695,7 +2698,7 @@ void PDBFileParser::ParseRemark200()
getCategory("diffrn")->emplace({ getCategory("diffrn")->emplace({
{ "id", diffrnNr }, { "id", diffrnNr },
{ "ambient_temp", ambientTemp }, { "ambient_temp", ambientTemp },
// { "ambient_temp_details", seqId }, // { "ambient_temp_details", seqID },
{ "crystal_id", 1 } { "crystal_id", 1 }
}); });
...@@ -2791,7 +2794,7 @@ void PDBFileParser::ParseRemark200() ...@@ -2791,7 +2794,7 @@ void PDBFileParser::ParseRemark200()
{ "ls_d_res_high", resolution }, { "ls_d_res_high", resolution },
{ "pdbx_diffrn_id", 1 }, { "pdbx_diffrn_id", 1 },
{ "pdbx_refine_id", mExpMethod }, { "pdbx_refine_id", mExpMethod },
{ "entry_id", mStructureId } { "entry_id", mStructureID }
}); });
} }
...@@ -2802,7 +2805,7 @@ void PDBFileParser::ParseRemark200() ...@@ -2802,7 +2805,7 @@ void PDBFileParser::ParseRemark200()
if (cat->empty()) if (cat->empty())
cat->emplace({}); cat->emplace({});
r = cat->back(); r = cat->back();
r["entry_id"] = mStructureId; r["entry_id"] = mStructureID;
r["observed_criterion_sigma_I"] = mRemark200["REJECTION CRITERIA (SIGMA(I))"]; r["observed_criterion_sigma_I"] = mRemark200["REJECTION CRITERIA (SIGMA(I))"];
r["d_resolution_high"] = mRemark200["RESOLUTION RANGE HIGH (A)"]; r["d_resolution_high"] = mRemark200["RESOLUTION RANGE HIGH (A)"];
r["d_resolution_low"] = mRemark200["RESOLUTION RANGE LOW (A)"]; r["d_resolution_low"] = mRemark200["RESOLUTION RANGE LOW (A)"];
...@@ -2851,7 +2854,7 @@ void PDBFileParser::ParseRemark350() ...@@ -2851,7 +2854,7 @@ void PDBFileParser::ParseRemark350()
kRX9(R"(AND CHAINS: (.+))"), kRX9(R"(AND CHAINS: (.+))"),
kRX10(R"(BIOMT([123])\s+(\d+)\s+(-?\d+(?:\.\d+)?)\s+(-?\d+(?:\.\d+)?)\s+(-?\d+(?:\.\d+)?)\s+(-?\d+(?:\.\d+)?))"); kRX10(R"(BIOMT([123])\s+(\d+)\s+(-?\d+(?:\.\d+)?)\s+(-?\d+(?:\.\d+)?)\s+(-?\d+(?:\.\d+)?)\s+(-?\d+(?:\.\d+)?))");
int biomolecule = 0, operId = 0; int biomolecule = 0, operID = 0;
vector<string> operExpression; vector<string> operExpression;
map<string,string> values; map<string,string> values;
vector<string> asymIdList; vector<string> asymIdList;
...@@ -2933,8 +2936,8 @@ void PDBFileParser::ParseRemark350() ...@@ -2933,8 +2936,8 @@ void PDBFileParser::ParseRemark350()
if (mt != 1) if (mt != 1)
throw runtime_error("Invalid REMARK 350"); throw runtime_error("Invalid REMARK 350");
operId = stoi(m[2].str()); operID = stoi(m[2].str());
operExpression.push_back(to_string(operId)); operExpression.push_back(to_string(operID));
mat.push_back(stod(m[3].str())); mat.push_back(stod(m[3].str()));
mat.push_back(stod(m[4].str())); mat.push_back(stod(m[4].str()));
...@@ -2951,10 +2954,10 @@ void PDBFileParser::ParseRemark350() ...@@ -2951,10 +2954,10 @@ void PDBFileParser::ParseRemark350()
if (mt == 1) if (mt == 1)
{ {
operId = stoi(m[2].str()); operID = stoi(m[2].str());
operExpression.push_back(to_string(operId)); operExpression.push_back(to_string(operID));
} }
else if (operId != stoi(m[2].str())) else if (operID != stoi(m[2].str()))
throw runtime_error("Invalid REMARK 350"); throw runtime_error("Invalid REMARK 350");
mat.push_back(stod(m[3].str())); mat.push_back(stod(m[3].str()));
...@@ -2967,7 +2970,7 @@ void PDBFileParser::ParseRemark350() ...@@ -2967,7 +2970,7 @@ void PDBFileParser::ParseRemark350()
if (vec.size() != 3 or mat.size() != 9) if (vec.size() != 3 or mat.size() != 9)
throw runtime_error("Invalid REMARK 350"); throw runtime_error("Invalid REMARK 350");
if (operId == 1) if (operID == 1)
{ {
string oligomer = values["AUTHOR DETERMINED BIOLOGICAL UNIT"]; string oligomer = values["AUTHOR DETERMINED BIOLOGICAL UNIT"];
if (oligomer.empty()) if (oligomer.empty())
...@@ -3041,7 +3044,7 @@ void PDBFileParser::ParseRemark350() ...@@ -3041,7 +3044,7 @@ void PDBFileParser::ParseRemark350()
boost::format fmt("%12.10f"); boost::format fmt("%12.10f");
getCategory("pdbx_struct_oper_list")->emplace({ getCategory("pdbx_struct_oper_list")->emplace({
{ "id", operId }, { "id", operID },
{ "type", { "type",
mat == vector<double>{ 1, 0, 0, 0, 1, 0, 0, 0, 1 } and vec == vector<double>{ 0, 0, 0 } mat == vector<double>{ 1, 0, 0, 0, 1, 0, 0, 0, 1 } and vec == vector<double>{ 0, 0, 0 }
? "identity operation" : "crystal symmetry operation" }, ? "identity operation" : "crystal symmetry operation" },
...@@ -3102,7 +3105,7 @@ void PDBFileParser::ParseRemark350() ...@@ -3102,7 +3105,7 @@ void PDBFileParser::ParseRemark350()
void PDBFileParser::ParsePrimaryStructure() void PDBFileParser::ParsePrimaryStructure()
{ {
// First locate the DBREF record. Might be missing // First locate the DBREF record. Might be missing
DBREF cur = { mStructureId }; DBREF cur = { mStructureID };
while (ba::starts_with(mRec->mName, "DBREF")) while (ba::starts_with(mRec->mName, "DBREF"))
{ {
...@@ -3192,7 +3195,7 @@ void PDBFileParser::ParsePrimaryStructure() ...@@ -3192,7 +3195,7 @@ void PDBFileParser::ParsePrimaryStructure()
{ // 8 - 10 Integer serNum Serial number of the SEQRES record for the { // 8 - 10 Integer serNum Serial number of the SEQRES record for the
// current chain. Starts at 1 and increments // current chain. Starts at 1 and increments
// by one each line. Reset to 1 for each chain. // by one each line. Reset to 1 for each chain.
char chainId = vC(12); // 12 Character chainID Chain identifier. This may be any single char chainID = vC(12); // 12 Character chainID Chain identifier. This may be any single
// legal character, including a blank which is // legal character, including a blank which is
// is used if there is only one chain. // is used if there is only one chain.
int numRes = vI(14, 17); // 14 - 17 Integer numRes Number of residues in the chain. int numRes = vI(14, 17); // 14 - 17 Integer numRes Number of residues in the chain.
...@@ -3200,17 +3203,17 @@ void PDBFileParser::ParsePrimaryStructure() ...@@ -3200,17 +3203,17 @@ void PDBFileParser::ParsePrimaryStructure()
string monomers = vS(20, 70); // 20 - 22 Residue name resName Residue name. string monomers = vS(20, 70); // 20 - 22 Residue name resName Residue name.
// ... // ...
auto& chain = GetChainForID(chainId, numRes); auto& chain = GetChainForID(chainID, numRes);
for (auto si = ba::make_split_iterator(monomers, ba::token_finder(ba::is_any_of(" "), ba::token_compress_on)); not si.eof(); ++si) for (auto si = ba::make_split_iterator(monomers, ba::token_finder(ba::is_any_of(" "), ba::token_compress_on)); not si.eof(); ++si)
{ {
string monId(si->begin(), si->end()); string monID(si->begin(), si->end());
if (monId.empty()) if (monID.empty())
continue; continue;
chain.mSeqres.push_back({monId, chain.mNextSeqNum++, ' ', chain.mNextDbSeqNum++}); chain.mSeqres.push_back({monID, chain.mNextSeqNum++, ' ', chain.mNextDbSeqNum++});
InsertChemComp(monId); InsertChemComp(monID);
} }
GetNextRecord(); GetNextRecord();
...@@ -3287,7 +3290,7 @@ void PDBFileParser::ParseHeterogen() ...@@ -3287,7 +3290,7 @@ void PDBFileParser::ParseHeterogen()
mFormuls[hetID] = formula; mFormuls[hetID] = formula;
if (waterMark == '*') if (waterMark == '*')
mWaterHetId = hetID; mWaterHetID = hetID;
GetNextRecord(); GetNextRecord();
} }
...@@ -3417,7 +3420,7 @@ void PDBFileParser::ConstructEntities() ...@@ -3417,7 +3420,7 @@ void PDBFileParser::ConstructEntities()
for (int ix = chain.mTerIndex; ix < static_cast<int>(chain.mResiduesSeen.size()); ++ix) for (int ix = chain.mTerIndex; ix < static_cast<int>(chain.mResiduesSeen.size()); ++ix)
{ {
string resName = chain.mResiduesSeen[ix].mMonId; string resName = chain.mResiduesSeen[ix].mMonID;
if (mmcif::kAAMap.count(resName) or if (mmcif::kAAMap.count(resName) or
mmcif::kBaseMap.count(resName) or mmcif::kBaseMap.count(resName) or
...@@ -3434,7 +3437,7 @@ void PDBFileParser::ConstructEntities() ...@@ -3434,7 +3437,7 @@ void PDBFileParser::ConstructEntities()
for (int ix = 0; ix < chain.mTerIndex; ++ix) for (int ix = 0; ix < chain.mTerIndex; ++ix)
{ {
auto& ar = chain.mResiduesSeen[ix]; auto& ar = chain.mResiduesSeen[ix];
chain.mSeqres.push_back({ar.mMonId, ar.mSeqNum, ar.mIcode, ar.mSeqNum, true}); chain.mSeqres.push_back({ar.mMonID, ar.mSeqNum, ar.mIcode, ar.mSeqNum, true});
} }
} }
} }
...@@ -3479,7 +3482,7 @@ void PDBFileParser::ConstructEntities() ...@@ -3479,7 +3482,7 @@ void PDBFileParser::ConstructEntities()
if (i != chain.mSeqres.end()) if (i != chain.mSeqres.end())
{ {
i->mSeen = true; i->mSeen = true;
if (i->mMonId != resName) if (i->mMonID != resName)
i->mAlts.insert(resName); i->mAlts.insert(resName);
} }
else else
...@@ -3508,7 +3511,7 @@ void PDBFileParser::ConstructEntities() ...@@ -3508,7 +3511,7 @@ void PDBFileParser::ConstructEntities()
(chain.mTerIndex > 0 and residueCount >= chain.mTerIndex)) (chain.mTerIndex > 0 and residueCount >= chain.mTerIndex))
{ {
if (isWater(resName)) if (isWater(resName))
mWaterHetId = resName; mWaterHetID = resName;
auto h = find_if(mHets.begin(), mHets.end(), [=](const HET& het) -> bool auto h = find_if(mHets.begin(), mHets.end(), [=](const HET& het) -> bool
{ {
...@@ -3538,29 +3541,29 @@ void PDBFileParser::ConstructEntities() ...@@ -3538,29 +3541,29 @@ void PDBFileParser::ConstructEntities()
// Create missing compounds // Create missing compounds
for (auto& chain: mChains) for (auto& chain: mChains)
{ {
if (chain.mMolId != 0 or chain.mSeqres.empty()) if (chain.mMolID != 0 or chain.mSeqres.empty())
continue; continue;
// now this chain may contain the same residues as another one // now this chain may contain the same residues as another one
for (auto& other: mChains) for (auto& other: mChains)
{ {
if (&other == &chain or other.mMolId == 0) if (&other == &chain or other.mMolID == 0)
continue; continue;
if (chain.SameSequence(other)) if (chain.SameSequence(other))
{ {
chain.mMolId = other.mMolId; chain.mMolID = other.mMolID;
break; break;
} }
} }
if (chain.mMolId != 0) if (chain.mMolID != 0)
continue; continue;
auto& comp = GetOrCreateCompound(mNextMolId++); auto& comp = GetOrCreateCompound(mNextMolID++);
comp.mChains.insert(chain.mDbref.chainID); comp.mChains.insert(chain.mDbref.chainID);
chain.mMolId = comp.mMolId; chain.mMolID = comp.mMolID;
