MzTab.h

Go to the documentation of this file.

// Copyright (c) 2002-present, OpenMS Inc. -- EKU Tuebingen, ETH Zurich, and FU Berlin
// SPDX-License-Identifier: BSD-3-Clause
//
// --------------------------------------------------------------------------
// $Maintainer: Timo Sachsenberg $
// $Authors: Timo Sachsenberg $
// --------------------------------------------------------------------------
 
#pragma once
 
#include <OpenMS/FORMAT/SVOutStream.h>
#include <OpenMS/FORMAT/MzTabBase.h>
#include <OpenMS/KERNEL/StandardTypes.h>
#include <OpenMS/KERNEL/FeatureMap.h>
#include <OpenMS/KERNEL/ConsensusMap.h>
#include <OpenMS/CHEMISTRY/AASequence.h>
#include <OpenMS/METADATA/PeptideEvidence.h>
#include <OpenMS/METADATA/PeptideIdentificationList.h>
 
#include <optional>
 
#ifdef __clang__
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wnon-virtual-dtor"
#endif
 
namespace OpenMS
{
  class OPENMS_DLLAPI MzTabModification
  {
public:
    MzTabModification();
 
    bool isNull() const;
 
    void setNull(bool b);
 
    void setPositionsAndParameters(const std::vector<std::pair<Size, MzTabParameter> >& ppp);
 
    std::vector<std::pair<Size, MzTabParameter> > getPositionsAndParameters() const;
 
    void setModificationIdentifier(const MzTabString& mod_id);
 
    MzTabString getModOrSubstIdentifier() const;
 
    std::string toCellString() const;
 
    void fromCellString(const std::string& s);
 
    ~MzTabModification() = default;
protected:
    std::vector<std::pair<Size, MzTabParameter> > pos_param_pairs_;
    MzTabString mod_identifier_;
  };
 
  class OPENMS_DLLAPI MzTabModificationList
  {
public:
    bool isNull() const;
 
    void setNull(bool b);
 
    std::string toCellString() const;
 
    void fromCellString(const std::string& s);
 
    std::vector<MzTabModification> get() const;
 
    void set(const std::vector<MzTabModification>& entries);
 
    ~MzTabModificationList() = default;
protected:
    std::vector<MzTabModification> entries_;
  };
 
// MTD
  struct OPENMS_DLLAPI MzTabModificationMetaData
  {
    MzTabParameter modification;
    MzTabString site;
    MzTabString position;
  };
 
  struct OPENMS_DLLAPI MzTabAssayMetaData
  {
    MzTabParameter quantification_reagent;
    std::map<Size, MzTabModificationMetaData> quantification_mod;
    MzTabString sample_ref;
    std::vector<int> ms_run_ref; // adapted to address https://github.com/HUPO-PSI/mzTab/issues/26
  };
 
  struct OPENMS_DLLAPI MzTabMSRunMetaData
  {
    MzTabParameter format;
    MzTabString location;
    MzTabParameter id_format;
    MzTabParameterList fragmentation_method;
  };
 
  struct OPENMS_DLLAPI MzTabStudyVariableMetaData
  {
    std::vector<int> assay_refs;
    std::vector<int> sample_refs;
    MzTabString description;
  };
 
  class OPENMS_DLLAPI MzTabMetaData
  {
public:
    MzTabMetaData();
 
    MzTabString mz_tab_version;
    MzTabString mz_tab_mode;
    MzTabString mz_tab_type;
    MzTabString mz_tab_id;
    MzTabString title;
    MzTabString description;
 
    std::map<Size, MzTabParameter> protein_search_engine_score;
    std::map<Size, MzTabParameter> peptide_search_engine_score;
    std::map<Size, MzTabParameter> psm_search_engine_score;
    std::map<Size, MzTabParameter> smallmolecule_search_engine_score;
    std::map<Size, MzTabParameter> nucleic_acid_search_engine_score;
    std::map<Size, MzTabParameter> oligonucleotide_search_engine_score;
    std::map<Size, MzTabParameter> osm_search_engine_score;
 
    std::map<Size, MzTabParameterList> sample_processing;
 
    std::map<Size, MzTabInstrumentMetaData> instrument;
 
    std::map<Size, MzTabSoftwareMetaData> software;
 
