MMCifReader Class Reference

reader for the mmcif file format More...

#include <mmcif_reader.hh>

Inherits ost::io::StarParser, and ost::io::StarParser.

Data Structures

struct  MMCifBioUAssembly
struct  MMCifEntityDesc
struct  MMCifHSEntry
struct  MMCifPSAEntry

Public Member Functions

 MMCifReader (std::istream &stream, mol::EntityHandle &ent_handle, const IOProfile &profile)
 MMCifReader (const String &filename, mol::EntityHandle &ent_handle, const IOProfile &profile)
void Init ()
void ClearState ()
void SetRestrictChains (const String &restrict_chains)
void SetReadCanonicalSeqRes (bool flag)
const String & GetRestrictChains () const
void SetAuthChainID (bool id)
virtual bool OnBeginData (const StringRef &data_name)
virtual bool OnBeginLoop (const StarLoopDesc &header)
virtual void OnDataRow (const StarLoopDesc &header, const std::vector< StringRef > &columns)
virtual void OnEndData ()
seq::SequenceList GetSeqRes () const
void SetReadSeqRes (bool flag)
bool GetReadSeqRes () const
const MMCifInfo & GetInfo ()
 MMCifReader (std::istream &stream, mol::EntityHandle &ent_handle, const IOProfile &profile)
 MMCifReader (const String &filename, mol::EntityHandle &ent_handle, const IOProfile &profile)
void Init ()
void ClearState ()
void SetRestrictChains (const String &restrict_chains)
void SetReadCanonicalSeqRes (bool flag)
const String & GetRestrictChains () const
void SetAuthChainID (bool id)
virtual bool OnBeginData (const StringRef &data_name)
virtual bool OnBeginLoop (const StarLoopDesc &header)
virtual void OnDataRow (const StarLoopDesc &header, const std::vector< StringRef > &columns)
virtual void OnEndData ()
seq::SequenceList GetSeqRes () const
void SetReadSeqRes (bool flag)
bool GetReadSeqRes () const
const MMCifInfo & GetInfo ()

Protected Types

enum  MMCifSecStructElement {
  MMCIF_HELIX, MMCIF_STRAND, MMCIF_TURN, MMCIF_HELIX,
  MMCIF_STRAND, MMCIF_TURN
}
enum  MMCifSecStructElement {
  MMCIF_HELIX, MMCIF_STRAND, MMCIF_TURN, MMCIF_HELIX,
  MMCIF_STRAND, MMCIF_TURN
}

