void MapAlignmentTransformer::transformRetentionTimes(
MSExperiment<>& msexp, const TransformationDescription& trafo,
bool store_original_rt)
{
msexp.clearRanges();
// Transform spectra
for (MSExperiment<>::iterator mse_iter = msexp.begin();
mse_iter != msexp.end(); ++mse_iter)
{
double rt = mse_iter->getRT();
if (store_original_rt) storeOriginalRT_(*mse_iter, rt);
mse_iter->setRT(trafo.apply(rt));
}
// Also transform chromatograms
for (Size i = 0; i < msexp.getNrChromatograms(); ++i)
{
MSChromatogram<ChromatogramPeak>& chromatogram = msexp.getChromatogram(i);
vector<double> original_rts;
if (store_original_rt) original_rts.reserve(chromatogram.size());
for (Size j = 0; j < chromatogram.size(); j++)
{
double rt = chromatogram[j].getRT();
if (store_original_rt) original_rts.push_back(rt);
chromatogram[j].setRT(trafo.apply(rt));
}
if (store_original_rt && !chromatogram.metaValueExists("original_rt"))
{
chromatogram.setMetaValue("original_rt", original_rts);
}
}
msexp.updateRanges();
}
void MapAlignmentTransformer::transformSinglePeakMap(MSExperiment<> & msexp,
const TransformationDescription & trafo)
{
msexp.clearRanges();
// Transform spectra
for (MSExperiment<>::iterator mse_iter = msexp.begin(); mse_iter != msexp.end(); ++mse_iter)
{
DoubleReal rt = mse_iter->getRT();
mse_iter->setRT(trafo.apply(rt));
}
// Also transform chromatograms
DoubleReal rt;
std::vector<MSChromatogram<ChromatogramPeak> > chromatograms;
for (Size i = 0; i < msexp.getChromatograms().size(); i++)
{
MSChromatogram<ChromatogramPeak> chromatogram = msexp.getChromatograms()[i];
for (Size j = 0; j < chromatogram.size(); j++)
{
rt = chromatogram[j].getRT();
chromatogram[j].setRT(trafo.apply(rt));
}
chromatograms.push_back(chromatogram);
}
msexp.setChromatograms(chromatograms);
msexp.updateRanges();
}
void TOFCalibration::matchMasses_(MSExperiment<> & calib_peaks,
std::vector<std::vector<unsigned int> > & monoiso_peaks,
std::vector<unsigned int> & obs_masses,
std::vector<double> & exp_masses, unsigned int idx)
{
for (unsigned int i = 0; i < monoiso_peaks[idx].size(); ++i)
{
for (unsigned int j = 0; j < exp_masses_.size(); ++j)
{
if (fabs(((calib_peaks.begin() + idx)->begin() + (monoiso_peaks[idx])[i])->getMZ() - exp_masses_[j]) < 1)
{
obs_masses.push_back((monoiso_peaks[idx])[i]);
exp_masses.push_back(exp_masses_[j]);
break;
}
}
}
#ifdef DEBUG_CALIBRATION
std::cout << "\n\n---------\nmatching monoisotopic peaks\n";
for (unsigned int i = 0; i < obs_masses.size(); ++i)
{
std::cout << ((calib_peaks_ft_.begin() + idx)->begin() + obs_masses[i])->getMZ()
<< "\t" << exp_masses[i]
<< std::endl;
}
#endif
}
// lists of peptide hits in "maps" will be sorted
void MapAlignmentAlgorithmIdentification::getRetentionTimes_(
MSExperiment<> & experiment, SeqToList & rt_data)
{
for (MSExperiment<>::Iterator exp_it = experiment.begin();
exp_it != experiment.end(); ++exp_it)
{
getRetentionTimes_(exp_it->getPeptideIdentifications(), rt_data);
}
// duplicates should not be possible -> no need to remove them
}
int main()
{
// create a peak map containing 4 dummy spectra and peaks
MSExperiment exp;
// The following examples creates a MSExperiment containing four MSSpectrum instances.
for (Size i = 0; i < 4; ++i)
{
MSSpectrum spectrum;
spectrum.setRT(i);
spectrum.setMSLevel(1);
for (float mz = 500.0; mz <= 900; mz += 100.0)
{
Peak1D peak;
peak.setMZ(mz + i);
spectrum.push_back(peak);
}
exp.addSpectrum(spectrum);
}
// Iteration over the RT range (2,3) and the m/z range (603,802) and print the peak positions.
for (auto it = exp.areaBegin(2.0, 3.0, 603.0, 802.0); it != exp.areaEnd(); ++it)
{
cout << it.getRT() << " - " << it->getMZ() << endl;
}
// Iteration over all peaks in the experiment.
// Output: RT, m/z, and intensity
// Note that the retention time is stored in the spectrum (not in the peak object)
for (auto s_it = exp.begin(); s_it != exp.end(); ++s_it)
{
for (auto p_it = s_it->begin(); p_it != s_it->end(); ++p_it)
{
cout << s_it->getRT() << " - " << p_it->getMZ() << " " << p_it->getIntensity() << endl;
}
}
// We could store the spectra to a mzML file with:
// MzMLFile mzml;
// mzml.store(filename, exp);
// And load it with
// mzml.load(filename, exp);
// If we wanted to load only the MS2 spectra we could speed up reading by setting:
// mzml.getOptions().addMSLevel(2);
// before executing: mzml.load(filename, exp);
return 0;
} //end of main
void SeedListGenerator::generateSeedList(const MSExperiment<>& experiment,
SeedList& seeds)
{
seeds.clear();
for (MSExperiment<>::ConstIterator exp_it = experiment.begin();
exp_it != experiment.end(); ++exp_it)
{
if (exp_it->getMSLevel() == 2) // MS2 spectrum -> look for precursor
{
MSExperiment<>::ConstIterator prec_it =
experiment.getPrecursorSpectrum(exp_it);
const vector<Precursor>& precursors = exp_it->getPrecursors();
DPosition<2> point(prec_it->getRT(), precursors[0].getMZ());
seeds.push_back(point);
}
}
}
int main(int argc, const char** argv)
{
if (argc < 2) return 1;
// the path to the data should be given on the command line
String tutorial_data_path(argv[1]);
MSExperiment spectra;
MzMLFile f;
// load mzML from code examples folder
f.load(tutorial_data_path + "/data/Tutorial_GaussFilter.mzML", spectra);
// iterate over map and output MS2 precursor information
for (auto s_it = spectra.begin(); s_it != spectra.end(); ++s_it)
{
// we are only interested in MS2 spectra so we skip all other levels
if (s_it->getMSLevel() != 2) continue;
// get a reference to the precursor information
const MSSpectrum& spectrum = *s_it;
const vector<Precursor>& precursors = spectrum.getPrecursors();
// size check & throw exception if needed
if (precursors.empty()) throw Exception::InvalidSize(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION, precursors.size());
// get m/z and intensity of precursor
double precursor_mz = precursors[0].getMZ();
float precursor_int = precursors[0].getIntensity();
// retrieve the precursor spectrum (the most recent MS1 spectrum)
PeakMap::ConstIterator precursor_spectrum = spectra.getPrecursorSpectrum(s_it);
double precursor_rt = precursor_spectrum->getRT();
// output precursor information
std::cout << " precusor m/z: " << precursor_mz
<< " intensity: " << precursor_int
<< " retention time (sec.): " << precursor_rt
<< std::endl;
}
return 0;
} // end of main
void markMS2Locations_(MSExperiment<> & exp, QImage & image, bool transpose,
QColor color, Size size)
{
double xcoef = image.width(), ycoef = image.height();
if (transpose)
{
xcoef /= exp.getMaxRT() - exp.getMinRT();
ycoef /= exp.getMaxMZ() - exp.getMinMZ();
}
else
{
xcoef /= exp.getMaxMZ() - exp.getMinMZ();
ycoef /= exp.getMaxRT() - exp.getMinRT();
}
for (MSExperiment<>::Iterator spec_iter = exp.begin();
spec_iter != exp.end(); ++spec_iter)
{
if (spec_iter->getMSLevel() == 2)
{
double mz = spec_iter->getPrecursors()[0].getMZ();
double rt = exp.getPrecursorSpectrum(spec_iter)->getRT();
int x, y;
if (transpose)
{
x = int(xcoef * (rt - exp.getMinRT()));
y = int(ycoef * (exp.getMaxMZ() - mz));
}
else
{
x = int(xcoef * (mz - exp.getMinMZ()));
y = int(ycoef * (exp.getMaxRT() - rt));
}
addPoint_(x, y, image, color, size); //mark MS2
}
}
}
void TOFCalibration::applyTOFConversion_(MSExperiment<> & calib_spectra)
{
MSExperiment<>::iterator spec_iter = calib_spectra.begin();
MSExperiment<>::SpectrumType::iterator peak_iter;
unsigned int idx = 0;
//two point conversion
if (ml3s_.empty())
{
for (; spec_iter != calib_spectra.end(); ++spec_iter)
{
peak_iter = spec_iter->begin();
double ml1, ml2;
if (ml1s_.size() == 1)
{
ml1 = ml1s_[0];
ml2 = ml2s_[0];
}
else
{
ml1 = ml1s_[idx];
ml2 = ml2s_[idx];
}
// go through current scan
for (; peak_iter != spec_iter->end(); ++peak_iter)
{
double time = peak_iter->getMZ();
peak_iter->setPos(ml1 / 1E12 * (time * 1000 - ml2));
}
++idx;
}
}
else
{
// three point conversion
for (; spec_iter != calib_spectra.end(); ++spec_iter)
{
peak_iter = spec_iter->begin();
double ml1, ml2, ml3;
if (ml1s_.size() == 1)
{
ml1 = ml1s_[0];
ml2 = ml2s_[0];
ml3 = ml3s_[0];
}
else
{
ml1 = ml1s_[idx];
ml2 = ml2s_[idx];
ml3 = ml3s_[idx];
}
// go through current scan
for (; peak_iter != spec_iter->end(); ++peak_iter)
{
double time = peak_iter->getMZ();
peak_iter->setPos((-ml2 - (0.1E7 * (-5E5 + sqrt(0.25E12 - ml1 * ml2 * ml3 + ml1 * ml3 * time))) / (ml1 * ml3) + time) / ml3);
}
++idx;
}
}
}
