PercolatorInfile.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/ANALYSIS/ID/PercolatorTypes.h>
#include <OpenMS/METADATA/PeptideIdentification.h>
#include <OpenMS/METADATA/PeptideIdentificationList.h>
#include <OpenMS/FORMAT/TextFile.h>
 
#include <map>
#include <set>
#include <utility>
#include <vector>
 
namespace OpenMS
{
 
  class OPENMS_DLLAPI PercolatorInfile
  {
    public:
      using PinFeatureMetaValueMap = std::map<std::pair<size_t, size_t>, std::set<std::string>>;
 
      static void store(const std::string& pin_file, 
        const PeptideIdentificationList& peptide_ids, 
        const StringList& feature_set, 
        const std::string& enz, 
        int min_charge, 
        int max_charge);
 
 
      static PeptideIdentificationList load(const std::string& pin_file, 
        bool higher_score_better, 
        const std::string& score_name, 
        const StringList& extra_scores,
        StringList& filenames, 
        std::string decoy_prefix = "",
        double threshold = 0.01, 
        bool SageAnnotation = false);
 
      // uses spectrum_reference, if empty uses spectrum_id, if also empty fall back to using index
      static std::string getScanIdentifier(const PeptideIdentification& pid, size_t index);
 
      static std::string getFileIdentifier(const PeptideIdentification& pid);
 
      static std::string getFileIdentifier(const PeptideIdentification& pid, UInt file_origin_index, UInt id_merge_index_index);
 
      static StringList getStandardFeatureSet(int min_charge, int max_charge);
 
      static StringList getPinColumnNames(int min_charge, int max_charge);
 
      static std::set<std::pair<size_t, size_t>> stampPinFeaturesOnHits(
        PeptideIdentificationList& peptide_ids,
        const std::string& enz,
        int min_charge,
        int max_charge);
 
      static std::set<std::pair<size_t, size_t>> stampPinFeaturesOnHits(
        PeptideIdentificationList& peptide_ids,
        const std::string& enz,
        int min_charge,
        int max_charge,
        PinFeatureMetaValueMap& added_meta_values);
 
      static double getFeatureValue(const DataValue& value, const std::string& feature);
 
      static Size buildFeatureMatrix(const PeptideIdentificationList& peptide_ids,
        const StringList& features,
        const std::string& enz,
        int min_charge,
        int max_charge,
        RescoreInput& input,
        std::vector<std::pair<size_t, size_t>>& rows);
 
      static void refreshPinMetaValues(PeptideIdentificationList& peptide_ids,
        const std::string& enz,
        int min_charge,
        int max_charge);
 
    protected:
      enum PinColumn_ : int
      {
        PIN_SPEC_ID, PIN_SCAN_NR, PIN_LABEL, PIN_CALC_MASS, PIN_EXP_MASS, PIN_DELTAMASS, PIN_RETENTIONTIME, PIN_MASS,
        PIN_SCORE, PIN_PEPLEN, PIN_ENZ_N, PIN_ENZ_C, PIN_ENZ_INT, PIN_DM, PIN_ABSDM, PIN_PEPTIDE, PIN_PROTEINS,
        PIN_CHARGE
      };
 
      enum PinLookup_ : int { LOOKUP_CALC_MASS, LOOKUP_ISOTOPE_ERROR_LEGACY, LOOKUP_ISOTOPE_ERROR };
 
      static void warnWithoutScanNumber_(const std::vector<std::string>& without_scan, const std::vector<char>& stamped);
 
      struct PinEnzyme_;
 
      template <bool with_strings, typename Exists, typename Get, typename Put>
      static double pinHitColumns_(const PeptideHit& hit, bool decoy, const std::string& spec_id, Int scan_number,
        double exp_mass, double retention_time, const PinEnzyme_& enz, int min_charge, int max_charge,
        Exists&& exists, Get&& get, Put&& put);
 
      //id <tab> label <tab> scannr <tab> calcmass <tab> expmass <tab> feature1 <tab> ... <tab> featureN <tab> peptide <tab> proteinId1 <tab> .. <tab> proteinIdM
      static TextFile preparePin_(
        const PeptideIdentificationList& peptide_ids, 
        const StringList& feature_set, 
        const std::string& enz, 
        int min_charge, 
        int max_charge);
 
      static bool isEnz_(const char& n, const char& c, const std::string& enz);
 
      static Size countEnzymatic_(const std::string& peptide, const std::string& enz);
 
  };
} // namespace OpenMS