ExitCodes main_(int, const char **)
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
//input/output files
String in(getStringOption_("in"));
String out(getStringOption_("out"));
//-------------------------------------------------------------
// loading input
//-------------------------------------------------------------
MSExperiment<> exp;
MzMLFile f;
f.setLogType(log_type_);
f.load(in, exp);
//-------------------------------------------------------------
// if meta data arrays are present, remove them and warn
//-------------------------------------------------------------
if (exp.clearMetaDataArrays())
{
writeLog_("Warning: Spectrum meta data arrays cannot be sorted. They are deleted.");
}
//-------------------------------------------------------------
// filter
//-------------------------------------------------------------
Param filter_param = getParam_().copy("algorithm:", true);
writeDebug_("Used filter parameters", filter_param, 3);
BernNorm filter;
filter.setParameters(filter_param);
filter.filterPeakMap(exp);
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
//annotate output with data processing info
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::FILTERING));
f.store(out, exp);
return EXECUTION_OK;
}
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]);
MzXMLFile mzxml;
MzMLFile mzml;
// temporary data storage
MSExperiment<Peak1D> map;
// convert MzXML to MzML
mzxml.load(tutorial_data_path + "/data/Tutorial_FileIO.mzXML", map);
mzml.store("Tutorial_FileIO.mzML", map);
return 0;
} //end of main
ExitCodes main_(int, const char **)
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
//input/output files
String in(getStringOption_("in"));
String out(getStringOption_("out"));
//-------------------------------------------------------------
// loading input
//-------------------------------------------------------------
MSExperiment<> exp;
MzMLFile f;
f.setLogType(log_type_);
f.load(in, exp);
//-------------------------------------------------------------
// filter
//-------------------------------------------------------------
Param filter_param = getParam_().copy("algorithm:", true);
writeDebug_("Used filter parameters", filter_param, 3);
Normalizer filter;
filter.setParameters(filter_param);
filter.filterPeakMap(exp);
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
//annotate output with data processing info
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::FILTERING));
f.store(out, exp);
return EXECUTION_OK;
}
ExitCodes main_(int, const char **)
{
//----------------------------------------------------------------
// load data
//----------------------------------------------------------------
String in = getStringOption_("in");
String out = getStringOption_("out");
MSExperiment<> exp;
MzMLFile f;
f.setLogType(log_type_);
f.load(in, exp);
DoubleReal sampling_rate = getDoubleOption_("sampling_rate");
LinearResampler lin_resampler;
Param resampler_param;
resampler_param.setValue("spacing", sampling_rate);
lin_resampler.setParameters(resampler_param);
// resample every scan
for (Size i = 0; i < exp.size(); ++i)
{
lin_resampler.raster(exp[i]);
}
//clear meta data because they are no longer meaningful
exp.clearMetaDataArrays();
//annotate output with data processing info
addDataProcessing_(exp,
getProcessingInfo_(DataProcessing::DATA_PROCESSING));
//store output
f.store(out, exp);
return EXECUTION_OK;
}
ExitCodes main_(int , const char**) override
{
String in = getStringOption_("in");
String out = getStringOption_("out");
MapType exp;
MapType out_exp;
Param picker_param = getParam_().copy("algorithm:", true);
MzMLFile f;
f.setLogType(log_type_);
f.load(in,exp);
PeakPickerIterative pp;
pp.setParameters(picker_param);
pp.setLogType(log_type_);
pp.pickExperiment(exp, out_exp);
addDataProcessing_(out_exp, getProcessingInfo_(DataProcessing::PEAK_PICKING));
f.store(out,out_exp);
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;
}
ExitCodes main_(int , const char**)
{
String in = getStringOption_("in");
String out_meta = getStringOption_("out");
String in_cached = in + ".cached";
String out_cached = out_meta + ".cached";
bool convert_back = getFlag_("convert_back");
if (!convert_back)
{
MapType exp;
CachedmzML cacher;
MzMLFile f;
cacher.setLogType(log_type_);
f.setLogType(log_type_);
f.load(in,exp);
cacher.writeMemdump(exp, out_cached);
DataProcessing dp;
std::set<DataProcessing::ProcessingAction> actions;