void TOFCalibration::getMonoisotopicPeaks_(MSExperiment<> & calib_peaks, std::vector<std::vector<unsigned int> > & monoiso_peaks)
{
MSExperiment<>::iterator spec_iter = calib_peaks.begin();
MSExperiment<>::SpectrumType::iterator peak_iter, help_iter;
#ifdef DEBUG_CALIBRATION
spec_iter = calib_peaks.begin();
std::cout << "\n\nbefore---------\n\n";
// iterate through all spectra
for (; spec_iter != calib_peaks.end(); ++spec_iter)
{
peak_iter = spec_iter->begin();
// go through current scan
for (; peak_iter != spec_iter->end(); ++peak_iter)
{
std::cout << peak_iter->getMZ() << std::endl;
}
}
#endif
spec_iter = calib_peaks.begin();
// iterate through all spectra
for (; spec_iter != calib_peaks.end(); ++spec_iter)
{
peak_iter = spec_iter->begin();
help_iter = peak_iter;
std::vector<unsigned int> vec;
// go through current scan
while (peak_iter < spec_iter->end())
{
while (peak_iter + 1 < spec_iter->end() && ((peak_iter + 1)->getMZ() - peak_iter->getMZ() < 1.2))
{
++peak_iter;
}
vec.push_back(distance(spec_iter->begin(), help_iter));
help_iter = peak_iter + 1;
++peak_iter;
}
monoiso_peaks.push_back(vec);
}
#ifdef DEBUG_CALIBRATION
std::cout << "\n\nafter---------\n\n";
for (unsigned int i = 0; i < monoiso_peaks.size(); ++i)
{
for (unsigned int j = 0; j < monoiso_peaks[i].size(); ++j)
{
std::cout << i << "\t" << ((calib_peaks.begin() + i)->begin() + (monoiso_peaks[i])[j])->getMZ() << std::endl;
}
std::cout << "--------------\n";
}
std::cout << "--------------\n\n\n";
#endif
}
ExitCodes main_(int, const char **)
{
//----------------------------------------------------------------
// load data
//----------------------------------------------------------------
String in = getStringOption_("in");
String in_featureXML = getStringOption_("in_featureXML");
String out = getStringOption_("out");
String format = getStringOption_("out_type");
if (format.trim() == "") // get from filename
{
try
{
format = out.suffix('.');
}
catch (Exception::ElementNotFound & /*e*/)
{
format = "nosuffix";
}
StringListUtils::toUpper(out_formats_);
if (!ListUtils::contains(out_formats_, format.toUpper()))
{
LOG_ERROR << "No explicit image output format was provided via 'out_type', and the suffix ('" << format << "') does not resemble a valid type. Please fix one of them." << std::endl;
return ILLEGAL_PARAMETERS;
}
}
MSExperiment<> exp;
MzMLFile f;
f.setLogType(log_type_);
f.load(in, exp);
exp.updateRanges(1);
SignedSize rows = getIntOption_("height");
if (rows == 0)
{
rows = exp.size();
}
if (rows <= 0)
{
writeLog_("Error: Zero rows is not possible.");
return ILLEGAL_PARAMETERS;
}
SignedSize cols = getIntOption_("width");
if (cols == 0)
{
cols = UInt(ceil(exp.getMaxMZ() - exp.getMinMZ()));
}
if (cols <= 0)
{
writeLog_("Error: Zero columns is not possible.");
return ILLEGAL_PARAMETERS;
}
//----------------------------------------------------------------
//Do the actual resampling
BilinearInterpolation<double, double> bilip;
bilip.getData().resize(rows, cols);
if (!getFlag_("transpose"))
{
// scans run bottom-up:
bilip.setMapping_0(0, exp.getMaxRT(), rows - 1, exp.getMinRT());
// peaks run left-right:
bilip.setMapping_1(0, exp.getMinMZ(), cols - 1, exp.getMaxMZ());
for (MSExperiment<>::Iterator spec_iter = exp.begin();
spec_iter != exp.end(); ++spec_iter)
{
if (spec_iter->getMSLevel() != 1) continue;
for (MSExperiment<>::SpectrumType::ConstIterator peak1_iter =
spec_iter->begin(); peak1_iter != spec_iter->end();
++peak1_iter)
{
bilip.addValue(spec_iter->getRT(), peak1_iter->getMZ(),
peak1_iter->getIntensity());
}
}
}
else // transpose
{
// spectra run bottom-up:
bilip.setMapping_0(0, exp.getMaxMZ(), rows - 1, exp.getMinMZ());
// scans run left-right:
bilip.setMapping_1(0, exp.getMinRT(), cols - 1, exp.getMaxRT());
for (MSExperiment<>::Iterator spec_iter = exp.begin();
spec_iter != exp.end(); ++spec_iter)
{
if (spec_iter->getMSLevel() != 1) continue;
for (MSExperiment<>::SpectrumType::ConstIterator peak1_iter =
spec_iter->begin(); peak1_iter != spec_iter->end();
++peak1_iter)
{
bilip.addValue(peak1_iter->getMZ(), spec_iter->getRT(),
peak1_iter->getIntensity());
}
}
}
//----------------------------------------------------------------
//create and store image
int scans = (int) bilip.getData().sizePair().first;
int peaks = (int) bilip.getData().sizePair().second;
MultiGradient gradient;
String gradient_str = getStringOption_("gradient");
if (gradient_str != "")
{
gradient.fromString(String("Linear|") + gradient_str);
}
else
{
gradient.fromString("Linear|0,#FFFFFF;2,#FFFF00;11,#FFAA00;32,#FF0000;55,#AA00FF;78,#5500FF;100,#000000");
}
bool use_log = getFlag_("log_intensity");
writeDebug_("log_intensity: " + String(use_log), 1);
QImage image(peaks, scans, QImage::Format_RGB32);
string s = getStringOption_("background_color");
QColor background_color(s.c_str());
string feature_color_string = getStringOption_("feature_color");
QColor feature_color(feature_color_string.c_str());
QPainter * painter = new QPainter(&image);
painter->setPen(background_color);
painter->fillRect(0, 0, peaks, scans, Qt::SolidPattern);
delete painter;
double factor = getDoubleOption_("max_intensity");
if (factor == 0)
{
factor = (*std::max_element(bilip.getData().begin(), bilip.getData().end()));
}
// logarithmize max. intensity as well:
if (use_log) factor = std::log(factor);
factor /= 100.0;
for (int i = 0; i < scans; ++i)
{
for (int j = 0; j < peaks; ++j)
{
double value = bilip.getData().getValue(i, j);
if (use_log) value = std::log(value);
if (value > 1e-4)
{
image.setPixel(j, i, gradient.interpolatedColorAt(value / factor).rgb());
}
else
{
image.setPixel(j, i, background_color.rgb());
}
}
}
if (getFlag_("precursors"))
{
markMS2Locations_(exp, image, getFlag_("transpose"),
getStringOption_("precursor_color").toQString(),
Size(getIntOption_("precursor_size")));
}
if (!in_featureXML.empty())
{
FeatureMap feature_map;
FeatureXMLFile ff;
ff.load(in_featureXML, feature_map);
markFeatureLocations_(feature_map, exp, image, getFlag_("transpose"), feature_color);
}
if (image.save(out.toQString(), format.c_str())) return EXECUTION_OK;
else return CANNOT_WRITE_OUTPUT_FILE;
}
ExitCodes main_(int, const char **)
{
// data to be passed through the algorithm
vector<vector<SILACPattern> > data;
MSQuantifications msq;
vector<Clustering *> cluster_data;
//
// Parameter handling
//
map<String, DoubleReal> label_identifiers; // list defining the mass shifts of each label (e.g. "Arg6" => 6.0201290268)
handleParameters_sample();
handleParameters_algorithm();
handleParameters_labels(label_identifiers);
handleParameters();
if (selected_labels.empty() && !out.empty()) // incompatible parameters
{
writeLog_("Error: The 'out' parameter cannot be used without a label (parameter 'sample:labels'). Use 'out_features' instead.");
return ILLEGAL_PARAMETERS;
}
//
// Initializing the SILACAnalzer with our parameters
//
SILACAnalyzer analyzer;
analyzer.setLogType(log_type_);
analyzer.initialize(
// section "sample"
selected_labels,
charge_min,
charge_max,
missed_cleavages,
isotopes_per_peptide_min,
isotopes_per_peptide_max,
// section "algorithm"
rt_threshold,
rt_min,
intensity_cutoff,
intensity_correlation,
model_deviation,
allow_missing_peaks,
// labels
label_identifiers);
//--------------------------------------------------
// loading input from .mzML
//--------------------------------------------------
MzMLFile file;
MSExperiment<Peak1D> exp;
// only read MS1 spectra ...
/*
std::vector<int> levels;
levels.push_back(1);
file.getOptions().setMSLevels(levels);
*/
LOG_DEBUG << "Loading input..." << endl;
file.setLogType(log_type_);
file.load(in, exp);
// set size of input map
exp.updateRanges();
// extract level 1 spectra
exp.getSpectra().erase(remove_if(exp.begin(), exp.end(), InMSLevelRange<MSExperiment<Peak1D>::SpectrumType>(IntList::create("1"), true)), exp.end());
// sort according to RT and MZ
exp.sortSpectra();
if (out_mzq != "")
{
vector<vector<String> > SILAClabels = analyzer.getSILAClabels(); // list of SILAC labels, e.g. selected_labels="[Lys4,Arg6][Lys8,Arg10]" => SILAClabels[0][1]="Arg6"
std::vector<std::vector<std::pair<String, DoubleReal> > > labels;
//add none label
labels.push_back(std::vector<std::pair<String, DoubleReal> >(1, std::make_pair<String, DoubleReal>(String("none"), DoubleReal(0))));
for (Size i = 0; i < SILAClabels.size(); ++i) //SILACLabels MUST be in weight order!!!
