OpenMS  2.4.0
XTandemXMLFile.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 2002-2018.
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: Andreas Bertsch $
33 // --------------------------------------------------------------------------
34 
35 #pragma once
36 
38 #include <OpenMS/FORMAT/XMLFile.h>
41 
42 namespace OpenMS
43 {
44  class String;
45  class ProteinIdentification;
46 
55  class OPENMS_DLLAPI XTandemXMLFile :
56  protected Internal::XMLHandler,
57  public Internal::XMLFile
58  {
59 public:
60 
63 
65  ~XTandemXMLFile() override;
79  void load(const String& filename, ProteinIdentification& protein_identification, std::vector<PeptideIdentification>& id_data, ModificationDefinitionsSet& mod_def_set);
80 
81 
82 protected:
83 
84  // Docu in base class
85  void startElement(const XMLCh* const /*uri*/, const XMLCh* const /*local_name*/, const XMLCh* const qname, const xercesc::Attributes& attributes) override;
86 
87  // Docu in base class
88  void endElement(const XMLCh* const /*uri*/, const XMLCh* const /*local_name*/, const XMLCh* const qname) override;
89 
90  // Docu in base class
91  void characters(const XMLCh* const chars, const XMLSize_t /*length*/) override;
92 
93  XTandemXMLFile(const XTandemXMLFile& rhs);
94 
95  XTandemXMLFile& operator=(const XTandemXMLFile& rhs);
96 
97 private:
98 
100 
101  // true during "note" element containing protein accession
103 
104  // true during "note" element containing spectrum ID
106 
107  // true after non-new protein entries, so that with the next "protein note" the
108  // accession will not be updated again
110 
111  // peptide hits per spectrum
112  std::map<UInt, std::vector<PeptideHit> > peptide_hits_;
113 
114  // protein hits
115  std::vector<ProteinHit> protein_hits_;
116 
117  // protein unique IDs (assigned by X! Tandem), to keep track of which proteins were already seen
118  std::set<UInt> protein_uids_;
119 
120  // accession of the current protein
122 
123  // charge of current peptide
125 
126  // X! Tandem ID of current peptide
128 
129  // tag
131 
132  // start position of current peptide in protein sequence
134 
135  // stop position of current peptide in protein sequence
137 
138  // previous peptide sequence
140 
141  // mapping from X! Tandem ID to spectrum ID
142  std::map<UInt, String> spectrum_ids_;
143 
144  // modification definitions
146 
147  // modifications used by X! Tandem by default
149  };
150 
151 } // namespace OpenMS
152 
Representation of a protein identification run.
Definition: ProteinIdentification.h:61
A more convenient string class.
Definition: String.h:57
Int current_charge_
Definition: XTandemXMLFile.h:124
std::set< UInt > protein_uids_
Definition: XTandemXMLFile.h:118
String tag_
Definition: XTandemXMLFile.h:130
unsigned int UInt
Unsigned integer type.
Definition: Types.h:94
std::map< UInt, std::vector< PeptideHit > > peptide_hits_
Definition: XTandemXMLFile.h:112
Base class for XML handlers.
Definition: XMLHandler.h:148
String current_protein_
Definition: XTandemXMLFile.h:121
bool skip_protein_acc_update_
Definition: XTandemXMLFile.h:109
ModificationDefinitionsSet default_nterm_mods_
Definition: XTandemXMLFile.h:148
ModificationDefinitionsSet mod_def_set_
Definition: XTandemXMLFile.h:145
Main OpenMS namespace.
Definition: FeatureDeconvolution.h:46
std::vector< ProteinHit > protein_hits_
Definition: XTandemXMLFile.h:115
Used to load XTandemXML files.
Definition: XTandemXMLFile.h:55
bool is_protein_note_
Definition: XTandemXMLFile.h:102
std::map< UInt, String > spectrum_ids_
Definition: XTandemXMLFile.h:142
bool is_spectrum_note_
Definition: XTandemXMLFile.h:105
Representation of a set of modification definitions.
Definition: ModificationDefinitionsSet.h:58
String previous_seq_
Definition: XTandemXMLFile.h:139
ProteinIdentification * protein_identification_
Definition: XTandemXMLFile.h:99
Base class for loading/storing XML files that have a handler derived from XMLHandler.
Definition: XMLFile.h:48
UInt current_stop_
Definition: XTandemXMLFile.h:136
int Int
Signed integer type.
Definition: Types.h:102
UInt current_id_
Definition: XTandemXMLFile.h:127
UInt current_start_
Definition: XTandemXMLFile.h:133