XFDRAlgorithm.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: Eugen Netz $
// $Authors: Lukas Zimmermann, Eugen Netz $
// --------------------------------------------------------------------------
 
#pragma once
 
#include <OpenMS/CONCEPT/ProgressLogger.h>
#include <OpenMS/DATASTRUCTURES/DefaultParamHandler.h>
#include <OpenMS/KERNEL/StandardTypes.h>
#include <OpenMS/METADATA/PeptideIdentification.h>
#include <OpenMS/METADATA/PeptideIdentificationList.h>
#include <OpenMS/METADATA/PeptideHit.h>
#include <OpenMS/METADATA/ProteinIdentification.h>
#include <OpenMS/MATH/STATISTICS/Histogram.h>
#include <cassert>
 
namespace OpenMS
{
 
  //-------------------------------------------------------------
  // Doxygen docu
  //-------------------------------------------------------------
 
  class OPENMS_DLLAPI XFDRAlgorithm :
  public DefaultParamHandler, public ProgressLogger
  {
 
  public:
 
    enum class ExitCodes
    {
      EXECUTION_OK,
      ILLEGAL_PARAMETERS,
      UNEXPECTED_RESULT
    };
 
    XFDRAlgorithm();
 
    ~XFDRAlgorithm() override;
 
    ExitCodes run(PeptideIdentificationList& peptide_ids, ProteinIdentification& protein_id);
 
    ExitCodes validateClassArguments() const;
 
private:
    void updateMembers_() override;
 
    void initDataStructures_(PeptideIdentificationList& peptide_ids, ProteinIdentification& protein_id);
 
    static void assignTypes_(PeptideHit& pep_id, StringList& types);
 
    void fdr_xprophet_(std::map< std::string, Math::Histogram<> >& cum_histograms,
                      const std::string& targetclass, const std::string& decoyclass, const std::string& fulldecoyclass,
                      std::vector< double >& fdr, bool mono) const;
 
    static void calc_qfdr_(const std::vector< double >& fdr, std::vector< double >& qfdr);
 
    void findTopUniqueHits_(PeptideIdentificationList& peptide_ids);
 
    void writeArgumentsLog_() const;
 
    std::string getId_(const PeptideHit& ph) const;
 
    static Size getMinIonsMatched_(const PeptideHit& ph)
    {
      Size alpha_ions = Size(ph.getMetaValue("matched_linear_alpha")) + Size(ph.getMetaValue("matched_xlink_alpha"));
      Size beta_ions = Size(ph.getMetaValue("matched_linear_beta")) + Size(ph.getMetaValue("matched_xlink_beta"));
      return std::min(alpha_ions, beta_ions);
    }
 
    inline static void setIntraProtein_(PeptideHit& ph, const bool value)
    {
      ph.setMetaValue("XFDR:is_intraprotein", DataValue(value ? "true" : "false"));
    }
 
    inline static void setInterProtein_(PeptideHit& ph, const bool value)
    {
      ph.setMetaValue("XFDR:is_interprotein", DataValue(value ? "true" : "false"));
    }
 
    static bool isSameProtein_(
            std::string prot1,
            std::string prot2,
            const std::string &decoy_string)
    {
      StringUtils::substitute(prot1, decoy_string, "");
      StringUtils::substitute(prot2, decoy_string, "");
      assert( ! StringUtils::hasSubstring(prot1, decoy_string));
      assert( ! StringUtils::hasSubstring(prot2, decoy_string));
      return prot1 == prot2;
    }
 
    // Score range for this of the tool
    Int min_score_;
    Int max_score_;
 
    // unique top hits
    std::vector<std::string> unique_ids_;
    std::vector<double> unique_id_scores_;
 
    // maps index of peptide id all_pep_ids_ to vector of cross link class
    std::map<std::string, std::vector<std::string>> cross_link_classes_;
 
    // Program arguments
    std::string decoy_string_;
    double arg_mindeltas_;
    double arg_minborder_;
    double arg_maxborder_;
    Int arg_minionsmatched_;
    double arg_minscore_;
    bool arg_uniquex_;
    bool arg_no_qvalues_;
    double arg_binsize_;
 
    // Names of the class parameters
    static const std::string param_decoy_string_;
    static const std::string param_minborder_;
    static const std::string param_maxborder_;
    static const std::string param_mindeltas_;
    static const std::string param_minionsmatched_;
    static const std::string param_uniquexl_;
    static const std::string param_no_qvalues_;
    static const std::string param_minscore_;
    static const std::string param_binsize_;
 
    // Constants related to particular crosslink classes
    static const std::string crosslink_class_intradecoys_;
    static const std::string crosslink_class_fulldecoysintralinks_;
    static const std::string crosslink_class_interdecoys_;
    static const std::string crosslink_class_fulldecoysinterlinks_;
    static const std::string crosslink_class_monodecoys_;
    static const std::string crosslink_class_intralinks_;
    static const std::string crosslink_class_interlinks_;
    static const std::string crosslink_class_monolinks_;
    static const std::string crosslink_class_decoys_;
    static const std::string crosslink_class_targets_;
    static const std::string crosslink_class_hybriddecoysintralinks_;
    static const std::string crosslink_class_hybriddecoysinterlinks_;
  };
}