} }
set<string> structTitle, structDescription; set<string> structTitle, structDescription;
...@@ -3571,49 +3574,49 @@ void PDBFileParser::ConstructEntities() ...@@ -3571,49 +3574,49 @@ void PDBFileParser::ConstructEntities()
int asymNr = 0; int asymNr = 0;
for (auto& chain: mChains) for (auto& chain: mChains)
{ {
string asymId = cifIdForInt(asymNr++); string asymID = cifIdForInt(asymNr++);
string entityId = mMolID2EntityID[chain.mMolId]; string entityID = mMolID2EntityID[chain.mMolID];
mAsymID2EntityID[asymId] = entityId; mAsymID2EntityID[asymID] = entityID;
getCategory("struct_asym")->emplace({ getCategory("struct_asym")->emplace({
{ "id", asymId }, { "id", asymID },
{ "pdbx_blank_PDB_chainid_flag", chain.mDbref.chainID == ' ' ? "Y" : "N" }, { "pdbx_blank_PDB_chainid_flag", chain.mDbref.chainID == ' ' ? "Y" : "N" },
// pdbx_modified // pdbx_modified
{ "entity_id", entityId }, { "entity_id", entityID },
// details // details
}); });
int seqNr = 1; int seqNr = 1;
for (auto& res: chain.mSeqres) for (auto& res: chain.mSeqres)
{ {
mChainSeq2AsymSeq[make_tuple(chain.mDbref.chainID, res.mSeqNum, res.mIcode)] = make_tuple(asymId, seqNr, true); mChainSeq2AsymSeq[make_tuple(chain.mDbref.chainID, res.mSeqNum, res.mIcode)] = make_tuple(asymID, seqNr, true);
string seqId = to_string(seqNr); string seqID = to_string(seqNr);
++seqNr; ++seqNr;
set<string> monIds = { res.mMonId }; set<string> monIds = { res.mMonID };
monIds.insert(res.mAlts.begin(), res.mAlts.end()); monIds.insert(res.mAlts.begin(), res.mAlts.end());
for (string monId: monIds) for (string monID: monIds)
{ {
string authMonId, authSeqNum; string authMonID, authSeqNum;
if (res.mSeen) if (res.mSeen)
{ {
authMonId = monId; authMonID = monID;
authSeqNum = to_string(res.mSeqNum); authSeqNum = to_string(res.mSeqNum);
} }
cat->emplace({ cat->emplace({
{ "asym_id", asymId }, { "asym_id", asymID },
{ "entity_id", mMolID2EntityID[chain.mMolId] }, { "entity_id", mMolID2EntityID[chain.mMolID] },
{ "seq_id", seqId }, { "seq_id", seqID },
{ "mon_id", monId }, { "mon_id", monID },
{ "ndb_seq_num", seqId }, { "ndb_seq_num", seqID },
{ "pdb_seq_num", res.mSeqNum }, { "pdb_seq_num", res.mSeqNum },
{ "auth_seq_num", authSeqNum }, { "auth_seq_num", authSeqNum },
{ "pdb_mon_id", authMonId }, { "pdb_mon_id", authMonID },
{ "auth_mon_id", authMonId }, { "auth_mon_id", authMonID },
{ "pdb_strand_id", string{chain.mDbref.chainID} }, { "pdb_strand_id", string{chain.mDbref.chainID} },
{ "pdb_ins_code", (res.mIcode == ' ' or res.mIcode == 0) ? "." : string{res.mIcode} }, { "pdb_ins_code", (res.mIcode == ' ' or res.mIcode == 0) ? "." : string{res.mIcode} },
{ "hetero", res.mAlts.empty() ? "n" : "y" } { "hetero", res.mAlts.empty() ? "n" : "y" }
...@@ -3623,11 +3626,11 @@ void PDBFileParser::ConstructEntities() ...@@ -3623,11 +3626,11 @@ void PDBFileParser::ConstructEntities()
} }
// We have now created all compounds, write them out // We have now created all compounds, write them out
uint32_t structRefId = 0, structRefSeqAlignId = 0; uint32_t structRefID = 0, structRefSeqAlignID = 0;
for (auto& cmp: mCompounds) for (auto& cmp: mCompounds)
{ {
++structRefId; ++structRefID;
string srcMethod; string srcMethod;
...@@ -3636,8 +3639,8 @@ void PDBFileParser::ConstructEntities() ...@@ -3636,8 +3639,8 @@ void PDBFileParser::ConstructEntities()
srcMethod = "syn"; srcMethod = "syn";
getCategory("pdbx_entity_src_syn")->emplace({ getCategory("pdbx_entity_src_syn")->emplace({
{ "entity_id", mMolID2EntityID[cmp.mMolId] }, { "entity_id", mMolID2EntityID[cmp.mMolID] },
{ "pdbx_src_id", structRefId }, { "pdbx_src_id", structRefID },
{ "organism_scientific", cmp.mSource["ORGANISM_SCIENTIFIC"] }, { "organism_scientific", cmp.mSource["ORGANISM_SCIENTIFIC"] },
{ "ncbi_taxonomy_id", cmp.mSource["ORGANISM_TAXID"] }, { "ncbi_taxonomy_id", cmp.mSource["ORGANISM_TAXID"] },
}); });
...@@ -3648,8 +3651,8 @@ void PDBFileParser::ConstructEntities() ...@@ -3648,8 +3651,8 @@ void PDBFileParser::ConstructEntities()
srcMethod = "man"; srcMethod = "man";
getCategory("entity_src_gen")->emplace({ getCategory("entity_src_gen")->emplace({
{ "entity_id", mMolID2EntityID[cmp.mMolId] }, { "entity_id", mMolID2EntityID[cmp.mMolID] },
{ "pdbx_src_id", structRefId }, { "pdbx_src_id", structRefID },
{ "gene_src_common_name", cmp.mSource["ORGANISM_COMMON"] }, { "gene_src_common_name", cmp.mSource["ORGANISM_COMMON"] },
{ "pdbx_gene_src_gene", cmp.mSource["GENE"] }, { "pdbx_gene_src_gene", cmp.mSource["GENE"] },
{ "gene_src_strain", cmp.mSource["STRAIN"] }, { "gene_src_strain", cmp.mSource["STRAIN"] },
...@@ -3680,8 +3683,8 @@ void PDBFileParser::ConstructEntities() ...@@ -3680,8 +3683,8 @@ void PDBFileParser::ConstructEntities()
srcMethod = "nat"; srcMethod = "nat";
getCategory("entity_src_nat")->emplace({ getCategory("entity_src_nat")->emplace({
{ "entity_id", mMolID2EntityID[cmp.mMolId] }, { "entity_id", mMolID2EntityID[cmp.mMolID] },
{ "pdbx_src_id", structRefId }, { "pdbx_src_id", structRefID },
{ "common_name", cmp.mSource["ORGANISM_COMMON"] }, { "common_name", cmp.mSource["ORGANISM_COMMON"] },
{ "strain", cmp.mSource["STRAIN"] }, { "strain", cmp.mSource["STRAIN"] },
{ "pdbx_secretion", cmp.mSource["SECRETION"] }, { "pdbx_secretion", cmp.mSource["SECRETION"] },
...@@ -3694,7 +3697,7 @@ void PDBFileParser::ConstructEntities() ...@@ -3694,7 +3697,7 @@ void PDBFileParser::ConstructEntities()
} }
getCategory("entity")->emplace({ getCategory("entity")->emplace({
{ "id", mMolID2EntityID[cmp.mMolId] }, { "id", mMolID2EntityID[cmp.mMolID] },
{ "type", "polymer" }, { "type", "polymer" },
{ "src_method", srcMethod }, { "src_method", srcMethod },
{ "pdbx_description", cmp.mInfo["MOLECULE"] }, { "pdbx_description", cmp.mInfo["MOLECULE"] },
...@@ -3709,7 +3712,7 @@ void PDBFileParser::ConstructEntities() ...@@ -3709,7 +3712,7 @@ void PDBFileParser::ConstructEntities()
if (not cmp.mInfo["SYNONYM"].empty()) if (not cmp.mInfo["SYNONYM"].empty())
{ {
getCategory("entity_name_com")->emplace({ getCategory("entity_name_com")->emplace({
{ "entity_id", mMolID2EntityID[cmp.mMolId] }, { "entity_id", mMolID2EntityID[cmp.mMolID] },
{ "name", cmp.mInfo["SYNONYM"] } { "name", cmp.mInfo["SYNONYM"] }
}); });
} }
...@@ -3730,8 +3733,8 @@ void PDBFileParser::ConstructEntities() ...@@ -3730,8 +3733,8 @@ void PDBFileParser::ConstructEntities()
if (ci != mChains.end() and not ci->mDbref.dbIdCode.empty()) if (ci != mChains.end() and not ci->mDbref.dbIdCode.empty())
{ {
getCategory("struct_ref")->emplace({ getCategory("struct_ref")->emplace({
{ "id", structRefId }, { "id", structRefID },
{ "entity_id", mMolID2EntityID[cmp.mMolId] }, { "entity_id", mMolID2EntityID[cmp.mMolID] },
{ "db_name", ci->mDbref.database }, { "db_name", ci->mDbref.database },
{ "db_code", ci->mDbref.dbIdCode }, { "db_code", ci->mDbref.dbIdCode },
{ "pdbx_db_accession", ci->mDbref.dbAccession }, { "pdbx_db_accession", ci->mDbref.dbAccession },
...@@ -3748,12 +3751,12 @@ void PDBFileParser::ConstructEntities() ...@@ -3748,12 +3751,12 @@ void PDBFileParser::ConstructEntities()
// write out the chains for this compound // write out the chains for this compound
for (auto& chain: mChains) for (auto& chain: mChains)
{ {
if (chain.mMolId != cmp.mMolId) if (chain.mMolID != cmp.mMolID)
continue; continue;
// chain.mEntityId = cmp.mEntityId; // chain.mEntityID = cmp.mEntityID;
++structRefSeqAlignId; ++structRefSeqAlignID;
DBREF& dbref = chain.mDbref; DBREF& dbref = chain.mDbref;
if (not dbref.database.empty()) if (not dbref.database.empty())
...@@ -3781,8 +3784,8 @@ void PDBFileParser::ConstructEntities() ...@@ -3781,8 +3784,8 @@ void PDBFileParser::ConstructEntities()
catch (...) {} catch (...) {}
getCategory("struct_ref_seq")->emplace({ getCategory("struct_ref_seq")->emplace({
{ "align_id", structRefSeqAlignId }, { "align_id", structRefSeqAlignID },
{ "ref_id", structRefId }, { "ref_id", structRefID },
{ "pdbx_PDB_id_code", dbref.PDBIDCode }, { "pdbx_PDB_id_code", dbref.PDBIDCode },
{ "pdbx_strand_id", string{ chain.mDbref.chainID } }, { "pdbx_strand_id", string{ chain.mDbref.chainID } },
{ "seq_align_beg", seqAlignBeg }, { "seq_align_beg", seqAlignBeg },
...@@ -3819,7 +3822,7 @@ void PDBFileParser::ConstructEntities() ...@@ -3819,7 +3822,7 @@ void PDBFileParser::ConstructEntities()
seqNum = to_string(labelSeq); seqNum = to_string(labelSeq);
getCategory("struct_ref_seq_dif")->emplace({ getCategory("struct_ref_seq_dif")->emplace({
{ "align_id", structRefSeqAlignId }, { "align_id", structRefSeqAlignID },
{ "pdbx_PDB_id_code", dbref.PDBIDCode }, { "pdbx_PDB_id_code", dbref.PDBIDCode },
{ "mon_id", seqadv.resName }, { "mon_id", seqadv.resName },
{ "pdbx_pdb_strand_id", seqadv.chainID }, { "pdbx_pdb_strand_id", seqadv.chainID },
...@@ -3836,7 +3839,7 @@ void PDBFileParser::ConstructEntities() ...@@ -3836,7 +3839,7 @@ void PDBFileParser::ConstructEntities()
} }
} }
if (not chains.empty()) // not the first one for this molId if (not chains.empty()) // not the first one for this molID
{ {
chains.push_back( string{ chain.mDbref.chainID } ); chains.push_back( string{ chain.mDbref.chainID } );
continue; continue;
...@@ -3850,26 +3853,26 @@ void PDBFileParser::ConstructEntities() ...@@ -3850,26 +3853,26 @@ void PDBFileParser::ConstructEntities()
{ {
string letter, stdRes; string letter, stdRes;
if (mMod2parent.count(res.mMonId)) if (mMod2parent.count(res.mMonID))
stdRes = mMod2parent.at(res.mMonId); stdRes = mMod2parent.at(res.mMonID);
if (mmcif::kAAMap.count(res.mMonId)) if (mmcif::kAAMap.count(res.mMonID))
{ {
letter = mmcif::kAAMap.at(res.mMonId); letter = mmcif::kAAMap.at(res.mMonID);
mightBeDNA = false; mightBeDNA = false;
} }
else if (mmcif::kBaseMap.count(res.mMonId)) else if (mmcif::kBaseMap.count(res.mMonID))
{ {
letter = mmcif::kBaseMap.at(res.mMonId); letter = mmcif::kBaseMap.at(res.mMonID);
mightBePolyPeptide = false; mightBePolyPeptide = false;
} }
else else
{ {
nstdMonomer = true; nstdMonomer = true;
letter = '(' + res.mMonId + ')'; letter = '(' + res.mMonID + ')';
// sja... // sja...
