ExitCodes main_(int, const char**)
{
// instance specific location of settings in INI file (e.g. 'TOPP_Skeleton:1:')
String ini_location;
// path to the log file
String logfile(getStringOption_("log"));
String xtandem_executable(getStringOption_("xtandem_executable"));
String inputfile_name;
String outputfile_name;
//-------------------------------------------------------------
// parsing parameters
//-------------------------------------------------------------
inputfile_name = getStringOption_("in");
writeDebug_(String("Input file: ") + inputfile_name, 1);
if (inputfile_name == "")
{
writeLog_("No input file specified. Aborting!");
printUsage_();
return ILLEGAL_PARAMETERS;
}
outputfile_name = getStringOption_("out");
writeDebug_(String("Output file: ") + outputfile_name, 1);
if (outputfile_name == "")
{
writeLog_("No output file specified. Aborting!");
printUsage_();
return ILLEGAL_PARAMETERS;
}
// write input xml file
String temp_directory = QDir::toNativeSeparators((File::getTempDirectory() + "/" + File::getUniqueName() + "/").toQString()); // body for the tmp files
{
QDir d;
d.mkpath(temp_directory.toQString());
}
String input_filename(temp_directory + "_tandem_input_file.xml");
String tandem_input_filename(temp_directory + "_tandem_input_file.mzData");
String tandem_output_filename(temp_directory + "_tandem_output_file.xml");
String tandem_taxonomy_filename(temp_directory + "_tandem_taxonomy_file.xml");
//-------------------------------------------------------------
// Validate user parameters
//-------------------------------------------------------------
if (getIntOption_("min_precursor_charge") > getIntOption_("max_precursor_charge"))
{
LOG_ERROR << "Given charge range is invalid: max_precursor_charge needs to be >= min_precursor_charge." << std::endl;
return ILLEGAL_PARAMETERS;
}
//-------------------------------------------------------------
// reading input
//-------------------------------------------------------------
String db_name(getStringOption_("database"));
if (!File::readable(db_name))
{
String full_db_name;
try
{
full_db_name = File::findDatabase(db_name);
}
catch (...)
{
printUsage_();
return ILLEGAL_PARAMETERS;
}
db_name = full_db_name;
}
PeakMap exp;
MzMLFile mzml_file;
mzml_file.getOptions().addMSLevel(2); // only load msLevel 2
mzml_file.setLogType(log_type_);
mzml_file.load(inputfile_name, exp);
if (exp.getSpectra().empty())
{
throw OpenMS::Exception::FileEmpty(__FILE__, __LINE__, __FUNCTION__, "Error: No MS2 spectra in input file.");
}
// determine type of spectral data (profile or centroided)
SpectrumSettings::SpectrumType spectrum_type = exp[0].getType();
if (spectrum_type == SpectrumSettings::RAWDATA)
{
if (!getFlag_("force"))
{
throw OpenMS::Exception::IllegalArgument(__FILE__, __LINE__, __FUNCTION__, "Error: Profile data provided but centroided MS2 spectra expected. To enforce processing of the data set the -force flag.");
}
}
// we need to replace the native id with a simple numbering schema, to be able to
// map the IDs back to the spectra (RT, and MZ information)
Size native_id(0);
for (PeakMap::Iterator it = exp.begin(); it != exp.end(); ++it)
{
it->setNativeID(++native_id);
}
// We store the file in mzData file format, because MGF files somehow produce in most
// of the cases IDs with charge 2+. We do not use the input file directly
// because XTandem sometimes stumbles over misleading substrings in the filename,
// e.g. mzXML ...