Protected Member Functions

void TryStoreIdx (const int mapping, const String &item, const StarLoopDesc &header)
bool IsValidPDBIdent (const StringRef &pdbid)
bool ParseAtomIdent (const std::vector< StringRef > &columns, String &auth_chain_name, String &cif_chain_name, StringRef &res_name, mol::ResNum &resnum, bool &valid_res_num, StringRef &atom_name, char &alt_loc)
void ParseAndAddAtom (const std::vector< StringRef > &columns)
void ParseEntity (const std::vector< StringRef > &columns)
void ParseEntityPoly (const std::vector< StringRef > &columns)
void ParseCitation (const std::vector< StringRef > &columns)
const MMCifInfoStructRefs & GetStructRefs () const
String ConvertSEQRES (const String &seqres, conop::CompoundLibPtr compound_lib)
void ParseCitationAuthor (const std::vector< StringRef > &columns)
void ParseStructRef (const std::vector< StringRef > &columns)
void ParseStructRefSeq (const std::vector< StringRef > &columns)
void ParseStructRefSeqDif (const std::vector< StringRef > &columns)
void ParseExptl (const std::vector< StringRef > &columns)
void ParseRefine (const std::vector< StringRef > &columns)
void ParsePdbxStructAssembly (const std::vector< StringRef > &columns)
void ParsePdbxStructAssemblyGen (const std::vector< StringRef > &columns)
std::vector< std::vector
< String > > 		UnPackOperExperession (StringRef expression)
void StoreExpression (const char *l, const char *s, bool &is_range, int lborder, std::vector< String > &single_block)
void StoreRange (const char *&l, const char *s, bool &is_range, int &lborder, std::vector< String > &single_block)
void ParsePdbxStructOperList (const std::vector< StringRef > &columns)
void ParseDatabasePDBRev (const std::vector< StringRef > &columns)
void ParseStruct (const std::vector< StringRef > &columns)
void ParseStructConf (const std::vector< StringRef > &columns)
void ParseStructSheetRange (const std::vector< StringRef > &columns)
void ParsePdbxDatabasePdbObsSpr (const std::vector< StringRef > &columns)
MMCifSecStructElement DetermineSecStructType (const StringRef &type) const
void AssignSecStructure (mol::EntityHandle ent)
void TryStoreIdx (const int mapping, const String &item, const StarLoopDesc &header)
bool IsValidPDBIdent (const StringRef &pdbid)
bool ParseAtomIdent (const std::vector< StringRef > &columns, String &auth_chain_name, String &cif_chain_name, StringRef &res_name, mol::ResNum &resnum, bool &valid_res_num, StringRef &atom_name, char &alt_loc)
void ParseAndAddAtom (const std::vector< StringRef > &columns)
void ParseEntity (const std::vector< StringRef > &columns)
void ParseEntityPoly (const std::vector< StringRef > &columns)
void ParseCitation (const std::vector< StringRef > &columns)
const MMCifInfoStructRefs & GetStructRefs () const
String ConvertSEQRES (const String &seqres, conop::CompoundLibPtr compound_lib)
void ParseCitationAuthor (const std::vector< StringRef > &columns)
void ParseStructRef (const std::vector< StringRef > &columns)
void ParseStructRefSeq (const std::vector< StringRef > &columns)
void ParseStructRefSeqDif (const std::vector< StringRef > &columns)
void ParseExptl (const std::vector< StringRef > &columns)
void ParseRefine (const std::vector< StringRef > &columns)
void ParsePdbxStructAssembly (const std::vector< StringRef > &columns)
void ParsePdbxStructAssemblyGen (const std::vector< StringRef > &columns)
std::vector< std::vector
< String > > 		UnPackOperExperession (StringRef expression)
void StoreExpression (const char *l, const char *s, bool &is_range, int lborder, std::vector< String > &single_block)
void StoreRange (const char *&l, const char *s, bool &is_range, int &lborder, std::vector< String > &single_block)
void ParsePdbxStructOperList (const std::vector< StringRef > &columns)
void ParseDatabasePDBRev (const std::vector< StringRef > &columns)
void ParseStruct (const std::vector< StringRef > &columns)
void ParseStructConf (const std::vector< StringRef > &columns)
void ParseStructSheetRange (const std::vector< StringRef > &columns)
void ParsePdbxDatabasePdbObsSpr (const std::vector< StringRef > &columns)
MMCifSecStructElement DetermineSecStructType (const StringRef &type) const
void AssignSecStructure (mol::EntityHandle ent)

Detailed Description

reader for the mmcif file format

mmcif format description/ coverage

mmcif is an instance of the STAR format to store entries of the PDB. The following data categories should be covered by this reader:

Definition at line 59 of file mmcif_reader.hh.

Member Enumeration Documentation

enum MMCifSecStructElement [protected]
Enumerator:
MMCIF_HELIX 
MMCIF_STRAND 
MMCIF_TURN 
MMCIF_HELIX 
MMCIF_STRAND 
MMCIF_TURN 

Definition at line 322 of file mmcif_reader.hh.

enum MMCifSecStructElement [protected]
Enumerator:
MMCIF_HELIX 
MMCIF_STRAND 
MMCIF_TURN 
MMCIF_HELIX 
MMCIF_STRAND 
MMCIF_TURN 

Definition at line 322 of file mmcif_reader.hh.