auto compound = mmcif::Compound::create(stdRes.empty() ? res.mMonId : stdRes); auto compound = mmcif::Compound::create(stdRes.empty() ? res.mMonID : stdRes);
if (compound != nullptr and if (compound != nullptr and
not iequals(compound->type(), "L-peptide linking") and not iequals(compound->type(), "L-peptide linking") and
not iequals(compound->type(), "RNA linking")) not iequals(compound->type(), "RNA linking"))
...@@ -3891,8 +3894,8 @@ void PDBFileParser::ConstructEntities() ...@@ -3891,8 +3894,8 @@ void PDBFileParser::ConstructEntities()
{ {
if (not stdRes.empty() and mmcif::kAAMap.count(stdRes)) if (not stdRes.empty() and mmcif::kAAMap.count(stdRes))
letter = mmcif::kAAMap.at(stdRes); letter = mmcif::kAAMap.at(stdRes);
else if (mmcif::kBaseMap.count(res.mMonId)) else if (mmcif::kBaseMap.count(res.mMonID))
letter = mmcif::kBaseMap.at(res.mMonId); letter = mmcif::kBaseMap.at(res.mMonID);
else else
letter = 'X'; letter = 'X';
} }
...@@ -3912,16 +3915,16 @@ void PDBFileParser::ConstructEntities() ...@@ -3912,16 +3915,16 @@ void PDBFileParser::ConstructEntities()
auto& rs = chain.mSeqres[i]; auto& rs = chain.mSeqres[i];
cat->emplace({ cat->emplace({
{ "entity_id", mMolID2EntityID[cmp.mMolId] }, { "entity_id", mMolID2EntityID[cmp.mMolID] },
{ "num", i + 1 }, { "num", i + 1 },
{ "mon_id", rs.mMonId }, { "mon_id", rs.mMonID },
{ "hetero", rs.mAlts.empty() ? "n" : "y"} { "hetero", rs.mAlts.empty() ? "n" : "y"}
}); });
for (auto& a: rs.mAlts) for (auto& a: rs.mAlts)
{ {
cat->emplace({ cat->emplace({
{ "entity_id", mMolID2EntityID[cmp.mMolId] }, { "entity_id", mMolID2EntityID[cmp.mMolID] },
{ "num", i + 1 }, { "num", i + 1 },
{ "mon_id", a }, { "mon_id", a },
{ "hetero", "y"} { "hetero", "y"}
...@@ -3937,7 +3940,7 @@ void PDBFileParser::ConstructEntities() ...@@ -3937,7 +3940,7 @@ void PDBFileParser::ConstructEntities()
type = "polyribonucleotide"; type = "polyribonucleotide";
getCategory("entity_poly")->emplace({ getCategory("entity_poly")->emplace({
{ "entity_id", mMolID2EntityID[cmp.mMolId] }, { "entity_id", mMolID2EntityID[cmp.mMolID] },
{ "pdbx_seq_one_letter_code", seq }, { "pdbx_seq_one_letter_code", seq },
{ "pdbx_seq_one_letter_code_can", seqCan }, { "pdbx_seq_one_letter_code_can", seqCan },
{ "nstd_monomer", (nstdMonomer ? "yes" : "no") }, { "nstd_monomer", (nstdMonomer ? "yes" : "no") },
...@@ -3950,7 +3953,7 @@ void PDBFileParser::ConstructEntities() ...@@ -3950,7 +3953,7 @@ void PDBFileParser::ConstructEntities()
if (not (structTitle.empty() and structDescription.empty())) if (not (structTitle.empty() and structDescription.empty()))
{ {
getCategory("struct")->emplace({ getCategory("struct")->emplace({
{ "entry_id", mStructureId }, { "entry_id", mStructureID },
{ "title", ba::join(structTitle, ", ") }, { "title", ba::join(structTitle, ", ") },
{ "pdbx_descriptor", ba::join(structDescription, ", ") }, { "pdbx_descriptor", ba::join(structDescription, ", ") },
{ "pdbx_model_type_details", mModelTypeDetails } { "pdbx_model_type_details", mModelTypeDetails }
...@@ -3964,10 +3967,10 @@ void PDBFileParser::ConstructEntities() ...@@ -3964,10 +3967,10 @@ void PDBFileParser::ConstructEntities()
{ {
auto& heti = mHets[i]; auto& heti = mHets[i];
if (not heti.asymId.empty()) if (not heti.asymID.empty())
continue; continue;
if (heti.hetID == mWaterHetId or isWater(heti.hetID)) if (heti.hetID == mWaterHetID or isWater(heti.hetID))
continue; continue;
// See if this residue is part of SEQRES // See if this residue is part of SEQRES
...@@ -3978,7 +3981,7 @@ void PDBFileParser::ConstructEntities() ...@@ -3978,7 +3981,7 @@ void PDBFileParser::ConstructEntities()
if (ih != chain.mSeqres.end()) if (ih != chain.mSeqres.end())
continue; continue;
heti.asymId = cifIdForInt(asymNr++); heti.asymID = cifIdForInt(asymNr++);
} }
set<string> writtenAsyms; set<string> writtenAsyms;
...@@ -4003,13 +4006,13 @@ void PDBFileParser::ConstructEntities() ...@@ -4003,13 +4006,13 @@ void PDBFileParser::ConstructEntities()
// See if we've already added it to the entities // See if we've already added it to the entities
if (mHet2EntityID.count(hetID) == 0) if (mHet2EntityID.count(hetID) == 0)
{ {
string entityId = to_string(mNextEntityNr++); string entityID = to_string(mNextEntityNr++);
mHet2EntityID[hetID] = entityId; mHet2EntityID[hetID] = entityID;
if (hetID == mWaterHetId) if (hetID == mWaterHetID)
{ {
getCategory("entity")->emplace({ getCategory("entity")->emplace({
{ "id", entityId }, { "id", entityID },
{ "type", "water" }, { "type", "water" },
{ "src_method", "nat" }, { "src_method", "nat" },
{ "pdbx_description", "water" }, { "pdbx_description", "water" },
...@@ -4026,7 +4029,7 @@ void PDBFileParser::ConstructEntities() ...@@ -4026,7 +4029,7 @@ void PDBFileParser::ConstructEntities()
} }
getCategory("entity")->emplace({ getCategory("entity")->emplace({
{ "id", entityId }, { "id", entityID },
{ "type", "non-polymer" }, { "type", "non-polymer" },
{ "src_method", "syn" }, { "src_method", "syn" },
{ "pdbx_description", mHetnams[hetID] }, { "pdbx_description", mHetnams[hetID] },
...@@ -4037,10 +4040,10 @@ void PDBFileParser::ConstructEntities() ...@@ -4037,10 +4040,10 @@ void PDBFileParser::ConstructEntities()
// write a pdbx_entity_nonpoly record // write a pdbx_entity_nonpoly record
string name = mHetnams[hetID]; string name = mHetnams[hetID];
if (name.empty() and hetID == mWaterHetId) if (name.empty() and hetID == mWaterHetID)
name = "water"; name = "water";
getCategory("pdbx_entity_nonpoly")->emplace({ getCategory("pdbx_entity_nonpoly")->emplace({
{ "entity_id", entityId }, { "entity_id", entityID },
{ "name", name }, { "name", name },
{ "comp_id", hetID } { "comp_id", hetID }
}); });
...@@ -4048,39 +4051,39 @@ void PDBFileParser::ConstructEntities() ...@@ -4048,39 +4051,39 @@ void PDBFileParser::ConstructEntities()
// create an asym for this het/chain combo, if needed // create an asym for this het/chain combo, if needed
string asymId = het.asymId; string asymID = het.asymID;
auto k = make_tuple(het.chainID, het.seqNum, het.iCode); auto k = make_tuple(het.chainID, het.seqNum, het.iCode);
if (mChainSeq2AsymSeq.count(k) == 0) if (mChainSeq2AsymSeq.count(k) == 0)
{ {
if (hetID == mWaterHetId or isWater(hetID)) if (hetID == mWaterHetID or isWater(hetID))
{ {
if (waterChains.count(het.chainID) == 0) if (waterChains.count(het.chainID) == 0)
{ {
asymId = cifIdForInt(asymNr++); asymID = cifIdForInt(asymNr++);
waterChains[het.chainID] = asymId; waterChains[het.chainID] = asymID;
} }
else else
asymId = waterChains[het.chainID]; asymID = waterChains[het.chainID];
} }
else else
asymId = het.asymId; asymID = het.asymID;
assert(asymId.empty() == false); assert(asymID.empty() == false);
mAsymID2EntityID[asymId] = mHet2EntityID[hetID]; mAsymID2EntityID[asymID] = mHet2EntityID[hetID];
// NOTE, a nonpoly residue has no label_seq_id // NOTE, a nonpoly residue has no label_seq_id
// but in pdbx_nonpoly_scheme there is such a number. // but in pdbx_nonpoly_scheme there is such a number.
// Since this number is not used anywhere else we // Since this number is not used anywhere else we
// just use it here and do not store it in the table // just use it here and do not store it in the table
mChainSeq2AsymSeq[k] = make_tuple(asymId, 0, false); mChainSeq2AsymSeq[k] = make_tuple(asymID, 0, false);
if (writtenAsyms.count(asymId) == 0) if (writtenAsyms.count(asymID) == 0)
{ {
writtenAsyms.insert(asymId); writtenAsyms.insert(asymID);
getCategory("struct_asym")->emplace({ getCategory("struct_asym")->emplace({
{ "id", asymId }, { "id", asymID },
{ "pdbx_blank_PDB_chainid_flag", het.chainID == ' ' ? "Y" : "N" }, { "pdbx_blank_PDB_chainid_flag", het.chainID == ' ' ? "Y" : "N" },
// pdbx_modified // pdbx_modified
{ "entity_id", mHet2EntityID[hetID] }, { "entity_id", mHet2EntityID[hetID] },
...@@ -4089,7 +4092,7 @@ void PDBFileParser::ConstructEntities() ...@@ -4089,7 +4092,7 @@ void PDBFileParser::ConstructEntities()
} }
} }
int seqNr = ++ndbSeqNum[make_tuple(hetID, asymId)]; int seqNr = ++ndbSeqNum[make_tuple(hetID, asymID)];
string iCode{het.iCode}; string iCode{het.iCode};
ba::trim(iCode); ba::trim(iCode);
...@@ -4097,7 +4100,7 @@ void PDBFileParser::ConstructEntities() ...@@ -4097,7 +4100,7 @@ void PDBFileParser::ConstructEntities()
iCode = { '.' }; iCode = { '.' };
getCategory("pdbx_nonpoly_scheme")->emplace({ getCategory("pdbx_nonpoly_scheme")->emplace({
{ "asym_id", asymId }, { "asym_id", asymID },
{ "entity_id", mHet2EntityID[hetID] }, { "entity_id", mHet2EntityID[hetID] },
{ "mon_id", hetID }, { "mon_id", hetID },
{ "ndb_seq_num", seqNr }, { "ndb_seq_num", seqNr },
...@@ -4110,10 +4113,10 @@ void PDBFileParser::ConstructEntities() ...@@ -4110,10 +4113,10 @@ void PDBFileParser::ConstructEntities()
}); });
// mapping needed? // mapping needed?
mChainSeq2AsymSeq[make_tuple(het.chainID, het.seqNum, het.iCode)] = make_tuple(asymId, seqNr, false); mChainSeq2AsymSeq[make_tuple(het.chainID, het.seqNum, het.iCode)] = make_tuple(asymID, seqNr, false);
} }
int modResId = 1; int modResID = 1;
set<string> modResSet; set<string> modResSet;
for (auto rec = FindRecord("MODRES"); rec != nullptr and rec->is("MODRES"); for (auto rec = FindRecord("MODRES"); rec != nullptr and rec->is("MODRES");
rec = rec->mNext) // 1 - 6 Record name "MODRES" rec = rec->mNext) // 1 - 6 Record name "MODRES"
...@@ -4125,11 +4128,11 @@ void PDBFileParser::ConstructEntities() ...@@ -4125,11 +4128,11 @@ void PDBFileParser::ConstructEntities()
string stdRes = rec->vS(25, 27); // 25 - 27 Residue name stdRes Standard residue name. string stdRes = rec->vS(25, 27); // 25 - 27 Residue name stdRes Standard residue name.
string comment = rec->vS(30, 70); // 30 - 70 String comment Description of the residue modification. string comment = rec->vS(30, 70); // 30 - 70 String comment Description of the residue modification.
string asymId; string asymID;
int seq; int seq;
std::error_code ec; std::error_code ec;
tie(asymId, seq, ignore) = MapResidue(chainID, seqNum, iCode, ec); tie(asymID, seq, ignore) = MapResidue(chainID, seqNum, iCode, ec);
if (ec) // no need to write a modres if it could not be found if (ec) // no need to write a modres if it could not be found
{ {
if (cif::VERBOSE) if (cif::VERBOSE)
...@@ -4138,8 +4141,8 @@ void PDBFileParser::ConstructEntities() ...@@ -4138,8 +4141,8 @@ void PDBFileParser::ConstructEntities()
} }
getCategory("pdbx_struct_mod_residue")->emplace({ getCategory("pdbx_struct_mod_residue")->emplace({
{ "id", modResId++ }, { "id", modResID++ },
{ "label_asym_id", asymId }, { "label_asym_id", asymID },
{ "label_seq_id", seq }, { "label_seq_id", seq },
{ "label_comp_id", resName }, { "label_comp_id", resName },
{ "auth_asym_id", string(1, chainID) }, { "auth_asym_id", string(1, chainID) },
...@@ -4218,11 +4221,11 @@ void PDBFileParser::ConstructEntities() ...@@ -4218,11 +4221,11 @@ void PDBFileParser::ConstructEntities()
for (auto& unobs: mUnobs) for (auto& unobs: mUnobs)
{ {
bool isPolymer = false; bool isPolymer = false;
string asymId, compId = unobs.res; string asymID, compID = unobs.res;
int seqNr = 0; int seqNr = 0;
std::error_code ec; std::error_code ec;
tie(asymId, seqNr, isPolymer) = MapResidue(unobs.chain, unobs.seq, unobs.iCode, ec); tie(asymID, seqNr, isPolymer) = MapResidue(unobs.chain, unobs.seq, unobs.iCode, ec);
if (ec) if (ec)
{ {
if (cif::VERBOSE) if (cif::VERBOSE)
...@@ -4241,8 +4244,8 @@ void PDBFileParser::ConstructEntities() ...@@ -4241,8 +4244,8 @@ void PDBFileParser::ConstructEntities()
{ "auth_comp_id", unobs.res }, { "auth_comp_id", unobs.res },
{ "auth_seq_id", unobs.seq }, { "auth_seq_id", unobs.seq },
{ "PDB_ins_code", unobs.iCode == ' ' ? "" : string{ unobs.iCode } }, { "PDB_ins_code", unobs.iCode == ' ' ? "" : string{ unobs.iCode } },
{ "label_asym_id", asymId }, { "label_asym_id", asymID },
{ "label_comp_id", compId }, // TODO: change to correct comp_id { "label_comp_id", compID }, // TODO: change to correct comp_id
{ "label_seq_id", seqNr > 0 ? to_string(seqNr) : "" } { "label_seq_id", seqNr > 0 ? to_string(seqNr) : "" }
}); });
} }
...@@ -4260,8 +4263,8 @@ void PDBFileParser::ConstructEntities() ...@@ -4260,8 +4263,8 @@ void PDBFileParser::ConstructEntities()
{ "auth_seq_id", unobs.seq }, { "auth_seq_id", unobs.seq },
{ "PDB_ins_code", unobs.iCode == ' ' ? "" : string{ unobs.iCode } }, { "PDB_ins_code", unobs.iCode == ' ' ? "" : string{ unobs.iCode } },
{ "auth_atom_id", atom }, { "auth_atom_id", atom },
{ "label_asym_id", asymId }, { "label_asym_id", asymID },
{ "label_comp_id", compId }, // TODO: change to correct comp_id { "label_comp_id", compID }, // TODO: change to correct comp_id
{ "label_seq_id", seqNr > 0 ? to_string(seqNr) : "" }, { "label_seq_id", seqNr > 0 ? to_string(seqNr) : "" },
{ "label_atom_id", atom } { "label_atom_id", atom }
}); });
...@@ -4297,13 +4300,13 @@ void PDBFileParser::ParseSecondaryStructure() ...@@ -4297,13 +4300,13 @@ void PDBFileParser::ParseSecondaryStructure()
// 41 - 70 String comment Comment about this helix. // 41 - 70 String comment Comment about this helix.