MzDataFile mzdata_outfile;
mzdata_outfile.store(tandem_input_filename, exp);
XTandemInfile infile;
infile.setInputFilename(tandem_input_filename);
infile.setOutputFilename(tandem_output_filename);
ofstream tax_out(tandem_taxonomy_filename.c_str());
tax_out << "<?xml version=\"1.0\"?>" << "\n";
tax_out << "\t<bioml label=\"x! taxon-to-file matching list\">" << "\n";
tax_out << "\t\t<taxon label=\"OpenMS_dummy_taxonomy\">" << "\n";
tax_out << "\t\t\t<file format=\"peptide\" URL=\"" << db_name << "\" />" << "\n";
tax_out << "\t</taxon>" << "\n";
tax_out << "</bioml>" << "\n";
tax_out.close();
infile.setTaxonomyFilename(tandem_taxonomy_filename);
if (getStringOption_("precursor_error_units") == "Da")
{
infile.setPrecursorMassErrorUnit(XTandemInfile::DALTONS);
}
else
{
infile.setPrecursorMassErrorUnit(XTandemInfile::PPM);
}
if (getStringOption_("fragment_error_units") == "Da")
{
infile.setFragmentMassErrorUnit(XTandemInfile::DALTONS);
}
else
{
infile.setFragmentMassErrorUnit(XTandemInfile::PPM);
}
if (getStringOption_("default_input_file") != "")
{
infile.load(getStringOption_("default_input_file"));
infile.setDefaultParametersFilename(getStringOption_("default_input_file"));
}
else
{
String default_file = File::find("CHEMISTRY/XTandem_default_input.xml");
infile.load(default_file);
infile.setDefaultParametersFilename(default_file);
}
infile.setPrecursorMassTolerancePlus(getDoubleOption_("precursor_mass_tolerance"));
infile.setPrecursorMassToleranceMinus(getDoubleOption_("precursor_mass_tolerance"));
infile.setFragmentMassTolerance(getDoubleOption_("fragment_mass_tolerance"));
infile.setMaxPrecursorCharge(getIntOption_("max_precursor_charge"));
infile.setNumberOfThreads(getIntOption_("threads"));
infile.setModifications(ModificationDefinitionsSet(getStringList_("fixed_modifications"), getStringList_("variable_modifications")));
infile.setTaxon("OpenMS_dummy_taxonomy");
infile.setOutputResults(getStringOption_("output_results"));
infile.setMaxValidEValue(getDoubleOption_("max_valid_expect"));
infile.setCleavageSite(getStringOption_("cleavage_site"));
infile.setNumberOfMissedCleavages(getIntOption_("missed_cleavages"));
infile.setRefine(getFlag_("refinement"));
infile.setSemiCleavage(getFlag_("semi_cleavage"));
bool allow_isotope_error = getStringOption_("allow_isotope_error") == "yes" ? true : false;
infile.setAllowIsotopeError(allow_isotope_error);
infile.write(input_filename);
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
int status = QProcess::execute(xtandem_executable.toQString(), QStringList(input_filename.toQString())); // does automatic escaping etc...
if (status != 0)
{
writeLog_("XTandem problem. Aborting! Calling command was: '" + xtandem_executable + " \"" + input_filename + "\"'.\nDoes the !XTandem executable exist?");
// clean temporary files
if (this->debug_level_ < 2)
{
File::removeDirRecursively(temp_directory);
LOG_WARN << "Set debug level to >=2 to keep the temporary files at '" << temp_directory << "'" << std::endl;
}
else
{
LOG_WARN << "Keeping the temporary files at '" << temp_directory << "'. Set debug level to <2 to remove them." << std::endl;
}
return EXTERNAL_PROGRAM_ERROR;
}
vector<ProteinIdentification> protein_ids;
ProteinIdentification protein_id;
vector<PeptideIdentification> peptide_ids;
// read the output of X!Tandem and write it to idXML
XTandemXMLFile tandem_output;
tandem_output.setModificationDefinitionsSet(ModificationDefinitionsSet(getStringList_("fixed_modifications"), getStringList_("variable_modifications")));
// find the file, because XTandem extends the filename with a timestamp we do not know (exactly)
StringList files;
File::fileList(temp_directory, "_tandem_output_file*.xml", files);
if (files.size() != 1)
{
throw Exception::FileNotFound(__FILE__, __LINE__, __PRETTY_FUNCTION__, tandem_output_filename);
}
tandem_output.load(temp_directory + files[0], protein_id, peptide_ids);
// now put the RTs into the peptide_ids from the spectrum ids
for (vector<PeptideIdentification>::iterator it = peptide_ids.begin(); it != peptide_ids.end(); ++it)
{
UInt id = (Int)it->getMetaValue("spectrum_id");
--id; // native IDs were written 1-based
if (id < exp.size())
{
it->setRT(exp[id].getRT());
double pre_mz(0.0);
if (!exp[id].getPrecursors().empty()) pre_mz = exp[id].getPrecursors()[0].getMZ();
it->setMZ(pre_mz);
