boost::shared_ptr<IsobaricQuantitationMethod> IBSpectraFile::guessExperimentType_(const ConsensusMap& cm)
{
if (cm.getExperimentType() != "labeled_MS2" && cm.getExperimentType() != "itraq")
{
throw Exception::InvalidParameter(__FILE__,
__LINE__,
__PRETTY_FUNCTION__,
"Given ConsensusMap does not hold any isobaric quantification data.");
}
// we take the mapcount as approximation
if (cm.getFileDescriptions().size() == 4)
{
return boost::shared_ptr<IsobaricQuantitationMethod>(new ItraqFourPlexQuantitationMethod);
}
else if (cm.getFileDescriptions().size() == 6)
{
return boost::shared_ptr<IsobaricQuantitationMethod>(new TMTSixPlexQuantitationMethod);
}
else if (cm.getFileDescriptions().size() == 8)
{
return boost::shared_ptr<IsobaricQuantitationMethod>(new ItraqEightPlexQuantitationMethod);
}
else
{
throw Exception::InvalidParameter(__FILE__,
__LINE__,
__PRETTY_FUNCTION__,
"Could not guess isobaric quantification data from ConsensusMap due to non-matching number of input maps.");
}
}
void SeedListGenerator::generateSeedLists(const ConsensusMap& consensus,
Map<UInt64, SeedList>& seed_lists)
{
seed_lists.clear();
// iterate over all consensus features...
for (ConsensusMap::ConstIterator cons_it = consensus.begin();
cons_it != consensus.end(); ++cons_it)
{
DPosition<2> point(cons_it->getRT(), cons_it->getMZ());
// for each sub-map in the consensus map, add a seed at the position of
// this consensus feature:
for (ConsensusMap::FileDescriptions::const_iterator file_it =
consensus.getFileDescriptions().begin(); file_it !=
consensus.getFileDescriptions().end(); ++file_it)
seed_lists[file_it->first].push_back(point);
// for each feature contained in the consensus feature, remove the seed of
// the corresponding map:
for (ConsensusFeature::HandleSetType::const_iterator feat_it =
cons_it->getFeatures().begin(); feat_it !=
cons_it->getFeatures().end(); ++feat_it)
{
seed_lists[feat_it->getMapIndex()].pop_back();
}
// this leaves seeds for maps where no feature was found near the
// consensus position
}
}
void FeatureGroupingAlgorithm::transferSubelements(const vector<ConsensusMap>& maps, ConsensusMap& out) const
{
// accumulate file descriptions from the input maps:
// cout << "Updating file descriptions..." << endl;
out.getFileDescriptions().clear();
// mapping: (map index, original id) -> new id
map<pair<Size, UInt64>, Size> mapid_table;
for (Size i = 0; i < maps.size(); ++i)
{
const ConsensusMap& consensus = maps[i];
for (ConsensusMap::FileDescriptions::const_iterator desc_it = consensus.getFileDescriptions().begin(); desc_it != consensus.getFileDescriptions().end(); ++desc_it)
{
Size counter = mapid_table.size();
mapid_table[make_pair(i, desc_it->first)] = counter;
out.getFileDescriptions()[counter] = desc_it->second;
}
}
// look-up table: input map -> unique ID -> consensus feature
// cout << "Creating look-up table..." << endl;
vector<map<UInt64, ConsensusMap::ConstIterator> > feat_lookup(maps.size());
for (Size i = 0; i < maps.size(); ++i)
{
const ConsensusMap& consensus = maps[i];
for (ConsensusMap::ConstIterator feat_it = consensus.begin();
feat_it != consensus.end(); ++feat_it)
{
// do NOT use "id_lookup[i][feat_it->getUniqueId()] = feat_it;" here as
// you will get "attempt to copy-construct an iterator from a singular
// iterator" in STL debug mode:
feat_lookup[i].insert(make_pair(feat_it->getUniqueId(), feat_it));
}
}
// adjust the consensus features:
// cout << "Adjusting consensus features..." << endl;
for (ConsensusMap::iterator cons_it = out.begin(); cons_it != out.end(); ++cons_it)
{
ConsensusFeature adjusted = ConsensusFeature(
static_cast<BaseFeature>(*cons_it)); // remove sub-features
for (ConsensusFeature::HandleSetType::const_iterator sub_it = cons_it->getFeatures().begin(); sub_it != cons_it->getFeatures().end(); ++sub_it)
{
UInt64 id = sub_it->getUniqueId();
Size map_index = sub_it->getMapIndex();
ConsensusMap::ConstIterator origin = feat_lookup[map_index][id];
for (ConsensusFeature::HandleSetType::const_iterator handle_it = origin->getFeatures().begin(); handle_it != origin->getFeatures().end(); ++handle_it)
{
FeatureHandle handle = *handle_it;
Size new_id = mapid_table[make_pair(map_index, handle.getMapIndex())];
handle.setMapIndex(new_id);
