Representation of a Sequest output file. More...
#include <OpenMS/FORMAT/SequestOutfile.h>
Public Member Functions | |
SequestOutfile () | |
Constructor. More... | |
SequestOutfile (const SequestOutfile &sequest_outfile) | |
copy constructor More... | |
virtual | ~SequestOutfile () |
destructor More... | |
SequestOutfile & | operator= (const SequestOutfile &sequest_outfile) |
assignment operator More... | |
bool | operator== (const SequestOutfile &sequest_outfile) const |
equality operator More... | |
void | load (const String &result_filename, std::vector< PeptideIdentification > &peptide_identifications, ProteinIdentification &protein_identification, const double p_value_threshold, std::vector< double > &pvalues, const String &database="", const bool ignore_proteins_per_peptide=false) |
loads data from a Sequest outfile More... | |
bool | getColumns (const String &line, std::vector< String > &substrings, Size number_of_columns, Size reference_column) |
retrieve columns from a Sequest outfile line More... | |
void | getSequences (const String &database_filename, const std::map< String, Size > &ac_position_map, std::vector< String > &sequences, std::vector< std::pair< String, Size > > &found, std::map< String, Size > ¬_found) |
void | getACAndACType (String line, String &accession, String &accession_type) |
void | readOutHeader (const String &result_filename, DateTime &datetime, double &precursor_mz_value, Int &charge, Size &precursor_mass_type, Size &ion_mass_type, Size &displayed_peptides, String &sequest, String &sequest_version, String &database_type, Int &number_column, Int &rank_sp_column, Int &id_column, Int &mh_column, Int &delta_cn_column, Int &xcorr_column, Int &sp_column, Int &sf_column, Int &ions_column, Int &reference_column, Int &peptide_column, Int &score_column, Size &number_of_columns) |
Static Private Attributes | |
static double | const_weights_ [] |
static double | xcorr_weights_ [] |
static double | delta_cn_weights_ [] |
static double | rank_sp_weights_ [] |
static double | delta_mass_weights_ [] |
static Size | max_pep_lens_ [] |
static Size | num_frags_ [] |
Representation of a Sequest output file.
This class serves to read in a Sequest outfile. The information can be retrieved via the load function.
Handle Modifications (Andreas)
Complete rewrite of the parser (and those of InsPecT and PepNovo), the code is bullshit... (Andreas)
SequestOutfile | ( | ) |
Constructor.
SequestOutfile | ( | const SequestOutfile & | sequest_outfile | ) |
copy constructor
|
virtual |
destructor
retrieve the accession type and accession number from a protein description line (e.g. from FASTA line: >gi|5524211|gb|AAD44166.1| cytochrome b [Elephas maximus maximus], get ac:AAD44166.1 ac type: GenBank)
bool getColumns | ( | const String & | line, |
std::vector< String > & | substrings, | ||
Size | number_of_columns, | ||
Size | reference_column | ||
) |
retrieve columns from a Sequest outfile line
void getSequences | ( | const String & | database_filename, |
const std::map< String, Size > & | ac_position_map, | ||
std::vector< String > & | sequences, | ||
std::vector< std::pair< String, Size > > & | found, | ||
std::map< String, Size > & | not_found | ||
) |
retrieve sequences from a FASTA database
database_filename | |
ac_position_map | |
sequences | |
found | |
not_found |
Exception::FileNotFound | is thrown if the database file could not be found |
void load | ( | const String & | result_filename, |
std::vector< PeptideIdentification > & | peptide_identifications, | ||
ProteinIdentification & | protein_identification, | ||
const double | p_value_threshold, | ||
std::vector< double > & | pvalues, | ||
const String & | database = "" , |
||
const bool | ignore_proteins_per_peptide = false |
||
) |
loads data from a Sequest outfile
result_filename | the file to be loaded |
peptide_identifications | the identifications |
protein_identification | the protein identifications |
p_value_threshold | the significance level (for the peptide hit scores) |
pvalues | a list with the pvalues of the peptides (pvalues computed with peptide prophet) |
database | the database used for the search |
ignore_proteins_per_peptide | this is a hack to deal with files that use a suffix like "+1" in column "Reference", but do not actually list extra protein references in subsequent lines |
Exception::FileNotFound | is thrown if the given result file could not be found |
Exception::ParseError | is thrown if the given result file could not be parsed |
Exception::IllegalArgument | This class serves to read in a Sequest outfile. The information can be retrieved via the load function. |
SequestOutfile& operator= | ( | const SequestOutfile & | sequest_outfile | ) |
assignment operator
bool operator== | ( | const SequestOutfile & | sequest_outfile | ) | const |
equality operator
void readOutHeader | ( | const String & | result_filename, |
DateTime & | datetime, | ||
double & | precursor_mz_value, | ||
Int & | charge, | ||
Size & | precursor_mass_type, | ||
Size & | ion_mass_type, | ||
Size & | displayed_peptides, | ||
String & | sequest, | ||
String & | sequest_version, | ||
String & | database_type, | ||
Int & | number_column, | ||
Int & | rank_sp_column, | ||
Int & | id_column, | ||
Int & | mh_column, | ||
Int & | delta_cn_column, | ||
Int & | xcorr_column, | ||
Int & | sp_column, | ||
Int & | sf_column, | ||
Int & | ions_column, | ||
Int & | reference_column, | ||
Int & | peptide_column, | ||
Int & | score_column, | ||
Size & | number_of_columns | ||
) |
read the header of an out file and retrieve various information
Exception::FileNotFound | is thrown if the results file could not be found |
Exception::ParseError | is thrown if the results file could not be parsed |
|
staticprivate |
|
staticprivate |
|
staticprivate |
|
staticprivate |
|
staticprivate |
|
staticprivate |
|
staticprivate |
OpenMS / TOPP release 2.3.0 | Documentation generated on Tue Jan 9 2018 18:22:12 using doxygen 1.8.13 |