//it->removeMetaValue("spectrum_id");
}
else
{
LOG_ERROR << "XTandemAdapter: Error: id '" << id << "' not found in peak map!" << endl;
}
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
// handle the search parameters
ProteinIdentification::SearchParameters search_parameters;
search_parameters.db = getStringOption_("database");
search_parameters.charges = "+" + String(getIntOption_("min_precursor_charge")) + "-+" + String(getIntOption_("max_precursor_charge"));
ProteinIdentification::PeakMassType mass_type = ProteinIdentification::MONOISOTOPIC;
search_parameters.mass_type = mass_type;
search_parameters.fixed_modifications = getStringList_("fixed_modifications");
search_parameters.variable_modifications = getStringList_("variable_modifications");
search_parameters.missed_cleavages = getIntOption_("missed_cleavages");
search_parameters.peak_mass_tolerance = getDoubleOption_("fragment_mass_tolerance");
search_parameters.precursor_tolerance = getDoubleOption_("precursor_mass_tolerance");
protein_id.setSearchParameters(search_parameters);
protein_id.setSearchEngineVersion("");
protein_id.setSearchEngine("XTandem");
protein_ids.push_back(protein_id);
IdXMLFile().store(outputfile_name, protein_ids, peptide_ids);
/// Deletion of temporary files
if (this->debug_level_ < 2)
{
File::removeDirRecursively(temp_directory);
LOG_WARN << "Set debug level to >=2 to keep the temporary files at '" << temp_directory << "'" << std::endl;
}
else
{
LOG_WARN << "Keeping the temporary files at '" << temp_directory << "'. Set debug level to <2 to remove them." << std::endl;
}
// some stats
LOG_INFO << "Statistics:\n"
<< " identified MS2 spectra: " << peptide_ids.size() << " / " << exp.size() << " = " << int(peptide_ids.size() * 100.0 / exp.size()) << "% (with e-value < " << String(getDoubleOption_("max_valid_expect")) << ")" << std::endl;
return EXECUTION_OK;
}
ExitCodes main_(int, const char**)
{
//input file names
String in = getStringOption_("in");
String out = getStringOption_("out");
String out_mzq = getStringOption_("out_mzq");
//prevent loading of fragment spectra
PeakFileOptions options;
options.setMSLevels(vector<Int>(1, 1));
//reading input data
MzMLFile f;
f.getOptions() = options;
f.setLogType(log_type_);
PeakMap exp;
f.load(in, exp);
exp.updateRanges();
if (exp.getSpectra().empty())
{
throw OpenMS::Exception::FileEmpty(__FILE__, __LINE__, __FUNCTION__, "Error: No MS1 spectra in input file.");
}
// determine type of spectral data (profile or centroided)
SpectrumSettings::SpectrumType spectrum_type = exp[0].getType();
if (spectrum_type == SpectrumSettings::RAWDATA)
{
if (!getFlag_("force"))
{
throw OpenMS::Exception::IllegalArgument(__FILE__, __LINE__, __FUNCTION__, "Error: Profile data provided but centroided spectra expected. To enforce processing of the data set the -force flag.");
}
}
//load seeds
FeatureMap seeds;
if (getStringOption_("seeds") != "")
{
FeatureXMLFile().load(getStringOption_("seeds"), seeds);
}
//setup of FeatureFinder
FeatureFinder ff;
ff.setLogType(log_type_);
// A map for the resulting features
FeatureMap features;
// get parameters specific for the feature finder
Param feafi_param = getParam_().copy("algorithm:", true);
writeDebug_("Parameters passed to FeatureFinder", feafi_param, 3);
// Apply the feature finder
ff.run(FeatureFinderAlgorithmPicked::getProductName(), exp, features, feafi_param, seeds);
features.applyMemberFunction(&UniqueIdInterface::setUniqueId);
// DEBUG
if (debug_level_ > 10)
{
FeatureMap::Iterator it;
for (it = features.begin(); it != features.end(); ++it)
{
if (!it->isMetaEmpty())
{
vector<String> keys;
it->getKeys(keys);
LOG_INFO << "Feature " << it->getUniqueId() << endl;
for (Size i = 0; i < keys.size(); i++)
{
LOG_INFO << " " << keys[i] << " = " << it->getMetaValue(keys[i]) << endl;
}
}
}
}
//-------------------------------------------------------------
// writing files
//-------------------------------------------------------------
//annotate output with data processing info
addDataProcessing_(features, getProcessingInfo_(DataProcessing::QUANTITATION));
// write features to user specified output file
FeatureXMLFile map_file;
// Remove detailed convex hull information and subordinate features
// (unless requested otherwise) to reduce file size of feature files
// unless debugging is turned on.