{
std::vector<std::pair<String, DoubleReal> > one_label;
for (UInt j = 0; j < SILAClabels[i].size(); ++j)
{
one_label.push_back(*(label_identifiers.find(SILAClabels[i][j]))); // this dereferencing would break if all SILAClabels would not have been checked before!
}
labels.push_back(one_label);
}
msq.registerExperiment(exp, labels); //add assays
msq.assignUIDs();
}
MSQuantifications::QUANT_TYPES quant_type = MSQuantifications::MS1LABEL;
msq.setAnalysisSummaryQuantType(quant_type); //add analysis_summary_
//--------------------------------------------------
// estimate peak width
//--------------------------------------------------
LOG_DEBUG << "Estimating peak width..." << endl;
PeakWidthEstimator::Result peak_width;
try
{
peak_width = analyzer.estimatePeakWidth(exp);
}
catch (Exception::InvalidSize &)
{
writeLog_("Error: Unable to estimate peak width of input data.");
return INCOMPATIBLE_INPUT_DATA;
}
if (in_filters == "")
{
//--------------------------------------------------
// filter input data
//--------------------------------------------------
LOG_DEBUG << "Filtering input data..." << endl;
analyzer.filterData(exp, peak_width, data);
//--------------------------------------------------
// store filter results
//--------------------------------------------------
if (out_filters != "")
{
LOG_DEBUG << "Storing filtering results..." << endl;
ConsensusMap map;
for (std::vector<std::vector<SILACPattern> >::const_iterator it = data.begin(); it != data.end(); ++it)
{
analyzer.generateFilterConsensusByPattern(map, *it);
}
analyzer.writeConsensus(out_filters, map);
}
}
else
{
//--------------------------------------------------
// load filter results
//--------------------------------------------------
LOG_DEBUG << "Loading filtering results..." << endl;
ConsensusMap map;
analyzer.readConsensus(in_filters, map);
analyzer.readFilterConsensusByPattern(map, data);
}
//--------------------------------------------------
// clustering
//--------------------------------------------------
LOG_DEBUG << "Clustering data..." << endl;
analyzer.clusterData(exp, peak_width, cluster_data, data);
//--------------------------------------------------------------
// write output
//--------------------------------------------------------------
if (out_debug != "")
{
LOG_DEBUG << "Writing debug output file..." << endl;
std::ofstream out((out_debug + ".clusters.csv").c_str());
vector<vector<DoubleReal> > massShifts = analyzer.getMassShifts(); // list of mass shifts
// generate header
out
<< std::fixed << std::setprecision(8)
<< "ID,RT,MZ_PEAK,CHARGE";
for (UInt i = 1; i <= massShifts[0].size(); ++i)
{
out << ",DELTA_MASS_" << i + 1;
}
for (UInt i = 0; i <= massShifts[0].size(); ++i)
{
for (UInt j = 1; j <= isotopes_per_peptide_max; ++j)
{
out << ",INT_PEAK_" << i + 1 << '_' << j;
}
}
out << ",MZ_RAW";
for (UInt i = 0; i <= massShifts[0].size(); ++i)
{
for (UInt j = 1; j <= isotopes_per_peptide_max; ++j)
{
out << ",INT_RAW_" << i + 1 << '_' << j;
}
}
for (UInt i = 0; i <= massShifts[0].size(); ++i)
{
for (UInt j = 1; j <= isotopes_per_peptide_max; ++j)
{
out << ",MZ_RAW_" << i + 1 << '_' << j;
}
}
out << '\n';
// write data
UInt cluster_id = 0;
for (vector<Clustering *>::const_iterator it = cluster_data.begin(); it != cluster_data.end(); ++it)
{
analyzer.generateClusterDebug(out, **it, cluster_id);
}
}
if (out != "")
{
LOG_DEBUG << "Generating output consensus map..." << endl;
ConsensusMap map;
for (vector<Clustering *>::const_iterator it = cluster_data.begin(); it != cluster_data.end(); ++it)
{
analyzer.generateClusterConsensusByCluster(map, **it);
}
LOG_DEBUG << "Adding meta data..." << endl;
// XXX: Need a map per mass shift
ConsensusMap::FileDescriptions& desc = map.getFileDescriptions();
Size id = 0;
for (ConsensusMap::FileDescriptions::iterator it = desc.begin(); it != desc.end(); ++it)
{
if (test_mode_) it->second.filename = in; // skip path, since its not cross platform and complicates verification
else it->second.filename = File::basename(in);
// Write correct label
// (this would crash if used without a label!)
if (id > 0) it->second.label = StringList(analyzer.getSILAClabels()[id - 1]).concatenate(""); // skip first round (empty label is not listed)
++id;
}
std::set<DataProcessing::ProcessingAction> actions;
actions.insert(DataProcessing::DATA_PROCESSING);
actions.insert(DataProcessing::PEAK_PICKING);
actions.insert(DataProcessing::FILTERING);
actions.insert(DataProcessing::QUANTITATION);
addDataProcessing_(map, getProcessingInfo_(actions));
analyzer.writeConsensus(out, map);
if (out_mzq != "")
{
LOG_DEBUG << "Generating output mzQuantML file..." << endl;
ConsensusMap numap(map);
//calc. ratios
for (ConsensusMap::iterator cit = numap.begin(); cit != numap.end(); ++cit)
{
//~ make ratio templates
std::vector<ConsensusFeature::Ratio> rts;
for (std::vector<MSQuantifications::Assay>::const_iterator ait = msq.getAssays().begin() + 1; ait != msq.getAssays().end(); ++ait)
{
ConsensusFeature::Ratio r;
r.numerator_ref_ = String(msq.getAssays().begin()->uid_);
r.denominator_ref_ = String(ait->uid_);
r.description_.push_back("Simple ratio calc");
r.description_.push_back("light to medium/.../heavy");
//~ "<cvParam cvRef=\"PSI-MS\" accession=\"MS:1001132\" name=\"peptide ratio\"/>"
rts.push_back(r);
}
const ConsensusFeature::HandleSetType& feature_handles = cit->getFeatures();
if (feature_handles.size() > 1)
{
std::set<FeatureHandle, FeatureHandle::IndexLess>::const_iterator fit = feature_handles.begin(); // this is unlabeled
fit++;
for (; fit != feature_handles.end(); ++fit)
{
Size ri = std::distance(feature_handles.begin(), fit);
rts[ri - 1].ratio_value_ = feature_handles.begin()->getIntensity() / fit->getIntensity(); // a proper silacalanyzer algo should never have 0-intensities so no 0devison ...
}
}
cit->setRatios(rts);
}
msq.addConsensusMap(numap); //add SILACAnalyzer result
//~ msq.addFeatureMap();//add SILACAnalyzer evidencetrail as soon as clear what is realy contained in the featuremap
//~ add AuditCollection - no such concept in TOPPTools yet
analyzer.writeMzQuantML(out_mzq, msq);
}
}
if (out_clusters != "")
{
LOG_DEBUG << "Generating cluster output file..." << endl;
ConsensusMap map;
for (vector<Clustering *>::const_iterator it = cluster_data.begin(); it != cluster_data.end(); ++it)
{
UInt cluster_id = 0;
analyzer.generateClusterConsensusByPattern(map, **it, cluster_id);
}
ConsensusMap::FileDescription & desc = map.getFileDescriptions()[0];
desc.filename = in;
desc.label = "Cluster";
analyzer.writeConsensus(out_clusters, map);
}
if (out_features != "")
{
LOG_DEBUG << "Generating output feature map..." << endl;
FeatureMap<> map;
for (vector<Clustering *>::const_iterator it = cluster_data.begin(); it != cluster_data.end(); ++it)
{
analyzer.generateClusterFeatureByCluster(map, **it);
}
analyzer.writeFeatures(out_features, map);
}
return EXECUTION_OK;
}
ExitCodes main_(int, const char **)
{
String in = getStringOption_("in"), out = getStringOption_("out"),
id_out = getStringOption_("id_out");
if (out.empty() && id_out.empty())
{
throw Exception::RequiredParameterNotGiven(__FILE__, __LINE__,
__PRETTY_FUNCTION__,
"out/id_out");
}
vector<ProteinIdentification> proteins;
vector<PeptideIdentification> peptides;
FileTypes::Type in_type = FileHandler::getType(in);
if (in_type == FileTypes::MZML)
{
MSExperiment<> experiment;
MzMLFile().load(in, experiment);
// what about unassigned peptide IDs?