// 72 - 76 Integer length Length of this helix. // 72 - 76 Integer length Length of this helix.
string begAsymId, endAsymId; string begAsymID, endAsymID;
int begSeq, endSeq; int begSeq, endSeq;
std::error_code ec; std::error_code ec;
tie(begAsymId, begSeq, ignore) = MapResidue(vC(20), vI(22, 25), vC(26), ec); tie(begAsymID, begSeq, ignore) = MapResidue(vC(20), vI(22, 25), vC(26), ec);
if (not ec) if (not ec)
tie(endAsymId, endSeq, ignore) = MapResidue(vC(32), vI(34, 37), vC(38), ec); tie(endAsymID, endSeq, ignore) = MapResidue(vC(32), vI(34, 37), vC(38), ec);
if (ec) if (ec)
{ {
...@@ -4318,11 +4321,11 @@ void PDBFileParser::ParseSecondaryStructure() ...@@ -4318,11 +4321,11 @@ void PDBFileParser::ParseSecondaryStructure()
{ "id", "HELX_P" + to_string(vI(8, 10)) }, { "id", "HELX_P" + to_string(vI(8, 10)) },
{ "pdbx_PDB_helix_id", vS(12, 14) }, { "pdbx_PDB_helix_id", vS(12, 14) },
{ "beg_label_comp_id", vS(16, 18) }, { "beg_label_comp_id", vS(16, 18) },
{ "beg_label_asym_id", begAsymId }, { "beg_label_asym_id", begAsymID },
{ "beg_label_seq_id", begSeq }, { "beg_label_seq_id", begSeq },
{ "pdbx_beg_PDB_ins_code", vS(26, 26) }, { "pdbx_beg_PDB_ins_code", vS(26, 26) },
{ "end_label_comp_id", vS(28, 30) }, { "end_label_comp_id", vS(28, 30) },
{ "end_label_asym_id", endAsymId }, { "end_label_asym_id", endAsymID },
{ "end_label_seq_id", endSeq }, { "end_label_seq_id", endSeq },
{ "pdbx_end_PDB_ins_code", vS(38, 38) }, { "pdbx_end_PDB_ins_code", vS(38, 38) },
...@@ -4377,7 +4380,7 @@ void PDBFileParser::ParseSecondaryStructure() ...@@ -4377,7 +4380,7 @@ void PDBFileParser::ParseSecondaryStructure()
// 1 if parallel,and -1 if anti-parallel. // 1 if parallel,and -1 if anti-parallel.
// 42 - 45 Atom curAtom Registration. Atom name in current strand. // 42 - 45 Atom curAtom Registration. Atom name in current strand.
// 46 - 48 Residue name curResName Registration. Residue name in current strand // 46 - 48 Residue name curResName Registration. Residue name in current strand
// 50 Character curChainId Registration. Chain identifier in // 50 Character curChainID Registration. Chain identifier in
// current strand. // current strand.
// 51 - 54 Integer curResSeq Registration. Residue sequence number // 51 - 54 Integer curResSeq Registration. Residue sequence number
// in current strand. // in current strand.
...@@ -4386,7 +4389,7 @@ void PDBFileParser::ParseSecondaryStructure() ...@@ -4386,7 +4389,7 @@ void PDBFileParser::ParseSecondaryStructure()
// 57 - 60 Atom prevAtom Registration. Atom name in previous strand. // 57 - 60 Atom prevAtom Registration. Atom name in previous strand.
// 61 - 63 Residue name prevResName Registration. Residue name in // 61 - 63 Residue name prevResName Registration. Residue name in
// previous strand. // previous strand.
// 65 Character prevChainId Registration. Chain identifier in // 65 Character prevChainID Registration. Chain identifier in
// previous strand. // previous strand.
// 66 - 69 Integer prevResSeq Registration. Residue sequence number // 66 - 69 Integer prevResSeq Registration. Residue sequence number
// in previous strand. // in previous strand.
...@@ -4418,13 +4421,13 @@ void PDBFileParser::ParseSecondaryStructure() ...@@ -4418,13 +4421,13 @@ void PDBFileParser::ParseSecondaryStructure()
}); });
} }
string begAsymId, endAsymId; string begAsymID, endAsymID;
int begSeq, endSeq; int begSeq, endSeq;
std::error_code ec; std::error_code ec;
tie(begAsymId, begSeq, ignore) = MapResidue(vC(22), vI(23, 26), vC(27), ec); tie(begAsymID, begSeq, ignore) = MapResidue(vC(22), vI(23, 26), vC(27), ec);
if (not ec) if (not ec)
tie(endAsymId, endSeq, ignore) = MapResidue(vC(33), vI(34, 37), vC(38), ec); tie(endAsymID, endSeq, ignore) = MapResidue(vC(33), vI(34, 37), vC(38), ec);
if (ec) if (ec)
{ {
...@@ -4437,11 +4440,11 @@ void PDBFileParser::ParseSecondaryStructure() ...@@ -4437,11 +4440,11 @@ void PDBFileParser::ParseSecondaryStructure()
{ "sheet_id", sheetID }, { "sheet_id", sheetID },
{ "id", vI(8, 10) }, { "id", vI(8, 10) },
{ "beg_label_comp_id", vS(18, 20) }, { "beg_label_comp_id", vS(18, 20) },
{ "beg_label_asym_id", begAsymId }, { "beg_label_asym_id", begAsymID },
{ "beg_label_seq_id", begSeq }, { "beg_label_seq_id", begSeq },
{ "pdbx_beg_PDB_ins_code", vS(27, 27) }, { "pdbx_beg_PDB_ins_code", vS(27, 27) },
{ "end_label_comp_id", vS(29, 31) }, { "end_label_comp_id", vS(29, 31) },
{ "end_label_asym_id", endAsymId }, { "end_label_asym_id", endAsymID },
{ "end_label_seq_id", endSeq }, { "end_label_seq_id", endSeq },
{ "pdbx_end_PDB_ins_code", vS(38, 38) }, { "pdbx_end_PDB_ins_code", vS(38, 38) },
...@@ -4455,13 +4458,13 @@ void PDBFileParser::ParseSecondaryStructure() ...@@ -4455,13 +4458,13 @@ void PDBFileParser::ParseSecondaryStructure()
if (sense != 0 and mRec->mVlen > 34) if (sense != 0 and mRec->mVlen > 34)
{ {
string r1AsymId, r2AsymId; string r1AsymID, r2AsymID;
int r1Seq, r2Seq; int r1Seq, r2Seq;
std::error_code ec; std::error_code ec;
tie(r1AsymId, r1Seq, ignore) = MapResidue(vC(65), vI(66, 69), vC(70), ec); tie(r1AsymID, r1Seq, ignore) = MapResidue(vC(65), vI(66, 69), vC(70), ec);
if (not ec) if (not ec)
tie(r2AsymId, r2Seq, ignore) = MapResidue(vC(50), vI(51, 54), vC(55), ec); tie(r2AsymID, r2Seq, ignore) = MapResidue(vC(50), vI(51, 54), vC(55), ec);
if (ec) if (ec)
{ {
...@@ -4475,7 +4478,7 @@ void PDBFileParser::ParseSecondaryStructure() ...@@ -4475,7 +4478,7 @@ void PDBFileParser::ParseSecondaryStructure()
{ "range_id_2", rangeID + 1 }, { "range_id_2", rangeID + 1 },
{ "range_1_label_atom_id", vS(57, 60) }, { "range_1_label_atom_id", vS(57, 60) },
{ "range_1_label_comp_id", vS(61, 63) }, { "range_1_label_comp_id", vS(61, 63) },
{ "range_1_label_asym_id", r1AsymId }, { "range_1_label_asym_id", r1AsymID },
{ "range_1_label_seq_id", r1Seq }, { "range_1_label_seq_id", r1Seq },
{ "range_1_PDB_ins_code", vS(70, 70) }, { "range_1_PDB_ins_code", vS(70, 70) },
{ "range_1_auth_atom_id", vS(57, 60) }, { "range_1_auth_atom_id", vS(57, 60) },
...@@ -4485,7 +4488,7 @@ void PDBFileParser::ParseSecondaryStructure() ...@@ -4485,7 +4488,7 @@ void PDBFileParser::ParseSecondaryStructure()
{ "range_2_label_atom_id", vS(42, 45) }, { "range_2_label_atom_id", vS(42, 45) },
{ "range_2_label_comp_id", vS(46, 48) }, { "range_2_label_comp_id", vS(46, 48) },
{ "range_2_label_asym_id", r2AsymId }, { "range_2_label_asym_id", r2AsymID },
{ "range_2_label_seq_id", r2Seq }, { "range_2_label_seq_id", r2Seq },
{ "range_2_PDB_ins_code", vS(55, 55) }, { "range_2_PDB_ins_code", vS(55, 55) },
{ "range_2_auth_atom_id", vS(42, 45) }, { "range_2_auth_atom_id", vS(42, 45) },
...@@ -4512,7 +4515,7 @@ static bool IsMetal(const string& resName, const string& atomID) ...@@ -4512,7 +4515,7 @@ static bool IsMetal(const string& resName, const string& atomID)
auto compound = mmcif::Compound::create(resName); auto compound = mmcif::Compound::create(resName);
if (compound != nullptr) if (compound != nullptr)
{ {
auto at = mmcif::AtomTypeTraits(compound->getAtomById(atomID).typeSymbol); auto at = mmcif::AtomTypeTraits(compound->getAtomByID(atomID).typeSymbol);
result = at.isMetal(); result = at.isMetal();
} }
} }
...@@ -4686,7 +4689,7 @@ void PDBFileParser::ParseConnectivtyAnnotation() ...@@ -4686,7 +4689,7 @@ void PDBFileParser::ParseConnectivtyAnnotation()
continue; continue;
} }
string distance, ccp4LinkId; string distance, ccp4LinkID;
if (mRec->is("LINK ")) if (mRec->is("LINK "))
{ {
...@@ -4699,11 +4702,11 @@ void PDBFileParser::ParseConnectivtyAnnotation() ...@@ -4699,11 +4702,11 @@ void PDBFileParser::ParseConnectivtyAnnotation()
{ {
if (cif::VERBOSE) if (cif::VERBOSE)
cerr << "Distance value '" << distance << "' is not a valid float in LINK record" << endl; cerr << "Distance value '" << distance << "' is not a valid float in LINK record" << endl;
swap(ccp4LinkId, distance); // assume this is a ccp4_link_id... oh really? swap(ccp4LinkID, distance); // assume this is a ccp4_link_id... oh really?
} }
} }
else // LINKR else // LINKR
ccp4LinkId = vS(74, 78); // the link ID ccp4LinkID = vS(74, 78); // the link ID
string sym1, sym2; string sym1, sym2;
try { try {
...@@ -4721,7 +4724,7 @@ void PDBFileParser::ParseConnectivtyAnnotation() ...@@ -4721,7 +4724,7 @@ void PDBFileParser::ParseConnectivtyAnnotation()
{ "id", type + to_string(linkNr) }, { "id", type + to_string(linkNr) },
{ "conn_type_id", type }, { "conn_type_id", type },
{ "ccp4_link_id", ccp4LinkId }, { "ccp4_link_id", ccp4LinkID },
{ "ptnr1_label_asym_id", p1Asym }, { "ptnr1_label_asym_id", p1Asym },
{ "ptnr1_label_comp_id", vS(18, 20) }, { "ptnr1_label_comp_id", vS(18, 20) },
...@@ -4823,7 +4826,7 @@ void PDBFileParser::ParseConnectivtyAnnotation() ...@@ -4823,7 +4826,7 @@ void PDBFileParser::ParseConnectivtyAnnotation()
void PDBFileParser::ParseMiscellaneousFeatures() void PDBFileParser::ParseMiscellaneousFeatures()
{ {
int structSiteGenId = 1; int structSiteGenID = 1;
while (mRec->is("SITE ")) while (mRec->is("SITE "))
{ // 1 - 6 Record name "SITE " { // 1 - 6 Record name "SITE "
...@@ -4858,7 +4861,7 @@ void PDBFileParser::ParseMiscellaneousFeatures() ...@@ -4858,7 +4861,7 @@ void PDBFileParser::ParseMiscellaneousFeatures()
} }
else else
cat->emplace({ cat->emplace({
{ "id", structSiteGenId++ }, { "id", structSiteGenID++ },
{ "site_id", siteID }, { "site_id", siteID },
{ "pdbx_num_res", numRes }, { "pdbx_num_res", numRes },
{ "label_comp_id", resName }, { "label_comp_id", resName },
...@@ -4884,7 +4887,7 @@ void PDBFileParser::ParseCrystallographic() ...@@ -4884,7 +4887,7 @@ void PDBFileParser::ParseCrystallographic()
Match("CRYST1", true); Match("CRYST1", true);
getCategory("cell")->emplace({ getCategory("cell")->emplace({
{ "entry_id", mStructureId }, // 1 - 6 Record name "CRYST1" { "entry_id", mStructureID }, // 1 - 6 Record name "CRYST1"
{ "length_a", vF(7, 15) }, // 7 - 15 Real(9.3) a a (Angstroms). { "length_a", vF(7, 15) }, // 7 - 15 Real(9.3) a a (Angstroms).
{ "length_b", vF(16, 24) }, // 16 - 24 Real(9.3) b b (Angstroms). { "length_b", vF(16, 24) }, // 16 - 24 Real(9.3) b b (Angstroms).
{ "length_c", vF(25, 33) }, // 25 - 33 Real(9.3) c c (Angstroms). { "length_c", vF(25, 33) }, // 25 - 33 Real(9.3) c c (Angstroms).