    MzTabParameterList false_discovery_rate;
 
    std::map<Size, MzTabString> publication;
 
    std::map<Size, MzTabContactMetaData> contact;
 
    std::map<Size, MzTabString> uri;
 
    std::map<Size, MzTabModificationMetaData> fixed_mod;
 
    std::map<Size, MzTabModificationMetaData> variable_mod;
 
    MzTabParameter quantification_method;
 
    MzTabParameter protein_quantification_unit;
    MzTabParameter peptide_quantification_unit;
    MzTabParameter small_molecule_quantification_unit;
 
    std::map<Size, MzTabMSRunMetaData> ms_run;
 
    std::map<Size, MzTabParameter> custom;
 
    std::map<Size, MzTabSampleMetaData> sample;
 
    std::map<Size, MzTabAssayMetaData> assay;
 
    std::map<Size, MzTabStudyVariableMetaData> study_variable;
 
    std::map<Size, MzTabCVMetaData> cv;
 
    std::vector<std::string> colunit_protein;
    std::vector<std::string> colunit_peptide;
    std::vector<std::string> colunit_psm;
    std::vector<std::string> colunit_small_molecule;
  };
 
  struct OPENMS_DLLAPI MzTabProteinSectionRow
  {
    MzTabProteinSectionRow();
    MzTabString accession; 
    MzTabString description; 
    MzTabInteger taxid; 
    MzTabString species; 
    MzTabString database; 
    MzTabString database_version; 
    MzTabParameterList search_engine; 
    std::map<Size, MzTabDouble>  best_search_engine_score; 
    std::map<Size, std::map<Size, MzTabDouble> > search_engine_score_ms_run; 
    MzTabInteger reliability;
    std::map<Size, MzTabInteger> num_psms_ms_run;
    std::map<Size, MzTabInteger> num_peptides_distinct_ms_run;
    std::map<Size, MzTabInteger> num_peptides_unique_ms_run;
    MzTabStringList ambiguity_members; 
    MzTabModificationList modifications; 
    MzTabString uri; 
    MzTabStringList go_terms; 
    MzTabDouble coverage; 
    std::map<Size, MzTabDouble> protein_abundance_assay;
    std::map<Size, MzTabDouble> protein_abundance_study_variable;
    std::map<Size, MzTabDouble> protein_abundance_stdev_study_variable;
    std::map<Size, MzTabDouble> protein_abundance_std_error_study_variable;
    std::vector<MzTabOptionalColumnEntry> opt_; 
 
    struct RowCompare
    {
      bool operator()(const MzTabProteinSectionRow& row1,
                      const MzTabProteinSectionRow& row2) const
      {
        return row1.accession.get() < row2.accession.get();
      }
    };
  };
 
  struct OPENMS_DLLAPI MzTabPeptideSectionRow
  {
    MzTabString sequence; 
    MzTabString accession; 
    MzTabBoolean unique; 
    MzTabString database; 
    MzTabString database_version; 
    MzTabParameterList search_engine; 
    std::map<Size, MzTabDouble> best_search_engine_score; 
    std::map<Size, std::map<Size, MzTabDouble> > search_engine_score_ms_run;
    MzTabInteger reliability; 
    MzTabModificationList modifications; 
    MzTabDoubleList retention_time; 
    MzTabDoubleList retention_time_window;
    MzTabInteger charge; 
    MzTabDouble mass_to_charge; 
    MzTabString uri; 
    MzTabSpectraRef spectra_ref; 
    std::map<Size, MzTabDouble> peptide_abundance_assay;
    std::map<Size, MzTabDouble> peptide_abundance_study_variable;
    std::map<Size, MzTabDouble> peptide_abundance_stdev_study_variable;
    std::map<Size, MzTabDouble> peptide_abundance_std_error_study_variable;
    std::vector<MzTabOptionalColumnEntry> opt_; 
 
 
    struct RowCompare
    {
      bool operator()(const MzTabPeptideSectionRow& row1,
                      const MzTabPeptideSectionRow& row2) const
      {
        return (std::make_pair(row1.sequence.get(), row1.accession.get()) <
                std::make_pair(row2.sequence.get(), row2.accession.get()));
      }
    };
  };
 