actions.insert(DataProcessing::FORMAT_CONVERSION);
dp.setProcessingActions(actions);
dp.setMetaValue("cached_data", "true");
for (Size i=0; i<exp.size(); ++i)
{
exp[i].getDataProcessing().push_back(dp);
}
std::vector<MSChromatogram<ChromatogramPeak> > chromatograms = exp.getChromatograms();
for (Size i=0; i<chromatograms.size(); ++i)
{
chromatograms[i].getDataProcessing().push_back(dp);
}
exp.setChromatograms(chromatograms);
cacher.writeMetadata(exp, out_meta);
}
else
{
MzMLFile f;
MapType meta_exp;
CachedmzML cacher;
MapType exp_reading;
cacher.setLogType(log_type_);
f.setLogType(log_type_);
f.load(in,meta_exp);
cacher.readMemdump(exp_reading, in_cached);
std::cout << " read back, got " << exp_reading.size() << " spectra " << exp_reading.getChromatograms().size() << " chromats " << std::endl;
{
for (Size i=0; i<meta_exp.size(); ++i)
{
for (Size j = 0; j < meta_exp[i].getDataProcessing().size(); j++)
{
DataProcessing& dp = meta_exp[i].getDataProcessing()[j];
if (dp.metaValueExists("cached_data"))
{
dp.removeMetaValue("cached_data");
}
}
}
std::vector<MSChromatogram<ChromatogramPeak> > chromatograms = meta_exp.getChromatograms();
for (Size i=0; i<chromatograms.size(); ++i)
{
for (Size j = 0; j < chromatograms[i].getDataProcessing().size(); j++)
{
DataProcessing& dp = chromatograms[i].getDataProcessing()[j];
if (dp.metaValueExists("cached_data"))
{
dp.removeMetaValue("cached_data");
}
}
}
}
if (meta_exp.size() != exp_reading.size())
{
std::cerr << " Both experiments need to have the same size!";
}
for (Size i=0; i<exp_reading.size(); ++i)
{
for (Size j = 0; j < exp_reading[i].size(); j++)
{
meta_exp[i].push_back(exp_reading[i][j]);
}
}
std::vector<MSChromatogram<ChromatogramPeak> > chromatograms = exp_reading.getChromatograms();
std::vector<MSChromatogram<ChromatogramPeak> > old_chromatograms = meta_exp.getChromatograms();
for (Size i=0; i<chromatograms.size(); ++i)
{
for (Size j = 0; j < chromatograms[i].size(); j++)
{
old_chromatograms[i].push_back(chromatograms[i][j]);
}
}
meta_exp.setChromatograms(old_chromatograms);
f.store(out_meta,meta_exp);
}
return EXECUTION_OK;
}
ExitCodes main_(int, const char **)
{
//-------------------------------------------------------------
// parsing parameters
//-------------------------------------------------------------
String in(getStringOption_("in"));
String out(getStringOption_("out"));
Size num_spots_per_row(getIntOption_("num_spots_per_row"));
double RT_distance(getDoubleOption_("RT_distance"));
//-------------------------------------------------------------
// reading input
//-------------------------------------------------------------
PeakMap exp;
MzMLFile f;
f.setLogType(log_type_);
f.load(in, exp);
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
ProgressLogger pl;
pl.setLogType(log_type_);
pl.startProgress(0, exp.size(), "Assigning pseudo RTs.");
Size num_ms1(0), num_ms1_base(0), row_counter(0);
bool row_to_reverse(false);
double actual_RT(0);
for (Size i = 0; i != exp.size(); ++i)
{
pl.setProgress(i);
if (row_to_reverse)
{
actual_RT = (double)(num_ms1_base + (num_spots_per_row - row_counter)) * RT_distance;
writeDebug_("RT=" + String(actual_RT) + " (modified, row_counter=" + String(row_counter) + ")", 1);
}
else
{
actual_RT = (double)num_ms1 * RT_distance;
writeDebug_("RT=" + String(actual_RT), 1);
}
exp[i].setRT(actual_RT);
if (exp[i].getMSLevel() == 1)
{
if (++row_counter >= num_spots_per_row)
{
row_counter = 0;
if (row_to_reverse)
{
row_to_reverse = false;
}
else
{
row_to_reverse = true;
}
}
++num_ms1;
if (!row_to_reverse)
{
num_ms1_base = num_ms1;
}
}
}
pl.endProgress();
// sort the spectra according to their new RT
exp.sortSpectra();
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
f.store(out, exp);
return EXECUTION_OK;
}
ExitCodes main_(int, const char **)
{
StringList file_list = getStringList_("in");
String tr_file_str = getStringOption_("tr");
String out = getStringOption_("out");
bool is_swath = getFlag_("is_swath");
bool ppm = getFlag_("ppm");
bool extract_MS1 = getFlag_("extract_MS1");
double min_upper_edge_dist = getDoubleOption_("min_upper_edge_dist");
double mz_extraction_window = getDoubleOption_("mz_window");
double rt_extraction_window = getDoubleOption_("rt_window");
String extraction_function = getStringOption_("extraction_function");
// If we have a transformation file, trafo will transform the RT in the
// scoring according to the model. If we dont have one, it will apply the
// null transformation.