...@@ -4907,7 +4910,7 @@ void PDBFileParser::ParseCrystallographic() ...@@ -4907,7 +4910,7 @@ void PDBFileParser::ParseCrystallographic()
} }
getCategory("symmetry")->emplace({ getCategory("symmetry")->emplace({
{ "entry_id", mStructureId }, { "entry_id", mStructureID },
{ "space_group_name_H-M", spaceGroup }, { "space_group_name_H-M", spaceGroup },
{ "Int_Tables_number", intTablesNr } { "Int_Tables_number", intTablesNr }
}); });
...@@ -4935,7 +4938,7 @@ void PDBFileParser::ParseCoordinateTransformation() ...@@ -4935,7 +4938,7 @@ void PDBFileParser::ParseCoordinateTransformation()
} }
getCategory("database_PDB_matrix")->emplace({ getCategory("database_PDB_matrix")->emplace({
{ "entry_id", mStructureId }, { "entry_id", mStructureID },
{ "origx[1][1]", m[0][0] }, { "origx[1][1]", m[0][0] },
{ "origx[1][2]", m[0][1] }, { "origx[1][2]", m[0][1] },
{ "origx[1][3]", m[0][2] }, { "origx[1][3]", m[0][2] },
...@@ -4967,7 +4970,7 @@ void PDBFileParser::ParseCoordinateTransformation() ...@@ -4967,7 +4970,7 @@ void PDBFileParser::ParseCoordinateTransformation()
} }
getCategory("atom_sites")->emplace({ getCategory("atom_sites")->emplace({
{ "entry_id", mStructureId }, { "entry_id", mStructureID },
{ "fract_transf_matrix[1][1]", m[0][0] }, { "fract_transf_matrix[1][1]", m[0][0] },
{ "fract_transf_matrix[1][2]", m[0][1] }, { "fract_transf_matrix[1][2]", m[0][1] },
{ "fract_transf_matrix[1][3]", m[0][2] }, { "fract_transf_matrix[1][3]", m[0][2] },
...@@ -5035,11 +5038,11 @@ void PDBFileParser::ParseCoordinate(int modelNr) ...@@ -5035,11 +5038,11 @@ void PDBFileParser::ParseCoordinate(int modelNr)
int resSeq = vI(23, 26); // 23 - 26 Integer resSeq Residue sequence number. int resSeq = vI(23, 26); // 23 - 26 Integer resSeq Residue sequence number.
char iCode = vC(27); char iCode = vC(27);
string asymId; string asymID;
int seqId; int seqID;
bool isResseq; bool isResseq;
tie(asymId, seqId, isResseq) = MapResidue(chainID, resSeq, iCode); tie(asymID, seqID, isResseq) = MapResidue(chainID, resSeq, iCode);
PDBRecord* atom = mRec; PDBRecord* atom = mRec;
PDBRecord* anisou = nullptr; PDBRecord* anisou = nullptr;
...@@ -5051,7 +5054,7 @@ void PDBFileParser::ParseCoordinate(int modelNr) ...@@ -5051,7 +5054,7 @@ void PDBFileParser::ParseCoordinate(int modelNr)
GetNextRecord(); GetNextRecord();
} }
atoms.emplace_back(asymId, seqId, isResseq, atom, anisou); atoms.emplace_back(asymID, seqID, isResseq, atom, anisou);
/*if?... */ while (mRec->is("TER ")) /*if?... */ while (mRec->is("TER "))
{ {
...@@ -5125,16 +5128,16 @@ void PDBFileParser::ParseCoordinate(int modelNr) ...@@ -5125,16 +5128,16 @@ void PDBFileParser::ParseCoordinate(int modelNr)
// while (mRec->is("ATOM ") or mRec->is("HETATM")) // 1 - 6 Record name "ATOM " // while (mRec->is("ATOM ") or mRec->is("HETATM")) // 1 - 6 Record name "ATOM "
for (auto& a: atoms) for (auto& a: atoms)
{ {
string asymId; string asymID;
int seqId; int seqID;
bool isResseq; bool isResseq;
PDBRecord* atom; PDBRecord* atom;
PDBRecord* anisou; PDBRecord* anisou;
tie(asymId, seqId, isResseq, atom, anisou) = a; tie(asymID, seqID, isResseq, atom, anisou) = a;
mRec = atom; mRec = atom;
++mAtomId; ++mAtomID;
string groupPDB = mRec->is("ATOM ") ? "ATOM" : "HETATM"; string groupPDB = mRec->is("ATOM ") ? "ATOM" : "HETATM";
// int serial = vI(7, 11); // 7 - 11 Integer serial Atom serial number. // int serial = vI(7, 11); // 7 - 11 Integer serial Atom serial number.
...@@ -5152,7 +5155,7 @@ void PDBFileParser::ParseCoordinate(int modelNr) ...@@ -5152,7 +5155,7 @@ void PDBFileParser::ParseCoordinate(int modelNr)
string element = vS(77, 78); // 77 - 78 LString(2) element Element symbol, right-justified. string element = vS(77, 78); // 77 - 78 LString(2) element Element symbol, right-justified.
string charge = vS(79, 80); // 79 - 80 LString(2) charge Charge on the atom. string charge = vS(79, 80); // 79 - 80 LString(2) charge Charge on the atom.
string entityId = mAsymID2EntityID[asymId]; string entityID = mAsymID2EntityID[asymID];
charge = pdb2cifCharge(charge); charge = pdb2cifCharge(charge);
...@@ -5178,14 +5181,14 @@ void PDBFileParser::ParseCoordinate(int modelNr) ...@@ -5178,14 +5181,14 @@ void PDBFileParser::ParseCoordinate(int modelNr)
getCategory("atom_site")->emplace({ getCategory("atom_site")->emplace({
{ "group_PDB" , groupPDB }, { "group_PDB" , groupPDB },
{ "id", mAtomId }, { "id", mAtomID },
{ "type_symbol", element }, { "type_symbol", element },
{ "label_atom_id", name }, { "label_atom_id", name },
{ "label_alt_id", altLoc != ' ' ? string { altLoc } : "." }, { "label_alt_id", altLoc != ' ' ? string { altLoc } : "." },
{ "label_comp_id", resName }, { "label_comp_id", resName },
{ "label_asym_id", asymId }, { "label_asym_id", asymID },
{ "label_entity_id", entityId }, { "label_entity_id", entityID },
{ "label_seq_id", (isResseq and seqId > 0) ? to_string(seqId) : "." }, { "label_seq_id", (isResseq and seqID > 0) ? to_string(seqID) : "." },
{ "pdbx_PDB_ins_code", iCode == ' ' ? "" : string { iCode } }, { "pdbx_PDB_ins_code", iCode == ' ' ? "" : string { iCode } },
{ "Cartn_x", x }, { "Cartn_x", x },
{ "Cartn_y", y }, { "Cartn_y", y },
...@@ -5220,13 +5223,13 @@ void PDBFileParser::ParseCoordinate(int modelNr) ...@@ -5220,13 +5223,13 @@ void PDBFileParser::ParseCoordinate(int modelNr)
auto f = [](float f) -> string { return (boost::format("%6.4f") % f).str(); }; auto f = [](float f) -> string { return (boost::format("%6.4f") % f).str(); };
getCategory("atom_site_anisotrop")->emplace({ getCategory("atom_site_anisotrop")->emplace({
{ "id", mAtomId }, { "id", mAtomID },
{ "type_symbol", element }, { "type_symbol", element },
{ "pdbx_label_atom_id", name }, { "pdbx_label_atom_id", name },
{ "pdbx_label_alt_id", altLoc != ' ' ? string { altLoc } : "." }, { "pdbx_label_alt_id", altLoc != ' ' ? string { altLoc } : "." },
{ "pdbx_label_comp_id", resName }, { "pdbx_label_comp_id", resName },
{ "pdbx_label_asym_id", asymId }, { "pdbx_label_asym_id", asymID },
{ "pdbx_label_seq_id", (isResseq and seqId > 0) ? to_string(seqId) : "." }, { "pdbx_label_seq_id", (isResseq and seqID > 0) ? to_string(seqID) : "." },
{ "U[1][1]", f(u11 / 10000.f) }, { "U[1][1]", f(u11 / 10000.f) },
{ "U[2][2]", f(u22 / 10000.f) }, { "U[2][2]", f(u22 / 10000.f) },
{ "U[3][3]", f(u33 / 10000.f) }, { "U[3][3]", f(u33 / 10000.f) },
...@@ -5339,7 +5342,7 @@ void PDBFileParser::Parse(istream& is, cif::File& result) ...@@ -5339,7 +5342,7 @@ void PDBFileParser::Parse(istream& is, cif::File& result)
if (exptl->empty()) if (exptl->empty())
{ {
exptl->emplace({ exptl->emplace({
{ "entry_id", mStructureId }, { "entry_id", mStructureID },
{ "method", mExpMethod }, { "method", mExpMethod },
{ "crystals_number", mRemark200["NUMBER OF CRYSTALS USED"] } { "crystals_number", mRemark200["NUMBER OF CRYSTALS USED"] }
}); });
...@@ -5359,17 +5362,17 @@ void PDBFileParser::Parse(istream& is, cif::File& result) ...@@ -5359,17 +5362,17 @@ void PDBFileParser::Parse(istream& is, cif::File& result)
// //
// try // try
// { // {
// string asymId; // string asymID;
// int resNum; // int resNum;
// //
// cif::tie(asymId, resNum) = r.get("beg_auth_asym_id", "beg_auth_seq_id"); // cif::tie(asymID, resNum) = r.get("beg_auth_asym_id", "beg_auth_seq_id");
// //
// r["beg_label_asym_id"] = asymId; // r["beg_label_asym_id"] = asymID;
// r["beg_label_seq_id"] = resNum; // r["beg_label_seq_id"] = resNum;
// //
// cif::tie(asymId, resNum) = r.get("end_auth_asym_id", "end_auth_seq_id"); // cif::tie(asymID, resNum) = r.get("end_auth_asym_id", "end_auth_seq_id");
// //
// r["end_label_asym_id"] = asymId; // r["end_label_asym_id"] = asymID;
// r["end_label_seq_id"] = resNum; // r["end_label_seq_id"] = resNum;
// } // }
// catch (const exception& ex) // catch (const exception& ex)
...@@ -5380,7 +5383,10 @@ void PDBFileParser::Parse(istream& is, cif::File& result) ...@@ -5380,7 +5383,10 @@ void PDBFileParser::Parse(istream& is, cif::File& result)
} }
catch (const exception& ex) catch (const exception& ex)
{ {
cerr << "Error parsing PDB at line " << mRec->mLineNr << endl; cerr << "Error parsing PDB";
if (mRec != nullptr)
cerr << " at line " << mRec->mLineNr;
cerr << endl;
throw; throw;
} }
} }
...@@ -5432,7 +5438,7 @@ int PDBFileParser::PDBChain::AlignResToSeqRes() ...@@ -5432,7 +5438,7 @@ int PDBFileParser::PDBChain::AlignResToSeqRes()
// score for alignment // score for alignment
float M; float M;
if (a.mMonId == b.mMonId) if (a.mMonID == b.mMonID)
M = kMatchReward; M = kMatchReward;
else else
M = kMismatchCost; M = kMismatchCost;
...@@ -5514,17 +5520,17 @@ int PDBFileParser::PDBChain::AlignResToSeqRes() ...@@ -5514,17 +5520,17 @@ int PDBFileParser::PDBChain::AlignResToSeqRes()
switch (tb(x, y)) switch (tb(x, y))
{ {
case -1: case -1:
alignment.push_back(make_pair("...", ry[y].mMonId)); alignment.push_back(make_pair("...", ry[y].mMonID));
--y; --y;
break; break;
case 1: case 1:
alignment.push_back(make_pair(rx[x].mMonId, "...")); alignment.push_back(make_pair(rx[x].mMonID, "..."));
--x; --x;
break; break;
case 0: case 0:
alignment.push_back(make_pair(rx[x].mMonId, ry[y].mMonId)); alignment.push_back(make_pair(rx[x].mMonID, ry[y].mMonID));
--x; --x;
--y; --y;
break; break;
...@@ -5533,13 +5539,13 @@ int PDBFileParser::PDBChain::AlignResToSeqRes() ...@@ -5533,13 +5539,13 @@ int PDBFileParser::PDBChain::AlignResToSeqRes()
while (x >= 0) while (x >= 0)
{ {
alignment.push_back(make_pair(rx[x].mMonId, "...")); alignment.push_back(make_pair(rx[x].mMonID, "..."));
--x; --x;
} }
while (y >= 0) while (y >= 0)
{ {
alignment.push_back(make_pair("...", ry[y].mMonId)); alignment.push_back(make_pair("...", ry[y].mMonID));
--y; --y;
} }
...@@ -5562,11 +5568,11 @@ int PDBFileParser::PDBChain::AlignResToSeqRes() ...@@ -5562,11 +5568,11 @@ int PDBFileParser::PDBChain::AlignResToSeqRes()
case -1: case -1:
// if (cif::VERBOSE) // if (cif::VERBOSE)
// cerr << "A residue found in the ATOM records " // cerr << "A residue found in the ATOM records "
// << "(" << ry[y].mMonId << " @ " << mDbref.chainID << ":" << ry[y].mSeqNum // << "(" << ry[y].mMonID << " @ " << mDbref.chainID << ":" << ry[y].mSeqNum
// << ((ry[y].mIcode == ' ' or ry[y].mIcode == 0) ? "" : string{ ry[y].mIcode }) << ")" // << ((ry[y].mIcode == ' ' or ry[y].mIcode == 0) ? "" : string{ ry[y].mIcode }) << ")"
// << " was not found in the SEQRES records" << endl; // << " was not found in the SEQRES records" << endl;
throw runtime_error("A residue found in the ATOM records (" + ry[y].mMonId + throw runtime_error("A residue found in the ATOM records (" + ry[y].mMonID +
" @ " + string{mDbref.chainID} + ":" + to_string(ry[y].mSeqNum) + " @ " + string{mDbref.chainID} + ":" + to_string(ry[y].mSeqNum) +
((ry[y].mIcode == ' ' or ry[y].mIcode == 0) ? "" : string{ ry[y].mIcode })+ ((ry[y].mIcode == ' ' or ry[y].mIcode == 0) ? "" : string{ ry[y].mIcode })+
") was not found in the SEQRES records"); ") was not found in the SEQRES records");
...@@ -5575,16 +5581,16 @@ int PDBFileParser::PDBChain::AlignResToSeqRes() ...@@ -5575,16 +5581,16 @@ int PDBFileParser::PDBChain::AlignResToSeqRes()
case 1: case 1:
if (cif::VERBOSE > 3) if (cif::VERBOSE > 3)
cerr << "Missing residue in ATOM records: " << rx[x].mMonId << " at " << rx[x].mSeqNum << endl; cerr << "Missing residue in ATOM records: " << rx[x].mMonID << " at " << rx[x].mSeqNum << endl;
--x; --x;
break; break;
case 0: case 0:
if (cif::VERBOSE > 3 and rx[x].mMonId != ry[y].mMonId) if (cif::VERBOSE > 3 and rx[x].mMonID != ry[y].mMonID)
cerr << "Warning, unaligned residues at " << x << "/" << y << "(" << rx[x].mMonId << '/' << ry[y].mMonId << ')' << endl; cerr << "Warning, unaligned residues at " << x << "/" << y << "(" << rx[x].mMonID << '/' << ry[y].mMonID << ')' << endl;
else if (cif::VERBOSE > 4) else if (cif::VERBOSE > 4)
cerr << rx[x].mMonId << " -> " << ry[y].mMonId << " (" << ry[y].mSeqNum << ')' << endl; cerr << rx[x].mMonID << " -> " << ry[y].mMonID << " (" << ry[y].mSeqNum << ')' << endl;
rx[x].mSeqNum = ry[y].mSeqNum; rx[x].mSeqNum = ry[y].mSeqNum;
rx[x].mIcode = ry[y].mIcode; rx[x].mIcode = ry[y].mIcode;
...@@ -5632,7 +5638,7 @@ bool PDBFileParser::PDBChain::SameSequence(const PDBChain& rhs) const ...@@ -5632,7 +5638,7 @@ bool PDBFileParser::PDBChain::SameSequence(const PDBChain& rhs) const
bool result = mSeqres.size() == rhs.mSeqres.size(); bool result = mSeqres.size() == rhs.mSeqres.size();
for (size_t i = 0; result and i < mSeqres.size(); ++i) for (size_t i = 0; result and i < mSeqres.size(); ++i)
result = mSeqres[i].mMonId == rhs.mSeqres[i].mMonId; result = mSeqres[i].mMonID == rhs.mSeqres[i].mMonID;
return result; return result;
} }
......