adjusted.insert(handle);
}
}
*cons_it = adjusted;
}
}
void FeatureGroupingAlgorithmLabeled::group(const std::vector<FeatureMap<> > & maps, ConsensusMap & out)
{
//check that the number of maps is ok
if (maps.size() != 1)
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__, "Exactly one map must be given!");
if (out.getFileDescriptions().size() != 2)
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__, "Two file descriptions must be set in 'out'!");
//initialize LabeledPairFinder
LabeledPairFinder pm;
pm.setParameters(param_.copy("", true));
//convert to consensus map
std::vector<ConsensusMap> input(1);
ConsensusMap::convert(0, maps[0], input[0]);
//run
pm.run(input, out);
}
void IsobaricChannelExtractor::registerChannelsInOutputMap_(ConsensusMap& consensus_map)
{
// register the individual channels in the output consensus map
Int index = 0;
for (IsobaricQuantitationMethod::IsobaricChannelList::const_iterator cl_it = quant_method_->getChannelInformation().begin();
cl_it != quant_method_->getChannelInformation().end();
++cl_it)
{
ConsensusMap::FileDescription channel_as_map;
// label is the channel + description provided in the Params
channel_as_map.label = quant_method_->getName() + "_" + cl_it->name;
// TODO(aiche): number of features need to be set later
channel_as_map.size = consensus_map.size();
// add some more MetaInfo
channel_as_map.setMetaValue("channel_name", cl_it->name);
channel_as_map.setMetaValue("channel_id", cl_it->id);
channel_as_map.setMetaValue("channel_description", cl_it->description);
channel_as_map.setMetaValue("channel_center", cl_it->center);
consensus_map.getFileDescriptions()[index++] = channel_as_map;
}
}
void IsobaricQuantifier::computeLabelingStatistics_(ConsensusMap& consensus_map_out)
{
// number of total quantified spectra
stats_.number_ms2_total = consensus_map_out.size();
// Labeling efficiency statistics
for (size_t i = 0; i < consensus_map_out.size(); ++i)
{
// is whole scan empty?!
if (consensus_map_out[i].getIntensity() == 0) ++stats_.number_ms2_empty;
// look at single reporters
for (ConsensusFeature::HandleSetType::const_iterator it_elements = consensus_map_out[i].begin();
it_elements != consensus_map_out[i].end();
++it_elements)
{
if (it_elements->getIntensity() == 0)
{
String ch_index = consensus_map_out.getFileDescriptions()[it_elements->getMapIndex()].getMetaValue("channel_name");
++stats_.empty_channels[ch_index];
}
}
}
LOG_INFO << "IsobaricQuantifier: skipped " << stats_.number_ms2_empty << " of " << consensus_map_out.size() << " selected scans due to lack of reporter information:\n";
consensus_map_out.setMetaValue("isoquant:scans_noquant", stats_.number_ms2_empty);
consensus_map_out.setMetaValue("isoquant:scans_total", consensus_map_out.size());
LOG_INFO << "IsobaricQuantifier: channels with signal\n";
for (std::map<String, Size>::const_iterator it_m = stats_.empty_channels.begin();
it_m != stats_.empty_channels.end();
++it_m)
{
LOG_INFO << " channel " << it_m->first << ": " << (consensus_map_out.size() - it_m->second) << " / " << consensus_map_out.size() << " (" << ((consensus_map_out.size() - it_m->second) * 100 / consensus_map_out.size()) << "%)\n";
consensus_map_out.setMetaValue(String("isoquant:quantifyable_ch") + it_m->first, (consensus_map_out.size() - it_m->second));
}
}
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;
}
vector<double> ConsensusMapNormalizerAlgorithmThreshold::computeCorrelation(const ConsensusMap& map, const double& ratio_threshold, const String& acc_filter, const String& desc_filter)
{
Size number_of_features = map.size();
Size number_of_maps = map.getFileDescriptions().size();
vector<vector<double> > feature_int(number_of_maps);
//get map with most features, resize feature_int
UInt map_with_most_features_idx = 0;
ConsensusMap::FileDescriptions::const_iterator map_with_most_features = map.getFileDescriptions().find(0);
for (UInt i = 0; i < number_of_maps; i++)
{
feature_int[i].resize(number_of_features);
ConsensusMap::FileDescriptions::const_iterator it = map.getFileDescriptions().find(i);
if (it->second.size > map_with_most_features->second.size)
{
map_with_most_features = it;
map_with_most_features_idx = i;
}
}
//fill feature_int with intensities