if (debug_level_ < 5)
{
FeatureMap::Iterator it;
for (it = features.begin(); it != features.end(); ++it)
{
it->getConvexHull().expandToBoundingBox();
for (Size i = 0; i < it->getConvexHulls().size(); ++i)
{
it->getConvexHulls()[i].expandToBoundingBox();
}
it->getSubordinates().clear();
}
}
map_file.store(out, features);
if (!out_mzq.trim().empty())
{
MSQuantifications msq(features, exp.getExperimentalSettings(), exp[0].getDataProcessing());
msq.assignUIDs();
MzQuantMLFile file;
file.store(out_mzq, msq);
}
return EXECUTION_OK;
}
ExitCodes main_(int, const char**) override
{
//-------------------------------------------------------------
// parsing parameters
//-------------------------------------------------------------
// do this early, to see if comet is installed
String comet_executable = getStringOption_("comet_executable");
String tmp_param = File::getTemporaryFile();
writeLog_("Comet is writing the default parameter file...");
runExternalProcess_(comet_executable.toQString(), QStringList() << "-p" << tmp_param.c_str());
String inputfile_name = getStringOption_("in");
String out = getStringOption_("out");
//-------------------------------------------------------------
// reading input
//-------------------------------------------------------------
String db_name(getStringOption_("database"));
if (!File::readable(db_name))
{
String full_db_name;
try
{
full_db_name = File::findDatabase(db_name);
}
catch (...)
{
printUsage_();
return ILLEGAL_PARAMETERS;
}
db_name = full_db_name;
}
//tmp_dir
String tmp_dir = makeAutoRemoveTempDirectory_();
String tmp_pepxml = tmp_dir + "result.pep.xml";
String tmp_pin = tmp_dir + "result.pin";
String default_params = getStringOption_("default_params_file");
String tmp_file;
//default params given or to be written
if (default_params.empty())
{
tmp_file = tmp_dir + "param.txt";
ofstream os(tmp_file.c_str());
createParamFile_(os);
os.close();
}
else
{
tmp_file = default_params;
}
PeakMap exp;
MzMLFile mzml_file;
mzml_file.getOptions().setMSLevels({2}); // only load msLevel 2
mzml_file.setLogType(log_type_);
mzml_file.load(inputfile_name, exp);
if (exp.getSpectra().empty())
{
throw OpenMS::Exception::FileEmpty(__FILE__, __LINE__, __FUNCTION__, "Error: No MS2 spectra in input file.");
}
// determine type of spectral data (profile or centroided)
SpectrumSettings::SpectrumType spectrum_type = exp[0].getType();
if (spectrum_type == SpectrumSettings::PROFILE)
{
if (!getFlag_("force"))
{
throw OpenMS::Exception::IllegalArgument(__FILE__, __LINE__, __FUNCTION__, "Error: Profile data provided but centroided MS2 spectra expected. To enforce processing of the data set the -force flag.");
}
}
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
String paramP = "-P" + tmp_file;
String paramN = "-N" + File::removeExtension(File::removeExtension(tmp_pepxml));
QStringList arguments;
arguments << paramP.toQString() << paramN.toQString() << inputfile_name.toQString();
//-------------------------------------------------------------
// run comet
//-------------------------------------------------------------
// Comet execution with the executable and the arguments StringList
TOPPBase::ExitCodes exit_code = runExternalProcess_(comet_executable.toQString(), arguments);
if (exit_code != EXECUTION_OK)
{
return exit_code;
}
//-------------------------------------------------------------
// writing IdXML output
//-------------------------------------------------------------
// read the pep.xml put of Comet and write it to idXML
vector<PeptideIdentification> peptide_identifications;
vector<ProteinIdentification> protein_identifications;
writeDebug_("load PepXMLFile", 1);
PepXMLFile().load(tmp_pepxml, protein_identifications, peptide_identifications);
writeDebug_("write idXMLFile", 1);
writeDebug_(out, 1);
IdXMLFile().store(out, protein_identifications, peptide_identifications);
//-------------------------------------------------------------
// create (move) optional pin output
//-------------------------------------------------------------
String pin_out = getStringOption_("pin_out");
if (!pin_out.empty())
{ // move the temporary file to the actual destination:
if (!File::rename(tmp_pin, pin_out))
{
return CANNOT_WRITE_OUTPUT_FILE;
}
}
return EXECUTION_OK;
}
ExitCodes main_(int, const char**) override
{