src/PDB2CifRemark3.cpp
...@@ -1166,14 +1166,14 @@ void Remark3Parser::storeCapture(const char* category, initializer_list<const ch ...@@ -1166,14 +1166,14 @@ void Remark3Parser::storeCapture(const char* category, initializer_list<const ch
} }
else if (iequals(category, "pdbx_refine_tls_group")) else if (iequals(category, "pdbx_refine_tls_group"))
{ {
string tlsGroupId; string tlsGroupID;
if (not mDb["pdbx_refine_tls"].empty()) if (not mDb["pdbx_refine_tls"].empty())
tlsGroupId = mDb["pdbx_refine_tls"].back()["id"].as<string>(); tlsGroupID = mDb["pdbx_refine_tls"].back()["id"].as<string>();
cat.emplace({ cat.emplace({
{ "pdbx_refine_id", mExpMethod }, { "pdbx_refine_id", mExpMethod },
{ "id", tlsGroupId }, { "id", tlsGroupID },
{ "refine_tls_id", tlsGroupId } { "refine_tls_id", tlsGroupID }
}); });
} }
else if (iequals(category, "pdbx_refine_tls")) else if (iequals(category, "pdbx_refine_tls"))
......
src/Secondary.cpp
...@@ -8,9 +8,8 @@ ...@@ -8,9 +8,8 @@
#include "cif++/Config.h" #include "cif++/Config.h"
#include <numeric> #include <numeric>
#include <chrono>
#include <iomanip> #include <iomanip>
#include <future> #include <thread>
#include <boost/algorithm/string.hpp> #include <boost/algorithm/string.hpp>
...@@ -164,22 +163,22 @@ struct Res ...@@ -164,22 +163,22 @@ struct Res
for (auto& a: mM.atoms()) for (auto& a: mM.atoms())
{ {
if (a.labelAtomId() == "CA") if (a.labelAtomID() == "CA")
{ {
mCAlpha = a.location(); mCAlpha = a.location();
ExtendBox(mCAlpha, kRadiusCA + 2 * kRadiusWater); ExtendBox(mCAlpha, kRadiusCA + 2 * kRadiusWater);
} }
else if (a.labelAtomId() == "C") else if (a.labelAtomID() == "C")
{ {
mC = a.location(); mC = a.location();
ExtendBox(mC, kRadiusC + 2 * kRadiusWater); ExtendBox(mC, kRadiusC + 2 * kRadiusWater);
} }
else if (a.labelAtomId() == "N") else if (a.labelAtomID() == "N")
{ {
mN = a.location(); mN = a.location();
ExtendBox(mN, kRadiusN + 2 * kRadiusWater); ExtendBox(mN, kRadiusN + 2 * kRadiusWater);
} }
else if (a.labelAtomId() == "O") else if (a.labelAtomID() == "O")
{ {
mO = a.location(); mO = a.location();
ExtendBox(mO, kRadiusO + 2 * kRadiusWater); ExtendBox(mO, kRadiusO + 2 * kRadiusWater);
...@@ -489,30 +488,6 @@ void CalculateAccessibilities(std::vector<Res>& inResidues, DSSP_Statistics& sta ...@@ -489,30 +488,6 @@ void CalculateAccessibilities(std::vector<Res>& inResidues, DSSP_Statistics& sta
for (auto& residue: inResidues) for (auto& residue: inResidues)
stats.accessibleSurface += residue.CalculateSurface(inResidues); stats.accessibleSurface += residue.CalculateSurface(inResidues);
// uint32_t nr_of_threads = boost::thread::hardware_concurrency();
// if (nr_of_threads <= 1)
// {
// foreach (MResidue* residue, inResidues)
// residue->CalculateSurface(inResidues);
// }
// else
// {
// MResidueQueue queue;
// boost::thread_group t;
// for (uint32 ti = 0; ti < nr_of_threads; ++ti)
// t.create_thread(boost::bind(&MProtein::CalculateAccessibility, this,
// boost::ref(queue), boost::ref(inResidues)));
// foreach (MResidue* residue, inResidues)
// queue.put(residue);
// queue.put(nullptr);
// t.join_all();
// }
} }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
...@@ -1003,51 +978,6 @@ void CalculateAlphaHelices(std::vector<Res>& inResidues, DSSP_Statistics& stats, ...@@ -1003,51 +978,6 @@ void CalculateAlphaHelices(std::vector<Res>& inResidues, DSSP_Statistics& stats,
} }
} }
// // --------------------------------------------------------------------
// void CalculateSecondaryStructure(Structure& s)
// {
// auto& polymers = s.polymers();
// size_t nRes = accumulate(polymers.begin(), polymers.end(),
// 0.0, [](double s, auto& p) { return s + p.size(); });
// vector<Res> residues;
// residues.reserve(nRes);
// for (auto& p: polymers)
// {
// for (auto& m: p)
// residues.emplace_back(m);
// }
// auto fa = std::async(std::launch::async, std::bind(&CalculateAccessibilities, std::ref(residues)));
// for (size_t i = 0; i + 1 < residues.size(); ++i)
// {
// residues[i].mNext = &residues[i + 1];
// residues[i + 1].mPrev = &residues[i];
// residues[i + 1].assignHydrogen();
// }
// CalculateHBondEnergies(residues);
// CalculateBetaSheets(residues);
// CalculateAlphaHelices(residues);
// if (cif::VERBOSE)
// {
// for (auto& r: residues)
// {
// auto& m = r.mM;
// cout << m.asymID() << ':' << m.seqID() << '/' << m.compoundID() << '\t'
// << char(r.mSecondaryStructure)
// << endl;
// }
// }
// }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
struct DSSPImpl struct DSSPImpl
...@@ -1069,37 +999,6 @@ struct DSSPImpl ...@@ -1069,37 +999,6 @@ struct DSSPImpl
// -------------------------------------------------------------------- // --------------------------------------------------------------------
std::ostream& operator<<(std::ostream& os, const std::chrono::duration<double>& t)
{
uint64_t s = static_cast<uint64_t>(std::trunc(t.count()));
if (s > 24 * 60 * 60)
{
uint32_t days = s / (24 * 60 * 60);
os << days << "d ";
s %= 24 * 60 * 60;
}
if (s > 60 * 60)
{
uint32_t hours = s / (60 * 60);
os << hours << "h ";
s %= 60 * 60;
}
if (s > 60)
{
uint32_t minutes = s / 60;
os << minutes << "m ";
s %= 60;
}
double ss = s + 1e-6 * (t.count() - s);
os << std::fixed << std::setprecision(1) << ss << 's';
return os;
}
DSSPImpl::DSSPImpl(const Structure& s) DSSPImpl::DSSPImpl(const Structure& s)
: mStructure(s) : mStructure(s)
, mPolymers(mStructure.polymers()) , mPolymers(mStructure.polymers())
...@@ -1144,7 +1043,7 @@ DSSPImpl::DSSPImpl(const Structure& s) ...@@ -1144,7 +1043,7 @@ DSSPImpl::DSSPImpl(const Structure& s)
mResidues[i + 1].assignHydrogen(); mResidues[i + 1].assignHydrogen();
} }
auto a = std::async(std::launch::async, &CalculateAccessibilities, std::ref(mResidues), std::ref(mStats)); std::thread ta(std::bind(&CalculateAccessibilities, std::ref(mResidues), std::ref(mStats)));
auto& db = s.getFile().data(); auto& db = s.getFile().data();
for (auto r: db["struct_conn"].find(cif::Key("conn_type_id") == "disulf")) for (auto r: db["struct_conn"].find(cif::Key("conn_type_id") == "disulf"))
...@@ -1207,9 +1106,8 @@ DSSPImpl::DSSPImpl(const Structure& s) ...@@ -1207,9 +1106,8 @@ DSSPImpl::DSSPImpl(const Structure& s)
mStats.nrOfSSBridges = mSSBonds.size(); mStats.nrOfSSBridges = mSSBonds.size();
mStats.nrOfIntraChainSSBridges = 0; mStats.nrOfIntraChainSSBridges = 0;
for (auto& ss: mSSBonds) for (const auto& [a, b]: mSSBonds)
{ {
const auto& [a, b] = ss;
if (a->mM.asymID() != b->mM.asymID()) if (a->mM.asymID() != b->mM.asymID())
++mStats.nrOfIntraChainSSBridges; ++mStats.nrOfIntraChainSSBridges;
} }
...@@ -1231,7 +1129,7 @@ DSSPImpl::DSSPImpl(const Structure& s) ...@@ -1231,7 +1129,7 @@ DSSPImpl::DSSPImpl(const Structure& s)
} }
} }
a.get(); ta.join();
} }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
......
src/Statistics.cpp
...@@ -286,10 +286,10 @@ struct AtomData ...@@ -286,10 +286,10 @@ struct AtomData
{ {
AtomData(Atom atom, float radius) AtomData(Atom atom, float radius)
: atom(atom) : atom(atom)
// , asymID(atom.authAsymId()) // , asymID(atom.authAsymID())
// , seqID(atom.property<string>("auth_seq_id")) // , seqID(atom.property<string>("auth_seq_id"))
, asymID(atom.labelAsymId()) , asymID(atom.labelAsymID())
, seqID(atom.labelSeqId()) , seqID(atom.labelSeqID())
, radius(radius) {} , radius(radius) {}
Atom atom; Atom atom;
...@@ -584,8 +584,8 @@ vector<ResidueStatistics> StatsCollector::collect() const ...@@ -584,8 +584,8 @@ vector<ResidueStatistics> StatsCollector::collect() const
if (atom.isWater()) if (atom.isWater())
continue; continue;
auto k = make_tuple(atom.labelAsymId(), atom.labelSeqId(), atom.labelCompId(), atom.authSeqId()); auto k = make_tuple(atom.labelAsymID(), atom.labelSeqID(), atom.labelCompID(), atom.authSeqID());
// auto k = make_tuple(atom.authAsymId(), atom.property<string>("auth_seq_id"), atom.authCompId()); // auto k = make_tuple(atom.authAsymID(), atom.property<string>("auth_seq_id"), atom.authCompID());
if (residues.empty() or residues.back() != k) if (residues.empty() or residues.back() != k)
{ {
...@@ -610,19 +610,19 @@ vector<ResidueStatistics> StatsCollector::collect(const string& asymID, int resF ...@@ -610,19 +610,19 @@ vector<ResidueStatistics> StatsCollector::collect(const string& asymID, int resF
if (authNameSpace) if (authNameSpace)
{ {
int authSeqID = stoi(atom.authSeqId()); int authSeqID = stoi(atom.authSeqID());
if (atom.authAsymId() != asymID or authSeqID < resFirst or authSeqID > resLast) if (atom.authAsymID() != asymID or authSeqID < resFirst or authSeqID > resLast)
continue; continue;
} }
else else
{ {
if (atom.labelAsymId() != asymID or atom.labelSeqId() < resFirst or atom.labelSeqId() > resLast) if (atom.labelAsymID() != asymID or atom.labelSeqID() < resFirst or atom.labelSeqID() > resLast)
continue; continue;
} }
auto k = make_tuple(atom.labelAsymId(), atom.labelSeqId(), atom.labelCompId(), atom.authSeqId()); auto k = make_tuple(atom.labelAsymID(), atom.labelSeqID(), atom.labelCompID(), atom.authSeqID());
// auto k = make_tuple(atom.authAsymId(), atom.property<string>("auth_seq_id"), atom.authCompId()); // auto k = make_tuple(atom.authAsymID(), atom.property<string>("auth_seq_id"), atom.authCompID());
if (residues.empty() or residues.back() != k) if (residues.empty() or residues.back() != k)
{ {
...@@ -710,7 +710,7 @@ vector<ResidueStatistics> StatsCollector::collect(const vector<tuple<string,int, ...@@ -710,7 +710,7 @@ vector<ResidueStatistics> StatsCollector::collect(const vector<tuple<string,int,
++n; ++n;
auto ci = find_if(atomData.begin(), atomData.end(), auto ci = find_if(atomData.begin(), atomData.end(),
[=](auto& d) { return d.asymID == asymID and d.seqID == seqID and d.atom.labelAtomId() == compAtom.id; }); [=](auto& d) { return d.asymID == asymID and d.seqID == seqID and d.atom.labelAtomID() == compAtom.id; });
if (ci == atomData.end()) if (ci == atomData.end())
{ {
...@@ -749,7 +749,7 @@ vector<ResidueStatistics> StatsCollector::collect(const vector<tuple<string,int, ...@@ -749,7 +749,7 @@ vector<ResidueStatistics> StatsCollector::collect(const vector<tuple<string,int,
continue; continue;
result.emplace_back(ResidueStatistics{d.asymID, d.seqID, "HOH", result.emplace_back(ResidueStatistics{d.asymID, d.seqID, "HOH",
atom.authSeqId(), atom.authSeqID(),
(d.sums.rfSums[0] / d.sums.rfSums[1]), // rsr (d.sums.rfSums[0] / d.sums.rfSums[1]), // rsr
d.sums.srg(), // srsr d.sums.srg(), // srsr
d.sums.cc(), // rsccs d.sums.cc(), // rsccs
...@@ -813,7 +813,7 @@ ResidueStatistics StatsCollector::collect(const vector<Atom>& atoms) const ...@@ -813,7 +813,7 @@ ResidueStatistics StatsCollector::collect(const vector<Atom>& atoms) const
++n; ++n;
auto ci = find_if(atomData.begin(), atomData.end(), auto ci = find_if(atomData.begin(), atomData.end(),
[=](auto& d) { return d.asymID == atom.labelAsymId() and d.seqID == atom.labelSeqId() and d.atom.labelAtomId() == atom.labelAtomId(); }); [=](auto& d) { return d.asymID == atom.labelAsymID() and d.seqID == atom.labelSeqID() and d.atom.labelAtomID() == atom.labelAtomID(); });
if (ci == atomData.end()) if (ci == atomData.end())
continue; continue;
......