Size pass_counter = 0;
ConsensusMap::ConstIterator cf_it;
UInt idx = 0;
for (cf_it = map.begin(); cf_it != map.end(); ++cf_it, ++idx)
{
if (!ConsensusMapNormalizerAlgorithmMedian::passesFilters_(cf_it, map, acc_filter, desc_filter))
{
continue;
}
++pass_counter;
ConsensusFeature::HandleSetType::const_iterator f_it;
for (f_it = cf_it->getFeatures().begin(); f_it != cf_it->getFeatures().end(); ++f_it)
{
feature_int[f_it->getMapIndex()][idx] = f_it->getIntensity();
}
}
LOG_INFO << endl << "Using " << pass_counter << "/" << map.size() << " consensus features for computing normalization coefficients" << endl << endl;
//determine ratio
vector<double> ratio_vector(number_of_maps);
for (UInt j = 0; j < number_of_maps; j++)
{
vector<double> ratios;
for (UInt k = 0; k < number_of_features; ++k)
{
if (feature_int[map_with_most_features_idx][k] != 0.0 && feature_int[j][k] != 0.0)
{
double ratio = feature_int[map_with_most_features_idx][k] / feature_int[j][k];
if (ratio > ratio_threshold && ratio < 1 / ratio_threshold)
{
ratios.push_back(ratio);
}
}
}
if (ratios.empty())
{
LOG_WARN << endl << "Not enough features passing filters. Cannot compute normalization coefficients for all maps. Result will be unnormalized." << endl << endl;
return vector<double>(number_of_maps, 1.0);
}
ratio_vector[j] = Math::mean(ratios.begin(), ratios.end());
}
return ratio_vector;
}
ExitCodes main_(int, const char **)
{
FeatureGroupingAlgorithmUnlabeled * algorithm = new FeatureGroupingAlgorithmUnlabeled();
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
StringList ins;
ins = getStringList_("in");
String out = getStringOption_("out");
//-------------------------------------------------------------
// check for valid input
//-------------------------------------------------------------
// check if all input files have the correct type
FileTypes::Type file_type = FileHandler::getType(ins[0]);
for (Size i = 0; i < ins.size(); ++i)
{
if (FileHandler::getType(ins[i]) != file_type)
{
writeLog_("Error: All input files must be of the same type!");
return ILLEGAL_PARAMETERS;
}
}
//-------------------------------------------------------------
// set up algorithm
//-------------------------------------------------------------
Param algorithm_param = getParam_().copy("algorithm:", true);
writeDebug_("Used algorithm parameters", algorithm_param, 3);
algorithm->setParameters(algorithm_param);
Size reference_index(0);
//-------------------------------------------------------------
// perform grouping
//-------------------------------------------------------------
// load input
ConsensusMap out_map;
StringList ms_run_locations;
if (file_type == FileTypes::FEATUREXML)
{
// use map with highest number of features as reference:
Size max_count(0);
FeatureXMLFile f;
for (Size i = 0; i < ins.size(); ++i)
{
Size s = f.loadSize(ins[i]);
if (s > max_count)
{
max_count = s;
reference_index = i;
}
}
// Load reference map and input it to the algorithm
UInt64 ref_id;
Size ref_size;
std::vector<PeptideIdentification> ref_pepids;
std::vector<ProteinIdentification> ref_protids;
{
FeatureMap map_ref;
FeatureXMLFile f_fxml_tmp;
f_fxml_tmp.getOptions().setLoadConvexHull(false);
f_fxml_tmp.getOptions().setLoadSubordinates(false);
f_fxml_tmp.load(ins[reference_index], map_ref);
algorithm->setReference(reference_index, map_ref);
ref_id = map_ref.getUniqueId();
ref_size = map_ref.size();
ref_pepids = map_ref.getUnassignedPeptideIdentifications();
ref_protids = map_ref.getProteinIdentifications();
}
ConsensusMap dummy;
// go through all input files and add them to the result one by one
for (Size i = 0; i < ins.size(); ++i)
{
FeatureXMLFile f_fxml_tmp;
FeatureMap tmp_map;
f_fxml_tmp.getOptions().setLoadConvexHull(false);
f_fxml_tmp.getOptions().setLoadSubordinates(false);
f_fxml_tmp.load(ins[i], tmp_map);
// copy over information on the primary MS run
StringList ms_runs;
tmp_map.getPrimaryMSRunPath(ms_runs);
ms_run_locations.insert(ms_run_locations.end(), ms_runs.begin(), ms_runs.end());
if (i != reference_index)
{
algorithm->addToGroup(i, tmp_map);
// store some meta-data about the maps in the "dummy" object -> try to
// keep the same order as they were given in the input independent of
// which map is the reference.
