BasicProteinInferenceAlgorithm.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: Julianus Pfeuffer $
// $Authors: Julianus Pfeuffer $
// --------------------------------------------------------------------------
#pragma once
 
#include <OpenMS/DATASTRUCTURES/DefaultParamHandler.h>
#include <OpenMS/CONCEPT/ProgressLogger.h>
#include <OpenMS/METADATA/ProteinIdentification.h>
#include <OpenMS/METADATA/PeptideHit.h>
#include <OpenMS/KERNEL/ConsensusMap.h>
#include <OpenMS/ANALYSIS/ID/IDScoreSwitcherAlgorithm.h>
#include <OpenMS/METADATA/PeptideIdentificationList.h>
 
namespace OpenMS
{
 
  class OPENMS_DLLAPI BasicProteinInferenceAlgorithm :
    public DefaultParamHandler,
    public ProgressLogger
  {
    public:
 
    typedef std::unordered_map<std::string, std::map<Int, PeptideHit*>> SequenceToChargeToPSM;
 
    enum class AggregationMethod
    {
      PROD, 
      SUM, 
      BEST 
    };
 
    BasicProteinInferenceAlgorithm();
 
    void run(PeptideIdentificationList& pep_ids, std::vector<ProteinIdentification>& prot_ids) const;
 
    void run(PeptideIdentificationList& pep_ids, ProteinIdentification& prot_id) const;
 
    void run(ConsensusMap& cmap, ProteinIdentification& prot_id, bool include_unassigned) const;
 
    static void annotateIndistinguishableGroups(ProteinIdentification& proteins,
                                                const PeptideIdentificationList& peptides,
                                                Size use_top_psms = 1,
                                                bool add_singletons = true);
 
  private:
 
    void processRun_(
      std::unordered_map<std::string, std::pair<ProteinHit*, Size>>& acc_to_protein_hitP_and_count,
      SequenceToChargeToPSM& best_pep,
      ProteinIdentification& prot_run,
      PeptideIdentificationList& pep_ids) const;
 
    void aggregatePeptideScores_(
        SequenceToChargeToPSM& best_pep,
        PeptideIdentificationList& pep_ids,
        const std::string& overall_score_type,
        bool higher_better,
        const std::string& run_id) const;
 
    void updateProteinScores_(
        std::unordered_map<std::string, std::pair<ProteinHit*, Size>>& acc_to_protein_hitP_and_count,
        const SequenceToChargeToPSM& best_pep,
        bool pep_scores,
        bool higher_better) const;
 
    AggregationMethod aggFromString_(const std::string& method_string) const;
 
    void checkCompat_(
        const std::string& score_type,
        const AggregationMethod& aggregation_method
        ) const;
 
    void checkCompat_(
        const IDScoreSwitcherAlgorithm::ScoreType& score_type,
        const AggregationMethod& aggregation_method
        ) const;
 
    double getInitScoreForAggMethod_(const AggregationMethod& aggregation_method, bool higher_better) const;
 
    typedef double (*fptr)(double, double);
 
    fptr aggFunFromEnum_(const BasicProteinInferenceAlgorithm::AggregationMethod& agg_method, bool higher_better) const;
  };
} //namespace OpenMS