Constructor & Destructor Documentation

MMCifReader ( std::istream &  stream,
mol::EntityHandle &  ent_handle,
const IOProfile &  profile 
)

create a MMCifReader

Parameters:
stream input stream
ent_handle 
profile 
MMCifReader ( const String &  filename,
mol::EntityHandle &  ent_handle,
const IOProfile &  profile 
)

create a MMCifReader

Parameters:
filename input file
ent_handle 
profile 
MMCifReader ( std::istream &  stream,
mol::EntityHandle &  ent_handle,
const IOProfile &  profile 
)

create a MMCifReader

Parameters:
stream input stream
ent_handle 
profile 
MMCifReader ( const String &  filename,
mol::EntityHandle &  ent_handle,
const IOProfile &  profile 
)

create a MMCifReader

Parameters:
filename input file
ent_handle 
profile 

Member Function Documentation

void AssignSecStructure ( mol::EntityHandle  ent  )  [protected]

Transform data from struct_conf entry into secondary structure.

Parameters:
ent Entity to assign secondary structure to
void AssignSecStructure ( mol::EntityHandle  ent  )  [protected]

Transform data from struct_conf entry into secondary structure.

Parameters:
ent Entity to assign secondary structure to
void ClearState (  ) 

Set up a fresh instance.

void ClearState (  ) 

Set up a fresh instance.

String ConvertSEQRES ( const String &  seqres,
conop::CompoundLibPtr  compound_lib 
) [protected]

convert the seqres data item to canonical form.

The seqres sequence lists non-standard residues in paranthesis. For proper handling of our sequence classes, these need to be converted to one-letter-codes. Ideally, we would use the canonical SEQRES. This is not possible, however, since the PDB assigns multiple one letter codes to some of the residues. To be consistent, we have to do the conversion on our own.

String ConvertSEQRES ( const String &  seqres,
conop::CompoundLibPtr  compound_lib 
) [protected]

convert the seqres data item to canonical form.

The seqres sequence lists non-standard residues in paranthesis. For proper handling of our sequence classes, these need to be converted to one-letter-codes. Ideally, we would use the canonical SEQRES. This is not possible, however, since the PDB assigns multiple one letter codes to some of the residues. To be consistent, we have to do the conversion on our own.

MMCifSecStructElement DetermineSecStructType ( const StringRef &  type  )  const [protected]

Check whether an element was classified sheet or helix.

Parameters:
type Type to be classified
MMCifSecStructElement DetermineSecStructType ( const StringRef &  type  )  const [protected]

Check whether an element was classified sheet or helix.

Parameters:
type Type to be classified
const MMCifInfo& GetInfo (  )  [inline]

Get additional information of the mmCIF file.

Returns:
MMCitfInfo object

Definition at line 165 of file mmcif_reader.hh.

const MMCifInfo& GetInfo (  )  [inline]

Get additional information of the mmCIF file.

Returns:
MMCitfInfo object

Definition at line 165 of file mmcif_reader.hh.

bool GetReadSeqRes (  )  const [inline]

Check if reading of SEQRES is enabled.

Returns:
True if reading of SEQRES is enabled

Definition at line 157 of file mmcif_reader.hh.

bool GetReadSeqRes (  )  const [inline]

Check if reading of SEQRES is enabled.

Returns:
True if reading of SEQRES is enabled

Definition at line 157 of file mmcif_reader.hh.

const String& GetRestrictChains (  )  const [inline]

Definition at line 100 of file mmcif_reader.hh.

const String& GetRestrictChains (  )  const [inline]

Definition at line 100 of file mmcif_reader.hh.

seq::SequenceList GetSeqRes (  )  const [inline]

Return sequences.

Returns:
List of sequences

Definition at line 142 of file mmcif_reader.hh.

seq::SequenceList GetSeqRes (  )  const [inline]

Return sequences.