String tmp_dir = QDir::toNativeSeparators((File::getTempDirectory() + "/" + File::getUniqueName() + "/").toQString()); // body for the tmp files
{
QDir d;
d.mkpath(tmp_dir.toQString());
}
String logfile(getStringOption_("log"));
String myrimatch_executable(getStringOption_("myrimatch_executable"));
//-------------------------------------------------------------
// get version of MyriMatch
//-------------------------------------------------------------
QProcess qp;
String myrimatch_version;
MyriMatchVersion myrimatch_version_i;
// we invoke myrimatch w/o arguments. that yields a return code != 0. but
// there is no other way for version 2.1 to get the version number
qp.start(myrimatch_executable.toQString(), QStringList(), QIODevice::ReadOnly); // does automatic escaping etc...
qp.waitForFinished();
String output(QString(qp.readAllStandardOutput()));
vector<String> lines;
vector<String> version_split;
output.split('\n', lines);
// the version number is expected to be in the second line
if (lines.size() < 2)
{
writeLog_("Warning: MyriMatch version output (" + output + ") not formatted as expected!");
return EXTERNAL_PROGRAM_ERROR;
}
// the version is expected to be something like:
// MyriMatch 2.1.111 (2011-12-27)
lines[1].split(' ', version_split);
if (version_split.size() == 3 && getVersion_(version_split[1], myrimatch_version_i))
{
myrimatch_version = version_split[1].removeWhitespaces();
writeDebug_("Setting MyriMatch version to " + myrimatch_version, 1);
}
else
{
writeLog_("Warning: MyriMatch version output (" + output + ") not formatted as expected!");
return EXTERNAL_PROGRAM_ERROR;
}
if (! ( (myrimatch_version_i.myrimatch_major == 2) && // major must be 2
(myrimatch_version_i.myrimatch_minor == 1 || myrimatch_version_i.myrimatch_minor == 2) // minor .1 or .2
))
{
writeLog_("Warning: unsupported MyriMatch version (" + myrimatch_version + "). Tested only for MyriMatch 2.1.x and 2.2.x."
"\nIf you encounter parameter errors, you can try the flag 'ignoreConfigErrors', but be aware that MyriMatch might be misconfigured.");
}
//-------------------------------------------------------------
// parsing parameters
//-------------------------------------------------------------
String inputfile_name = File::absolutePath(getStringOption_("in"));
String outputfile_name = getStringOption_("out");
String db_name = File::absolutePath(String(getStringOption_("database")));
// building parameter String
StringList parameters;
if (getFlag_("ignoreConfigErrors")) parameters << "-ignoreConfigErrors";
// Common Identification engine options
StringList static_mod_list;
StringList dynamic_mod_list;
translateModifications(static_mod_list, dynamic_mod_list);
if (!static_mod_list.empty())
parameters << "-StaticMods" << ListUtils::concatenate(static_mod_list, " ");
if (!dynamic_mod_list.empty())
parameters << "-DynamicMods" << ListUtils::concatenate(dynamic_mod_list, " ");
parameters << "-ProteinDatabase" << File::absolutePath(db_name);
if (getFlag_("precursor_mass_tolerance_avg"))
{
parameters << "-AvgPrecursorMzTolerance";
}
else
{
parameters << "-MonoPrecursorMzTolerance";
}
String precursor_mass_tolerance_unit = getStringOption_("precursor_mass_tolerance_unit") == "Da" ? " m/z" : " ppm";
parameters << String(getDoubleOption_("precursor_mass_tolerance")) + precursor_mass_tolerance_unit;
String fragment_mass_tolerance_unit = getStringOption_("fragment_mass_tolerance_unit");
if (fragment_mass_tolerance_unit == "Da")
{
fragment_mass_tolerance_unit = "m/z";
}
parameters << "-FragmentMzTolerance" << String(getDoubleOption_("fragment_mass_tolerance")) + " " + fragment_mass_tolerance_unit;
StringList slf = getStringList_("SpectrumListFilters");
if (slf.size() > 0)
{
if (myrimatch_version_i.myrimatch_minor <= 1)
{ // use quotes around the slf arguments (will be added automatically by Qt during call), i.e. "-SpectrumListFilters" "peakPicking false 2-"
parameters << "-SpectrumListFilters" << ListUtils::concatenate(slf, ";") << "";
}
else
{ // no quotes -- pass a single argument, i.e. "-SpectrumListFilters peakPicking false 2-"
parameters << "-SpectrumListFilters " + ListUtils::concatenate(slf, ";") << "";
}
}
//parameters << "-ThreadCountMultiplier" << String(getIntOption_("threads")); // MyriMatch does not recognise this, even though it's in the manual.
