void registerOptionsAndFlags_()
{
registerInputFile_("id", "<file>", "", "Protein/peptide identifications file");
setValidFormats_("id", ListUtils::create<String>("mzid,idXML"));
registerInputFile_("in", "<file>", "", "Feature map/consensus map file");
setValidFormats_("in", ListUtils::create<String>("featureXML,consensusXML,mzq"));
registerOutputFile_("out", "<file>", "", "Output file (the format depends on the input file format).");
setValidFormats_("out", ListUtils::create<String>("featureXML,consensusXML,mzq"));
addEmptyLine_();
IDMapper mapper;
Param p = mapper.getParameters();
registerDoubleOption_("rt_tolerance", "<value>", p.getValue("rt_tolerance"), "RT tolerance (in seconds) for the matching of peptide identifications and (consensus) features.\nTolerance is understood as 'plus or minus x', so the matching range increases by twice the given value.", false);
setMinFloat_("rt_tolerance", 0.0);
registerDoubleOption_("mz_tolerance", "<value>", p.getValue("mz_tolerance"), "m/z tolerance (in ppm or Da) for the matching of peptide identifications and (consensus) features.\nTolerance is understood as 'plus or minus x', so the matching range increases by twice the given value.", false);
setMinFloat_("mz_tolerance", 0.0);
registerStringOption_("mz_measure", "<choice>", p.getEntry("mz_measure").valid_strings[0], "Unit of 'mz_tolerance'.", false);
setValidStrings_("mz_measure", p.getEntry("mz_measure").valid_strings);
registerStringOption_("mz_reference", "<choice>", p.getEntry("mz_reference").valid_strings[0], "Source of m/z values for peptide identifications. If 'precursor', the precursor-m/z from the idXML is used. If 'peptide',\nmasses are computed from the sequences of peptide hits; in this case, an identification matches if any of its hits matches.\n('peptide' should be used together with 'feature:use_centroid_mz' to avoid false-positive matches.)", false);
setValidStrings_("mz_reference", p.getEntry("mz_reference").valid_strings);
registerFlag_("ignore_charge", "For feature/consensus maps: Assign an ID independently of whether its charge state matches that of the (consensus) feature.");
addEmptyLine_();
registerTOPPSubsection_("feature", "Additional options for featureXML input");
registerFlag_("feature:use_centroid_rt", "Use the RT coordinates of the feature centroids for matching, instead of the RT ranges of the features/mass traces.");
registerFlag_("feature:use_centroid_mz", "Use the m/z coordinates of the feature centroids for matching, instead of the m/z ranges of the features/mass traces.\n(If you choose 'peptide' as 'mz_reference', you should usually set this flag to avoid false-positive matches.)");
addEmptyLine_();
registerTOPPSubsection_("consensus", "Additional options for consensusXML input");
registerFlag_("consensus:use_subelements", "Match using RT and m/z of sub-features instead of consensus RT and m/z. A consensus feature matches if any of its sub-features matches.");
registerFlag_("consensus:annotate_ids_with_subelements", "Store the map index of the sub-feature in the peptide ID.", true);
}
ExitCodes main_(int, const char**)
{
// LOG_DEBUG << "Starting..." << endl;
//----------------------------------------------------------------
// load ids
//----------------------------------------------------------------
// LOG_DEBUG << "Loading idXML..." << endl;
String id = getStringOption_("id");
vector<ProteinIdentification> protein_ids;
vector<PeptideIdentification> peptide_ids;
FileTypes::Type in_type = FileHandler::getType(id);
if (in_type == FileTypes::IDXML)
{
IdXMLFile().load(id, protein_ids, peptide_ids);
}
else if (in_type == FileTypes::MZIDENTML)
{
MzIdentMLFile().load(id, protein_ids, peptide_ids);
}
else
{
throw Exception::IllegalArgument(__FILE__, __LINE__,
__PRETTY_FUNCTION__,
"wrong id fileformat");
}
String in = getStringOption_("in");
String out = getStringOption_("out");
in_type = FileHandler::getType(in);
//----------------------------------------------------------------
//create mapper
//----------------------------------------------------------------
// LOG_DEBUG << "Creating mapper..." << endl;
IDMapper mapper;
Param p = mapper.getParameters();
p.setValue("rt_tolerance", getDoubleOption_("rt_tolerance"));
p.setValue("mz_tolerance", getDoubleOption_("mz_tolerance"));
p.setValue("mz_measure", getStringOption_("mz_measure"));
p.setValue("mz_reference", getStringOption_("mz_reference"));
p.setValue("ignore_charge", getFlag_("ignore_charge") ? "true" : "false");
mapper.setParameters(p);
//----------------------------------------------------------------
// consensusXML
//----------------------------------------------------------------
if (in_type == FileTypes::CONSENSUSXML)
{
// LOG_DEBUG << "Processing consensus map..." << endl;
ConsensusXMLFile file;
ConsensusMap map;
file.load(in, map);
bool measure_from_subelements = getFlag_("consensus:use_subelements");
bool annotate_ids_with_subelements = getFlag_("consensus:annotate_ids_with_subelements");
mapper.annotate(map, peptide_ids, protein_ids, measure_from_subelements, annotate_ids_with_subelements);
//annotate output with data processing info
addDataProcessing_(map, getProcessingInfo_(DataProcessing::IDENTIFICATION_MAPPING));
file.store(out, map);
}
//----------------------------------------------------------------
// featureXML
//----------------------------------------------------------------
if (in_type == FileTypes::FEATUREXML)
{
// LOG_DEBUG << "Processing feature map..." << endl;
FeatureMap map;
FeatureXMLFile file;
file.load(in, map);
mapper.annotate(map, peptide_ids, protein_ids,
getFlag_("feature:use_centroid_rt"),
getFlag_("feature:use_centroid_mz"));
//annotate output with data processing info
addDataProcessing_(map, getProcessingInfo_(DataProcessing::IDENTIFICATION_MAPPING));
file.store(out, map);
}
//----------------------------------------------------------------
// MzQuantML
//----------------------------------------------------------------
if (in_type == FileTypes::MZQUANTML)
{
// LOG_DEBUG << "Processing mzq ..." << endl;
MSQuantifications msq;
MzQuantMLFile file;
file.load(in, msq);
bool measure_from_subelements = getFlag_("consensus:use_subelements");
for (std::vector<ConsensusMap>::iterator it = msq.getConsensusMaps().begin(); it != msq.getConsensusMaps().end(); ++it)
{
mapper.annotate(*it, peptide_ids, protein_ids, measure_from_subelements);
//annotate output with data processing info
addDataProcessing_(*it, getProcessingInfo_(DataProcessing::IDENTIFICATION_MAPPING));
}
//~ writeDebug_(msq.getConsensusMaps().size(),3);
//~ writeDebug_(msq.getConsensusMaps().back().size(),3);
//~ writeDebug_(msq.getAnalysisSummary().quant_type_,3);
file.store(out, msq);
}
// LOG_DEBUG << "Done." << endl;
return EXECUTION_OK;
}