for (MSExperiment<>::Iterator exp_it = experiment.begin();
exp_it != experiment.end(); ++exp_it)
{
peptides.insert(peptides.end(),
exp_it->getPeptideIdentifications().begin(),
exp_it->getPeptideIdentifications().end());
exp_it->getPeptideIdentifications().clear();
}
experiment.getProteinIdentifications().swap(proteins);
if (!out.empty())
{
addDataProcessing_(experiment,
getProcessingInfo_(DataProcessing::FILTERING));
MzMLFile().store(out, experiment);
}
}
else if (in_type == FileTypes::FEATUREXML)
{
FeatureMap features;
FeatureXMLFile().load(in, features);
features.getUnassignedPeptideIdentifications().swap(peptides);
for (FeatureMap::Iterator feat_it = features.begin();
feat_it != features.end(); ++feat_it)
{
peptides.insert(peptides.end(),
feat_it->getPeptideIdentifications().begin(),
feat_it->getPeptideIdentifications().end());
feat_it->getPeptideIdentifications().clear();
}
features.getProteinIdentifications().swap(proteins);
if (!out.empty())
{
addDataProcessing_(features,
getProcessingInfo_(DataProcessing::FILTERING));
FeatureXMLFile().store(out, features);
}
}
else // consensusXML
{
ConsensusMap consensus;
ConsensusXMLFile().load(in, consensus);
consensus.getUnassignedPeptideIdentifications().swap(peptides);
for (ConsensusMap::Iterator cons_it = consensus.begin();
cons_it != consensus.end(); ++cons_it)
{
peptides.insert(peptides.end(),
cons_it->getPeptideIdentifications().begin(),
cons_it->getPeptideIdentifications().end());
cons_it->getPeptideIdentifications().clear();
}
consensus.getProteinIdentifications().swap(proteins);
if (!out.empty())
{
addDataProcessing_(consensus,
getProcessingInfo_(DataProcessing::FILTERING));
ConsensusXMLFile().store(out, consensus);
}
}
if (!id_out.empty())
{
// IDMapper can match a peptide ID to several overlapping features,
// resulting in duplicates; this shouldn't be the case for peak data
if (in_type != FileTypes::MZML) removeDuplicates_(peptides);
IdXMLFile().store(id_out, proteins, peptides);
}
return EXECUTION_OK;
}
void IsobaricChannelExtractor::extractChannels(const MSExperiment<Peak1D>& ms_exp_data, ConsensusMap& consensus_map)
{
if (ms_exp_data.empty())
{
LOG_WARN << "The given file does not contain any conventional peak data, but might"
" contain chromatograms. This tool currently cannot handle them, sorry.\n";
throw Exception::MissingInformation(__FILE__, __LINE__, __PRETTY_FUNCTION__, "Experiment has no scans!");
}
// clear the output map
consensus_map.clear(false);
consensus_map.setExperimentType("labeled_MS2");
// create predicate for spectrum checking
LOG_INFO << "Selecting scans with activation mode: " << (selected_activation_ == "" ? "any" : selected_activation_) << "\n";
HasActivationMethod<MSExperiment<Peak1D>::SpectrumType> activation_predicate(StringList::create(selected_activation_));
// now we have picked data
// --> assign peaks to channels
UInt64 element_index(0);
// remember the current precusor spectrum
MSExperiment<Peak1D>::ConstIterator prec_spec = ms_exp_data.end();
for (MSExperiment<Peak1D>::ConstIterator it = ms_exp_data.begin(); it != ms_exp_data.end(); ++it)
{
// remember the last MS1 spectra as we assume it to be the precursor spectrum
if (it->getMSLevel() == 1) prec_spec = it;
if (selected_activation_ == "" || activation_predicate(*it))
{
// check if precursor is available
if (it->getPrecursors().empty())
{
throw Exception::MissingInformation(__FILE__, __LINE__, __PRETTY_FUNCTION__, String("No precursor information given for scan native ID ") + it->getNativeID() + " with RT " + String(it->getRT()));
}
// check precursor constraints
if (!isValidPrecursor_(it->getPrecursors()[0]))
{
LOG_DEBUG << "Skip spectrum " << it->getNativeID() << ": Precursor doesn't fulfill all constraints." << std::endl;
continue;
}
// check precursor purity if we have a valid precursor ..
if (prec_spec != ms_exp_data.end())
{
const DoubleReal purity = computePrecursorPurity_(it, prec_spec);
if (purity < min_precursor_purity_)
{
LOG_DEBUG << "Skip spectrum " << it->getNativeID() << ": Precursor purity is below the threshold. [purity = " << purity << "]" << std::endl;
continue;
}
}
else
{
LOG_INFO << "No precursor available for spectrum: " << it->getNativeID() << std::endl;
}
if (!(prec_spec == ms_exp_data.end()) && computePrecursorPurity_(it, prec_spec) < min_precursor_purity_)
{
LOG_DEBUG << "Skip spectrum " << it->getNativeID() << ": Precursor purity is below the threshold." << std::endl;
continue;
}
// store RT&MZ of parent ion as centroid of ConsensusFeature
ConsensusFeature cf;
cf.setUniqueId();
cf.setRT(it->getRT());
cf.setMZ(it->getPrecursors()[0].getMZ());
Peak2D channel_value;
channel_value.setRT(it->getRT());
// for each each channel
UInt64 map_index = 0;
Peak2D::IntensityType overall_intensity = 0;
for (IsobaricQuantitationMethod::IsobaricChannelList::const_iterator cl_it = quant_method_->getChannelInformation().begin();
cl_it != quant_method_->getChannelInformation().end();
++cl_it)
{
// set mz-position of channel
channel_value.setMZ(cl_it->center);
// reset intensity
channel_value.setIntensity(0);
// as every evaluation requires time, we cache the MZEnd iterator
const MSExperiment<Peak1D>::SpectrumType::ConstIterator mz_end = it->MZEnd(cl_it->center + reporter_mass_shift_);
// add up all signals
for (MSExperiment<Peak1D>::SpectrumType::ConstIterator mz_it = it->MZBegin(cl_it->center - reporter_mass_shift_);
mz_it != mz_end;
++mz_it)
{
channel_value.setIntensity(channel_value.getIntensity() + mz_it->getIntensity());
}
// discard contribution of this channel as it is below the required intensity threshold
if (channel_value.getIntensity() < min_reporter_intensity_)
{
channel_value.setIntensity(0);
}
overall_intensity += channel_value.getIntensity();
// add channel to ConsensusFeature
cf.insert(map_index++, channel_value, element_index);
} // ! channel_iterator
// check if we keep this feature or if it contains low-intensity quantifications
if (remove_low_intensity_quantifications_ && hasLowIntensityReporter_(cf))
{
continue;
}
// check featureHandles are not empty
if (overall_intensity == 0)
{
cf.setMetaValue("all_empty", String("true"));
}
cf.setIntensity(overall_intensity);
consensus_map.push_back(cf);
// the tandem-scan in the order they appear in the experiment
++element_index;
}
} // ! Experiment iterator
/// add meta information to the map
registerChannelsInOutputMap_(consensus_map);
}
ExitCodes
main_(int, const char**)
{
//-------------------------------------------------------------
// general variables and data
//-------------------------------------------------------------
FileHandler fh;
vector<PeptideIdentification> peptide_identifications;
vector<ProteinIdentification> protein_identifications;
//-------------------------------------------------------------
// reading input
//-------------------------------------------------------------
const String in = getStringOption_("in");
ProgressLogger logger;
logger.setLogType(ProgressLogger::CMD);
logger.startProgress(0, 1, "Loading...");
if (File::isDirectory(in))
{
const String in_directory = File::absolutePath(in).ensureLastChar('/');
const String mz_file = getStringOption_("mz_file");
const bool ignore_proteins_per_peptide = getFlag_("ignore_proteins_per_peptide");
UInt i = 0;
FileHandler fh;
FileTypes::Type type;
MSExperiment<Peak1D> msexperiment;
// Note: we had issues with leading zeroes, so let us represent scan numbers as Int (next line used to be map<String, float> num_and_rt;) However, now String::toInt() might throw.
map<Int, float> num_and_rt;
vector<String> NativeID;
// The mz-File (if given)
if (!mz_file.empty())
{
type = fh.getTypeByFileName(mz_file);
fh.loadExperiment(mz_file, msexperiment, type);
for (MSExperiment<Peak1D>::Iterator spectra_it = msexperiment.begin(); spectra_it != msexperiment.end(); ++spectra_it)
{
String(spectra_it->getNativeID()).split('=', NativeID);
try
{
num_and_rt[NativeID[1].toInt()] = spectra_it->getRT();
// cout << "num_and_rt: " << NativeID[1] << " = " << NativeID[1].toInt() << " : " << num_and_rt[NativeID[1].toInt()] << endl; // CG debuggging 2009-07-01
}
catch (Exception::ConversionError& e)
{
writeLog_(String("Error: Cannot read scan number as integer. '") + e.getMessage());
}
}
}
// Get list of the actual Sequest .out-Files
StringList in_files;
if (!File::fileList(in_directory, String("*.out"), in_files))
{
writeLog_(String("Error: No .out files found in '") + in_directory + "'. Aborting!");
}
// Now get to work ...
for (vector<String>::const_iterator in_files_it = in_files.begin(); in_files_it != in_files.end(); ++in_files_it)
{
vector<PeptideIdentification> peptide_ids_seq;
ProteinIdentification protein_id_seq;
vector<double> pvalues_seq;
vector<String> in_file_vec;
SequestOutfile sequest_outfile;
writeDebug_(String("Reading file ") + *in_files_it, 3);
try
{
sequest_outfile.load((String) (in_directory + *in_files_it), peptide_ids_seq, protein_id_seq, 1.0, pvalues_seq, "Sequest", ignore_proteins_per_peptide);
in_files_it->split('.', in_file_vec);
for (Size j = 0; j < peptide_ids_seq.size(); ++j)
{
// We have to explicitly set the identifiers, because the normal set ones are composed of search engine name and date, which is the same for a bunch of sequest out-files.
peptide_ids_seq[j].setIdentifier(*in_files_it + "_" + i);
Int scan_number = 0;
if (!mz_file.empty())
{
try
{
scan_number = in_file_vec[2].toInt();
peptide_ids_seq[j].setRT(num_and_rt[scan_number]);
}
catch (Exception::ConversionError& e)
{
writeLog_(String("Error: Cannot read scan number as integer. '") + e.getMessage());
}
catch (exception& e)
{
writeLog_(String("Error: Cannot read scan number as integer. '") + e.what());
}
//double real_mz = ( peptide_ids_seq[j].getMZ() - hydrogen_mass )/ (double)peptide_ids_seq[j].getHits()[0].getCharge(); // ???? semantics of mz
const double real_mz = peptide_ids_seq[j].getMZ() / (double) peptide_ids_seq[j].getHits()[0].getCharge();
peptide_ids_seq[j].setMZ(real_mz);
}
writeDebug_(String("scan: ") + String(scan_number) + String(" RT: ") + String(peptide_ids_seq[j].getRT()) + " MZ: " + String(peptide_ids_seq[j].getMZ()) + " Ident: " + peptide_ids_seq[j].getIdentifier(), 4);
peptide_identifications.push_back(peptide_ids_seq[j]);
}
protein_id_seq.setIdentifier(*in_files_it + "_" + i);
protein_identifications.push_back(protein_id_seq);
++i;
}
catch (Exception::ParseError& pe)
{
writeLog_(pe.getMessage() + String("(file: ") + *in_files_it + ")");
throw;
}
catch (...)