// MyriMatch specific parameters
parameters << "-NumChargeStates" << getIntOption_("NumChargeStates");
parameters << "-TicCutoffPercentage" << String(getDoubleOption_("TicCutoffPercentage"));
parameters << "-MaxDynamicMods" << getIntOption_("MaxDynamicMods");
parameters << "-MaxResultRank" << getIntOption_("MaxResultRank");
parameters << "-MinTerminiCleavages" << getIntOption_("MinTerminiCleavages");
parameters << "-MaxMissedCleavages" << getIntOption_("MaxMissedCleavages");
String cleavage_rule = getStringOption_("CleavageRules");
if (cleavage_rule.empty())
{
cleavage_rule = "Trypsin/P";
}
parameters << "-CleavageRules" << cleavage_rule;
// advanced parameters
parameters << "-MinPeptideMass" << getDoubleOption_("MinPeptideMass");
parameters << "-MaxPeptideMass" << getDoubleOption_("MaxPeptideMass");
parameters << "-MinPeptideLength" << getIntOption_("MinPeptideLength");
parameters << "-MaxPeptideLength" << getIntOption_("MaxPeptideLength");
parameters << "-NumIntensityClasses" << getIntOption_("NumIntensityClasses");
parameters << "-ClassSizeMultiplier" << getDoubleOption_("ClassSizeMultiplier");
parameters << "-MonoisotopeAdjustmentSet" << getStringOption_("MonoisotopeAdjustmentSet");
parameters << "-cpus" << getIntOption_("threads");
// Constant parameters
// DecoyPrefix worked only when set through the config file
String cfg_file = tmp_dir + "myrimatch.cfg";
ofstream f(cfg_file.c_str());
f << "DecoyPrefix=\"\"\n";
f.close();
parameters << "-cfg" << cfg_file;
// path to input file must be the last parameter
parameters << inputfile_name;
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
QStringList qparam;
writeDebug_("MyriMatch arguments:", 1);
writeDebug_(String("\"") + ListUtils::concatenate(parameters, "\" \"") + "\"", 1);
for (Size i = 0; i < parameters.size(); ++i)
{
qparam << parameters[i].toQString();
}
QProcess process;
// Bad style, because it breaks relative paths?