dummy.getFileDescriptions()[i].filename = ins[i];
dummy.getFileDescriptions()[i].size = tmp_map.size();
dummy.getFileDescriptions()[i].unique_id = tmp_map.getUniqueId();
// add protein identifications to result map
dummy.getProteinIdentifications().insert(
dummy.getProteinIdentifications().end(),
tmp_map.getProteinIdentifications().begin(),
tmp_map.getProteinIdentifications().end());
// add unassigned peptide identifications to result map
dummy.getUnassignedPeptideIdentifications().insert(
dummy.getUnassignedPeptideIdentifications().end(),
tmp_map.getUnassignedPeptideIdentifications().begin(),
tmp_map.getUnassignedPeptideIdentifications().end());
}
else
{
// copy the meta-data from the refernce map
dummy.getFileDescriptions()[i].filename = ins[i];
dummy.getFileDescriptions()[i].size = ref_size;
dummy.getFileDescriptions()[i].unique_id = ref_id;
// add protein identifications to result map
dummy.getProteinIdentifications().insert(
dummy.getProteinIdentifications().end(),
ref_protids.begin(),
ref_protids.end());
// add unassigned peptide identifications to result map
dummy.getUnassignedPeptideIdentifications().insert(
dummy.getUnassignedPeptideIdentifications().end(),
ref_pepids.begin(),
ref_pepids.end());
}
}
// get the resulting map
out_map = algorithm->getResultMap();
//
// Copy back meta-data (Protein / Peptide ids / File descriptions)
//
// add protein identifications to result map
out_map.getProteinIdentifications().insert(
out_map.getProteinIdentifications().end(),
dummy.getProteinIdentifications().begin(),
dummy.getProteinIdentifications().end());
// add unassigned peptide identifications to result map
out_map.getUnassignedPeptideIdentifications().insert(
out_map.getUnassignedPeptideIdentifications().end(),
dummy.getUnassignedPeptideIdentifications().begin(),
dummy.getUnassignedPeptideIdentifications().end());
out_map.setFileDescriptions(dummy.getFileDescriptions());
// canonical ordering for checking the results, and the ids have no real meaning anyway
// the way this was done in DelaunayPairFinder and StablePairFinder
// -> the same ordering as FeatureGroupingAlgorithmUnlabeled::group applies!
