QPXFile.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/CONCEPT/Types.h>
#include <OpenMS/METADATA/ProteinIdentification.h>
#include <OpenMS/METADATA/PeptideIdentification.h>
#include <OpenMS/METADATA/PeptideIdentificationList.h>
#include <OpenMS/FORMAT/MSExperimentArrowExport.h>
#include <OpenMS/FORMAT/QPXIdentity.h>
 
#include <memory>
#include <vector>
 
// Forward declarations
namespace arrow
{
  class Table;
}
 
namespace OpenMS
{
 
class OPENMS_DLLAPI QPXFile
{
public:
  static std::shared_ptr<arrow::Table> exportToArrow(
    const std::vector<ProteinIdentification>& protein_identifications,
    const PeptideIdentificationList& peptide_identifications,
    bool export_all_psms = false);
 
  static std::shared_ptr<arrow::Table> exportPSMsToQPXArrow(
    const std::vector<ProteinIdentification>& protein_identifications,
    const PeptideIdentificationList& peptide_identifications,
    bool export_all_psms = false,
    const QPXIdentity::FeatureLinks* feature_links = nullptr);
 
  static bool exportToParquet(
    const std::vector<ProteinIdentification>& protein_identifications,
    const PeptideIdentificationList& peptide_identifications,
    const std::string& filename,
    bool export_all_psms = false,
    const ParquetWriteConfig& config = ParquetWriteConfig{},
    const QPXIdentity::FeatureLinks* feature_links = nullptr);
 
  static bool exportToParquet(
    const std::shared_ptr<arrow::Table>& table,
    const std::string& filename,
    const ParquetWriteConfig& config = ParquetWriteConfig{},
    const std::string& scan_format = "");
 
  static bool exportToParquetStreaming(
    const std::vector<ProteinIdentification>& protein_identifications,
    const std::vector<const PeptideIdentification*>& peptide_identification_ptrs,
    const std::string& filename,
    bool export_all_psms = false,
    size_t batch_size = 1000000,
    const ParquetWriteConfig& config = ParquetWriteConfig{},
    int n_threads = 1,
    const QPXIdentity::FeatureLinks* feature_links = nullptr);
 
  static void requireResolvableMergeIndices(
    const std::vector<ProteinIdentification>& protein_identifications,
    const PeptideIdentificationList& peptide_identifications);
 
  static void requireResolvableMergeIndices(
    const std::vector<ProteinIdentification>& protein_identifications,
    const std::vector<const PeptideIdentification*>& peptide_identifications);
 
  static bool importFromArrow(
    const std::shared_ptr<arrow::Table>& table,
    std::vector<ProteinIdentification>& protein_identifications,
    PeptideIdentificationList& peptide_identifications);
};
 
} // namespace OpenMS