OpenMS
ModificationsDB.h
Go to the documentation of this file.
1 // Copyright (c) 2002-present, OpenMS Inc. -- EKU Tuebingen, ETH Zurich, and FU Berlin
2 // SPDX-License-Identifier: BSD-3-Clause
3 //
4 // --------------------------------------------------------------------------
5 // $Maintainer: Timo Sachsenberg $
6 // $Authors: Andreas Bertsch $
7 // --------------------------------------------------------------------------
8 
9 #pragma once
10 
14 
15 #include <set>
16 #include <memory> // unique_ptr
17 #include <unordered_map>
18 
19 namespace OpenMS
20 {
21  // forward declarations
22  class ResidueModification;
23  class Residue;
24 
49  class OPENMS_DLLAPI ModificationsDB
50  {
51 public:
52 
55 
57  static ModificationsDB* initializeModificationsDB(OpenMS::String unimod_file = "CHEMISTRY/unimod.xml", OpenMS::String custommod_file = "CHEMISTRY/custom_mods.xml", OpenMS::String psimod_file = "CHEMISTRY/PSI-MOD.obo", OpenMS::String xlmod_file = "CHEMISTRY/XLMOD.obo");
58 
60  static bool isInstantiated();
61 
62  friend class CrossLinksDB;
63  // for access to addNewModification_ (without checking presence)
64  friend class Residue;
65  friend class AASequence;
66 
69 
75 
84  void searchModifications(std::set<const ResidueModification*>& mods,
85  const String& mod_name,
86  const String& residue = "",
88 
99 
115  bool& multiple_matches,
116  const String& residue = "",
118 
133 
135  bool has(const String& modification) const;
136 
144  const ResidueModification* addModification(std::unique_ptr<ResidueModification> new_mod);
145 
154 
163  Size findModificationIndex(const String& mod_name) const;
164 
172  void searchModificationsByDiffMonoMass(std::vector<String>& mods, double mass, double max_error, const String& residue = "", ResidueModification::TermSpecificity term_spec = ResidueModification::NUMBER_OF_TERM_SPECIFICITY);
173  void searchModificationsByDiffMonoMass(std::vector<const ResidueModification*>& mods, double mass, double max_error, const String& residue = "", ResidueModification::TermSpecificity term_spec = ResidueModification::NUMBER_OF_TERM_SPECIFICITY);
174 
182  void searchModificationsByDiffMonoMassSorted(std::vector<String>& mods, double mass, double max_error, const String& residue = "", ResidueModification::TermSpecificity term_spec = ResidueModification::NUMBER_OF_TERM_SPECIFICITY);
183  void searchModificationsByDiffMonoMassSorted(std::vector<const ResidueModification*>& mods, double mass, double max_error, const String& residue = "", ResidueModification::TermSpecificity term_spec = ResidueModification::NUMBER_OF_TERM_SPECIFICITY);
184 
185 
207 
209  void getAllSearchModifications(std::vector<String>& modifications) const;
210 
212  void writeTSV(const String& filename);
213 
214  protected:
215 
217  static bool is_instantiated_;
218 
220  std::vector<ResidueModification*> mods_;
221 
223  std::unordered_map<String, std::set<const ResidueModification*> > modification_names_;
224 
239  bool residuesMatch_(const char residue, const ResidueModification* curr_mod) const;
240 
241 private:
242 
251  explicit ModificationsDB(const OpenMS::String& unimod_file = "CHEMISTRY/unimod.xml", const OpenMS::String& custommod_file = "CHEMISTRY/custom_mods.xml", const OpenMS::String& psimod_file = "CHEMISTRY/PSI-MOD.obo", const OpenMS::String& xlmod_file = "CHEMISTRY/XLMOD.obo");
252 
254  ModificationsDB(const ModificationsDB& residue_db);
255 
257  virtual ~ModificationsDB();
259 
266 
273 
279  void readFromOBOFile(const String& filename);
280 
282  void readFromUnimodXMLFile(const String& filename);
283  };
284 }
Representation of a peptide/protein sequence.
Definition: AASequence.h:86
Definition: CrossLinksDB.h:17
database which holds all residue modifications from UniMod
Definition: ModificationsDB.h:50
void searchModificationsByDiffMonoMass(std::vector< String > &mods, double mass, double max_error, const String &residue="", ResidueModification::TermSpecificity term_spec=ResidueModification::NUMBER_OF_TERM_SPECIFICITY)
Collects all modifications with delta mass inside a tolerance window.