  struct OPENMS_DLLAPI MzTabPSMSectionRow
  {
    MzTabString sequence; 
    MzTabInteger PSM_ID; 
    MzTabString accession; 
    MzTabBoolean unique; 
    MzTabString database; 
    MzTabString database_version; 
    MzTabParameterList search_engine; 
    std::map<Size, MzTabDouble> search_engine_score; 
    MzTabInteger reliability; 
    MzTabModificationList modifications; 
    MzTabDoubleList retention_time; 
    MzTabInteger charge; 
    MzTabDouble exp_mass_to_charge; 
    MzTabDouble calc_mass_to_charge; 
    MzTabString uri; 
    MzTabSpectraRef spectra_ref; 
    MzTabString pre; 
    MzTabString post; 
    MzTabString start; 
    MzTabString end; 
    std::vector<MzTabOptionalColumnEntry> opt_; 
 
    void addPepEvidenceToRows(const std::vector<PeptideEvidence>& peptide_evidences);
    struct RowCompare
    {
      bool operator()(const MzTabPSMSectionRow& row1,
                      const MzTabPSMSectionRow& row2) const
      {
        // @TODO: sort by "PSM_ID"? what's the point of that field?
        return (std::make_tuple(row1.sequence.get(),
                                row1.spectra_ref.getMSFile(),
                                row1.spectra_ref.getSpecRef(),
                                row1.accession.get()) <
                std::make_tuple(row2.sequence.get(),
                                row2.spectra_ref.getMSFile(),
                                row2.spectra_ref.getSpecRef(),
                                row2.accession.get()));
      }
    };
  };
 
  struct OPENMS_DLLAPI MzTabSmallMoleculeSectionRow
  {
    MzTabStringList identifier; 
    MzTabString chemical_formula; 
    MzTabString smiles; 
    MzTabString inchi_key; 
    MzTabString description; 
    MzTabDouble exp_mass_to_charge; 
    MzTabDouble calc_mass_to_charge; 
    MzTabInteger charge; 
    MzTabDoubleList retention_time; 
    MzTabInteger taxid; 
    MzTabString species; 
    MzTabString database; 
    MzTabString database_version; 
    MzTabInteger reliability; 
    MzTabString uri; 
    MzTabSpectraRef spectra_ref; 
    MzTabParameterList search_engine; 
    std::map<Size, MzTabDouble> best_search_engine_score; 
    std::map<Size, std::map<Size, MzTabDouble> > search_engine_score_ms_run;
    MzTabString modifications; 
    std::map<Size, MzTabDouble> smallmolecule_abundance_assay;
    std::map<Size, MzTabDouble> smallmolecule_abundance_study_variable;
    std::map<Size, MzTabDouble> smallmolecule_abundance_stdev_study_variable;
    std::map<Size, MzTabDouble> smallmolecule_abundance_std_error_study_variable;
    std::vector<MzTabOptionalColumnEntry> opt_; 
  };
 
  struct OPENMS_DLLAPI MzTabNucleicAcidSectionRow
  {
    MzTabString accession; 
    MzTabString description; 
    MzTabInteger taxid; 
    MzTabString species; 
    MzTabString database; 
    MzTabString database_version; 
    MzTabParameterList search_engine; 
    std::map<Size, MzTabDouble>  best_search_engine_score; 
    std::map<Size, std::map<Size, MzTabDouble> > search_engine_score_ms_run;
    MzTabInteger reliability;
    std::map<Size, MzTabInteger> num_osms_ms_run;
    std::map<Size, MzTabInteger> num_oligos_distinct_ms_run;
    std::map<Size, MzTabInteger> num_oligos_unique_ms_run;
    MzTabStringList ambiguity_members; 
    MzTabModificationList modifications; 
    MzTabString uri; 
    // do GO terms make sense for nucleic acid sequences?
    MzTabStringList go_terms; 
    MzTabDouble coverage; 
    std::vector<MzTabOptionalColumnEntry> opt_; 
 
    struct RowCompare
    {
      bool operator()(const MzTabNucleicAcidSectionRow& row1,
                      const MzTabNucleicAcidSectionRow& row2) const
      {
        return row1.accession.get() < row2.accession.get();
      }
    };
  };
 