String trafo_in = getStringOption_("rt_norm");
TransformationDescription trafo;
if (trafo_in.size() > 0)
{
TransformationXMLFile trafoxml;
String model_type = getStringOption_("model:type");
Param model_params = getParam_().copy("model:", true);
trafoxml.load(trafo_in, trafo);
trafo.fitModel(model_type, model_params);
}
TransformationDescription trafo_inverse = trafo;
trafo_inverse.invert();
const char * tr_file = tr_file_str.c_str();
MapType out_exp;
std::vector< OpenMS::MSChromatogram > chromatograms;
TraMLFile traml;
OpenMS::TargetedExperiment targeted_exp;
std::cout << "Loading TraML file" << std::endl;
traml.load(tr_file, targeted_exp);
std::cout << "Loaded TraML file" << std::endl;
// Do parallelization over the different input files
// Only in OpenMP 3.0 are unsigned loop variables allowed
#ifdef _OPENMP
#pragma omp parallel for
#endif
for (SignedSize i = 0; i < boost::numeric_cast<SignedSize>(file_list.size()); ++i)
{
boost::shared_ptr<PeakMap > exp(new PeakMap);
MzMLFile f;
// Logging and output to the console
// IF_MASTERTHREAD f.setLogType(log_type_);
// Find the transitions to extract and extract them
MapType tmp_out;
OpenMS::TargetedExperiment transition_exp_used;
f.load(file_list[i], *exp);
if (exp->empty() ) { continue; } // if empty, go on
OpenSwath::SpectrumAccessPtr expptr = SimpleOpenMSSpectraFactory::getSpectrumAccessOpenMSPtr(exp);
bool do_continue = true;
if (is_swath)
{
do_continue = OpenSwathHelper::checkSwathMapAndSelectTransitions(*exp, targeted_exp, transition_exp_used, min_upper_edge_dist);
}
else
{
transition_exp_used = targeted_exp;
}
#ifdef _OPENMP
#pragma omp critical (OpenSwathChromatogramExtractor_metadata)
#endif
// after loading the first file, copy the meta data from that experiment
// this may happen *after* chromatograms were already added to the
// output, thus we do NOT fill the experiment here but rather store all
// the chromatograms in the "chromatograms" array and store them in
// out_exp afterwards.
if (i == 0)
{
out_exp = *exp;
out_exp.clear(false);
}
std::cout << "Extracting " << transition_exp_used.getTransitions().size() << " transitions" << std::endl;
std::vector< OpenSwath::ChromatogramPtr > chromatogram_ptrs;
std::vector< ChromatogramExtractor::ExtractionCoordinates > coordinates;
// continue if the map is not empty
if (do_continue)
{
// Prepare the coordinates (with or without rt extraction) and then extract the chromatograms
ChromatogramExtractor extractor;
if (rt_extraction_window < 0)
{
extractor.prepare_coordinates(chromatogram_ptrs, coordinates, transition_exp_used, rt_extraction_window, extract_MS1);
}
else
{
// Use an rt extraction window of 0.0 which will just write the retention time in start / end positions
extractor.prepare_coordinates(chromatogram_ptrs, coordinates, transition_exp_used, 0.0, extract_MS1);
for (std::vector< ChromatogramExtractor::ExtractionCoordinates >::iterator it = coordinates.begin(); it != coordinates.end(); ++it)
{
it->rt_start = trafo_inverse.apply(it->rt_start) - rt_extraction_window / 2.0;
it->rt_end = trafo_inverse.apply(it->rt_end) + rt_extraction_window / 2.0;
}
}
extractor.extractChromatograms(expptr, chromatogram_ptrs, coordinates,
mz_extraction_window, ppm, extraction_function);
#ifdef _OPENMP
#pragma omp critical (OpenSwathChromatogramExtractor_insertMS1)
#endif
{
// Remove potential meta value indicating cached data
SpectrumSettings exp_settings = (*exp)[0];
for (Size j = 0; j < exp_settings.getDataProcessing().size(); j++)
{
if (exp_settings.getDataProcessing()[j]->metaValueExists("cached_data"))
{ exp_settings.getDataProcessing()[j]->removeMetaValue("cached_data"); }
}
extractor.return_chromatogram(chromatogram_ptrs, coordinates, transition_exp_used, exp_settings, chromatograms, extract_MS1);
}
} // end of do_continue
} // end of loop over all files / end of OpenMP
// TODO check that no chromatogram IDs occur multiple times !