process.setWorkingDirectory(tmp_dir.toQString());
process.start(myrimatch_executable.toQString(), qparam, QIODevice::ReadOnly);
bool success = process.waitForFinished(-1);
String myri_msg(QString(process.readAllStandardOutput()));
String myri_err(QString(process.readAllStandardError()));
writeDebug_(myri_msg, 1);
writeDebug_(myri_err, 0);
if (!success || process.exitStatus() != 0 || process.exitCode() != 0)
{
writeLog_("Error: MyriMatch problem! (Details can be seen in the logfile: \"" + logfile + "\")");
writeLog_("Note: This message can also be triggered if you run out of space in your tmp directory");
return EXTERNAL_PROGRAM_ERROR;
}
//-------------------------------------------------------------
// reading MyriMatch output
//-------------------------------------------------------------
writeDebug_("Reading output of MyriMatch", 5);
String exp_name = File::basename(inputfile_name);
String pep_file = tmp_dir + File::removeExtension(exp_name) + ".pepXML";
vector<ProteinIdentification> protein_identifications;
vector<PeptideIdentification> peptide_identifications;
PeakMap exp;
if (File::exists(pep_file))
{
MzMLFile fh;
fh.load(inputfile_name, exp);
SpectrumMetaDataLookup lookup;
lookup.readSpectra(exp.getSpectra());
PepXMLFile().load(pep_file, protein_identifications,
peptide_identifications, exp_name, lookup);
}
else
{
writeLog_("Error: MyriMatch problem! No pepXML output file (expected as '" + pep_file + "') was generated by MyriMatch.");
writeLog_("Note: This message can be triggered if no MS2 spectra were found or no identifications were made.");
writeLog_(" Myrimatch expects MS2 spectra in mzML files to contain the MSn tag. MSSpectrum with MS level 2 is not sufficient. You can use FileConverter to create such an mzML file by converting from mzML --> mzXML --> mzML.");
return EXTERNAL_PROGRAM_ERROR;
}
if (debug_level_ == 0)
{
QFile(pep_file.toQString()).remove();
QFile(cfg_file.toQString()).remove();
}
else
{
writeDebug_(String("Not removing '") + pep_file + "' for debugging purposes. Please delete manually!", 1);
writeDebug_(String("Not removing '") + cfg_file + "' for debugging purposes. Please delete manually!", 1);
}
//-------------------------------------------------------------
// writing results
//-------------------------------------------------------------
ProteinIdentification::SearchParameters search_parameters;
search_parameters.db = getStringOption_("database");
ProteinIdentification::PeakMassType mass_type = getFlag_("precursor_mass_tolerance_avg") == true ? ProteinIdentification::AVERAGE : ProteinIdentification::MONOISOTOPIC;
search_parameters.mass_type = mass_type;
search_parameters.fixed_modifications = getStringList_("fixed_modifications");
search_parameters.variable_modifications = getStringList_("variable_modifications");
search_parameters.missed_cleavages = getIntOption_("MaxMissedCleavages");
search_parameters.fragment_mass_tolerance = getDoubleOption_("fragment_mass_tolerance");
search_parameters.precursor_mass_tolerance = getDoubleOption_("precursor_mass_tolerance");
search_parameters.precursor_mass_tolerance_ppm = getStringOption_("precursor_mass_tolerance_unit") == "ppm" ? true : false;
search_parameters.fragment_mass_tolerance_ppm = getStringOption_("fragment_mass_tolerance_unit") == "ppm" ? true : false;
protein_identifications[0].setSearchParameters(search_parameters);
protein_identifications[0].setSearchEngineVersion(myrimatch_version);
protein_identifications[0].setSearchEngine("MyriMatch");
if (!protein_identifications.empty())
{
StringList ms_runs;
exp.getPrimaryMSRunPath(ms_runs);
protein_identifications[0].setPrimaryMSRunPath(ms_runs);
}
IdXMLFile().store(outputfile_name, protein_identifications, peptide_identifications);
return EXECUTION_OK;
}
ExitCodes main_(int argc, const char** argv)
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
//input/output files
String in(getStringOption_("in")), out(getStringOption_("out"));
FileHandler fh;
FileTypes::Type in_type = fh.getType(in);
//-------------------------------------------------------------
// loading input
//-------------------------------------------------------------
PeakMap exp;
// keep only MS2 spectra
fh.getOptions().addMSLevel(2);
fh.loadExperiment(in, exp, in_type, log_type_);
writeDebug_(String("Spectra loaded: ") + exp.size(), 2);