  struct OPENMS_DLLAPI MzTabOligonucleotideSectionRow
  {
    MzTabString sequence; 
    MzTabString accession; 
    MzTabBoolean unique; 
    MzTabParameterList search_engine; 
    std::map<Size, MzTabDouble> best_search_engine_score; 
    std::map<Size, std::map<Size, MzTabDouble>> search_engine_score_ms_run; 
    MzTabInteger reliability; 
    MzTabModificationList modifications; 
    MzTabDoubleList retention_time; 
    MzTabDoubleList retention_time_window;
    MzTabString uri; 
    MzTabString pre;
    MzTabString post;
    MzTabInteger start;
    MzTabInteger end;
    std::vector<MzTabOptionalColumnEntry> opt_; 
 
    struct RowCompare
    {
      bool operator()(const MzTabOligonucleotideSectionRow& row1,
                      const MzTabOligonucleotideSectionRow& row2) const
        {
          return (std::make_tuple(row1.sequence.get(), row1.accession.get(),
                                  row1.start.get(), row1.end.get()) <
                  std::make_tuple(row2.sequence.get(), row2.accession.get(),
                                  row2.start.get(), row2.end.get()));
        }
    };
 
  };
 
  struct OPENMS_DLLAPI MzTabOSMSectionRow
  {
    MzTabString sequence; 
    MzTabParameterList search_engine; 
    std::map<Size, MzTabDouble> search_engine_score; 
    MzTabInteger reliability; 
    MzTabModificationList modifications; 
    MzTabDoubleList retention_time; 
    MzTabInteger charge; 
    MzTabDouble exp_mass_to_charge; 
    MzTabDouble calc_mass_to_charge; 
    MzTabString uri; 
    MzTabSpectraRef spectra_ref; 
    std::vector<MzTabOptionalColumnEntry> opt_; 
 
    struct RowCompare
    {
      bool operator()(const MzTabOSMSectionRow& row1,
                      const MzTabOSMSectionRow& row2) const
      {
        return (std::make_tuple(row1.sequence.get(),
                                row1.spectra_ref.getMSFile(),
                                row1.spectra_ref.getSpecRef()) <
                std::make_tuple(row2.sequence.get(),
                                row2.spectra_ref.getMSFile(),
                                row2.spectra_ref.getSpecRef()));
      }
    };
  };
 
  typedef std::vector<MzTabProteinSectionRow> MzTabProteinSectionRows;
  typedef std::vector<MzTabPeptideSectionRow> MzTabPeptideSectionRows;
  typedef std::vector<MzTabPSMSectionRow> MzTabPSMSectionRows;
  typedef std::vector<MzTabSmallMoleculeSectionRow> MzTabSmallMoleculeSectionRows;
  typedef std::vector<MzTabNucleicAcidSectionRow> MzTabNucleicAcidSectionRows;
  typedef std::vector<MzTabOligonucleotideSectionRow> MzTabOligonucleotideSectionRows;
  typedef std::vector<MzTabOSMSectionRow> MzTabOSMSectionRows;
 
  namespace Internal
  {
    struct MzTabStreamHelper; 
  }
 
  class OPENMS_DLLAPI MzTab : public MzTabBase
  {
    friend struct Internal::MzTabStreamHelper;
 
  public:
    MzTab() = default;
    ~MzTab() = default;
 
    const MzTabMetaData& getMetaData() const;
 
    void setMetaData(const MzTabMetaData& md);
 
    MzTabProteinSectionRows& getProteinSectionRows();
 
    const MzTabProteinSectionRows& getProteinSectionRows() const;
 
    void setProteinSectionRows(const MzTabProteinSectionRows& psd);
 
    MzTabPeptideSectionRows& getPeptideSectionRows();
 
    const MzTabPeptideSectionRows& getPeptideSectionRows() const;
 
    void setPeptideSectionRows(const MzTabPeptideSectionRows& psd);
 