Returns:
List of sequences

Definition at line 142 of file mmcif_reader.hh.

const MMCifInfoStructRefs& GetStructRefs (  )  const [inline, protected]

Definition at line 239 of file mmcif_reader.hh.

const MMCifInfoStructRefs& GetStructRefs (  )  const [inline, protected]

Definition at line 239 of file mmcif_reader.hh.

void Init (  ) 

Initialise the reader.

void Init (  ) 

Initialise the reader.

bool IsValidPDBIdent ( const StringRef &  pdbid  )  [protected]

Check a PDB id to be of length 4 and start with a digit.

Parameters:
pdbid putative PDB id
Returns:
true for a valid id, false otherwise
bool IsValidPDBIdent ( const StringRef &  pdbid  )  [protected]

Check a PDB id to be of length 4 and start with a digit.

Parameters:
pdbid putative PDB id
Returns:
true for a valid id, false otherwise
virtual bool OnBeginData ( const StringRef &  data_name  )  [virtual]

check mmcif input to be read. Substitutional function for StarParser.

Parameters:
data_name value of the data_ tag
Returns:
true, if the blockcode (PDB id) is valid, false otherwise

Reimplemented from StarParser.

virtual bool OnBeginData ( const StringRef &  data_name  )  [virtual]

check mmcif input to be read. Substitutional function for StarParser.

Parameters:
data_name value of the data_ tag
Returns:
true, if the blockcode (PDB id) is valid, false otherwise

Reimplemented from StarParser.

virtual bool OnBeginLoop ( const StarLoopDesc &  header  )  [virtual]

check if a current loop is to be parsed

Parameters:
header categories of the upcoming loop block
Returns:
bool

Reimplemented from StarParser.

virtual bool OnBeginLoop ( const StarLoopDesc &  header  )  [virtual]

check if a current loop is to be parsed

Parameters:
header categories of the upcoming loop block
Returns:
bool

Reimplemented from StarParser.

virtual void OnDataRow ( const StarLoopDesc &  header,
const std::vector< StringRef > &  columns 
) [virtual]

read a row of data

Parameters:
header categories and items
columns data

Reimplemented from StarParser.

virtual void OnDataRow ( const StarLoopDesc &  header,
const std::vector< StringRef > &  columns 
) [virtual]

read a row of data

Parameters:
header categories and items
columns data

Reimplemented from StarParser.

virtual void OnEndData (  )  [virtual]

Finalise parsing.

Reimplemented from StarParser.

virtual void OnEndData (  )  [virtual]

Finalise parsing.

Reimplemented from StarParser.

void ParseAndAddAtom ( const std::vector< StringRef > &  columns  )  [protected]

Fetch atom information and store it.

Parameters:
columns data row
void ParseAndAddAtom ( const std::vector< StringRef > &  columns  )  [protected]

Fetch atom information and store it.

Parameters:
columns data row
bool ParseAtomIdent ( const std::vector< StringRef > &  columns,
String &  auth_chain_name,
String &  cif_chain_name,
StringRef &  res_name,
mol::ResNum &  resnum,
bool &  valid_res_num,
StringRef &  atom_name,
char &  alt_loc 
) [protected]

fetch values identifying atoms

Parameters:
[in] columns data row
[out] auth_chain_name takes atom_site.label_asym_id or, if auth_chain_id_ is set, atom_site.auth_asym_id as a chain name
[out] cif_chain_name 
[out] res_name fetches atom_site.label_comp_id
[out] resnum gets atom_site.label_seq_id if available, consecutive numbers, otherwise
[out] valid_res_num shows if we have a valid residue number or if we have to invent our own
[out] atom_name corresponds to label_atom_id
[out] alt_loc gets first letter of atom_site.label_alt_id
bool ParseAtomIdent ( const std::vector< StringRef > &  columns,
String &  auth_chain_name,
String &  cif_chain_name,
StringRef &  res_name,
mol::ResNum &  resnum,
bool &  valid_res_num,
StringRef &  atom_name,
char &  alt_loc 
) [protected]