out_map.sortByMZ();
out_map.updateRanges();
}
else
{
vector<ConsensusMap> maps(ins.size());
ConsensusXMLFile f;
for (Size i = 0; i < ins.size(); ++i)
{
f.load(ins[i], maps[i]);
StringList ms_runs;
maps[i].getPrimaryMSRunPath(ms_runs);
ms_run_locations.insert(ms_run_locations.end(), ms_runs.begin(), ms_runs.end());
}
// group
algorithm->FeatureGroupingAlgorithm::group(maps, out_map);
// set file descriptions:
bool keep_subelements = getFlag_("keep_subelements");
if (!keep_subelements)
{
for (Size i = 0; i < ins.size(); ++i)
{
out_map.getFileDescriptions()[i].filename = ins[i];
out_map.getFileDescriptions()[i].size = maps[i].size();
out_map.getFileDescriptions()[i].unique_id = maps[i].getUniqueId();
}
}
else
{
// components of the output map are not the input maps themselves, but
// the components of the input maps:
algorithm->transferSubelements(maps, out_map);
}
}
// assign unique ids
out_map.applyMemberFunction(&UniqueIdInterface::setUniqueId);
// annotate output with data processing info
addDataProcessing_(out_map, getProcessingInfo_(DataProcessing::FEATURE_GROUPING));
out_map.setPrimaryMSRunPath(ms_run_locations);
// write output
ConsensusXMLFile().store(out, out_map);
// some statistics
map<Size, UInt> num_consfeat_of_size;
for (ConsensusMap::const_iterator cmit = out_map.begin(); cmit != out_map.end(); ++cmit)
{
++num_consfeat_of_size[cmit->size()];
}
LOG_INFO << "Number of consensus features:" << endl;
for (map<Size, UInt>::reverse_iterator i = num_consfeat_of_size.rbegin(); i != num_consfeat_of_size.rend(); ++i)
{
LOG_INFO << " of size " << setw(2) << i->first << ": " << setw(6) << i->second << endl;
}
LOG_INFO << " total: " << setw(6) << out_map.size() << endl;
delete algorithm;
return EXECUTION_OK;
}
/// @brief extracts the iTRAQ channels from the MS data and stores intensity values in a consensus map
///
/// @param ms_exp_data Raw data to read
/// @param consensus_map Output each MS² scan as a consensus feature
/// @throws Exception::MissingInformation if no scans present or MS² scan has no precursor
void ItraqChannelExtractor::run(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.";
throw Exception::MissingInformation(__FILE__, __LINE__, __PRETTY_FUNCTION__, "Experiment has no scans!");
}
MSExperiment<> ms_exp_MS2;
String mode = (String) param_.getValue("select_activation");
std::cout << "Selecting scans with activation mode: " << (mode == "" ? "any" : mode) << "\n";
HasActivationMethod<MSExperiment<Peak1D>::SpectrumType> activation_predicate(ListUtils::create<String>(mode));
for (size_t idx = 0; idx < ms_exp_data.size(); ++idx)
{
if (ms_exp_data[idx].getMSLevel() == 2)
{
if (mode == "" || activation_predicate(ms_exp_data[idx]))
{
// copy only MS² scans
ms_exp_MS2.addSpectrum(ms_exp_data[idx]);
}
else
{
//std::cout << "deleting spectrum # " << idx << " with RT: " << ms_exp_data[idx].getRT() << "\n";
}
}
}
#ifdef ITRAQ_DEBUG
std::cout << "we have " << ms_exp_MS2.size() << " scans left of level " << ms_exp_MS2[0].getMSLevel() << std::endl;
std::cout << "run: channel_map_ has " << channel_map_.size() << " entries!" << std::endl;
#endif
consensus_map.clear(false);
// set <mapList> header
Int index_cnt = 0;
for (ChannelMapType::const_iterator cm_it = channel_map_.begin(); cm_it != channel_map_.end(); ++cm_it)
{
// structure of Map cm_it
// first == channel-name as Int e.g. 114
// second == ChannelInfo struct
ConsensusMap::FileDescription channel_as_map;
// label is the channel + description provided in the Params
if (itraq_type_ != TMT_SIXPLEX)
channel_as_map.label = "iTRAQ_" + String(cm_it->second.name) + "_" + String(cm_it->second.description);
else
channel_as_map.label = "TMT_" + String(cm_it->second.name) + "_" + String(cm_it->second.description);
channel_as_map.size = ms_exp_MS2.size();
//TODO what about .filename? leave empty?