    MzTabPSMSectionRows& getPSMSectionRows();
 
    const MzTabPSMSectionRows& getPSMSectionRows() const;
 
    size_t getNumberOfPSMs() const;
 
    void setPSMSectionRows(const MzTabPSMSectionRows& psd);
 
    const MzTabSmallMoleculeSectionRows& getSmallMoleculeSectionRows() const;
 
    void setSmallMoleculeSectionRows(const MzTabSmallMoleculeSectionRows& smsd);
 
    const MzTabNucleicAcidSectionRows& getNucleicAcidSectionRows() const;
 
    void setNucleicAcidSectionRows(const MzTabNucleicAcidSectionRows& nasd);
 
    const MzTabOligonucleotideSectionRows& getOligonucleotideSectionRows() const;
 
    void setOligonucleotideSectionRows(const MzTabOligonucleotideSectionRows& onsd);
 
    const MzTabOSMSectionRows& getOSMSectionRows() const;
 
    void setOSMSectionRows(const MzTabOSMSectionRows& osd);
 
    void setCommentRows(const std::map<Size, std::string>& com);
 
    void setEmptyRows(const std::vector<Size>& empty);
 
    const std::vector<Size>& getEmptyRows() const;
 
    const std::map<Size, std::string>& getCommentRows() const;
 
    std::vector<std::string> getProteinOptionalColumnNames() const;
 
    std::vector<std::string> getPeptideOptionalColumnNames() const;
 
    std::vector<std::string> getPSMOptionalColumnNames() const;
 
    std::vector<std::string> getSmallMoleculeOptionalColumnNames() const;
 
    std::vector<std::string> getNucleicAcidOptionalColumnNames() const;
 
    std::vector<std::string> getOligonucleotideOptionalColumnNames() const;
 
    static void addMetaInfoToOptionalColumns(const std::set<std::string>& keys, std::vector<MzTabOptionalColumnEntry>& opt, const std::string& id, const MetaInfoInterface& meta);
 
    std::vector<std::string> getOSMOptionalColumnNames() const;
 
    static std::map<Size, MzTabModificationMetaData> generateMzTabStringFromModifications(const std::vector<std::string>& mods);
 
    static std::map<Size, MzTabModificationMetaData> generateMzTabStringFromVariableModifications(const std::vector<std::string>& mods);
 
    static std::map<Size, MzTabModificationMetaData> generateMzTabStringFromFixedModifications(const std::vector<std::string>& mods);
 
    static MzTab exportFeatureMapToMzTab(const FeatureMap& feature_map, const std::string& filename);
 
    static MzTab exportIdentificationsToMzTab(
        const std::vector<ProteinIdentification>& prot_ids,
        const PeptideIdentificationList& peptide_ids,
        const std::string& filename,
        bool first_run_inference_only,
        bool export_empty_pep_ids = false,
        bool export_all_psms = false,
        const std::string& title = "ID export from OpenMS");
 
 
    static MzTabModificationList extractModificationList(const PeptideHit& pep_hit, const std::vector<std::string>& fixed_mods, const std::vector<std::string>& localization_mods);
 
    static MzTab exportConsensusMapToMzTab(
      const ConsensusMap& consensus_map,
      const std::string& filename,
      const bool first_run_inference_only,
      const bool export_unidentified_features,
      const bool export_unassigned_ids,
      const bool export_subfeatures,
      const bool export_empty_pep_ids = false,
      const bool export_all_psms = false,
      const std::string& title = "ConsensusMap export from OpenMS");
 
    class IDMzTabStream
    {
       public:
        IDMzTabStream(
          const std::vector<const ProteinIdentification*>& prot_ids,
          const std::vector<const PeptideIdentification*>& peptide_ids,
          const std::string& filename,
          bool first_run_inference_only,
          bool export_empty_pep_ids = false,
          bool export_all_psms = false,
          const std::string& title = "ID export from OpenMS");
 
         const MzTabMetaData& getMetaData() const;
 
         const std::vector<std::string>& getProteinOptionalColumnNames() const; 
         const std::vector<std::string>& getPeptideOptionalColumnNames() const;
         const std::vector<std::string>& getPSMOptionalColumnNames() const;
 
         bool nextPRTRow(MzTabProteinSectionRow& row);
         bool nextPEPRow(MzTabPeptideSectionRow& row);
         bool nextPSMRow(MzTabPSMSectionRow& row);
       private:
         friend struct Internal::MzTabStreamHelper;
 
         std::set<std::string> protein_hit_user_value_keys_;
         std::set<std::string> peptide_id_user_value_keys_;
         std::set<std::string> peptide_hit_user_value_keys_;
 