// store the output
out_exp.setChromatograms(chromatograms);
MzMLFile mzf;
mzf.setLogType(log_type_);
addDataProcessing_(out_exp, getProcessingInfo_(DataProcessing::SMOOTHING));
mzf.store(out, out_exp);
return EXECUTION_OK;
}
ExitCodes main_(int, const char **) override
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
String in = getStringOption_("in");
String out = getStringOption_("out");
//-------------------------------------------------------------
// loading input
//-------------------------------------------------------------
PeakMap exp;
MzMLFile f;
f.load(in, exp);
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
//determine maximum peak
exp.updateRanges();
double max = exp.getMaxInt() / 100.0;
for (PeakMap::Iterator it = exp.begin(); it != exp.end(); ++it)
{
if (it->getMSLevel() < 2)
{
for (PeakMap::SpectrumType::Iterator it2 = it->begin(); it2 != it->end(); ++it2)
{
it2->setIntensity(it2->getIntensity() / max);
}
}
}
/// @todo add chromatogram support for normalization, e.g. for MRM stuff (Andreas)
/*
vector<MSChromatogram > chroms = exp.getChromatograms();
double sum(0);
for (vector<MSChromatogram >::iterator it = chroms.begin(); it != chroms.end(); ++it)
{
for (MSChromatogram::Iterator it2 = it->begin(); it2 != it->end(); ++it2)
{
sum += it2->getIntensity();
}
}
for (vector<MSChromatogram >::iterator it = chroms.begin(); it != chroms.end(); ++it)
{
for (MSChromatogram::Iterator it2 = it->begin(); it2 != it->end(); ++it2)
{
it2->setIntensity(it2->getIntensity() / sum * 1000000.0);
}
}
exp.setChromatograms(chroms);
*/
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
//annotate output with data processing info
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::NORMALIZATION));
f.store(out, exp);
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**)
{
String out_meta = getStringOption_("out");
String out_cached = out_meta + ".cached";
bool convert_back = getFlag_("convert_back");
FileHandler fh;
//input file type
String in = getStringOption_("in");
String in_cached = in + ".cached";
FileTypes::Type in_type = FileTypes::nameToType(getStringOption_("in_type"));
if (in_type == FileTypes::UNKNOWN)
{
in_type = fh.getType(in);
writeDebug_(String("Input file type: ") + FileTypes::typeToName(in_type), 2);
}
if (in_type == FileTypes::UNKNOWN)
{
writeLog_("Error: Could not determine input file type!");
return PARSE_ERROR;
}
//output file names and types
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;
}
if (in_type == FileTypes::SQMASS && out_type == FileTypes::MZML)
{
MapType exp;
SqMassFile sqfile;
MzMLFile f;
sqfile.load(in, exp);
f.store(out, exp);
return EXECUTION_OK;
}
else if (in_type == FileTypes::MZML && out_type == FileTypes::SQMASS)
{
MzMLFile f;
SqMassFile sqfile;
MapType exp;
f.load(in, exp);
sqfile.store(out, exp);
return EXECUTION_OK;
}
if (!convert_back)
{
MapType exp;
CachedmzML cacher;
MzMLFile f;
cacher.setLogType(log_type_);
f.setLogType(log_type_);
f.load(in,exp);
cacher.writeMemdump(exp, out_cached);
cacher.writeMetadata(exp, out_meta, true);
}
else
{
MzMLFile f;
MapType meta_exp;
CachedmzML cacher;
MapType exp_reading;
cacher.setLogType(log_type_);
f.setLogType(log_type_);
f.load(in,meta_exp);
cacher.readMemdump(exp_reading, in_cached);
std::cout << " read back, got " << exp_reading.size() << " spectra " << exp_reading.getChromatograms().size() << " chromats " << std::endl;
{
for (Size i=0; i<meta_exp.size(); ++i)
{
for (Size j = 0; j < meta_exp[i].getDataProcessing().size(); j++)
{
if (meta_exp[i].getDataProcessing()[j]->metaValueExists("cached_data"))
{
meta_exp[i].getDataProcessing()[j]->removeMetaValue("cached_data");
}
}
}
for (Size i=0; i < meta_exp.getNrChromatograms(); ++i)
{
for (Size j = 0; j < meta_exp.getChromatogram(i).getDataProcessing().size(); j++)
{
if (meta_exp.getChromatogram(i).getDataProcessing()[j]->metaValueExists("cached_data"))
{
meta_exp.getChromatogram(i).getDataProcessing()[j]->removeMetaValue("cached_data");
}
}
}
}
if (meta_exp.size() != exp_reading.size())
{
std::cerr << " Both experiments need to have the same size!";
}
for (Size i=0; i<exp_reading.size(); ++i)
{
for (Size j = 0; j < exp_reading[i].size(); j++)
{
meta_exp[i].push_back(exp_reading[i][j]);
}
}
std::vector<MSChromatogram<ChromatogramPeak> > chromatograms = exp_reading.getChromatograms();
std::vector<MSChromatogram<ChromatogramPeak> > old_chromatograms = meta_exp.getChromatograms();
for (Size i=0; i<chromatograms.size(); ++i)
{