// add some more MetaInfo
channel_as_map.setMetaValue("channel_name", cm_it->second.name);
channel_as_map.setMetaValue("channel_id", cm_it->second.id);
channel_as_map.setMetaValue("channel_description", cm_it->second.description);
channel_as_map.setMetaValue("channel_center", cm_it->second.center);
channel_as_map.setMetaValue("channel_active", String(cm_it->second.active ? "true" : "false"));
consensus_map.getFileDescriptions()[index_cnt++] = channel_as_map;
}
// create consensusElements
Peak2D::CoordinateType allowed_deviation = (Peak2D::CoordinateType) param_.getValue("reporter_mass_shift");
// now we have picked data
// --> assign peaks to channels
UInt element_index(0);
for (MSExperiment<>::ConstIterator it = ms_exp_MS2.begin(); it != ms_exp_MS2.end(); ++it)
{
// store RT&MZ of parent ion as centroid of ConsensusFeature
ConsensusFeature cf;
cf.setUniqueId();
cf.setRT(it->getRT());
if (it->getPrecursors().size() >= 1)
{
cf.setMZ(it->getPrecursors()[0].getMZ());
}
else
{
throw Exception::MissingInformation(__FILE__, __LINE__, __PRETTY_FUNCTION__, String("No precursor information given for scan native ID ") + String(it->getNativeID()) + " with RT " + String(it->getRT()));
}
Peak2D channel_value;
channel_value.setRT(it->getRT());
// for each each channel
Int index = 0;
Peak2D::IntensityType overall_intensity = 0;
for (ChannelMapType::const_iterator cm_it = channel_map_.begin(); cm_it != channel_map_.end(); ++cm_it)
{
// set mz-position of channel
channel_value.setMZ(cm_it->second.center);
// reset intensity
channel_value.setIntensity(0);
//add up all signals
for (MSExperiment<>::SpectrumType::ConstIterator mz_it =
it->MZBegin(cm_it->second.center - allowed_deviation)
; mz_it != it->MZEnd(cm_it->second.center + allowed_deviation)
; ++mz_it
)
{
channel_value.setIntensity(channel_value.getIntensity() + mz_it->getIntensity());
}
overall_intensity += channel_value.getIntensity();
// add channel to ConsensusFeature
cf.insert(index++, channel_value, element_index);
} // ! channel_iterator
// 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
#ifdef ITRAQ_DEBUG
std::cout << "processed " << element_index << " scans" << std::endl;
#endif
consensus_map.setExperimentType("itraq");
return;
}
ExitCodes outputTo(ostream& os)
{
//-------------------------------------------------------------
// Parameter handling
//-------------------------------------------------------------
// File names
String in = getStringOption_("in");
// 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;
}
MSExperiment<Peak1D> exp;
FeatureMap feat;
ConsensusMap cons;
if (in_type == FileTypes::FEATUREXML) //features
{
FeatureXMLFile().load(in, feat);
feat.updateRanges();
}
else if (in_type == FileTypes::CONSENSUSXML) //consensus features
{
ConsensusXMLFile().load(in, cons);
cons.updateRanges();
}
//-------------------------------------------------------------
// meta information
//-------------------------------------------------------------
if (getFlag_("m"))
{
os << endl
<< "-- General information --" << endl
<< endl
<< "file name: " << in << endl
<< "file type: " << FileTypes::typeToName(in_type) << endl;
//basic info
os << endl
<< "-- Meta information --" << endl
<< endl;
if (in_type == FileTypes::FEATUREXML) //features
{
os << "Document id : " << feat.getIdentifier() << endl << endl;
}
else if (in_type == FileTypes::CONSENSUSXML) //consensus features
{
os << "Document id : " << cons.getIdentifier() << endl << endl;
}
}
//-------------------------------------------------------------
// data processing
//-------------------------------------------------------------
if (getFlag_("p"))
{
//basic info
os << endl
<< "-- Data processing information --" << endl
<< endl;
//get data processing info
vector<DataProcessing> dp;
if (in_type == FileTypes::FEATUREXML) //features
{
dp = feat.getDataProcessing();
}
else if (in_type == FileTypes::CONSENSUSXML) //consensus features
{
dp = cons.getDataProcessing();
}
int i = 0;
for (vector<DataProcessing>::iterator it = dp.begin(); it != dp.end(); ++it)
{
os << "Data processing " << i << endl;
os << "\tcompletion_time: " << (*it).getCompletionTime().getDate() << 'T' << (*it).getCompletionTime().getTime() << endl;