Size getNumberOfModifications() const
Returns the number of modifications read from the unimod.xml file.
static ModificationsDB * getInstance()
Returns a pointer to the modifications DB (singleton)
static ModificationsDB * initializeModificationsDB(OpenMS::String unimod_file="CHEMISTRY/unimod.xml", OpenMS::String custommod_file="CHEMISTRY/custom_mods.xml", OpenMS::String psimod_file="CHEMISTRY/PSI-MOD.obo", OpenMS::String xlmod_file="CHEMISTRY/XLMOD.obo")
Initializes the modification DB with non-default modification files (can only be done once)
bool residuesMatch_(const char residue, const ResidueModification *curr_mod) const
Helper function to check if a residue matches the origin for a modification.
const ResidueModification * getBestModificationByDiffMonoMass(double mass, double max_error, const String &residue="", ResidueModification::TermSpecificity term_spec=ResidueModification::NUMBER_OF_TERM_SPECIFICITY)
Returns the best matching modification for the given delta mass and residue.
void writeTSV(const String &filename)
Writes tab separated entries: FullId,FullName,Origin,AA,TerminusSpecificity,DiffMonoMass (including h...
std::vector< ResidueModification * > mods_
Stores the modifications.
Definition: ModificationsDB.h:220
ModificationsDB & operator=(const ModificationsDB &aa)
Assignment operator.
void searchModificationsByDiffMonoMassSorted(std::vector< const ResidueModification * > &mods, double mass, double max_error, const String &residue="", ResidueModification::TermSpecificity term_spec=ResidueModification::NUMBER_OF_TERM_SPECIFICITY)
const ResidueModification * addModification(const ResidueModification &new_mod)
Add a new modification to ModificationsDB. If the modification already exists (based on its fullID) i...
bool has(const String &modification) const
Returns true if the modification exists.
Size findModificationIndex(const String &mod_name) const
Returns the index of the modification in the mods_ vector; a unique name must be given.
void searchModificationsByDiffMonoMass(std::vector< const ResidueModification * > &mods, double mass, double max_error, const String &residue="", ResidueModification::TermSpecificity term_spec=ResidueModification::NUMBER_OF_TERM_SPECIFICITY)
void searchModificationsByDiffMonoMassSorted(std::vector< String > &mods, double mass, double max_error, const String &residue="", ResidueModification::TermSpecificity term_spec=ResidueModification::NUMBER_OF_TERM_SPECIFICITY)
Collects all modifications with delta mass inside a tolerance window and adds them sorted by mass dif...
const ResidueModification * searchModification(const ResidueModification &mod_in) const
Returns a pointer to an exact match of the given modification if present in the DB.
const ResidueModification * searchModificationsFast(const String &mod_name, bool &multiple_matches, const String &residue="", ResidueModification::TermSpecificity term_spec=ResidueModification::NUMBER_OF_TERM_SPECIFICITY) const
Returns the modification which has the given name as synonym (fast version)
void readFromUnimodXMLFile(const String &filename)
Adds modifications from a given file in Unimod XML format.
virtual ~ModificationsDB()
Destructor.
static bool isInstantiated()
Check whether ModificationsDB was instantiated before.
ModificationsDB(const OpenMS::String &unimod_file="CHEMISTRY/unimod.xml", const OpenMS::String &custommod_file="CHEMISTRY/custom_mods.xml", const OpenMS::String &psimod_file="CHEMISTRY/PSI-MOD.obo", const OpenMS::String &xlmod_file="CHEMISTRY/XLMOD.obo")
const ResidueModification * getModification(const String &mod_name, const String &residue="", ResidueModification::TermSpecificity term_spec=ResidueModification::NUMBER_OF_TERM_SPECIFICITY) const
Returns the modification with the given name.
const ResidueModification * getModification(Size index) const
Returns the modification with the given index. note: out-of-bounds check is only performed in debug m...
static bool is_instantiated_
Stores whether ModificationsDB was instantiated before.
Definition: ModificationsDB.h:217
const ResidueModification * addNewModification_(const ResidueModification &new_mod)
Add a new modification to ModificationsDB without checking if it was inside already.
void searchModifications(std::set< const ResidueModification * > &mods, const String &mod_name, const String &residue="", ResidueModification::TermSpecificity term_spec=ResidueModification::NUMBER_OF_TERM_SPECIFICITY) const
Collects all modifications which have the given name as synonym.
ModificationsDB(const ModificationsDB &residue_db)
Copy constructor.
void readFromOBOFile(const String &filename)
Adds modifications from a given file in OBO format.
const ResidueModification * addModification(std::unique_ptr< ResidueModification > new_mod)
Add a new modification to ModificationsDB. If the modification already exists (based on its fullID) i...
void getAllSearchModifications(std::vector< String > &modifications) const
Collects all modifications that can be used for identification searches.
std::unordered_map< String, std::set< const ResidueModification * > > modification_names_
Stores the mappings of (unique) names to the modifications.
Definition: ModificationsDB.h:223
Representation of a modification on an amino acid residue.
Definition: ResidueModification.h:53
TermSpecificity
Position where the modification is allowed to occur.
Definition: ResidueModification.h:72
@ NUMBER_OF_TERM_SPECIFICITY
Definition: ResidueModification.h:78
Representation of an amino acid residue.
Definition: Residue.h:40
A more convenient string class.
Definition: String.h:34
size_t Size
Size type e.g. used as variable which can hold result of size()
Definition: Types.h:97
Main OpenMS namespace.
Definition: openswathalgo/include/OpenMS/OPENSWATHALGO/DATAACCESS/ISpectrumAccess.h:19