         // beautiful mapping structs
         std::map<Size, std::set<Size>> ind2prot_;
         std::map<Size, std::set<Size>> pg2prot_;
         std::map<std::string, size_t> idrunid_2_idrunindex_;
         std::map<Size, std::vector<std::pair<std::string, std::string>>> run_to_search_engines_;
         std::map<Size, std::vector<std::vector<std::pair<std::string, std::string>>>> run_to_search_engines_settings_;
         std::map<std::pair<size_t,size_t>,size_t> map_id_run_fileidx_2_msfileidx_;
         std::map<std::pair< std::string, unsigned >, unsigned> path_label_to_assay_;
 
         std::vector<const ProteinIdentification*> prot_ids_;
         std::vector<const PeptideIdentification*> peptide_ids_;
 
         StringList ms_runs_;
         bool first_run_inference_;
         std::string filename_;
         StringList fixed_mods_;
         /* currently unused
         bool export_unidentified_features_; 
         bool export_subfeatures_; */
         bool export_empty_pep_ids_;
         bool export_all_psms_;
         size_t quant_study_variables_ = 0;
         // size_t n_study_variables_ = 0; //currently unused
         size_t PRT_STATE_ = 0;
         size_t prt_run_id_ = 0; // current (protein) identification run
         size_t prt_hit_id_ = 0; // current protein in (protein) identification run
         size_t prt_group_id_ = 0;
         size_t prt_indistgroup_id_ = 0;
         size_t pep_id_ = 0;
         size_t psm_id_ = 0;
         size_t current_psm_idx_ = 0;
         MzTabString db_, db_version_;
 
         std::vector<std::string> prt_optional_column_names_;
         std::vector<std::string> pep_optional_column_names_;
         std::vector<std::string> psm_optional_column_names_;
 
         MzTabMetaData meta_data_;
    };
 
    class CMMzTabStream
    {
       public:
        CMMzTabStream(
          const ConsensusMap& consensus_map,
          const std::string& filename,
          const bool first_run_inference_only,
          const bool export_unidentified_features,
          const bool export_unassigned_ids,
          const bool export_subfeatures,
          const bool export_empty_pep_ids = false,
          const bool export_all_psms = false,
          const std::string& title = "ConsensusMap export from OpenMS");
 
         const MzTabMetaData& getMetaData() const;
 
         const std::vector<std::string>& getProteinOptionalColumnNames() const; 
         const std::vector<std::string>& getPeptideOptionalColumnNames() const;
         const std::vector<std::string>& getPSMOptionalColumnNames() const;
 
         bool nextPRTRow(MzTabProteinSectionRow& row);
         bool nextPEPRow(MzTabPeptideSectionRow& row);
         bool nextPSMRow(MzTabPSMSectionRow& row);
 
       private:
         friend struct Internal::MzTabStreamHelper;
 
         const ConsensusMap& consensus_map_;
         std::set<std::string> protein_hit_user_value_keys_;
         std::set<std::string> consensus_feature_user_value_keys_;
         std::set<std::string> consensus_feature_peptide_identification_user_value_keys_;
         std::set<std::string> consensus_feature_peptide_hit_user_value_keys_;
 
         // beautiful mapping structs
         std::map<Size, std::set<Size>> ind2prot_;
         std::map<Size, std::set<Size>> pg2prot_;
         std::map<std::string, size_t> idrunid_2_idrunindex_;
         std::map<Size, std::vector<std::pair<std::string, std::string>>> run_to_search_engines_;
         std::map<Size, std::vector<std::vector<std::pair<std::string, std::string>>>> run_to_search_engines_settings_;
         std::map<std::pair<size_t,size_t>,size_t> map_id_run_fileidx_2_msfileidx_;
         std::map<std::pair< std::string, unsigned >, unsigned> path_label_to_assay_;
         std::vector<std::pair<UInt, UInt>> assay_keys_;
         std::vector<Size> assay_to_study_variable_;
         std::vector<std::vector<Size>> study_variable_to_assays_;
 
         std::vector<const ProteinIdentification*> prot_ids_;
         std::vector<const PeptideIdentification*> peptide_ids_;
 