if (exp.getSpectra().empty())
{
throw OpenMS::Exception::FileEmpty(__FILE__, __LINE__, __FUNCTION__, "Error: No MS2 spectra in input file.");
}
// determine type of spectral data (profile or centroided)
SpectrumSettings::SpectrumType spectrum_type = exp[0].getType();
if (spectrum_type == SpectrumSettings::RAWDATA)
{
if (!getFlag_("force"))
{
throw OpenMS::Exception::IllegalArgument(__FILE__, __LINE__, __FUNCTION__, "Error: Profile data provided but centroided MS2 spectra expected. To enforce processing of the data set the -force flag.");
}
}
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
Param mascot_param = getParam_().copy("Mascot_parameters:", true);
MascotGenericFile mgf_file;
Param p;
// TODO: switch this to mzML (much smaller)
p.setValue("internal:format", "Mascot generic", "Sets the format type of the peak list, this should not be changed unless you write the header only.", ListUtils::create<String>("advanced"));
p.setValue("internal:HTTP_format", "true", "Write header with MIME boundaries instead of simple key-value pairs. For HTTP submission only.", ListUtils::create<String>("advanced"));
p.setValue("internal:content", "all", "Use parameter header + the peak lists with BEGIN IONS... or only one of them.", ListUtils::create<String>("advanced"));
mgf_file.setParameters(mascot_param);
// get the spectra into string stream
writeDebug_("Writing MGF file to stream", 1);
stringstream ss;
mgf_file.store(ss, in, exp, true); // write in compact format
// Usage of a QCoreApplication is overkill here (and ugly too), but we just use the
// QEventLoop to process the signals and slots and grab the results afterwards from
// the MascotRemotQuery instance
char** argv2 = const_cast<char**>(argv);
QCoreApplication event_loop(argc, argv2);
MascotRemoteQuery* mascot_query = new MascotRemoteQuery(&event_loop);
Param mascot_query_param = getParam_().copy("Mascot_server:", true);
writeDebug_("Setting parameters for Mascot query", 1);
mascot_query->setParameters(mascot_query_param);
writeDebug_("Setting spectra for Mascot query", 1);
mascot_query->setQuerySpectra(ss.str());
// remove unnecessary spectra
ss.clear();
QObject::connect(mascot_query, SIGNAL(done()), &event_loop, SLOT(quit()));
QTimer::singleShot(1000, mascot_query, SLOT(run()));
writeDebug_("Fire off Mascot query", 1);
event_loop.exec();
writeDebug_("Mascot query finished", 1);
if (mascot_query->hasError())
{
writeLog_("An error occurred during the query: " + mascot_query->getErrorMessage());
delete mascot_query;
return EXTERNAL_PROGRAM_ERROR;
}
// write Mascot response to file
String mascot_tmp_file_name(File::getTempDirectory() + "/" + File::getUniqueName() + "_Mascot_response");
QFile mascot_tmp_file(mascot_tmp_file_name.c_str());
mascot_tmp_file.open(QIODevice::WriteOnly);
mascot_tmp_file.write(mascot_query->getMascotXMLResponse());
mascot_tmp_file.close();
// clean up
delete mascot_query;
vector<PeptideIdentification> pep_ids;
ProteinIdentification prot_id;
// set up mapping between scan numbers and retention times:
MascotXMLFile::RTMapping rt_mapping;
MascotXMLFile::generateRTMapping(exp.begin(), exp.end(), rt_mapping);
// read the response
MascotXMLFile().load(mascot_tmp_file_name, prot_id, pep_ids, rt_mapping);
writeDebug_("Read " + String(pep_ids.size()) + " peptide ids and " + String(prot_id.getHits().size()) + " protein identifications from Mascot", 5);
// for debugging errors relating to unexpected response files
if (this->debug_level_ >= 100)
{
writeDebug_(String("\nMascot Server Response file saved to: '") + mascot_tmp_file_name + "'. If an error occurs, send this file to the OpenMS team.\n", 100);
}
else
{
// delete file
mascot_tmp_file.remove();
}
// keep or delete protein identifications?!
vector<ProteinIdentification> prot_ids;
if (!getFlag_("keep_protein_links"))
{
// remove protein links from peptides
for (Size i = 0; i < pep_ids.size(); ++i)
{
std::vector<PeptideHit> hits = pep_ids[i].getHits();
for (Size h = 0; h < hits.size(); ++h)
{
hits[h].setPeptideEvidences(vector<PeptideEvidence>());
}
pep_ids[i].setHits(hits);
}
// remove proteins
std::vector<ProteinHit> p_hit;
prot_id.setHits(p_hit);
}
prot_ids.push_back(prot_id);
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
IdXMLFile().store(out, prot_ids, pep_ids);
return EXECUTION_OK;
}