src/Structure.cpp
...@@ -159,7 +159,7 @@ void FileImpl::save(const std::string& p) ...@@ -159,7 +159,7 @@ void FileImpl::save(const std::string& p)
struct AtomImpl struct AtomImpl
{ {
AtomImpl(const AtomImpl& i) AtomImpl(const AtomImpl& i)
: mFile(i.mFile), mId(i.mId), mType(i.mType) : mFile(i.mFile), mID(i.mID), mType(i.mType)
, mAtomID(i.mAtomID), mCompID(i.mCompID), mAsymID(i.mAsymID) , mAtomID(i.mAtomID), mCompID(i.mCompID), mAsymID(i.mAsymID)
, mSeqID(i.mSeqID), mAltID(i.mAltID), mLocation(i.mLocation) , mSeqID(i.mSeqID), mAltID(i.mAltID), mLocation(i.mLocation)
, mRefcount(1), mRow(i.mRow), mCompound(i.mCompound) , mRefcount(1), mRow(i.mRow), mCompound(i.mCompound)
...@@ -170,24 +170,24 @@ struct AtomImpl ...@@ -170,24 +170,24 @@ struct AtomImpl
} }
AtomImpl(const File& f, const string& id) AtomImpl(const File& f, const string& id)
: mFile(f), mId(id), mRefcount(1), mCompound(nullptr) : mFile(f), mID(id), mRefcount(1), mCompound(nullptr)
{ {
auto& db = *mFile.impl().mDb; auto& db = *mFile.impl().mDb;
auto& cat = db["atom_site"]; auto& cat = db["atom_site"];
mRow = cat[cif::Key("id") == mId]; mRow = cat[cif::Key("id") == mID];
prefetch(); prefetch();
} }
AtomImpl(const File& f, const string& id, cif::Row row) AtomImpl(const File& f, const string& id, cif::Row row)
: mFile(f), mId(id), mRefcount(1), mRow(row), mCompound(nullptr) : mFile(f), mID(id), mRefcount(1), mRow(row), mCompound(nullptr)
{ {
prefetch(); prefetch();
} }
AtomImpl(const AtomImpl& impl, const Point& d, const clipper::RTop_orth& rt) AtomImpl(const AtomImpl& impl, const Point& d, const clipper::RTop_orth& rt)
: mFile(impl.mFile), mId(impl.mId), mType(impl.mType), mAtomID(impl.mAtomID) : mFile(impl.mFile), mID(impl.mID), mType(impl.mType), mAtomID(impl.mAtomID)
, mCompID(impl.mCompID), mAsymID(impl.mAsymID), mSeqID(impl.mSeqID) , mCompID(impl.mCompID), mAsymID(impl.mAsymID), mSeqID(impl.mSeqID)
, mAltID(impl.mAltID), mLocation(impl.mLocation), mRefcount(1) , mAltID(impl.mAltID), mLocation(impl.mLocation), mRefcount(1)
, mRow(impl.mRow), mCompound(impl.mCompound), mRadius(impl.mRadius) , mRow(impl.mRow), mCompound(impl.mCompound), mRadius(impl.mRadius)
...@@ -214,10 +214,10 @@ struct AtomImpl ...@@ -214,10 +214,10 @@ struct AtomImpl
mLocation = Point(x, y, z); mLocation = Point(x, y, z);
string compId; string compID;
cif::tie(compId) = mRow.get("label_comp_id"); cif::tie(compID) = mRow.get("label_comp_id");
mCompound = Compound::create(compId); mCompound = Compound::create(compID);
} }
clipper::Atom toClipper() const clipper::Atom toClipper() const
...@@ -252,7 +252,7 @@ struct AtomImpl ...@@ -252,7 +252,7 @@ struct AtomImpl
auto& db = *mFile.impl().mDb; auto& db = *mFile.impl().mDb;
auto& cat = db["atom_site_anisotrop"]; auto& cat = db["atom_site_anisotrop"];
auto r = cat[cif::Key("id") == mId]; auto r = cat[cif::Key("id") == mID];
if (r.empty()) if (r.empty())
result.set_u_aniso_orth(clipper::U_aniso_orth(nan("0"), 0, 0, 0, 0, 0)); result.set_u_aniso_orth(clipper::U_aniso_orth(nan("0"), 0, 0, 0, 0, 0));
else else
...@@ -282,7 +282,7 @@ struct AtomImpl ...@@ -282,7 +282,7 @@ struct AtomImpl
{ {
auto& db = *mFile.impl().mDb; auto& db = *mFile.impl().mDb;
auto& cat = db["atom_site_anisotrop"]; auto& cat = db["atom_site_anisotrop"];
auto r = cat[cif::Key("id") == mId]; auto r = cat[cif::Key("id") == mID];
bool result = false; bool result = false;
if (not r.empty()) if (not r.empty())
...@@ -321,13 +321,13 @@ struct AtomImpl ...@@ -321,13 +321,13 @@ struct AtomImpl
{ {
if (mCompound == nullptr) if (mCompound == nullptr)
{ {
string compId; string compID;
cif::tie(compId) = mRow.get("label_comp_id"); cif::tie(compID) = mRow.get("label_comp_id");
mCompound = Compound::create(compId); mCompound = Compound::create(compID);
if (cif::VERBOSE and mCompound == nullptr) if (cif::VERBOSE and mCompound == nullptr)
cerr << "Compound not found: '" << compId << '\'' << endl; cerr << "Compound not found: '" << compID << '\'' << endl;
} }
if (mCompound == nullptr) if (mCompound == nullptr)
...@@ -379,7 +379,7 @@ struct AtomImpl ...@@ -379,7 +379,7 @@ struct AtomImpl
} }
const File& mFile; const File& mFile;
string mId; string mID;
AtomType mType; AtomType mType;
string mAtomID; string mAtomID;
...@@ -466,7 +466,7 @@ float Atom::property<float>(const string& name) const ...@@ -466,7 +466,7 @@ float Atom::property<float>(const string& name) const
const string& Atom::id() const const string& Atom::id() const
{ {
return mImpl->mId; return mImpl->mID;
} }
AtomType Atom::type() const AtomType Atom::type() const
...@@ -484,7 +484,7 @@ string Atom::energyType() const ...@@ -484,7 +484,7 @@ string Atom::energyType() const
string result; string result;
if (mImpl and mImpl->mCompound) if (mImpl and mImpl->mCompound)
result = mImpl->mCompound->getAtomById(mImpl->mAtomID).typeEnergy; result = mImpl->mCompound->getAtomByID(mImpl->mAtomID).typeEnergy;
return result; return result;
} }
...@@ -513,42 +513,42 @@ float Atom::occupancy() const ...@@ -513,42 +513,42 @@ float Atom::occupancy() const
return property<float>("occupancy"); return property<float>("occupancy");
} }
string Atom::labelAtomId() const string Atom::labelAtomID() const
{ {
return mImpl->mAtomID; return mImpl->mAtomID;
} }
string Atom::labelCompId() const string Atom::labelCompID() const
{ {
return mImpl->mCompID; return mImpl->mCompID;
} }
string Atom::labelAsymId() const string Atom::labelAsymID() const
{ {
return mImpl->mAsymID; return mImpl->mAsymID;
} }
string Atom::labelAltId() const string Atom::labelAltID() const
{ {
return mImpl->mAltID; return mImpl->mAltID;
} }
int Atom::labelSeqId() const int Atom::labelSeqID() const
{ {
return mImpl->mSeqID; return mImpl->mSeqID;
} }
string Atom::authAsymId() const string Atom::authAsymID() const
{ {
return property<string>("auth_asym_id"); return property<string>("auth_asym_id");
} }
string Atom::authAtomId() const string Atom::authAtomID() const
{ {
return property<string>("auth_atom_id"); return property<string>("auth_atom_id");
} }
string Atom::pdbxAuthAltId() const string Atom::pdbxAuthAltID() const
{ {
return property<string>("pdbx_auth_alt_id"); return property<string>("pdbx_auth_alt_id");
} }
...@@ -558,12 +558,12 @@ string Atom::pdbxAuthInsCode() const ...@@ -558,12 +558,12 @@ string Atom::pdbxAuthInsCode() const
return property<string>("pdbx_PDB_ins_code"); return property<string>("pdbx_PDB_ins_code");
} }
string Atom::authCompId() const string Atom::authCompID() const
{ {
return property<string>("auth_comp_id"); return property<string>("auth_comp_id");
} }
string Atom::authSeqId() const string Atom::authSeqID() const
{ {
return property<string>("auth_seq_id"); return property<string>("auth_seq_id");
} }
...@@ -625,7 +625,7 @@ bool Atom::isWater() const ...@@ -625,7 +625,7 @@ bool Atom::isWater() const
bool Atom::operator==(const Atom& rhs) const bool Atom::operator==(const Atom& rhs) const
{ {
return mImpl == rhs.mImpl or return mImpl == rhs.mImpl or
(&mImpl->mFile == &rhs.mImpl->mFile and mImpl->mId == rhs.mImpl->mId); (&mImpl->mFile == &rhs.mImpl->mFile and mImpl->mID == rhs.mImpl->mID);
} }
clipper::Atom Atom::toClipper() const clipper::Atom Atom::toClipper() const
...@@ -655,7 +655,7 @@ int Atom::compare(const Atom& b) const ...@@ -655,7 +655,7 @@ int Atom::compare(const Atom& b) const
void Atom::setID(int id) void Atom::setID(int id)
{ {
mImpl->mId = to_string(id); mImpl->mID = to_string(id);
} }
// -------------------------------------------------------------------- // --------------------------------------------------------------------
...@@ -670,11 +670,11 @@ Residue::Residue(const Structure& structure, const string& compoundID, ...@@ -670,11 +670,11 @@ Residue::Residue(const Structure& structure, const string& compoundID,
for (auto& a: mStructure->atoms()) for (auto& a: mStructure->atoms())
{ {
if (a.labelAsymId() != mAsymID or if (a.labelAsymID() != mAsymID or
a.labelCompId() != mCompoundID) a.labelCompID() != mCompoundID)
continue; continue;
if (not mAuthSeqID.empty() and a.authSeqId() != mAuthSeqID) // water! if (not mAuthSeqID.empty() and a.authSeqID() != mAuthSeqID) // water!
continue; continue;
mAtoms.push_back(a); mAtoms.push_back(a);
...@@ -692,11 +692,11 @@ Residue::Residue(const Structure& structure, const string& compoundID, ...@@ -692,11 +692,11 @@ Residue::Residue(const Structure& structure, const string& compoundID,
for (auto& a: mStructure->atoms()) for (auto& a: mStructure->atoms())
{ {
if (mSeqID > 0 and a.labelSeqId() != mSeqID) if (mSeqID > 0 and a.labelSeqID() != mSeqID)
continue; continue;
if (a.labelAsymId() != mAsymID or if (a.labelAsymID() != mAsymID or
a.labelCompId() != mCompoundID) a.labelCompID() != mCompoundID)
continue; continue;
mAtoms.push_back(a); mAtoms.push_back(a);
...@@ -750,6 +750,24 @@ string Residue::authInsCode() const ...@@ -750,6 +750,24 @@ string Residue::authInsCode() const
return result; return result;
} }
string Residue::authAsymID() const
{
assert(mStructure);
string result;
try
{
tie(result, ignore, ignore) = mStructure->MapLabelToAuth(mAsymID, mSeqID);
}
catch (...)
