QPXDatasetExport.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/config.h>
#include <OpenMS/FORMAT/ArrowIOHelpers.h>
#include <OpenMS/METADATA/PeptideHit.h>
 
#include <map>
#include <set>
#include <memory>
#include <optional>
#include <string>
#include <utility>
#include <vector>
 
namespace OpenMS
{
  class MSExperiment;
  class MSSpectrum;
  class Param;
  class PeptideIdentificationList;
 
class OPENMS_DLLAPI QPXDatasetExport
{
public:
  using Column = ArrowIOHelpers::ParquetColumn;
 
  static std::string scoreName(const std::string& name);
 
  static std::vector<Column> psmColumns(const PeptideIdentificationList& peptide_ids,
                                        const std::vector<bool>& has_spectrum,
                                        bool isotope_observed_minus_theoretical);
 
  struct PeakFilter
  {
    double window = 100.0;
    Size top = 100;
    bool deisotoped = false;
    int max_charge = 3;
    bool cap_at_precursor = true;
  };
 
  static std::vector<Size> keptPeaks(const MSSpectrum& spectrum, const std::vector<PeptideHit::PeakAnnotation>& annotations,
                                     int precursor_charge, const PeakFilter& filter);
 
  struct MzView
  {
    std::shared_ptr<arrow::Table> table;
    std::vector<bool> has_spectrum;
    Size without_spectrum = 0;
    Size unresolved = 0;
    Size peaks_read = 0;
    Size peaks_kept = 0;
  };
 
  static MzView mzView(const MSExperiment& spectra, const PeptideIdentificationList& peptide_ids,
                       const std::string& run_file_name, const PeakFilter& filter);
 
  struct RunSample
  {
    std::string accession;
    std::string label = "LFQ";
    std::optional<Int32> biological_replicate;
    std::optional<Int32> technical_replicate;
  };
 
  struct Run
  {
    std::string accession;
    std::string run_file_name;
    std::string file_name;
    std::vector<RunSample> samples;
    std::optional<std::string> fraction;
    std::optional<std::string> instrument;
    std::optional<std::string> dissociation_method;
    std::optional<std::string> acquisition_method;
    std::vector<std::string> enzymes;
    std::vector<std::string> fixed_modifications;
    std::vector<std::string> variable_modifications;
  };
 
  struct Sample
  {
    std::string accession;
    std::string organism = "not available";
    std::string organism_part = "not available";
  };
 
  struct ProvenanceStep
  {
    std::string category;
    std::string name;
    std::string tool;
    std::vector<std::pair<std::string, std::string>> parameters;
    std::string config;
    std::vector<std::string> output_views;
  };
 
  static std::shared_ptr<arrow::Table> runView(const std::vector<Run>& runs);
 
  static std::shared_ptr<arrow::Table> sampleView(const std::vector<Sample>& samples);
 
  static std::shared_ptr<arrow::Table> provenanceView(const std::vector<ProvenanceStep>& steps);
 
  static std::string paramToJSON(const Param& param);
 
  static std::string formatNumber(double value, const std::string& non_finite = "null");
 
  struct View
  {
    std::vector<std::shared_ptr<arrow::Table>> tables;
    ParquetWriteConfig config;
    std::map<std::string, std::string> metadata;
  };
 
  static bool writeDataset(const std::string& directory, const std::string& prefix,
                           const std::map<std::string, View>& views, std::set<std::string>* failed = nullptr);
};
 
} // namespace OpenMS