fetch values identifying atoms

Parameters:
[in] columns data row
[out] auth_chain_name takes atom_site.label_asym_id or, if auth_chain_id_ is set, atom_site.auth_asym_id as a chain name
[out] cif_chain_name 
[out] res_name fetches atom_site.label_comp_id
[out] resnum gets atom_site.label_seq_id if available, consecutive numbers, otherwise
[out] valid_res_num shows if we have a valid residue number or if we have to invent our own
[out] atom_name corresponds to label_atom_id
[out] alt_loc gets first letter of atom_site.label_alt_id
void ParseCitation ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF citation information.

Parameters:
columns data row
void ParseCitation ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF citation information.

Parameters:
columns data row
void ParseCitationAuthor ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF citation_author information.

Parameters:
columns data row
void ParseCitationAuthor ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF citation_author information.

Parameters:
columns data row
void ParseDatabasePDBRev ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF database_PDB_rev information.

Parameters:
columns data row
void ParseDatabasePDBRev ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF database_PDB_rev information.

Parameters:
columns data row
void ParseEntity ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF entity information.

Parameters:
columns data row
void ParseEntity ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF entity information.

Parameters:
columns data row
void ParseEntityPoly ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF entity_poly information.

Parameters:
columns data row
void ParseEntityPoly ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF entity_poly information.

Parameters:
columns data row
void ParseExptl ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF exptl information.

Parameters:
columns data row
void ParseExptl ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF exptl information.

Parameters:
columns data row
void ParsePdbxDatabasePdbObsSpr ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF pdbx_database_PDB_obs_spr information.

Parameters:
columns data row
void ParsePdbxDatabasePdbObsSpr ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF pdbx_database_PDB_obs_spr information.

Parameters:
columns data row
void ParsePdbxStructAssembly ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF pdbx_struct_assembly information.

Parameters:
columns data row
void ParsePdbxStructAssembly ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF pdbx_struct_assembly information.

Parameters:
columns data row
void ParsePdbxStructAssemblyGen ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF pdbx_struct_assembly_gen information.

Parameters:
columns data row
void ParsePdbxStructAssemblyGen ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF pdbx_struct_assembly_gen information.

Parameters:
columns data row
void ParsePdbxStructOperList ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF pdbx_struct_oper_list information.

Parameters:
columns data row
void ParsePdbxStructOperList ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF pdbx_struct_oper_list information.

Parameters:
columns data row
void ParseRefine ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF refine information.

Parameters:
columns data row
void ParseRefine ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF refine information.

Parameters:
columns data row
void ParseStruct ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF struct information.

Parameters:
columns data row
void ParseStruct ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF struct information.

Parameters:
columns data row
void ParseStructConf ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF struct_conf (secondary structure) information.

Parameters:
columns data row
void ParseStructConf ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF struct_conf (secondary structure) information.

Parameters:
columns data row
void ParseStructRef ( const std::vector< StringRef > &  columns  )  [protected]

\ brief parse a row in the struct_ref category

void ParseStructRef ( const std::vector< StringRef > &  columns  )  [protected]

\ brief parse a row in the struct_ref category

void ParseStructRefSeq ( const std::vector< StringRef > &  columns  )  [protected]

parse row in the struct_ref_seq category

void ParseStructRefSeq ( const std::vector< StringRef > &  columns  )  [protected]

parse row in the struct_ref_seq category

void ParseStructRefSeqDif ( const std::vector< StringRef > &  columns  )  [protected]

parse row in the struct_ref_seq_dif category

void ParseStructRefSeqDif ( const std::vector< StringRef > &  columns  )  [protected]

parse row in the struct_ref_seq_dif category

void ParseStructSheetRange ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF struct_sheet_range (beta sheets) information.

