OpenMS
SequestOutfile.h
Go to the documentation of this file.
1 // --------------------------------------------------------------------------
2 // OpenMS -- Open-Source Mass Spectrometry
3 // --------------------------------------------------------------------------
4 // Copyright The OpenMS Team -- Eberhard Karls University Tuebingen,
5 // ETH Zurich, and Freie Universitaet Berlin 2002-2023.
6 //
7 // This software is released under a three-clause BSD license:
8 // * Redistributions of source code must retain the above copyright
9 // notice, this list of conditions and the following disclaimer.
10 // * Redistributions in binary form must reproduce the above copyright
11 // notice, this list of conditions and the following disclaimer in the
12 // documentation and/or other materials provided with the distribution.
13 // * Neither the name of any author or any participating institution
14 // may be used to endorse or promote products derived from this software
15 // without specific prior written permission.
16 // For a full list of authors, refer to the file AUTHORS.
17 // --------------------------------------------------------------------------
18 // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
19 // AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
20 // IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
21 // ARE DISCLAIMED. IN NO EVENT SHALL ANY OF THE AUTHORS OR THE CONTRIBUTING
22 // INSTITUTIONS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
23 // EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
24 // PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
25 // OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
26 // WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
27 // OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
28 // ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
29 //
30 // --------------------------------------------------------------------------
31 // $Maintainer: Timo Sachsenberg $
32 // $Authors: Martin Langwisch $
33 // --------------------------------------------------------------------------
34 
35 #pragma once
36 
40 
41 #include <map>
42 #include <vector>
43 #include <cmath>
44 
45 namespace OpenMS
46 {
47  class ProteinIdentification;
48  class DateTime;
49 
61  class OPENMS_DLLAPI SequestOutfile
62  {
63 public:
66 
68  SequestOutfile(const SequestOutfile & sequest_outfile);
69 
71  virtual ~SequestOutfile();
72 
74  SequestOutfile & operator=(const SequestOutfile & sequest_outfile);
75 
77  bool operator==(const SequestOutfile & sequest_outfile) const;
78 
97  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);
98 
99 // /// retrieve the p-values from the out files
100 // void getPValuesFromOutFiles(vector< pair < String, vector< double > > >& filenames_and_pvalues) throw (Exception::FileNotFound&, Exception::ParseError);
101 
103  bool getColumns(const String & line, std::vector<String> & substrings, Size number_of_columns, Size reference_column);
104 
113  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);
114 
117  void getACAndACType(String line, String & accession, String & accession_type);
118 
124  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);
125 
126 private:
127 
128  static double const_weights_[];
129  static double xcorr_weights_[];
130  static double delta_cn_weights_[];
131  static double rank_sp_weights_[];
132  static double delta_mass_weights_[];
133  static Size max_pep_lens_[];
134  static Size num_frags_[];
135  };
136 
137 } //namespace OpenMS
138 
DateTime Class.
Definition: DateTime.h:59
Representation of a protein identification run.
Definition: ProteinIdentification.h:76
Representation of a Sequest output file.
Definition: SequestOutfile.h:62
bool operator==(const SequestOutfile &sequest_outfile) const
equality operator
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)
SequestOutfile()
Constructor.
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)
bool getColumns(const String &line, std::vector< String > &substrings, Size number_of_columns, Size reference_column)
retrieve columns from a Sequest outfile line
SequestOutfile(const SequestOutfile &sequest_outfile)
copy constructor
virtual ~SequestOutfile()
destructor
void getACAndACType(String line, String &accession, String &accession_type)
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
SequestOutfile & operator=(const SequestOutfile &sequest_outfile)
assignment operator
A more convenient string class.
Definition: String.h:60
int Int
Signed integer type.
Definition: Types.h:102
size_t Size
Size type e.g. used as variable which can hold result of size()
Definition: Types.h:127
Main OpenMS namespace.
Definition: FeatureDeconvolution.h:48