for (Size j = 0; j < chromatograms[i].size(); j++)
{
old_chromatograms[i].push_back(chromatograms[i][j]);
}
}
meta_exp.setChromatograms(old_chromatograms);
f.store(out_meta,meta_exp);
}
return EXECUTION_OK;
}
ExitCodes main_(int, const char**)
{
ExitCodes ret = checkParameters_();
if (ret != EXECUTION_OK) return ret;
MapAlignmentAlgorithmSpectrumAlignment algorithm;
Param algo_params = getParam_().copy("algorithm:", true);
algorithm.setParameters(algo_params);
algorithm.setLogType(log_type_);
StringList ins = getStringList_("in");
StringList outs = getStringList_("out");
StringList trafos = getStringList_("trafo_out");
Param model_params = getParam_().copy("model:", true);
String model_type = model_params.getValue("type");
model_params = model_params.copy(model_type + ":", true);
std::vector<TransformationDescription> transformations;
//-------------------------------------------------------------
// perform peak alignment
//-------------------------------------------------------------
ProgressLogger progresslogger;
progresslogger.setLogType(log_type_);
// load input
std::vector<MSExperiment<> > peak_maps(ins.size());
MzMLFile f;
f.setLogType(log_type_);
progresslogger.startProgress(0, ins.size(), "loading input files");
for (Size i = 0; i < ins.size(); ++i)
{
progresslogger.setProgress(i);
f.load(ins[i], peak_maps[i]);
}
progresslogger.endProgress();
// try to align
algorithm.align(peak_maps, transformations);
if (model_type != "none")
{
for (vector<TransformationDescription>::iterator it =
transformations.begin(); it != transformations.end(); ++it)
{
it->fitModel(model_type, model_params);
}
}
// write output
progresslogger.startProgress(0, outs.size(), "applying RT transformations and writing output files");
for (Size i = 0; i < outs.size(); ++i)
{
progresslogger.setProgress(i);
MapAlignmentTransformer::transformRetentionTimes(peak_maps[i],
transformations[i]);
// annotate output with data processing info
addDataProcessing_(peak_maps[i],
getProcessingInfo_(DataProcessing::ALIGNMENT));
f.store(outs[i], peak_maps[i]);
}
progresslogger.endProgress();
if (!trafos.empty())
{
TransformationXMLFile trafo_file;
for (Size i = 0; i < transformations.size(); ++i)
{
trafo_file.store(trafos[i], transformations[i]);
}
}
return EXECUTION_OK;
}
ExitCodes main_(int, const char**)
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
//input file names
String in = getStringOption_("in");
//input file type
FileHandler fh;
FileTypes::Type in_type = FileTypes::nameToType(getStringOption_("in_type"));
if (in_type == FileTypes::UNKNOWN)
{
in_type = fh.getType(in);
writeDebug_(String("Input file type: ") + FileTypes::typeToName(in_type), 2);
}
if (in_type == FileTypes::UNKNOWN)
{
writeLog_("Error: Could not determine input file type!");
return PARSE_ERROR;
}
//output file names and types
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;
}
bool TIC_DTA2D = getFlag_("TIC_DTA2D");
writeDebug_(String("Output file type: ") + FileTypes::typeToName(out_type), 1);
//-------------------------------------------------------------
// reading input
//-------------------------------------------------------------
typedef MSExperiment<Peak1D> MSExperimentType;
MSExperimentType exp;
typedef MSExperimentType::SpectrumType SpectrumType;
typedef FeatureMap<> FeatureMapType;
FeatureMapType fm;
ConsensusMap cm;
writeDebug_(String("Loading input file"), 1);
if (in_type == FileTypes::CONSENSUSXML)
{
ConsensusXMLFile().load(in, cm);
cm.sortByPosition();
if ((out_type != FileTypes::FEATUREXML) &&
(out_type != FileTypes::CONSENSUSXML))
{
// You you will lose information and waste memory. Enough reasons to issue a warning!
writeLog_("Warning: Converting consensus features to peaks. You will lose information!");
exp.set2DData(cm);
}
}
else if (in_type == FileTypes::EDTA)
{
EDTAFile().load(in, cm);
cm.sortByPosition();
if ((out_type != FileTypes::FEATUREXML) &&
(out_type != FileTypes::CONSENSUSXML))
{
// You you will lose information and waste memory. Enough reasons to issue a warning!
writeLog_("Warning: Converting consensus features to peaks. You will lose information!");
exp.set2DData(cm);
}
}
else if (in_type == FileTypes::FEATUREXML ||
in_type == FileTypes::TSV ||
in_type == FileTypes::PEPLIST ||
in_type == FileTypes::KROENIK)
{
fh.loadFeatures(in, fm, in_type);
fm.sortByPosition();
if ((out_type != FileTypes::FEATUREXML) &&
(out_type != FileTypes::CONSENSUSXML))
{
// You will lose information and waste memory. Enough reasons to issue a warning!