Parameters:
columns data row
void ParseStructSheetRange ( const std::vector< StringRef > &  columns  )  [protected]

Fetch mmCIF struct_sheet_range (beta sheets) information.

Parameters:
columns data row
void SetAuthChainID ( bool  id  )  [inline]

Enable or disable reading of auth_chain_id instead aof label_chain id (default).

Parameters:
id enable (true) or disable (false) reading of auth_chain_id.

Definition at line 109 of file mmcif_reader.hh.

void SetAuthChainID ( bool  id  )  [inline]

Enable or disable reading of auth_chain_id instead aof label_chain id (default).

Parameters:
id enable (true) or disable (false) reading of auth_chain_id.

Definition at line 109 of file mmcif_reader.hh.

void SetReadCanonicalSeqRes ( bool  flag  )  [inline]

Toggle reading of canonical sequence residues (entity_poly.pdbx_seq_one_letter_code_can instead of entity_poly.pdbx_seq_one_letter_code). This flag is exclusive.

Parameters:
flag True for reading canonical sequences.

Definition at line 95 of file mmcif_reader.hh.

void SetReadCanonicalSeqRes ( bool  flag  )  [inline]

Toggle reading of canonical sequence residues (entity_poly.pdbx_seq_one_letter_code_can instead of entity_poly.pdbx_seq_one_letter_code). This flag is exclusive.

Parameters:
flag True for reading canonical sequences.

Definition at line 95 of file mmcif_reader.hh.

void SetReadSeqRes ( bool  flag  )  [inline]

Toggle reading of SEQRES.

Parameters:
flag True enables, False disables reading SEQRES

Definition at line 149 of file mmcif_reader.hh.

void SetReadSeqRes ( bool  flag  )  [inline]

Toggle reading of SEQRES.

Parameters:
flag True enables, False disables reading SEQRES

Definition at line 149 of file mmcif_reader.hh.

void SetRestrictChains ( const String &  restrict_chains  ) 

Set names of restricted chains for the reader.

Parameters:
restrict_chains chain name
void SetRestrictChains ( const String &  restrict_chains  ) 

Set names of restricted chains for the reader.

Parameters:
restrict_chains chain name
void StoreExpression ( const char *  l,
const char *  s,
bool &  is_range,
int  lborder,
std::vector< String > &  single_block 
) [protected]
void StoreExpression ( const char *  l,
const char *  s,
bool &  is_range,
int  lborder,
std::vector< String > &  single_block 
) [protected]
void StoreRange ( const char *&  l,
const char *  s,
bool &  is_range,
int &  lborder,
std::vector< String > &  single_block 
) [protected]
void StoreRange ( const char *&  l,
const char *  s,
bool &  is_range,
int &  lborder,
std::vector< String > &  single_block 
) [protected]
void TryStoreIdx ( const int  mapping,
const String &  item,
const StarLoopDesc &  header 
) [inline, protected]

Store an item index from loop header in preparation for reading a row. Throws an exception if the item does not exist.

Parameters:
mapping position the item index is stored at
item exact item name to fetch
header loop header to pull index from

Definition at line 174 of file mmcif_reader.hh.

void TryStoreIdx ( const int  mapping,
const String &  item,
const StarLoopDesc &  header 
) [inline, protected]

Store an item index from loop header in preparation for reading a row. Throws an exception if the item does not exist.

Parameters:
mapping position the item index is stored at
item exact item name to fetch
header loop header to pull index from

Definition at line 174 of file mmcif_reader.hh.

std::vector<std::vector<String> > UnPackOperExperession ( StringRef  expression  )  [protected]
std::vector<std::vector<String> > UnPackOperExperession ( StringRef  expression  )  [protected]
The documentation for this class was generated from the following files:
 All Data Structures Namespaces Files Functions Variables Typedefs Enumerations Enumerator Properties Friends Defines
Generated on 20 Jun 2016 for OpenStructure by  doxygen 1.6.1