{
writeLog_(String("Error reading file: ") + *in_files_it);
throw;
}
}
writeDebug_("All files processed.", 3);
} // ! directory
else
{
FileTypes::Type in_type = fh.getType(in);
if (in_type == FileTypes::PEPXML)
{
String exp_name = getStringOption_("mz_file");
String orig_name = getStringOption_("mz_name");
bool use_precursor_data = getFlag_("use_precursor_data");
if (exp_name.empty())
{
PepXMLFile().load(in, protein_identifications,
peptide_identifications, orig_name);
}
else
{
MSExperiment<> exp;
fh.loadExperiment(exp_name, exp);
if (!orig_name.empty())
{
exp_name = orig_name;
}
PepXMLFile().load(in, protein_identifications,
peptide_identifications, exp_name, exp,
use_precursor_data);
}
}
else if (in_type == FileTypes::IDXML)
{
IdXMLFile().load(in, protein_identifications, peptide_identifications);
}
else if (in_type == FileTypes::MZIDENTML)
{
LOG_WARN << "Converting from mzid: you might experience loss of information depending on the capabilities of the target format." << endl;
MzIdentMLFile().load(in, protein_identifications, peptide_identifications);
}
else if (in_type == FileTypes::PROTXML)
{
protein_identifications.resize(1);
peptide_identifications.resize(1);
ProtXMLFile().load(in, protein_identifications[0],
peptide_identifications[0]);
}
else if (in_type == FileTypes::OMSSAXML)
{
protein_identifications.resize(1);
OMSSAXMLFile().load(in, protein_identifications[0],
peptide_identifications, true);
}
else if (in_type == FileTypes::MASCOTXML)
{
String scan_regex = getStringOption_("scan_regex");
String exp_name = getStringOption_("mz_file");
MascotXMLFile::RTMapping rt_mapping;
if (!exp_name.empty())
{
PeakMap exp;
// load only MS2 spectra:
fh.getOptions().addMSLevel(2);
fh.loadExperiment(exp_name, exp, FileTypes::MZML, log_type_);
MascotXMLFile::generateRTMapping(exp.begin(), exp.end(), rt_mapping);
}
protein_identifications.resize(1);
MascotXMLFile().load(in, protein_identifications[0],
peptide_identifications, rt_mapping, scan_regex);
}
else if (in_type == FileTypes::XML)
{
ProteinIdentification protein_id;
XTandemXMLFile().load(in, protein_id, peptide_identifications);
protein_id.setSearchEngineVersion("");
protein_id.setSearchEngine("XTandem");
protein_identifications.push_back(protein_id);
String exp_name = getStringOption_("mz_file");
if (!exp_name.empty())
{
PeakMap exp;
fh.getOptions().addMSLevel(2);
fh.loadExperiment(exp_name, exp, FileTypes::MZML, log_type_);
for (vector<PeptideIdentification>::iterator it = peptide_identifications.begin(); it != peptide_identifications.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 << "XTandem xml: Error: id '" << id << "' not found in peak map!" << endl;
}
}
}
}
else
{
writeLog_("Unknown input file type given. Aborting!");
printUsage_();
return ILLEGAL_PARAMETERS;
}
}
logger.endProgress();
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
const String out = getStringOption_("out");
FileTypes::Type out_type = FileTypes::nameToType(getStringOption_("out_type"));
if (out_type == FileTypes::UNKNOWN)
{
out_type = fh.getTypeByFileName(out);
}
if (out_type == FileTypes::UNKNOWN)
{
writeLog_("Error: Could not determine output file type!");
return PARSE_ERROR;
}
logger.startProgress(0, 1, "Storing...");
if (out_type == FileTypes::PEPXML)
{
bool peptideprophet_analyzed = getFlag_("peptideprophet_analyzed");
String mz_file = getStringOption_("mz_file");
String mz_name = getStringOption_("mz_name");
PepXMLFile().store(out, protein_identifications, peptide_identifications, mz_file, mz_name, peptideprophet_analyzed);
}
else if (out_type == FileTypes::IDXML)
{
IdXMLFile().store(out, protein_identifications, peptide_identifications);
}
else if (out_type == FileTypes::MZIDENTML)
{
MzIdentMLFile().store(out, protein_identifications, peptide_identifications);
}
else if (out_type == FileTypes::FASTA)
{
Size count = 0;
ofstream fasta(out.c_str(), ios::out);
for (Size i = 0; i < peptide_identifications.size(); ++i)
{
for (Size l = 0; l < peptide_identifications[i].getHits().size(); ++l)
{
const PeptideHit& hit = peptide_identifications[i].getHits()[l];
fasta << ">" << hit.getSequence().toUnmodifiedString() << "|" << count++
<< "|" << hit.getSequence().toString() << endl;
String seq = hit.getSequence().toUnmodifiedString();
// FASTA files should have at most 60 characters of sequence info per line
for (Size j = 0; j < seq.size(); j += 60)
{
Size k = min(j + 60, seq.size());
fasta << string(seq[j], seq[k]) << endl;
}
}
}
}
else
{
writeLog_("Unsupported output file type given. Aborting!");
printUsage_();
return ILLEGAL_PARAMETERS;
}
logger.endProgress();
return EXECUTION_OK;
}
ExitCodes main_(int, const char**)
{
vector<ProteinIdentification> prot_ids;
vector<PeptideIdentification> pep_ids;
ProteinHit temp_protein_hit;
//-------------------------------------------------------------
// parsing parameters
//-------------------------------------------------------------
String inputfile_id = getStringOption_("id");
String inputfile_feature = getStringOption_("feature");
String inputfile_consensus = getStringOption_("consensus");
String inputfile_raw = getStringOption_("in");
String outputfile_name = getStringOption_("out");
//~ bool Ms1(getFlag_("MS1"));
//~ bool Ms2(getFlag_("MS2"));
bool remove_duplicate_features(getFlag_("remove_duplicate_features"));
//-------------------------------------------------------------
// fetch vocabularies
//------------------------------------------------------------
ControlledVocabulary cv;
cv.loadFromOBO("PSI-MS", File::find("/CV/psi-ms.obo"));
cv.loadFromOBO("QC", File::find("/CV/qc-cv.obo"));
QcMLFile qcmlfile;
//-------------------------------------------------------------
// MS aqiusition
//------------------------------------------------------------
String base_name = QFileInfo(QString::fromStdString(inputfile_raw)).baseName();
cout << "Reading mzML file..." << endl;
MzMLFile mz_data_file;
MSExperiment<Peak1D> exp;
MzMLFile().load(inputfile_raw, exp);
//---prep input
exp.sortSpectra();
UInt min_mz = std::numeric_limits<UInt>::max();
UInt max_mz = 0;
std::map<Size, UInt> mslevelcounts;
qcmlfile.registerRun(base_name,base_name); //TODO use UIDs
//---base MS aquisition qp
String msaq_ref = base_name + "_msaq";
QcMLFile::QualityParameter qp;
qp.id = msaq_ref; ///< Identifier
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000004";
try
{
//~ const ControlledVocabulary::CVTerm& test = cv.getTermByName("MS aquisition result details");
//~ cout << test.name << test.id << endl;
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
//~ const ControlledVocabulary::CVTerm& term = cv.getTerm("0000004");
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "mzML file"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
//---file origin qp
qp = QcMLFile::QualityParameter();
qp.name = "mzML file"; ///< Name
qp.id = base_name + "_run_name"; ///< Identifier
qp.cvRef = "MS"; ///< cv reference
qp.cvAcc = "MS:1000577";
qp.value = base_name;
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.name = "instrument model"; ///< Name
qp.id = base_name + "_instrument_name"; ///< Identifier
qp.cvRef = "MS"; ///< cv reference
qp.cvAcc = "MS:1000031";
qp.value = exp.getInstrument().getName();
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.name = "completion time"; ///< Name
qp.id = base_name + "_date"; ///< Identifier
qp.cvRef = "MS"; ///< cv reference
qp.cvAcc = "MS:1000747";
qp.value = exp.getDateTime().getDate();
qcmlfile.addRunQualityParameter(base_name, qp);
//---precursors at
QcMLFile::Attachment at;
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000044";
at.qualityRef = msaq_ref;
at.id = base_name + "_precursors"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "precursors"; ///< Name
}
at.colTypes.push_back("MS:1000894_[sec]"); //RT
at.colTypes.push_back("MS:1000040"); //MZ
for (Size i = 0; i < exp.size(); ++i)
{
mslevelcounts[exp[i].getMSLevel()]++;
if (exp[i].getMSLevel() == 2)
{
if (exp[i].getPrecursors().front().getMZ() < min_mz)
{
min_mz = exp[i].getPrecursors().front().getMZ();
}
if (exp[i].getPrecursors().front().getMZ() > max_mz)
{
max_mz = exp[i].getPrecursors().front().getMZ();
}
std::vector<String> row;
row.push_back(exp[i].getRT());
row.push_back(exp[i].getPrecursors().front().getMZ());
at.tableRows.push_back(row);
}
}
qcmlfile.addRunAttachment(base_name, at);
//---aquisition results qp
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000006"; ///< cv accession for "aquisition results"
qp.id = base_name + "_ms1aquisition"; ///< Identifier
qp.value = String(mslevelcounts[1]);
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "number of ms1 spectra"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000007"; ///< cv accession for "aquisition results"
qp.id = base_name + "_ms2aquisition"; ///< Identifier
qp.value = String(mslevelcounts[2]);
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "number of ms2 spectra"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000008"; ///< cv accession for "aquisition results"
qp.id = base_name + "_Chromaquisition"; ///< Identifier
qp.value = String(exp.getChromatograms().size());