writeLog_("Warning: Converting features to peaks. You will lose information! Mass traces are added, if present as 'num_of_masstraces' and 'masstrace_intensity_<X>' (X>=0) meta values.");
exp.set2DData<true>(fm);
}
}
else
{
fh.loadExperiment(in, exp, in_type, log_type_);
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
writeDebug_(String("Writing output file"), 1);
if (out_type == FileTypes::MZML)
{
//add data processing entry
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::
CONVERSION_MZML));
MzMLFile f;
f.setLogType(log_type_);
ChromatogramTools().convertSpectraToChromatograms(exp, true);
f.store(out, exp);
}
else if (out_type == FileTypes::MZDATA)
{
//annotate output with data processing info
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::
CONVERSION_MZDATA));
MzDataFile f;
f.setLogType(log_type_);
ChromatogramTools().convertChromatogramsToSpectra<MSExperimentType>(exp);
f.store(out, exp);
}
else if (out_type == FileTypes::MZXML)
{
//annotate output with data processing info
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::
CONVERSION_MZXML));
MzXMLFile f;
f.setLogType(log_type_);
ChromatogramTools().convertChromatogramsToSpectra<MSExperimentType>(exp);
f.store(out, exp);
}
else if (out_type == FileTypes::DTA2D)
{
//add data processing entry
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::
FORMAT_CONVERSION));
DTA2DFile f;
f.setLogType(log_type_);
ChromatogramTools().convertChromatogramsToSpectra<MSExperimentType>(exp);
if (TIC_DTA2D)
{
// store the total ion chromatogram (TIC)
f.storeTIC(out, exp);
}
else
{
// store entire experiment
f.store(out, exp);
}
}
else if (out_type == FileTypes::MGF)
{
//add data processing entry
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::
FORMAT_CONVERSION));
MascotGenericFile f;
f.setLogType(log_type_);
f.store(out, exp);
}
else if (out_type == FileTypes::FEATUREXML)
{
if ((in_type == FileTypes::FEATUREXML) || (in_type == FileTypes::TSV) ||
(in_type == FileTypes::PEPLIST) || (in_type == FileTypes::KROENIK))
{
fm.applyMemberFunction(&UniqueIdInterface::setUniqueId);
}
else if (in_type == FileTypes::CONSENSUSXML || in_type == FileTypes::EDTA)
{
ConsensusMap::convert(cm, true, fm);
}
else // not loaded as feature map or consensus map
{
// The feature specific information is only defaulted. Enough reasons to issue a warning!
writeLog_("Warning: Converting peaks to features will lead to incomplete features!");
fm.clear();
fm.reserve(exp.getSize());
typedef FeatureMapType::FeatureType FeatureType;
FeatureType feature;
feature.setQuality(0, 1); // override default
feature.setQuality(1, 1); // override default
feature.setOverallQuality(1); // override default
for (MSExperimentType::ConstIterator spec_iter = exp.begin();
spec_iter != exp.end();
++spec_iter
)
{
feature.setRT(spec_iter->getRT());
for (SpectrumType::ConstIterator peak1_iter = spec_iter->begin();
peak1_iter != spec_iter->end();
++peak1_iter
)
{
feature.setMZ(peak1_iter->getMZ());
feature.setIntensity(peak1_iter->getIntensity());
feature.setUniqueId();
fm.push_back(feature);
}
}
fm.updateRanges();
}
addDataProcessing_(fm, getProcessingInfo_(DataProcessing::
FORMAT_CONVERSION));
FeatureXMLFile().store(out, fm);
}
else if (out_type == FileTypes::CONSENSUSXML)
{
if ((in_type == FileTypes::FEATUREXML) || (in_type == FileTypes::TSV) ||
(in_type == FileTypes::PEPLIST) || (in_type == FileTypes::KROENIK))
{
fm.applyMemberFunction(&UniqueIdInterface::setUniqueId);
ConsensusMap::convert(0, fm, cm);
}
// nothing to do for consensus input
else if (in_type == FileTypes::CONSENSUSXML || in_type == FileTypes::EDTA)
{
}
else // experimental data
{
ConsensusMap::convert(0, exp, cm, exp.size());
}
addDataProcessing_(cm, getProcessingInfo_(DataProcessing::
FORMAT_CONVERSION));
ConsensusXMLFile().store(out, cm);
}
else if (out_type == FileTypes::EDTA)
{
if (fm.size() > 0 && cm.size() > 0)
{
LOG_ERROR << "Internal error: cannot decide on container (Consensus or Feature)! This is a bug. Please report it!";
return INTERNAL_ERROR;
}
if (fm.size() > 0) EDTAFile().store(out, fm);
else if (cm.size() > 0) EDTAFile().store(out, cm);
}
else
{
writeLog_("Unknown output file type given. Aborting!");
printUsage_();
return ILLEGAL_PARAMETERS;
}
return EXECUTION_OK;
}
ExitCodes main_(int, const char**)
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
//input file names
String in = getStringOption_("in");
bool write_mzML_index = getFlag_("write_mzML_index");
//input file type
FileHandler fh;
FileTypes::Type in_type = FileTypes::nameToType(getStringOption_("in_type"));
if (in_type == FileTypes::UNKNOWN)
{
in_type = fh.getType(in);
writeDebug_(String("Input file type: ") + FileTypes::typeToName(in_type), 2);
}
if (in_type == FileTypes::UNKNOWN)
{
writeLog_("Error: Could not determine input file type!");
return PARSE_ERROR;
}
//output file names and types
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;
}
bool TIC_DTA2D = getFlag_("TIC_DTA2D");
bool process_lowmemory = getFlag_("process_lowmemory");
writeDebug_(String("Output file type: ") + FileTypes::typeToName(out_type), 1);
String uid_postprocessing = getStringOption_("UID_postprocessing");
//-------------------------------------------------------------
// reading input
//-------------------------------------------------------------
typedef MSExperiment<Peak1D> MSExperimentType;
MSExperimentType exp;
typedef MSExperimentType::SpectrumType SpectrumType;
typedef FeatureMap FeatureMapType;
FeatureMapType fm;
ConsensusMap cm;
writeDebug_(String("Loading input file"), 1);
if (in_type == FileTypes::CONSENSUSXML)
{
ConsensusXMLFile().load(in, cm);
cm.sortByPosition();
if ((out_type != FileTypes::FEATUREXML) &&
(out_type != FileTypes::CONSENSUSXML))
{
// You you will lose information and waste memory. Enough reasons to issue a warning!
