DDAWorkflowCommons.h

Go to the documentation of this file.

// Copyright (c) 2002-present, The 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/CONCEPT/Exception.h>
#include <OpenMS/CONCEPT/LogStream.h>
#include <OpenMS/DATASTRUCTURES/StringUtils.h>
#include <OpenMS/DATASTRUCTURES/StringListUtils.h>
#include <OpenMS/SYSTEM/File.h>
#include <OpenMS/KERNEL/MSExperiment.h>
#include <OpenMS/FEATUREFINDER/MassTraceDetection.h>
#include <OpenMS/PROCESSING/FILTERING/ThresholdMower.h>
#include <OpenMS/PROCESSING/CALIBRATION/InternalCalibration.h>
#include <OpenMS/PROCESSING/CALIBRATION/MZTrafoModel.h>
#include <OpenMS/MATH/StatisticFunctions.h>
#include <OpenMS/FEATUREFINDER/FeatureFinderMultiplexAlgorithm.h>
 
#include <map>
#include <vector>
 
namespace OpenMS
{
    class OPENMS_DLLAPI DDAWorkflowCommons
    {
        public:
        /* @brief create Map between mzML file and corresponding id file
         * Checks implemented:
         *      - Check if the number of spectra and id files match.
         *      - If spectra and id files share common base names (without extension)
         *        but appear in different order, throw an error.
         *
         * @param[in] in <StringList> List of mzML file paths.
         * @param[in] in_ids <StringList> List of identification file paths.
         * @return <std::map<std::string, std::string>> A map where keys are mzML file paths and values are corresponding id file paths.
         * @throws Exception::InvalidParameter if the number of mzML files and identification files don't match
         * @throws Exception::MissingInformation if files share common base names but appear in different order
         * @note This mapping is crucial for linking raw data with identification results in DDA workflows.
         */
        static std::map<std::string, std::string> mapMzML2Ids(StringList & in, StringList & in_ids);
 
        static std::map<std::string, std::string> mapId2MzMLs(const std::map<std::string, std::string>& m2i);
 
        static double estimateMedianChromatographicFWHM(MSExperiment & ms_centroided);          
            
        static void recalibrateMS1(MSExperiment & ms_centroided,
            PeptideIdentificationList& peptide_ids,
            const std::string & id_file_abs_path = ""
        );
 
        static void calculateSeeds(
            const MSExperiment & ms_centroided, 
            const double intensity_threshold,
            FeatureMap & seeds, 
            double median_fwhm,
            Size charge_min = 2,
            Size charge_max = 5
        );
 
    };
 
}