os << "\tsoftware name: " << (*it).getSoftware().getName() << " version " << (*it).getSoftware().getVersion() << endl;
for (set<DataProcessing::ProcessingAction>::const_iterator paIt = (*it).getProcessingActions().begin(); paIt != (*it).getProcessingActions().end(); ++paIt)
{
os << "\t\tprocessing action: " << DataProcessing::NamesOfProcessingAction[*paIt] << endl;
}
}
++i;
}
//-------------------------------------------------------------
// statistics
//-------------------------------------------------------------
if (getFlag_("s"))
{
//-------------------------------------------------------------
// Content statistics
//-------------------------------------------------------------
Map<String, int> meta_names;
if (in_type == FileTypes::FEATUREXML) //features
{
os << "Number of features: " << feat.size() << endl
<< endl
<< "Ranges:" << endl
<< " retention time: " << String::number(feat.getMin()[Peak2D::RT], 2) << " : " << String::number(feat.getMax()[Peak2D::RT], 2) << endl
<< " mass-to-charge: " << String::number(feat.getMin()[Peak2D::MZ], 2) << " : " << String::number(feat.getMax()[Peak2D::MZ], 2) << endl
<< " intensity: " << String::number(feat.getMinInt(), 2) << " : " << String::number(feat.getMaxInt(), 2) << endl
<< endl;
// Charge distribution
Map<UInt, UInt> charges;
for (Size i = 0; i < feat.size(); ++i)
{
charges[feat[i].getCharge()]++;
}
os << "Charge distribution" << endl;
for (Map<UInt, UInt>::const_iterator it = charges.begin();
it != charges.end(); ++it)
{
os << "charge " << it->first << ": " << it->second << endl;
}
}
else if (in_type == FileTypes::CONSENSUSXML) //consensus features
{
map<Size, UInt> num_consfeat_of_size;
for (ConsensusMap::const_iterator cmit = cons.begin();
cmit != cons.end(); ++cmit)
{
++num_consfeat_of_size[cmit->size()];
}
os << endl << "Number of consensus features:" << endl;
for (map<Size, UInt>::reverse_iterator i = num_consfeat_of_size.rbegin(); i != num_consfeat_of_size.rend(); ++i)
{
os << " of size " << setw(2) << i->first << ": " << setw(6) << i->second << endl;
}
os << " total: " << setw(6) << cons.size() << endl << endl;
os << "Ranges:" << endl
<< " retention time: " << String::number(cons.getMin()[Peak2D::RT], 2) << " : " << String::number(cons.getMax()[Peak2D::RT], 2) << endl
<< " mass-to-charge: " << String::number(cons.getMin()[Peak2D::MZ], 2) << " : " << String::number(cons.getMax()[Peak2D::MZ], 2) << endl
<< " intensity: " << String::number(cons.getMinInt(), 2) << " : " << String::number(cons.getMaxInt(), 2) << endl;
// file descriptions
const ConsensusMap::FileDescriptions& descs = cons.getFileDescriptions();
if (!descs.empty())
{
os << endl <<
"File descriptions:" << endl;
for (ConsensusMap::FileDescriptions::const_iterator it = descs.begin(); it != descs.end(); ++it)
{
os << " - " << it->second.filename << endl
<< " identifier: " << it->first << endl
<< " label : " << it->second.label << endl
<< " size : " << it->second.size << endl;
}
}
}
os << endl
<< "-- Summary Statistics --" << endl
<< endl;
}
if (in_type == FileTypes::FEATUREXML) //features
{
feat.sortByRT();
vector<double> slice_stats;
Size n = getIntOption_("n");
Size begin = 0;
Size end = 0;
os << "#slice\tRT_begin\tRT_end\tnumber_of_features\ttic\t"
<< "int_mean\tint_stddev\tint_min\tint_max\tint_median\tint_lowerq\tint_upperq\t"
<< "mz_mean\tmz_stddev\tmz_min\tmz_max\tmz_median\tmz_lowerq\tmz_upperq\t"
<< "width_mean\twidth_stddev\twidth_min\twidth_max\twidth_median\twidth_lowerq\twidth_upperq\t"
<< "qual_mean\tqual_stddev\tqual_min\tqual_max\tqual_median\tqual_lowerq\tqual_upperq\t"
<< "rt_qual_mean\trt_qual_stddev\trt_qual_min\trt_qual_max\trt_qual_median\trt_qual_lowerq\trt_qual_upperq\t"
<< "mz_qual_mean\tmz_qual_stddev\tmz_qual_min\tmz_qual_max\tmz_qual_median\tmz_qual_lowerq\tmz_qual_upperq"
<< endl;
double rt_begin = 0.0;
for (Size slice = 0; slice < n; ++slice)
{
// Determine slice boundaries.
double rt_end = feat.back().getRT() / (double)n * (slice + 1);
for (end = begin; end < feat.size() && feat[end].getRT() < rt_end; ++end) {}
// Compute statistics on all features in this slice.
slice_stats = sliceStatistics(feat, begin, end);
// Write the beginning and end of the slices to the output as well as the slice index.