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "number of chromatograms"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000009";
at.qualityRef = msaq_ref;
at.id = base_name + "_mzrange"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "MS MZ aquisition ranges"; ///< Name
}
at.colTypes.push_back("QC:0000010"); //MZ
at.colTypes.push_back("QC:0000011"); //MZ
std::vector<String> rowmz;
rowmz.push_back(String(min_mz));
rowmz.push_back(String(max_mz));
at.tableRows.push_back(rowmz);
qcmlfile.addRunAttachment(base_name, at);
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000012";
at.qualityRef = msaq_ref;
at.id = base_name + "_rtrange"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "MS RT aquisition ranges"; ///< Name
}
at.colTypes.push_back("QC:0000013"); //MZ
at.colTypes.push_back("QC:0000014"); //MZ
std::vector<String> rowrt;
rowrt.push_back(String(exp.begin()->getRT()));
rowrt.push_back(String(exp.getSpectra().back().getRT()));
at.tableRows.push_back(rowrt);
qcmlfile.addRunAttachment(base_name, at);
//---ion current stability ( & tic ) qp
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000022";
at.qualityRef = msaq_ref;
at.id = base_name + "_tics"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "MS TICs"; ///< Name
}
at.colTypes.push_back("MS:1000894_[sec]");
at.colTypes.push_back("MS:1000285");
UInt max = 0;
Size below_10k = 0;
for (Size i = 0; i < exp.size(); ++i)
{
if (exp[i].getMSLevel() == 1)
{
UInt sum = 0;
for (Size j = 0; j < exp[i].size(); ++j)
{
sum += exp[i][j].getIntensity();
}
if (sum > max)
{
max = sum;
}
if (sum < 10000)
{
++below_10k;
}
std::vector<String> row;
row.push_back(exp[i].getRT());
row.push_back(sum);
at.tableRows.push_back(row);
}
}
qcmlfile.addRunAttachment(base_name, at);
qp = QcMLFile::QualityParameter();
qp.id = base_name + "_ticslump"; ///< Identifier
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000023";
qp.value = String((100 / exp.size()) * below_10k);
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "percentage of tic slumps"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
//-------------------------------------------------------------
// MS id
//------------------------------------------------------------
if (inputfile_id != "")
{
IdXMLFile().load(inputfile_id, prot_ids, pep_ids);
cerr << "idXML read ended. Found " << pep_ids.size() << " peptide identifications." << endl;
ProteinIdentification::SearchParameters params = prot_ids[0].getSearchParameters();
vector<String> var_mods = params.variable_modifications;
//~ boost::regex re("(?<=[KR])(?=[^P])");
String msid_ref = base_name + "_msid";
QcMLFile::QualityParameter qp;
qp.id = msid_ref; ///< Identifier
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000025";
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "MS identification result details"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000026";
at.qualityRef = msid_ref;
at.id = base_name + "_idsetting"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "MS id settings"; ///< Name
}
at.colTypes.push_back("MS:1001013"); //MS:1001013 db name MS:1001016 version MS:1001020 taxonomy
at.colTypes.push_back("MS:1001016");
at.colTypes.push_back("MS:1001020");
std::vector<String> row;
row.push_back(String(prot_ids.front().getSearchParameters().db));
row.push_back(String(prot_ids.front().getSearchParameters().db_version));
row.push_back(String(prot_ids.front().getSearchParameters().taxonomy));
at.tableRows.push_back(row);
qcmlfile.addRunAttachment(base_name, at);
UInt spectrum_count = 0;
Size peptide_hit_count = 0;
UInt runs_count = 0;
Size protein_hit_count = 0;
set<String> peptides;
set<String> proteins;
Size missedcleavages = 0;
for (Size i = 0; i < pep_ids.size(); ++i)
{
if (!pep_ids[i].empty())
{
++spectrum_count;
peptide_hit_count += pep_ids[i].getHits().size();
const vector<PeptideHit>& temp_hits = pep_ids[i].getHits();
for (Size j = 0; j < temp_hits.size(); ++j)
{
peptides.insert(temp_hits[j].getSequence().toString());
}
}
}
for (set<String>::iterator it = peptides.begin(); it != peptides.end(); ++it)
{
for (String::const_iterator st = it->begin(); st != it->end() - 1; ++st)
{
if (*st == 'K' || *st == 'R')
{
++missedcleavages;
}
}
}
for (Size i = 0; i < prot_ids.size(); ++i)
{
++runs_count;
protein_hit_count += prot_ids[i].getHits().size();
const vector<ProteinHit>& temp_hits = prot_ids[i].getHits();
for (Size j = 0; j < temp_hits.size(); ++j)
{
proteins.insert(temp_hits[j].getAccession());
}
}
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000037"; ///< cv accession
qp.id = base_name + "_misscleave"; ///< Identifier
qp.value = missedcleavages;
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of missed cleavages"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000032"; ///< cv accession
qp.id = base_name + "_totprot"; ///< Identifier
qp.value = protein_hit_count;
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of identified proteins"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000033"; ///< cv accession
qp.id = base_name + "_totuniqprot"; ///< Identifier
qp.value = String(proteins.size());
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of uniquely identified proteins"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000029"; ///< cv accession
qp.id = base_name + "_psms"; ///< Identifier
qp.value = String(spectrum_count);
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of PSM"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000030"; ///< cv accession
qp.id = base_name + "_totpeps"; ///< Identifier
qp.value = String(peptide_hit_count);
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of identified peptides"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000031"; ///< cv accession
qp.id = base_name + "_totuniqpeps"; ///< Identifier
qp.value = String(peptides.size());
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of uniquely identified peptides"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000038";
at.qualityRef = msid_ref;
at.id = base_name + "_massacc"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "delta ppm tables";
}
//~ delta ppm QC:0000039 RT MZ uniqueness ProteinID MS:1000885 target/decoy Score PeptideSequence MS:1000889 Annots string Similarity Charge UO:0000219 TheoreticalWeight UO:0000221 Oxidation_(M)
at.colTypes.push_back("RT");
at.colTypes.push_back("MZ");
at.colTypes.push_back("Score");
at.colTypes.push_back("PeptideSequence");
at.colTypes.push_back("Charge");
at.colTypes.push_back("TheoreticalWeight");
at.colTypes.push_back("delta_ppm");
for (UInt w = 0; w < var_mods.size(); ++w)
{
at.colTypes.push_back(String(var_mods[w]).substitute(' ', '_'));
}
std::vector<double> deltas;
//~ prot_ids[0].getSearchParameters();
for (vector<PeptideIdentification>::iterator it = pep_ids.begin(); it != pep_ids.end(); ++it)
{
if (it->getHits().size() > 0)
{
std::vector<String> row;
row.push_back(it->getRT());
row.push_back(it->getMZ());
PeptideHit tmp = it->getHits().front(); //TODO depends on score & sort
vector<UInt> pep_mods;
for (UInt w = 0; w < var_mods.size(); ++w)
{
pep_mods.push_back(0);
}
for (AASequence::ConstIterator z = tmp.getSequence().begin(); z != tmp.getSequence().end(); ++z)
{
Residue res = *z;
String temp;
if (res.getModification().size() > 0 && res.getModification() != "Carbamidomethyl")
{
temp = res.getModification() + " (" + res.getOneLetterCode() + ")";
//cout<<res.getModification()<<endl;
for (UInt w = 0; w < var_mods.size(); ++w)
{
if (temp == var_mods[w])
{
//cout<<temp;
pep_mods[w] += 1;
}
}
}
}
row.push_back(tmp.getScore());
row.push_back(tmp.getSequence().toString().removeWhitespaces());
row.push_back(tmp.getCharge());
row.push_back(String((tmp.getSequence().getMonoWeight() + tmp.getCharge() * Constants::PROTON_MASS_U) / tmp.getCharge()));
double dppm = /* std::abs */ (getMassDifference(((tmp.getSequence().getMonoWeight() + tmp.getCharge() * Constants::PROTON_MASS_U) / tmp.getCharge()), it->getMZ(), true));
row.push_back(String(dppm));
deltas.push_back(dppm);
for (UInt w = 0; w < var_mods.size(); ++w)
{
row.push_back(pep_mods[w]);
}
at.tableRows.push_back(row);
}
}
qcmlfile.addRunAttachment(base_name, at);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000040"; ///< cv accession
qp.id = base_name + "_mean_delta"; ///< Identifier
qp.value = String(OpenMS::Math::mean(deltas.begin(), deltas.end()));
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "mean delta ppm"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000041"; ///< cv accession
qp.id = base_name + "_median_delta"; ///< Identifier
qp.value = String(OpenMS::Math::median(deltas.begin(), deltas.end(), false));
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "median delta ppm"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000035"; ///< cv accession
qp.id = base_name + "_ratio_id"; ///< Identifier
qp.value = String(double(pep_ids.size()) / double(mslevelcounts[2]));
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "id ratio"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
}
//-------------------------------------------------------------