writeLog_("Warning: Converting consensus features to peaks. You will lose information!");
exp.set2DData(cm);
}
}
else if (in_type == FileTypes::EDTA)
{
EDTAFile().load(in, cm);
cm.sortByPosition();
if ((out_type != FileTypes::FEATUREXML) &&
(out_type != FileTypes::CONSENSUSXML))
{
// You you will lose information and waste memory. Enough reasons to issue a warning!
writeLog_("Warning: Converting consensus features to peaks. You will lose information!");
exp.set2DData(cm);
}
}
else if (in_type == FileTypes::FEATUREXML ||
in_type == FileTypes::TSV ||
in_type == FileTypes::PEPLIST ||
in_type == FileTypes::KROENIK)
{
fh.loadFeatures(in, fm, in_type);
fm.sortByPosition();
if ((out_type != FileTypes::FEATUREXML) &&
(out_type != FileTypes::CONSENSUSXML))
{
// You will lose information and waste memory. Enough reasons to issue a warning!
writeLog_("Warning: Converting features to peaks. You will lose information! Mass traces are added, if present as 'num_of_masstraces' and 'masstrace_intensity_<X>' (X>=0) meta values.");
exp.set2DData<true>(fm);
}
}
else if (process_lowmemory)
{
// Special switch for the low memory options:
// We can transform the complete experiment directly without first
// loading the complete data into memory. PlainMSDataWritingConsumer will
// write out mzML to disk as they are read from the input.
if (in_type == FileTypes::MZML && out_type == FileTypes::MZML)
{
PlainMSDataWritingConsumer consumer(out);
consumer.getOptions().setWriteIndex(write_mzML_index);
consumer.addDataProcessing(getProcessingInfo_(DataProcessing::CONVERSION_MZML));
MzMLFile mzmlfile;
mzmlfile.setLogType(log_type_);
mzmlfile.transform(in, &consumer);
return EXECUTION_OK;
}
else if (in_type == FileTypes::MZXML && out_type == FileTypes::MZML)
{
PlainMSDataWritingConsumer consumer(out);
consumer.getOptions().setWriteIndex(write_mzML_index);
consumer.addDataProcessing(getProcessingInfo_(DataProcessing::CONVERSION_MZML));
MzXMLFile mzxmlfile;
mzxmlfile.setLogType(log_type_);
mzxmlfile.transform(in, &consumer);
return EXECUTION_OK;
}
else
{
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__,
"Process_lowmemory option can only be used with mzML / mzXML input and mzML output data types.");
}
}
else
{
fh.loadExperiment(in, exp, in_type, log_type_);
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
writeDebug_(String("Writing output file"), 1);
if (out_type == FileTypes::MZML)
{
//add data processing entry
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::
CONVERSION_MZML));
MzMLFile f;
f.setLogType(log_type_);
f.getOptions().setWriteIndex(write_mzML_index);
ChromatogramTools().convertSpectraToChromatograms(exp, true);
f.store(out, exp);
}
else if (out_type == FileTypes::MZDATA)
{
//annotate output with data processing info
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::
CONVERSION_MZDATA));
MzDataFile f;
f.setLogType(log_type_);
ChromatogramTools().convertChromatogramsToSpectra<MSExperimentType>(exp);
f.store(out, exp);
}
else if (out_type == FileTypes::MZXML)
{
//annotate output with data processing info
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::
CONVERSION_MZXML));
MzXMLFile f;
f.setLogType(log_type_);
ChromatogramTools().convertChromatogramsToSpectra<MSExperimentType>(exp);
f.store(out, exp);
}
else if (out_type == FileTypes::DTA2D)
{
//add data processing entry
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::
FORMAT_CONVERSION));
DTA2DFile f;
f.setLogType(log_type_);
ChromatogramTools().convertChromatogramsToSpectra<MSExperimentType>(exp);
if (TIC_DTA2D)
{
// store the total ion chromatogram (TIC)
