PeptDeepRescoring.h

Go to the documentation of this file.

// Copyright (c) 2002-present, OpenMS Team -- EKU Tuebingen, ETH Zurich, and FU Berlin
// SPDX-License-Identifier: BSD-3-Clause
//
// --------------------------------------------------------------------------
// $Maintainer: Timo Sachsenberg $
// $Authors: Timo Sachsenberg $
// --------------------------------------------------------------------------
 
#pragma once
 
#include <OpenMS/config.h>
#include <OpenMS/CONCEPT/ProgressLogger.h>
#include <OpenMS/DATASTRUCTURES/DefaultParamHandler.h>
#include <OpenMS/DATASTRUCTURES/ListUtils.h>
#include <OpenMS/KERNEL/StandardTypes.h>
 
#include <map>
#include <string>
#include <vector>
 
namespace OpenMS
{
  class PeptideIdentificationList;
  class ProteinIdentification;
  class PeptDeepMS2Inference;
  class PeptDeepRTInference;
 
  class OPENMS_DLLAPI PeptDeepRescoring :
    public DefaultParamHandler,
    public ProgressLogger
  {
  public:
    PeptDeepRescoring();
 
    ~PeptDeepRescoring() override;
 
    static StringList featureNames();
 
    static constexpr const char* NCE_META_VALUE = "peptdeep_nce";
 
    void annotate(const PeakMap& spectra,
                  std::vector<ProteinIdentification>& protein_ids,
                  PeptideIdentificationList& peptide_ids);
 
    void selectNCE(const PeakMap& spectra,
                   std::vector<ProteinIdentification>& protein_ids,
                   const PeptideIdentificationList& peptide_ids);
 
    void selectNCE(const PeakMap& spectra,
                   std::vector<ProteinIdentification>& protein_ids,
                   const PeptideIdentificationList& peptide_ids,
                   PeptDeepMS2Inference& ms2_inference);
 
    double getUsedNCE() const;
 
    double getRTCalibrationError() const;
 
    Size getNumPSMs() const;
 
    Size getNumPredictedPSMs() const;
 
  protected:
    void updateMembers_() override;
 
    struct Row
    {
      Size pi;      
      Size hit;     
      Size len;     
      Size key;     
      double score; 
      bool calibration_candidate; 
    };
 
    struct PSMRows
    {
      std::vector<Row> rows;
      std::vector<std::string> uniq_seq;
      std::vector<float> uniq_charge;
      std::map<std::string, std::vector<Size>> rows_by_run;
    };
 
    bool startCall_(const PeptideIdentificationList& peptide_ids, const StringList& models, const std::string& what);
 
    void selectNCE_(const PeakMap& spectra,
                    std::vector<ProteinIdentification>& protein_ids,
                    const PeptideIdentificationList& peptide_ids,
                    PeptDeepMS2Inference& ms2_inference);
 
    static PSMRows gatherPSMs_(const PeptideIdentificationList& peptide_ids);
 
    static std::map<std::string, double> collisionEnergies_(const PeakMap& spectra);
 
    std::vector<Size> confidentRows_(const std::vector<Row>& rows, const std::vector<Size>& run_rows, bool higher_better) const;
 
    double selectRunNCE_(const std::map<std::string, double>& collision_energies,
                         const PeptideIdentificationList& peptide_ids,
                         const PSMRows& psms,
                         const std::vector<Size>& run_rows,
                         const std::vector<Size>& confident,
                         PeptDeepMS2Inference& ms2_inference,
                         double& centre,
                         double& median_cosine);
 
    static void storeNCE_(std::vector<ProteinIdentification>& protein_ids, const std::map<std::string, double>& nce_by_run);
 
    void annotateRun_(const std::string& run_id,
                      const std::map<std::string, double>& collision_energies,
                      PeptideIdentificationList& peptide_ids,
                      const PSMRows& psms,
                      const std::vector<Size>& run_rows,
                      bool higher_better,
                      PeptDeepMS2Inference& ms2_inference,
                      PeptDeepRTInference& rt_inference);
 
    std::string ms2_model_;
    std::string rt_model_;
    double nce_{-1.0};
    double nce_grid_halfwidth_{6.0};
    double nce_grid_step_{2.0};
    double nce_fallback_{30.0};
    Size nce_sample_size_{2000};
    std::string instrument_;
    double calibration_quantile_{0.5};
    std::string rt_model_type_{"b_spline"};
    Size rt_num_nodes_{5};
    int ms2_min_ordinal_{1};
    double ms2_strong_fraction_{0.05};
    Size batch_size_{64};
    Int threads_{4};
 
    double used_nce_{-1.0};
    double rt_calibration_error_{-1.0};
    Size num_psms_{0};
    Size num_predicted_psms_{0};
  };
 
} // namespace OpenMS