{
result = mAsymID;
}
return result;
}
string Residue::authSeqID() const string Residue::authSeqID() const
{ {
assert(mStructure); assert(mStructure);
...@@ -789,7 +807,7 @@ Atom Residue::atomByID(const string& atomID) const ...@@ -789,7 +807,7 @@ Atom Residue::atomByID(const string& atomID) const
{ {
for (auto& a: mAtoms) for (auto& a: mAtoms)
{ {
if (a.labelAtomId() == atomID) if (a.labelAtomID() == atomID)
return a; return a;
} }
...@@ -1014,7 +1032,7 @@ float Monomer::tco() const ...@@ -1014,7 +1032,7 @@ float Monomer::tco() const
catch (const exception& ex) catch (const exception& ex)
{ {
if (cif::VERBOSE) if (cif::VERBOSE)
cerr << "When trying to calculate kappa for " << asymID() << ':' << seqID() << ": " cerr << "When trying to calculate tco for " << asymID() << ':' << seqID() << ": "
<< ex.what() << endl; << ex.what() << endl;
} }
...@@ -1111,10 +1129,10 @@ bool Monomer::isComplete() const ...@@ -1111,10 +1129,10 @@ bool Monomer::isComplete() const
int seen = 0; int seen = 0;
for (auto& a: mAtoms) for (auto& a: mAtoms)
{ {
if (a.labelAtomId() == "CA") seen |= 1; if (a.labelAtomID() == "CA") seen |= 1;
else if (a.labelAtomId() == "C") seen |= 2; else if (a.labelAtomID() == "C") seen |= 2;
else if (a.labelAtomId() == "N") seen |= 4; else if (a.labelAtomID() == "N") seen |= 4;
else if (a.labelAtomId() == "O") seen |= 8; else if (a.labelAtomID() == "O") seen |= 8;
} }
return seen == 15; return seen == 15;
} }
...@@ -1460,7 +1478,7 @@ cif::File& File::file() ...@@ -1460,7 +1478,7 @@ cif::File& File::file()
// -------------------------------------------------------------------- // --------------------------------------------------------------------
// Structure // Structure
Structure::Structure(File& f, uint32_t modelNr) Structure::Structure(File& f, uint32_t modelNr, StructureOpenOptions options)
: mFile(f), mModelNr(modelNr) : mFile(f), mModelNr(modelNr)
{ {
auto& db = *mFile.impl().mDb; auto& db = *mFile.impl().mDb;
...@@ -1468,10 +1486,18 @@ Structure::Structure(File& f, uint32_t modelNr) ...@@ -1468,10 +1486,18 @@ Structure::Structure(File& f, uint32_t modelNr)
for (auto& a: atomCat) for (auto& a: atomCat)
{ {
auto modelNr = a["pdbx_PDB_model_num"]; std::string id, typeSymbol;
std::optional<int> modelNr;
cif::tie(id, typeSymbol, modelNr) = a.get("id", "type_symbol", "pdbx_PDB_model_num");
if (modelNr and *modelNr != mModelNr)
continue;
if ((options bitand StructureOpenOptions::SkipHydrogen) and typeSymbol == "H")
continue;
if (modelNr.empty() or modelNr.as<uint32_t>() == mModelNr) mAtoms.emplace_back(new AtomImpl(f, id, a));
mAtoms.emplace_back(new AtomImpl(f, a["id"].as<string>(), a));
} }
loadData(); loadData();
...@@ -1553,28 +1579,28 @@ AtomView Structure::waters() const ...@@ -1553,28 +1579,28 @@ AtomView Structure::waters() const
// Get the entity id for water // Get the entity id for water
auto& entityCat = db["entity"]; auto& entityCat = db["entity"];
string waterEntityId; string waterEntityID;
for (auto& e: entityCat) for (auto& e: entityCat)
{ {
string id, type; string id, type;
cif::tie(id, type) = e.get("id", "type"); cif::tie(id, type) = e.get("id", "type");
if (ba::iequals(type, "water")) if (ba::iequals(type, "water"))
{ {
waterEntityId = id; waterEntityID = id;
break; break;
} }
} }
for (auto& a: mAtoms) for (auto& a: mAtoms)
{ {
if (a.property<string>("label_entity_id") == waterEntityId) if (a.property<string>("label_entity_id") == waterEntityID)
result.push_back(a); result.push_back(a);
} }
return result; return result;
} }
Atom Structure::getAtomById(string id) const Atom Structure::getAtomByID(string id) const
{ {
auto i = lower_bound(mAtomIndex.begin(), mAtomIndex.end(), auto i = lower_bound(mAtomIndex.begin(), mAtomIndex.end(),
id, [this](auto& a, auto& b) { return mAtoms[a].id() < b; }); id, [this](auto& a, auto& b) { return mAtoms[a].id() < b; });
...@@ -1588,15 +1614,15 @@ Atom Structure::getAtomById(string id) const ...@@ -1588,15 +1614,15 @@ Atom Structure::getAtomById(string id) const
return mAtoms[*i]; return mAtoms[*i];
} }
Atom Structure::getAtomByLabel(const string& atomId, const string& asymId, const string& compId, int seqId, const string& altId) Atom Structure::getAtomByLabel(const string& atomID, const string& asymID, const string& compID, int seqID, const string& altID)
{ {
for (auto& a: mAtoms) for (auto& a: mAtoms)
{ {
if (a.labelAtomId() == atomId and if (a.labelAtomID() == atomID and
a.labelAsymId() == asymId and a.labelAsymID() == asymID and
a.labelCompId() == compId and a.labelCompID() == compID and
a.labelSeqId() == seqId and a.labelSeqID() == seqID and
a.labelAltId() == altId) a.labelAltID() == altID)
{ {
return a; return a;
} }
...@@ -1617,7 +1643,7 @@ cif::Category& Structure::category(const char* name) const ...@@ -1617,7 +1643,7 @@ cif::Category& Structure::category(const char* name) const
} }
tuple<char,int,char> Structure::MapLabelToAuth( tuple<char,int,char> Structure::MapLabelToAuth(
const string& asymId, int seqId) const const string& asymID, int seqID) const
{ {
auto& db = *getFile().impl().mDb; auto& db = *getFile().impl().mDb;
...@@ -1625,8 +1651,8 @@ tuple<char,int,char> Structure::MapLabelToAuth( ...@@ -1625,8 +1651,8 @@ tuple<char,int,char> Structure::MapLabelToAuth(
bool found = false; bool found = false;
for (auto r: db["pdbx_poly_seq_scheme"].find( for (auto r: db["pdbx_poly_seq_scheme"].find(
cif::Key("asym_id") == asymId and cif::Key("asym_id") == asymID and
cif::Key("seq_id") == seqId)) cif::Key("seq_id") == seqID))
{ {
string auth_asym_id, pdb_ins_code; string auth_asym_id, pdb_ins_code;
int pdb_seq_num; int pdb_seq_num;
...@@ -1644,8 +1670,8 @@ tuple<char,int,char> Structure::MapLabelToAuth( ...@@ -1644,8 +1670,8 @@ tuple<char,int,char> Structure::MapLabelToAuth(
if (not found) if (not found)
{ {
for (auto r: db["pdbx_nonpoly_scheme"].find( for (auto r: db["pdbx_nonpoly_scheme"].find(
cif::Key("asym_id") == asymId and cif::Key("asym_id") == asymID and
cif::Key("seq_id") == seqId)) cif::Key("seq_id") == seqID))
{ {
string pdb_strand_id, pdb_ins_code; string pdb_strand_id, pdb_ins_code;
int pdb_seq_num; int pdb_seq_num;
...@@ -1665,19 +1691,19 @@ tuple<char,int,char> Structure::MapLabelToAuth( ...@@ -1665,19 +1691,19 @@ tuple<char,int,char> Structure::MapLabelToAuth(
} }
tuple<string,int,string,string> Structure::MapLabelToPDB( tuple<string,int,string,string> Structure::MapLabelToPDB(
const string& asymId, int seqId, const string& monId, const string& asymID, int seqID, const string& monID,
const string& authSeqID) const const string& authSeqID) const
{ {
auto& db = datablock(); auto& db = datablock();
tuple<string,int,string,string> result; tuple<string,int,string,string> result;
if (monId == "HOH") if (monID == "HOH")
{ {
for (auto r: db["pdbx_nonpoly_scheme"].find( for (auto r: db["pdbx_nonpoly_scheme"].find(
cif::Key("asym_id") == asymId and cif::Key("asym_id") == asymID and
cif::Key("pdb_seq_num") == authSeqID and cif::Key("pdb_seq_num") == authSeqID and
cif::Key("mon_id") == monId)) cif::Key("mon_id") == monID))
{ {
result = r.get("pdb_strand_id", "pdb_seq_num", "pdb_mon_id", "pdb_ins_code"); result = r.get("pdb_strand_id", "pdb_seq_num", "pdb_mon_id", "pdb_ins_code");
break; break;
...@@ -1686,17 +1712,17 @@ tuple<string,int,string,string> Structure::MapLabelToPDB( ...@@ -1686,17 +1712,17 @@ tuple<string,int,string,string> Structure::MapLabelToPDB(
else else
{ {
for (auto r: db["pdbx_poly_seq_scheme"].find( for (auto r: db["pdbx_poly_seq_scheme"].find(
cif::Key("asym_id") == asymId and cif::Key("asym_id") == asymID and
cif::Key("seq_id") == seqId and cif::Key("seq_id") == seqID and
cif::Key("mon_id") == monId)) cif::Key("mon_id") == monID))
{ {
result = r.get("pdb_strand_id", "pdb_seq_num", "pdb_mon_id", "pdb_ins_code"); result = r.get("pdb_strand_id", "pdb_seq_num", "pdb_mon_id", "pdb_ins_code");
break; break;
} }
for (auto r: db["pdbx_nonpoly_scheme"].find( for (auto r: db["pdbx_nonpoly_scheme"].find(
cif::Key("asym_id") == asymId and cif::Key("asym_id") == asymID and
cif::Key("mon_id") == monId)) cif::Key("mon_id") == monID))
{ {
result = r.get("pdb_strand_id", "pdb_seq_num", "pdb_mon_id", "pdb_ins_code"); result = r.get("pdb_strand_id", "pdb_seq_num", "pdb_mon_id", "pdb_ins_code");
break; break;
...@@ -1706,8 +1732,8 @@ tuple<string,int,string,string> Structure::MapLabelToPDB( ...@@ -1706,8 +1732,8 @@ tuple<string,int,string,string> Structure::MapLabelToPDB(
return result; return result;
} }
tuple<string,int,string> Structure::MapPDBToLabel(const string& asymId, int seqId, tuple<string,int,string> Structure::MapPDBToLabel(const string& asymID, int seqID,
const string& compId, const string& iCode) const const string& compID, const string& iCode) const
{ {
auto& db = datablock(); auto& db = datablock();
...@@ -1716,9 +1742,9 @@ tuple<string,int,string> Structure::MapPDBToLabel(const string& asymId, int seqI ...@@ -1716,9 +1742,9 @@ tuple<string,int,string> Structure::MapPDBToLabel(const string& asymId, int seqI
if (iCode.empty()) if (iCode.empty())
{ {
for (auto r: db["pdbx_poly_seq_scheme"].find( for (auto r: db["pdbx_poly_seq_scheme"].find(
cif::Key("pdb_strand_id") == asymId and cif::Key("pdb_strand_id") == asymID and
cif::Key("pdb_seq_num") == seqId and cif::Key("pdb_seq_num") == seqID and
cif::Key("pdb_mon_id") == compId and cif::Key("pdb_mon_id") == compID and
cif::Key("pdb_ins_code") == cif::Empty())) cif::Key("pdb_ins_code") == cif::Empty()))
{ {
result = r.get("asym_id", "seq_id", "mon_id"); result = r.get("asym_id", "seq_id", "mon_id");
...@@ -1726,9 +1752,9 @@ tuple<string,int,string> Structure::MapPDBToLabel(const string& asymId, int seqI ...@@ -1726,9 +1752,9 @@ tuple<string,int,string> Structure::MapPDBToLabel(const string& asymId, int seqI
} }
for (auto r: db["pdbx_nonpoly_scheme"].find( for (auto r: db["pdbx_nonpoly_scheme"].find(
cif::Key("pdb_strand_id") == asymId and cif::Key("pdb_strand_id") == asymID and
cif::Key("pdb_seq_num") == seqId and cif::Key("pdb_seq_num") == seqID and
cif::Key("pdb_mon_id") == compId and cif::Key("pdb_mon_id") == compID and
cif::Key("pdb_ins_code") == cif::Empty())) cif::Key("pdb_ins_code") == cif::Empty()))
{ {
result = r.get("asym_id", "ndb_seq_num", "mon_id"); result = r.get("asym_id", "ndb_seq_num", "mon_id");
...@@ -1739,9 +1765,9 @@ tuple<string,int,string> Structure::MapPDBToLabel(const string& asymId, int seqI ...@@ -1739,9 +1765,9 @@ tuple<string,int,string> Structure::MapPDBToLabel(const string& asymId, int seqI
else else
{ {
for (auto r: db["pdbx_poly_seq_scheme"].find( for (auto r: db["pdbx_poly_seq_scheme"].find(
cif::Key("pdb_strand_id") == asymId and cif::Key("pdb_strand_id") == asymID and
cif::Key("pdb_seq_num") == seqId and cif::Key("pdb_seq_num") == seqID and
cif::Key("pdb_mon_id") == compId and cif::Key("pdb_mon_id") == compID and
cif::Key("pdb_ins_code") == iCode)) cif::Key("pdb_ins_code") == iCode))
{ {
result = r.get("asym_id", "seq_id", "mon_id"); result = r.get("asym_id", "seq_id", "mon_id");
...@@ -1749,9 +1775,9 @@ tuple<string,int,string> Structure::MapPDBToLabel(const string& asymId, int seqI ...@@ -1749,9 +1775,9 @@ tuple<string,int,string> Structure::MapPDBToLabel(const string& asymId, int seqI
} }
for (auto r: db["pdbx_nonpoly_scheme"].find( for (auto r: db["pdbx_nonpoly_scheme"].find(
cif::Key("pdb_strand_id") == asymId and cif::Key("pdb_strand_id") == asymID and
cif::Key("pdb_seq_num") == seqId and cif::Key("pdb_seq_num") == seqID and
cif::Key("pdb_mon_id") == compId and cif::Key("pdb_mon_id") == compID and
cif::Key("pdb_ins_code") == iCode)) cif::Key("pdb_ins_code") == iCode))
{ {
result = r.get("asym_id", "ndb_seq_num", "mon_id"); result = r.get("asym_id", "ndb_seq_num", "mon_id");
...@@ -1944,7 +1970,7 @@ void Structure::changeResidue(const Residue& res, const string& newCompound, ...@@ -1944,7 +1970,7 @@ void Structure::changeResidue(const Residue& res, const string& newCompound,
string a1, a2; string a1, a2;
tie(a1, a2) = a; tie(a1, a2) = a;
auto i = find_if(atoms.begin(), atoms.end(), [&](const Atom& a) { return a.labelAtomId() == a1; }); auto i = find_if(atoms.begin(), atoms.end(), [&](const Atom& a) { return a.labelAtomID() == a1; });
if (i == atoms.end()) if (i == atoms.end())
{ {
cerr << "Missing atom for atom ID " << a1 << endl; cerr << "Missing atom for atom ID " << a1 << endl;
......
Markdown is supported
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