f.storeTIC(out, exp);
}
else
{
// store entire experiment
f.store(out, exp);
}
}
else if (out_type == FileTypes::MGF)
{
//add data processing entry
addDataProcessing_(exp, getProcessingInfo_(DataProcessing::
FORMAT_CONVERSION));
MascotGenericFile f;
f.setLogType(log_type_);
f.store(out, exp, getFlag_("MGF_compact"));
}
else if (out_type == FileTypes::FEATUREXML)
{
if ((in_type == FileTypes::FEATUREXML) || (in_type == FileTypes::TSV) ||
(in_type == FileTypes::PEPLIST) || (in_type == FileTypes::KROENIK))
{
if (uid_postprocessing == "ensure")
{
fm.applyMemberFunction(&UniqueIdInterface::ensureUniqueId);
} else if (uid_postprocessing == "reassign")
{
fm.applyMemberFunction(&UniqueIdInterface::setUniqueId);
}
}
else if (in_type == FileTypes::CONSENSUSXML || in_type == FileTypes::EDTA)
{
MapConversion::convert(cm, true, fm);
}
else // not loaded as feature map or consensus map
{
// The feature specific information is only defaulted. Enough reasons to issue a warning!
writeLog_("Warning: Converting peaks to features will lead to incomplete features!");
fm.clear();
fm.reserve(exp.getSize());
typedef FeatureMapType::FeatureType FeatureType;
FeatureType feature;
feature.setQuality(0, 1); // override default
feature.setQuality(1, 1); // override default
feature.setOverallQuality(1); // override default
for (MSExperimentType::ConstIterator spec_iter = exp.begin();
spec_iter != exp.end();
++spec_iter
)
{
feature.setRT(spec_iter->getRT());
for (SpectrumType::ConstIterator peak1_iter = spec_iter->begin();
peak1_iter != spec_iter->end();
++peak1_iter
)
{
feature.setMZ(peak1_iter->getMZ());
feature.setIntensity(peak1_iter->getIntensity());
feature.setUniqueId();
fm.push_back(feature);
}
}
fm.updateRanges();
}
addDataProcessing_(fm, getProcessingInfo_(DataProcessing::
FORMAT_CONVERSION));
FeatureXMLFile().store(out, fm);
}
else if (out_type == FileTypes::CONSENSUSXML)
{
if ((in_type == FileTypes::FEATUREXML) || (in_type == FileTypes::TSV) ||
(in_type == FileTypes::PEPLIST) || (in_type == FileTypes::KROENIK))
{
if (uid_postprocessing == "ensure")
{
fm.applyMemberFunction(&UniqueIdInterface::ensureUniqueId);
} else if (uid_postprocessing == "reassign")
{
fm.applyMemberFunction(&UniqueIdInterface::setUniqueId);
}
MapConversion::convert(0, fm, cm);
}
// nothing to do for consensus input
else if (in_type == FileTypes::CONSENSUSXML || in_type == FileTypes::EDTA)
{
}
else // experimental data
{
MapConversion::convert(0, exp, cm, exp.size());
}
addDataProcessing_(cm, getProcessingInfo_(DataProcessing::
FORMAT_CONVERSION));
ConsensusXMLFile().store(out, cm);
}
else if (out_type == FileTypes::EDTA)
{
if (fm.size() > 0 && cm.size() > 0)
{
LOG_ERROR << "Internal error: cannot decide on container (Consensus or Feature)! This is a bug. Please report it!";
return INTERNAL_ERROR;
}
if (fm.size() > 0) EDTAFile().store(out, fm);
else if (cm.size() > 0) EDTAFile().store(out, cm);
}
else if (out_type == FileTypes::CSV)
{
// as ibspectra is currently the only csv/text based format we assume
// that out_type == FileTypes::CSV means ibspectra, if more formats
// are added we need a more intelligent strategy to decide which
// conversion is requested
// IBSpectra selected as output type
if (in_type != FileTypes::CONSENSUSXML)
{
LOG_ERROR << "Incompatible input data: FileConverter can only convert consensusXML files to ibspectra format.";
return INCOMPATIBLE_INPUT_DATA;
}
IBSpectraFile ibfile;
ibfile.store(out, cm);
}
else
{
writeLog_("Unknown output file type given. Aborting!");
printUsage_();
return ILLEGAL_PARAMETERS;
}
return EXECUTION_OK;
}
