InspectOutfile.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: Martin Langwisch $
// --------------------------------------------------------------------------
 
#pragma once
 
#include <OpenMS/CONCEPT/Exception.h>
#include <OpenMS/DATASTRUCTURES/StringUtils.h>
#include <OpenMS/KERNEL/MSExperiment.h>
#include <OpenMS/KERNEL/StandardTypes.h>
#include <OpenMS/METADATA/PeptideIdentification.h>
#include <OpenMS/METADATA/PeptideIdentificationList.h>
#include <OpenMS/FORMAT/FileHandler.h>
#include <OpenMS/FORMAT/FileTypes.h>
 
 
namespace OpenMS
{
  class OPENMS_DLLAPI InspectOutfile
  {
public:
    InspectOutfile();
 
    InspectOutfile(const InspectOutfile & inspect_outfile);
 
    virtual ~InspectOutfile();
 
    InspectOutfile & operator=(const InspectOutfile & inspect_outfile);
 
    bool operator==(const InspectOutfile & inspect_outfile) const;
 
    std::vector<Size> load(const std::string & result_filename, PeptideIdentificationList & peptide_identifications, ProteinIdentification & protein_identification, const double p_value_threshold, const std::string & database_filename = "");
 
    std::vector<Size> getWantedRecords(const std::string & result_filename, double p_value_threshold);
 
    void compressTrieDB(const std::string & database_filename, const std::string & index_filename, std::vector<Size> & wanted_records, const std::string & snd_database_filename, const std::string & snd_index_filename, bool append = false);
 
    void generateTrieDB(const std::string & source_database_filename, const std::string & database_filename, const std::string & index_filename, bool append = false, const std::string& species = "");
 
 
    void getACAndACType(std::string line, std::string &accession, std::string &accession_type);
 
    void getPrecursorRTandMZ(const std::vector<std::pair<std::string, std::vector<std::pair<Size, Size> > > > & files_and_peptide_identification_with_scan_number, PeptideIdentificationList & ids);
 
    void getLabels(const std::string & source_database_filename, std::string &ac_label, std::string &sequence_start_label, std::string &sequence_end_label, std::string &comment_label, std::string &species_label);
 
    std::vector<Size> getSequences(const std::string & database_filename, const std::map<Size, Size> & wanted_records, std::vector<std::string> & sequences);
 
    void getExperiment(PeakMap & exp, std::string &type, const std::string & in_filename)
    {
      type.clear();
      exp.reset();
      //input file type
      FileHandler fh;
      FileTypes::Type in_type = fh.getTypeByContent(in_filename);
      if (in_type == FileTypes::UNKNOWN)
      {
        throw Exception::ParseError(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION, "Could not determine type of the file. Aborting!", in_filename);
      }
      type = FileTypes::typeToName(in_type);
      fh.loadExperiment(in_filename, exp, {in_type});
    }
 
    bool getSearchEngineAndVersion(const std::string & cmd_output, ProteinIdentification & protein_identification);
 
    void readOutHeader(const std::string & filename, const std::string & header_line, Int & spectrum_file_column, Int & scan_column, Int & peptide_column, Int & protein_column, Int & charge_column, Int & MQ_score_column, Int & p_value_column, Int & record_number_column, Int & DB_file_pos_column, Int & spec_file_pos_column, Size & number_of_columns);
 
protected:
    static const Size db_pos_length_;         
    static const Size trie_db_pos_length_;         
    static const Size protein_name_length_;         
    static const Size record_length_;         
    static const char trie_delimiter_;         
    static const std::string score_type_;        
  };
 
} //namespace OpenMS