ProteinIdentificationArrowIO.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/PeptideIdentificationList.h>
#include <OpenMS/FORMAT/MSExperimentArrowExport.h>
 
#include <map>
#include <memory>
#include <vector>
 
// Forward declarations
namespace arrow
{
  class Table;
}
 
namespace OpenMS
{
 
class OPENMS_DLLAPI ProteinIdentificationArrowIO
{
public:
  // ==================== Export methods ====================
 
  static std::shared_ptr<arrow::Table> exportProteinsToArrow(
    const std::vector<ProteinIdentification>& protein_identifications);
 
  static bool exportProteinsToParquet(
    const std::vector<ProteinIdentification>& protein_identifications,
    const std::string& filename,
    const ParquetWriteConfig& config = ParquetWriteConfig{});
 
  static std::shared_ptr<arrow::Table> exportProteinGroupsToArrow(
    const std::vector<ProteinIdentification>& protein_identifications);
 
  static bool exportProteinGroupsToParquet(
    const std::vector<ProteinIdentification>& protein_identifications,
    const std::string& filename,
    const ParquetWriteConfig& config = ParquetWriteConfig{});
 
  static std::shared_ptr<arrow::Table> exportSearchParamsToArrow(
    const std::vector<ProteinIdentification>& protein_identifications);
 
  static bool exportSearchParamsToParquet(
    const std::vector<ProteinIdentification>& protein_identifications,
    const std::string& filename,
    const ParquetWriteConfig& config = ParquetWriteConfig{});
 
  // ==================== Import methods ====================
 
  static bool importFromParquet(
    const std::string& proteins_filename,
    const std::string& protein_groups_filename,
    const std::string& search_params_filename,
    std::vector<ProteinIdentification>& protein_identifications);
 
  static bool importSearchParamsFromArrow(
    const std::shared_ptr<arrow::Table>& table,
    std::vector<ProteinIdentification>& protein_identifications);
 
  static bool importProteinsFromArrow(
    const std::shared_ptr<arrow::Table>& table,
    std::vector<ProteinIdentification>& protein_identifications);
 
  static bool importProteinGroupsFromArrow(
    const std::shared_ptr<arrow::Table>& table,
    std::vector<ProteinIdentification>& protein_identifications);
 
  static bool importSearchParamsFromParquet(
    const std::string& filename,
    std::vector<ProteinIdentification>& protein_identifications);
 
  static bool importProteinsFromParquet(
    const std::string& filename,
    std::vector<ProteinIdentification>& protein_identifications);
 
  static bool importProteinGroupsFromParquet(
    const std::string& filename,
    std::vector<ProteinIdentification>& protein_identifications);
 
  // ==================== Identifier handling parity with XML lane ====================
 
  static std::map<std::string, std::string> synthesizeRunIdentifiers(
    std::vector<ProteinIdentification>& protein_identifications);
 
  static void applyRunIdentifierRename(
    const std::map<std::string, std::string>& rename,
    PeptideIdentificationList& pep_ids);
 
  static void checkUniqueIdentifiers(
    const std::vector<ProteinIdentification>& protein_identifications);
};
 
} // namespace OpenMS