         StringList ms_runs_;
         bool first_run_inference_;
         std::string filename_;
         StringList fixed_mods_;
         bool export_unidentified_features_; 
         bool export_subfeatures_;
         bool export_empty_pep_ids_;
         bool export_all_psms_;
         size_t quant_study_variables_ = 0;
         size_t n_assays_ = 0;
         size_t n_study_variables_ = 0;
         size_t PRT_STATE_ = 0;
         size_t prt_run_id_ = 0; // current (protein) identification run
         size_t prt_hit_id_ = 0; // current protein in (protein) identification run
         size_t prt_group_id_ = 0;
         size_t prt_indistgroup_id_ = 0;
         size_t pep_id_ = 0;
         size_t pep_counter_ = 0;
         size_t psm_id_ = 0;
         size_t current_psm_idx_ = 0;
         MzTabString db_, db_version_;
 
         std::vector<std::string> prt_optional_column_names_;
         std::vector<std::string> pep_optional_column_names_;
         std::vector<std::string> psm_optional_column_names_;
 
         MzTabMetaData meta_data_;
    };
 
     
  protected:
    // extract basic mappings
 
    static std::map<std::string, Size> mapIDRunIdentifier2IDRunIndex_(const std::vector<const ProteinIdentification*>& prot_ids);
 
    static std::optional<MzTabPSMSectionRow> PSMSectionRowFromPeptideID_(
      PeptideIdentification const& pid,
      std::vector<ProteinIdentification const*> const& prot_id,
      std::map<std::string, size_t>& idrun_2_run_index,
      std::map<std::pair<size_t, size_t>, size_t>& map_run_fileidx_2_msfileidx,
      std::map<Size, std::vector<std::pair<std::string, std::string>>>& run_to_search_engines,
      Size const current_psm_idx,
      Size const psm_id,
      MzTabString const& db,
      MzTabString const& db_version,
      bool const export_empty_pep_ids,
      bool const export_all_psms);
 
    static MzTabPeptideSectionRow peptideSectionRowFromConsensusFeature_(
      const ConsensusFeature& c, 
      const ConsensusMap& consensus_map,
      const StringList& ms_runs,
      const Size n_assays,
      const Size n_study_variables,
      const std::set<std::string>& consensus_feature_user_value_keys,
      const std::set<std::string>& peptide_identifications_user_value_keys,
      const std::set<std::string>& peptide_hit_user_value_keys,
      const std::map<std::string, size_t>& idrun_2_run_index,
      const std::map<std::pair<size_t,size_t>,size_t>& map_run_fileidx_2_msfileidx,
      const std::map< std::pair< std::string, unsigned >, unsigned>& path_label_to_assay,
      const std::vector<Size>& assay_to_study_variable,
      const std::vector<std::vector<Size>>& study_variable_to_assays,
      const std::vector<std::string>& fixed_mods,
      bool export_subfeatures);
 
    static MzTabPeptideSectionRow peptideSectionRowFromFeature_(
      const Feature& c, 
      const std::set<std::string>& feature_user_value_keys,
      const std::set<std::string>& peptide_identifications_user_value_keys,
      const std::set<std::string>& peptide_hit_user_value_keys,
      const std::vector<std::string>& fixed_mods);
 
    static MzTabProteinSectionRow proteinSectionRowFromProteinHit_(
      const ProteinHit& hit,
      const MzTabString& db,
      const MzTabString& db_version,
      const std::set<std::string>& protein_hit_user_value_keys);
 
    static MzTabProteinSectionRow nextProteinSectionRowFromProteinGroup_(
      const ProteinIdentification::ProteinGroup& group,
      const MzTabString& db,
      const MzTabString& db_version);
 
    static MzTabProteinSectionRow nextProteinSectionRowFromIndistinguishableGroup_(
      const std::vector<ProteinHit>& protein_hits,
      const ProteinIdentification::ProteinGroup& group,
      const size_t g,
      const std::map<Size, std::set<Size>>& ind2prot,
      const MzTabString& db,
      const MzTabString& db_version);
 
    static void addMSRunMetaData_(
      const std::map<size_t, std::string>& msrunindex_2_msfilename,
      MzTabMetaData& meta_data);
 
    static void mapBetweenMSFileNameAndMSRunIndex_(
      const std::vector<const ProteinIdentification*>& prot_ids, 
      bool skip_first, 
      std::map<std::string, size_t>& msfilename_2_msrunindex,
      std::map<size_t, std::string>& msrunindex_2_msfilename);
 
    static size_t getQuantStudyVariables_(const ProteinIdentification& pid);
 
    static MzTabParameter getProteinScoreType_(const ProteinIdentification& prot_id);
 
