FalseDiscoveryRate.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: Chris Bielow $
// $Authors: Andreas Bertsch, Chris Bielow $
// --------------------------------------------------------------------------
 
#pragma once
 
#include <OpenMS/DATASTRUCTURES/DefaultParamHandler.h>
#include <OpenMS/METADATA/ID/IdentificationData.h>
#include <OpenMS/METADATA/PeptideIdentification.h>
#include <OpenMS/METADATA/ProteinIdentification.h>
#include <OpenMS/KERNEL/ConsensusMap.h>
 
#include <unordered_map>
 
#include <vector>
#include <unordered_set>
 
namespace OpenMS
{
 
  struct ScoreToTgtDecLabelPairs;
 
  class OPENMS_DLLAPI FalseDiscoveryRate :
    public DefaultParamHandler
  {
public:
    FalseDiscoveryRate();
 
    void apply(std::vector<PeptideIdentification>& fwd_ids, std::vector<PeptideIdentification>& rev_ids) const;
 
    void apply(std::vector<PeptideIdentification>& id, bool annotate_peptide_fdr = false) const;
 
    void apply(std::vector<ProteinIdentification>& fwd_ids, std::vector<ProteinIdentification>& rev_ids) const;
 
    void apply(std::vector<ProteinIdentification>& ids) const;
 
    void applyEstimated(std::vector<ProteinIdentification>& ids) const;
 
    double applyEvaluateProteinIDs(const std::vector<ProteinIdentification>& ids, double pepCutoff = 1.0, UInt fpCutoff = 50, double diffWeight = 0.2) const;
    double applyEvaluateProteinIDs(const ProteinIdentification& ids, double pepCutoff = 1.0, UInt fpCutoff = 50, double diffWeight = 0.2) const;
 
    double applyEvaluateProteinIDs(ScoreToTgtDecLabelPairs& score_to_tgt_dec_fraction_pairs, double pepCutoff = 1.0, UInt fpCutoff = 50, double diffWeight = 0.2) const;
 
    void applyBasic(const std::vector<ProteinIdentification> & run_info, std::vector<PeptideIdentification> & ids);
 
    void applyBasic(std::vector<PeptideIdentification> & ids, bool higher_score_better, int charge = 0, String identifier = "", bool only_best_per_pep = false);
    void applyBasicPeptideLevel(std::vector<PeptideIdentification> & ids);
    void applyBasicPeptideLevel(ConsensusMap & ids, bool use_unassigned_peptides = true);
    void applyBasic(ConsensusMap & cmap, bool use_unassigned_peptides = true);
    void applyBasic(ProteinIdentification & id, bool groups_too = true);
 
    void applyPickedProteinFDR(ProteinIdentification& id, String decoy_string = "", bool prefix = true, bool groups_too = true);
 
    double rocN(const std::vector<PeptideIdentification>& ids, Size fp_cutoff) const;
 
    double rocN(const std::vector<PeptideIdentification>& ids, Size fp_cutoff, const String& identifier) const;
 
    double rocN(const ConsensusMap& ids, Size fp_cutoff, bool include_unassigned_peptides = false) const;
 
    double rocN(const ConsensusMap& ids, Size fp_cutoff, const String& identifier, bool include_unassigned_peptides = false) const;
 
    //TODO the next two methods could potentially be merged for speed (they iterate over the same structure)
    //But since they have different cutoff types and it is more generic, I leave it like this.
    double diffEstimatedEmpirical(const ScoreToTgtDecLabelPairs& scores_labels, double pepCutoff = 1.0) const;
 
    double rocN(const ScoreToTgtDecLabelPairs& scores_labels, Size fpCutoff = 50) const;
 
    IdentificationData::ScoreTypeRef applyToObservationMatches(IdentificationData& id_data, IdentificationData::ScoreTypeRef score_ref) const;
 
    class DecoyStringHelper
    {
    public:
      struct Result
      {
        bool success; 
        String name; 
        bool is_prefix; 
      };
 
      static Result findDecoyString(const ProteinIdentification& proteins);
    };
private:
 
    FalseDiscoveryRate(const FalseDiscoveryRate&);
 
    FalseDiscoveryRate& operator=(const FalseDiscoveryRate&);
 
    void calculateFDRs_(std::map<double, double>& score_to_fdr, std::vector<double>& target_scores, std::vector<double>& decoy_scores, bool q_value, bool higher_score_better) const;
 
    void handleObservationMatch_(
        IdentificationData::ObservationMatchRef match_ref,
        IdentificationData::ScoreTypeRef score_ref,
        std::vector<double>& target_scores,
        std::vector<double>& decoy_scores,
        std::map<IdentificationData::IdentifiedMolecule, bool>& molecule_to_decoy,
        std::map<IdentificationData::ObservationMatchRef, double>& match_to_score) const;
 
    void calculateEstimatedQVal_(std::map<double, double> &scores_to_FDR,
                                 ScoreToTgtDecLabelPairs &scores_labels,
                                 bool higher_score_better) const;
 
    void calculateFDRBasic_(std::map<double,double>& scores_to_FDR, ScoreToTgtDecLabelPairs& scores_labels, bool qvalue, bool higher_score_better) const;
 
    double trapezoidal_area_xEqy(double exp1, double exp2, double act1, double act2) const;
 
    double trapezoidal_area(double x1, double x2, double y1, double y2) const;
  };
 
} // namespace OpenMS