// MS quantitation
//------------------------------------------------------------
FeatureMap map;
String msqu_ref = base_name + "_msqu";
if (inputfile_feature != "")
{
FeatureXMLFile f;
f.load(inputfile_feature, map);
cout << "Read featureXML file..." << endl;
//~ UInt fiter = 0;
map.sortByRT();
map.updateRanges();
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000045"; ///< cv accession
qp.id = msqu_ref; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "MS quantification result details"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000046"; ///< cv accession
qp.id = base_name + "_feature_count"; ///< Identifier
qp.value = String(map.size());
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "number of features"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
}
if (inputfile_feature != "" && !remove_duplicate_features)
{
QcMLFile::Attachment at;
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000047";
at.qualityRef = msqu_ref;
at.id = base_name + "_features"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "features"; ///< Name
}
at.colTypes.push_back("MZ");
at.colTypes.push_back("RT");
at.colTypes.push_back("Intensity");
at.colTypes.push_back("Charge");
at.colTypes.push_back("Quality");
at.colTypes.push_back("FWHM");
at.colTypes.push_back("IDs");
UInt fiter = 0;
map.sortByRT();
//ofstream out(outputfile_name.c_str());
while (fiter < map.size())
{
std::vector<String> row;
row.push_back(map[fiter].getMZ());
row.push_back(map[fiter].getRT());
row.push_back(map[fiter].getIntensity());
row.push_back(map[fiter].getCharge());
row.push_back(map[fiter].getOverallQuality());
row.push_back(map[fiter].getWidth());
row.push_back(map[fiter].getPeptideIdentifications().size());
fiter++;
at.tableRows.push_back(row);
}
qcmlfile.addRunAttachment(base_name, at);
}
else if (inputfile_feature != "" && remove_duplicate_features)
{
QcMLFile::Attachment at;
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000047";
at.qualityRef = msqu_ref;
at.id = base_name + "_features"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "features"; ///< Name
}
at.colTypes.push_back("MZ");
at.colTypes.push_back("RT");
at.colTypes.push_back("Intensity");
at.colTypes.push_back("Charge");
FeatureMap map, map_out;
FeatureXMLFile f;
f.load(inputfile_feature, map);
UInt fiter = 0;
map.sortByRT();
while (fiter < map.size())
{
FeatureMap map_tmp;
for (UInt k = fiter; k <= map.size(); ++k)
{
if (abs(map[fiter].getRT() - map[k].getRT()) < 0.1)
{
//~ cout << fiter << endl;
map_tmp.push_back(map[k]);
}
else
{
fiter = k;
break;
}
}
map_tmp.sortByMZ();
UInt retif = 1;
map_out.push_back(map_tmp[0]);
while (retif < map_tmp.size())
{
if (abs(map_tmp[retif].getMZ() - map_tmp[retif - 1].getMZ()) > 0.01)
{
cout << "equal RT, but mass different" << endl;
map_out.push_back(map_tmp[retif]);
}
retif++;
}
}
qcmlfile.addRunAttachment(base_name, at);
}
if (inputfile_consensus != "")
{
cout << "Reading consensusXML file..." << endl;
ConsensusXMLFile f;
ConsensusMap map;
f.load(inputfile_consensus, map);
//~ String CONSENSUS_NAME = "_consensus.tsv";
//~ String combined_out = outputfile_name + CONSENSUS_NAME;
//~ ofstream out(combined_out.c_str());
at = QcMLFile::Attachment();
qp.name = "consensuspoints"; ///< Name
//~ qp.id = base_name + "_consensuses"; ///< Identifier
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:xxxxxxxx"; ///< cv accession "featuremapper results"
at.colTypes.push_back("Native_spectrum_ID");
at.colTypes.push_back("DECON_RT_(sec)");
at.colTypes.push_back("DECON_MZ_(Th)");
at.colTypes.push_back("DECON_Intensity");
at.colTypes.push_back("Feature_RT_(sec)");
at.colTypes.push_back("Feature_MZ_(Th)");
at.colTypes.push_back("Feature_Intensity");
at.colTypes.push_back("Feature_Charge");
for (ConsensusMap::const_iterator cmit = map.begin(); cmit != map.end(); ++cmit)
{
const ConsensusFeature& CF = *cmit;
for (ConsensusFeature::const_iterator cfit = CF.begin(); cfit != CF.end(); ++cfit)
{
std::vector<String> row;
FeatureHandle FH = *cfit;
row.push_back(CF.getMetaValue("spectrum_native_id"));
row.push_back(CF.getRT()); row.push_back(CF.getMZ());
row.push_back(CF.getIntensity());
row.push_back(FH.getRT());
row.push_back(FH.getMZ());
row.push_back(FH.getCharge());
at.tableRows.push_back(row);
}
}
qcmlfile.addRunAttachment(base_name, at);
}
//-------------------------------------------------------------
// finalize
//------------------------------------------------------------
qcmlfile.store(outputfile_name);
return EXECUTION_OK;
}
ExitCodes main_(int, const char**)
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
// file list
StringList file_list = getStringList_("in");
// file type
FileHandler file_handler;
FileTypes::Type force_type;
if (getStringOption_("in_type").size() > 0)
{
force_type = FileTypes::nameToType(getStringOption_("in_type"));
}
else
{
force_type = file_handler.getType(file_list[0]);
}
// output file names and types
String out_file = getStringOption_("out");
bool annotate_file_origin = getFlag_("annotate_file_origin");
rt_gap_ = getDoubleOption_("rt_concat:gap");
vector<String> trafo_out = getStringList_("rt_concat:trafo_out");
if (trafo_out.empty())
{
// resize now so we don't have to worry about indexing out of bounds:
trafo_out.resize(file_list.size());
}
else if (trafo_out.size() != file_list.size())
{
writeLog_("Error: Number of transformation output files must equal the number of input files (parameters 'rt_concat:trafo_out'/'in')!");
return ILLEGAL_PARAMETERS;
}
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
if (force_type == FileTypes::FEATUREXML)
{
FeatureMap out;
FeatureXMLFile fh;
for (Size i = 0; i < file_list.size(); ++i)
{
FeatureMap map;
fh.load(file_list[i], map);
if (annotate_file_origin)
{
for (FeatureMap::iterator it = map.begin(); it != map.end(); ++it)
{
it->setMetaValue("file_origin", DataValue(file_list[i]));
}
}
if (rt_gap_ > 0.0) // concatenate in RT
{
adjustRetentionTimes_(map, trafo_out[i], i == 0);
}
out += map;
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
// annotate output with data processing info
addDataProcessing_(out, getProcessingInfo_(DataProcessing::FORMAT_CONVERSION));
fh.store(out_file, out);
}
else if (force_type == FileTypes::CONSENSUSXML)
{
ConsensusMap out;
ConsensusXMLFile fh;
fh.load(file_list[0], out);
// skip first file
for (Size i = 1; i < file_list.size(); ++i)
{
ConsensusMap map;
fh.load(file_list[i], map);
if (annotate_file_origin)
{
for (ConsensusMap::iterator it = map.begin(); it != map.end(); ++it)
{
it->setMetaValue("file_origin", DataValue(file_list[i]));
}
}
if (rt_gap_ > 0.0) // concatenate in RT
{
adjustRetentionTimes_(map, trafo_out[i], i == 0);
}
out += map;
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
// annotate output with data processing info
addDataProcessing_(out, getProcessingInfo_(DataProcessing::FORMAT_CONVERSION));
fh.store(out_file, out);
}
else if (force_type == FileTypes::TRAML)
{
TargetedExperiment out;
TraMLFile fh;
for (Size i = 0; i < file_list.size(); ++i)
{
TargetedExperiment map;
fh.load(file_list[i], map);
out += map;
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
// annotate output with data processing info
Software software;
software.setName("FileMerger");
software.setVersion(VersionInfo::getVersion());
out.addSoftware(software);
fh.store(out_file, out);
}
else // raw data input (e.g. mzML)
{
// RT
bool rt_auto_number = getFlag_("raw:rt_auto");
bool rt_filename = getFlag_("raw:rt_filename");
bool rt_custom = false;
DoubleList custom_rts = getDoubleList_("raw:rt_custom");
if (!custom_rts.empty())
{
rt_custom = true;
if (custom_rts.size() != file_list.size())
{
writeLog_("Custom retention time list (parameter 'raw:rt_custom') must have as many elements as there are input files (parameter 'in')!");
return ILLEGAL_PARAMETERS;
}
}
// MS level
Int ms_level = getIntOption_("raw:ms_level");
MSExperiment<> out;
UInt rt_auto = 0;
UInt native_id = 0;
for (Size i = 0; i < file_list.size(); ++i)
{
String filename = file_list[i];
// load file
force_type = file_handler.getType(file_list[i]);
MSExperiment<> in;
file_handler.loadExperiment(filename, in, force_type, log_type_);
if (in.empty() && in.getChromatograms().empty())
{
writeLog_(String("Warning: Empty file '") + filename + "'!");
continue;
}
out.reserve(out.size() + in.size());
// warn if custom RT and more than one scan in input file
if (rt_custom && in.size() > 1)
{
writeLog_(String("Warning: More than one scan in file '") + filename + "'! All scans will have the same retention time!");
}
// handle special raw data options:
for (MSExperiment<>::iterator spec_it = in.begin();
spec_it != in.end(); ++spec_it)
{
float rt_final = spec_it->getRT();
if (rt_auto_number)
{
rt_final = ++rt_auto;
}
else if (rt_custom)
{
rt_final = custom_rts[i];
}
else if (rt_filename)
{
static const boost::regex re("rt(\\d+(\\.\\d+)?)");
boost::smatch match;
bool found = boost::regex_search(filename, match, re);
if (found)
{
rt_final = String(match[1]).toFloat();
}
else
{
writeLog_("Warning: could not extract retention time from filename '" + filename + "'");