    // TODO: move to core classes?
    static void getConsensusMapMetaValues_(const ConsensusMap& consensus_map, 
      std::set<std::string>& consensus_feature_user_value_keys,
      std::set<std::string>& peptide_identification_user_value_keys,
      std::set<std::string>& peptide_hit_user_value_keys);
 
    static void getFeatureMapMetaValues_(const FeatureMap& feature_map,
      std::set<std::string>& feature_user_value_keys,
      std::set<std::string>& peptide_identification_user_value_keys,
      std::set<std::string>& peptide_hit_user_value_keys);
 
    static void getIdentificationMetaValues_(
      const std::vector<const ProteinIdentification*>& prot_ids, 
      std::vector<const PeptideIdentification*>& peptide_ids_,
      std::set<std::string>& protein_hit_user_value_keys,
      std::set<std::string>& peptide_id_user_value_keys,
      std::set<std::string>& peptide_hit_user_value_keys);
 
    // determine spectrum reference identifier type (e.g., Thermo nativeID) from spectrum references
    static MzTabParameter getMSRunSpectrumIdentifierType_(const std::vector<const PeptideIdentification*>& peptide_ids_);
 
    static void mapBetweenRunAndSearchEngines_(
      const std::vector<const ProteinIdentification*>& prot_ids,
      const std::vector<const PeptideIdentification*>& pep_ids,
      bool skip_first_run,
      std::map<std::tuple<std::string, std::string, std::string>, std::set<Size>>& search_engine_to_runs,
      std::map<Size, std::vector<std::pair<std::string, std::string>>>& run_to_search_engines,
      std::map<Size, std::vector<std::vector<std::pair<std::string, std::string>>>>& run_to_search_engines_settings,
      std::map<std::string, std::vector<std::pair<std::string, std::string>>>& search_engine_to_settings);
 
    static std::map<Size, std::set<Size>> mapGroupsToProteins_(
      const std::vector<ProteinIdentification::ProteinGroup>& groups, 
      const std::vector<ProteinHit>& proteins);
 
    static void addSearchMetaData_(
        const std::vector<const ProteinIdentification*>& prot_ids,
        const std::map<std::tuple<std::string, std::string, std::string>, std::set<Size>>& search_engine_to_runs,
        const std::map<std::string, std::vector<std::pair<std::string, std::string>>>& search_engine_to_settings,
        MzTabMetaData& meta_data,
        bool first_run_inference_only);
 
    static void mapIDRunFileIndex2MSFileIndex_(
      const std::vector<const ProteinIdentification*>& prot_ids,
      const std::map<std::string, size_t>& msfilename_2_msrunindex,
      bool skip_first_run, 
      std::map<std::pair<size_t, size_t>, size_t>& map_run_fileidx_2_msfileidx);
 
    static void getSearchModifications_(
      const std::vector<const ProteinIdentification*>& prot_ids,
      StringList& var_mods, 
      StringList& fixed_mods);
 
    // create MzTab compatible modification identifier from ResidueModification
    // If the Modification has a unimod identifier it will be prefixed as UNIMOD
    // otherwise as CHEMMOD (see MzTab specification for details)
    static MzTabString getModificationIdentifier_(const ResidueModification& r);
 
    static void checkSequenceUniqueness_(const PeptideIdentificationList& curr_pep_ids);
 
    MzTabMetaData meta_data_;
    MzTabProteinSectionRows protein_data_;
    MzTabPeptideSectionRows peptide_data_;
    MzTabPSMSectionRows psm_data_;
    MzTabSmallMoleculeSectionRows small_molecule_data_;
    MzTabNucleicAcidSectionRows nucleic_acid_data_;
    MzTabOligonucleotideSectionRows oligonucleotide_data_;
    MzTabOSMSectionRows osm_data_; 
    std::vector<Size> empty_rows_; 
    std::map<Size, std::string> comment_rows_; 
  };
 
} // namespace OpenMS
#ifdef __clang__
  #pragma clang diagnostic pop
#endif