}
}
// none of the rt methods were successful
if (rt_final < 0)
{
writeLog_(String("Warning: No valid retention time for output scan '") + rt_auto + "' from file '" + filename + "'");
}
spec_it->setRT(rt_final);
spec_it->setNativeID("spectrum=" + String(native_id));
if (ms_level > 0)
{
spec_it->setMSLevel(ms_level);
}
++native_id;
}
// if we have only one spectrum, we can annotate it directly, for more spectra, we just name the source file leaving the spectra unannotated (to avoid a long and redundant list of sourceFiles)
if (in.size() == 1)
{
in[0].setSourceFile(in.getSourceFiles()[0]);
in.getSourceFiles().clear(); // delete source file annotated from source file (it's in the spectrum anyways)
}
if (rt_gap_ > 0.0) // concatenate in RT
{
adjustRetentionTimes_(in, trafo_out[i], i == 0);
}
// add spectra to output
for (MSExperiment<>::const_iterator spec_it = in.begin();
spec_it != in.end(); ++spec_it)
{
out.addSpectrum(*spec_it);
}
// also add the chromatograms
for (vector<MSChromatogram<ChromatogramPeak> >::const_iterator
chrom_it = in.getChromatograms().begin(); chrom_it !=
in.getChromatograms().end(); ++chrom_it)
{
out.addChromatogram(*chrom_it);
}
// copy experimental settings from first file
if (i == 0)
{
out.ExperimentalSettings::operator=(in);
}
else // otherwise append
{
out.getSourceFiles().insert(out.getSourceFiles().end(), in.getSourceFiles().begin(), in.getSourceFiles().end()); // could be emtpty if spectrum was annotated above, but that's ok then
}
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
// annotate output with data processing info
addDataProcessing_(out, getProcessingInfo_(DataProcessing::FORMAT_CONVERSION));
MzMLFile f;
f.setLogType(log_type_);
f.store(out_file, out);
}
return EXECUTION_OK;
}
ExitCodes main_(int, const char**)
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
//file list
StringList file_list = getStringList_("in");
//file type
FileHandler fh;
FileTypes::Type force_type;
if (getStringOption_("in_type").size() > 0)
{
force_type = FileTypes::nameToType(getStringOption_("in_type"));
}
else
{
force_type = fh.getType(file_list[0]);
}
//output file names and types
String out_file = getStringOption_("out");
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
bool annotate_file_origin = getFlag_("annotate_file_origin");
if (force_type == FileTypes::FEATUREXML)
{
FeatureMap<> out;
for (Size i = 0; i < file_list.size(); ++i)
{
FeatureMap<> map;
FeatureXMLFile fh;
fh.load(file_list[i], map);
if (annotate_file_origin)
{
for (FeatureMap<>::iterator it = map.begin(); it != map.end(); ++it)
{
it->setMetaValue("file_origin", DataValue(file_list[i]));
}
}
out += map;
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
//annotate output with data processing info
addDataProcessing_(out, getProcessingInfo_(DataProcessing::FORMAT_CONVERSION));
FeatureXMLFile f;
f.store(out_file, out);
}
else if (force_type == FileTypes::CONSENSUSXML)
{
ConsensusMap out;
ConsensusXMLFile fh;
fh.load(file_list[0], out);
//skip first file
for (Size i = 1; i < file_list.size(); ++i)
{
ConsensusMap map;
ConsensusXMLFile fh;
fh.load(file_list[i], map);
if (annotate_file_origin)
{
for (ConsensusMap::iterator it = map.begin(); it != map.end(); ++it)
{
it->setMetaValue("file_origin", DataValue(file_list[i]));
}
}
out += map;
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
//annotate output with data processing info
addDataProcessing_(out, getProcessingInfo_(DataProcessing::FORMAT_CONVERSION));
ConsensusXMLFile f;
f.store(out_file, out);
}
else if (force_type == FileTypes::TRAML)
{
TargetedExperiment out;
for (Size i = 0; i < file_list.size(); ++i)
{
TargetedExperiment map;
TraMLFile fh;
fh.load(file_list[i], map);
out += map;
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
//annotate output with data processing info
Software software;
software.setName("FileMerger");
software.setVersion(VersionInfo::getVersion());
out.addSoftware(software);
TraMLFile f;
f.store(out_file, out);
}
else
{
// we might want to combine different types, thus we only
// query in_type (which applies to all files)
// and not the suffix or content of a single file
force_type = FileTypes::nameToType(getStringOption_("in_type"));
//rt
bool rt_auto_number = getFlag_("raw:rt_auto");
bool rt_filename = getFlag_("raw:rt_filename");
bool rt_custom = false;
DoubleList custom_rts = getDoubleList_("raw:rt_custom");
if (custom_rts.size() != 0)
{
rt_custom = true;
if (custom_rts.size() != file_list.size())
{
writeLog_("Custom retention time list must have as many elements as there are input files!");
printUsage_();
return ILLEGAL_PARAMETERS;
}
}
//ms level
bool user_ms_level = getFlag_("raw:user_ms_level");
MSExperiment<> out;
out.reserve(file_list.size());
UInt rt_auto = 0;
UInt native_id = 0;
std::vector<MSChromatogram<ChromatogramPeak> > all_chromatograms;
for (Size i = 0; i < file_list.size(); ++i)
{
String filename = file_list[i];
//load file
MSExperiment<> in;
fh.loadExperiment(filename, in, force_type, log_type_);
if (in.empty() && in.getChromatograms().empty())
{
writeLog_(String("Warning: Empty file '") + filename + "'!");
continue;
}
out.reserve(out.size() + in.size());
//warn if custom RT and more than one scan in input file
if (rt_custom && in.size() > 1)
{
writeLog_(String("Warning: More than one scan in file '") + filename + "'! All scans will have the same retention time!");
}
for (MSExperiment<>::const_iterator it2 = in.begin(); it2 != in.end(); ++it2)
{
//handle rt
Real rt_final = it2->getRT();
if (rt_auto_number)
{
rt_final = ++rt_auto;
}
else if (rt_custom)
{
rt_final = custom_rts[i];
}
else if (rt_filename)
{
if (!filename.hasSubstring("rt"))
{
writeLog_(String("Warning: cannot guess retention time from filename as it does not contain 'rt'"));
}
for (Size i = 0; i < filename.size(); ++i)
{
if (filename[i] == 'r' && ++i != filename.size() && filename[i] == 't' && ++i != filename.size() && isdigit(filename[i]))
{
String rt;
while (i != filename.size() && (filename[i] == '.' || isdigit(filename[i])))
{
rt += filename[i++];
}
if (rt.size() > 0)
{
// remove dot from rt3892.98.dta
// ^
if (rt[rt.size() - 1] == '.')
{
// remove last character
rt.erase(rt.end() - 1);
}
}
try
{
float tmp = rt.toFloat();
rt_final = tmp;
}
catch (Exception::ConversionError)
{
writeLog_(String("Warning: cannot convert the found retention time in a value '" + rt + "'."));
}
}
}
}
// none of the rt methods were successful
if (rt_final == -1)
{
writeLog_(String("Warning: No valid retention time for output scan '") + rt_auto + "' from file '" + filename + "'");
}
out.addSpectrum(*it2);
out.getSpectra().back().setRT(rt_final);
out.getSpectra().back().setNativeID(native_id);
if (user_ms_level)
{
out.getSpectra().back().setMSLevel((int)getIntOption_("raw:ms_level"));
}
++native_id;
}
// if we had only one spectrum, we can annotate it directly, for more spectra, we just name the source file leaving the spectra unannotated (to avoid a long and redundant list of sourceFiles)
if (in.size() == 1)
{
out.getSpectra().back().setSourceFile(in.getSourceFiles()[0]);
in.getSourceFiles().clear(); // delete source file annotated from source file (its in the spectrum anyways)
}
// copy experimental settings from first file
if (i == 0)
{
out.ExperimentalSettings::operator=(in);
}
else // otherwise append
{
out.getSourceFiles().insert(out.getSourceFiles().end(), in.getSourceFiles().begin(), in.getSourceFiles().end()); // could be emtpty if spectrum was annotated above, but that's ok then
}
// also add the chromatograms
for (std::vector<MSChromatogram<ChromatogramPeak> >::const_iterator it2 = in.getChromatograms().begin(); it2 != in.getChromatograms().end(); ++it2)
{
all_chromatograms.push_back(*it2);
}
}
// set the chromatograms
out.setChromatograms(all_chromatograms);
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
//annotate output with data processing info
addDataProcessing_(out, getProcessingInfo_(DataProcessing::FORMAT_CONVERSION));
MzMLFile f;
f.setLogType(log_type_);
f.store(out_file, out);
}
return EXECUTION_OK;
}
TEST_STRING_EQUAL(FileTypes::typeToName(e.getLoadedFileType()),"dta2d"); TEST_EQUAL(e.size(), 9); ABORT_IF(e.size() != 9) TEST_STRING_EQUAL(e[0].getNativeID(),"index=0") TEST_STRING_EQUAL(e[1].getNativeID(),"index=1") TEST_STRING_EQUAL(e[2].getNativeID(),"index=2") TEST_STRING_EQUAL(e[3].getNativeID(),"index=3") TEST_STRING_EQUAL(e[4].getNativeID(),"index=4") TEST_STRING_EQUAL(e[5].getNativeID(),"index=5") TEST_STRING_EQUAL(e[6].getNativeID(),"index=6") TEST_STRING_EQUAL(e[7].getNativeID(),"index=7") TEST_STRING_EQUAL(e[8].getNativeID(),"index=8") MSExperiment<>::const_iterator it(e.begin()); TEST_REAL_SIMILAR((*it)[0].getPosition()[0], 230.02) TEST_REAL_SIMILAR(it->getRT(), 4711.1) TEST_REAL_SIMILAR((*it)[0].getIntensity(), 47218.89) ++it; TEST_REAL_SIMILAR((*it)[0].getPosition()[0], 231.51) TEST_REAL_SIMILAR(it->getRT(), 4711.2) TEST_REAL_SIMILAR((*it)[0].getIntensity(), 89935.22) ++it; TEST_REAL_SIMILAR((*it)[0].getPosition()[0], 139.42) TEST_REAL_SIMILAR(it->getRT(), 4711.3) TEST_REAL_SIMILAR((*it)[0].getIntensity(), 318.52) ++it;