os << slice << "\t" << rt_begin << "\t" << rt_end << "\t" << end - begin << "\t";
// Write the statistics as a line of an csv file
copy(slice_stats.begin(), slice_stats.end(), ostream_iterator<double>(os, "\t"));
os << endl;
begin = end;
rt_begin = rt_end;
}
}
else if (in_type == FileTypes::CONSENSUSXML) //consensus features
{
Size size = cons.size();
vector<double> intensities;
intensities.reserve(size);
vector<double> qualities(size);
qualities.reserve(size);
vector<double> widths(size);
widths.reserve(size);
vector<double> rt_delta_by_elems;
vector<double> rt_aad_by_elems;
vector<double> rt_aad_by_cfs;
rt_aad_by_cfs.reserve(size);
vector<double> mz_delta_by_elems;
vector<double> mz_aad_by_elems;
vector<double> mz_aad_by_cfs;
mz_aad_by_cfs.reserve(size);
vector<double> it_delta_by_elems;
vector<double> it_aad_by_elems;
vector<double> it_aad_by_cfs;
it_aad_by_cfs.reserve(size);
for (ConsensusMap::const_iterator cm_iter = cons.begin();
cm_iter != cons.end(); ++cm_iter)
{
double rt_aad = 0;
double mz_aad = 0;
double it_aad = 0;
intensities.push_back(cm_iter->getIntensity());
qualities.push_back(cm_iter->getQuality());
widths.push_back(cm_iter->getWidth());
for (ConsensusFeature::HandleSetType::const_iterator hs_iter = cm_iter->begin();
hs_iter != cm_iter->end(); ++hs_iter)
{
double rt_diff = hs_iter->getRT() - cm_iter->getRT();
rt_delta_by_elems.push_back(rt_diff);
if (rt_diff < 0)
{
rt_diff = -rt_diff;
}
rt_aad_by_elems.push_back(rt_diff);
rt_aad += rt_diff;
double mz_diff = hs_iter->getMZ() - cm_iter->getMZ();
mz_delta_by_elems.push_back(mz_diff);
if (mz_diff < 0)
{
mz_diff = -mz_diff;
}
mz_aad_by_elems.push_back(mz_diff);
mz_aad += mz_diff;
double it_ratio = hs_iter->getIntensity() / (cm_iter->getIntensity() ? cm_iter->getIntensity() : 1.);
it_delta_by_elems.push_back(it_ratio);
if (it_ratio < 1.)
{
it_ratio = 1. / it_ratio;
}
it_aad_by_elems.push_back(it_ratio);
it_aad += it_ratio;
}
if (!cm_iter->empty())
{
rt_aad /= cm_iter->size();
mz_aad /= cm_iter->size();
it_aad /= cm_iter->size();
} // otherwise rt_aad etc. are 0 anyway
rt_aad_by_cfs.push_back(rt_aad);
mz_aad_by_cfs.push_back(mz_aad);
it_aad_by_cfs.push_back(it_aad);
}
OpenMS::SomeStatistics some_statistics;
os.precision(writtenDigits(ConsensusFeature::IntensityType()));
os << "Intensities of consensus features:" << endl << some_statistics(intensities) << endl;
os.precision(writtenDigits(ConsensusFeature::QualityType()));
os << "Qualities of consensus features:" << endl << some_statistics(qualities) << endl;
os.precision(writtenDigits(ConsensusFeature::CoordinateType()));
os << "Retention time differences ( element-center, weight 1 per element):" << endl << some_statistics(rt_delta_by_elems) << endl;
os << "Absolute retention time differences ( |element-center|, weight 1 per element):" << endl << some_statistics(rt_aad_by_elems) << endl;
os << "Average absolute differences of retention time within consensus features ( |element-center|, weight 1 per consensus features):" << endl << some_statistics(rt_aad_by_cfs) << endl;
os.precision(writtenDigits(ConsensusFeature::CoordinateType()));
os << "Mass-to-charge differences ( element-center, weight 1 per element):" << endl << some_statistics(mz_delta_by_elems) << endl;
os << "Absolute differences of mass-to-charge ( |element-center|, weight 1 per element):" << endl << some_statistics(mz_aad_by_elems) << endl;
os << "Average absolute differences of mass-to-charge within consensus features ( |element-center|, weight 1 per consensus features):" << endl << some_statistics(mz_aad_by_cfs) << endl;
os.precision(writtenDigits(ConsensusFeature::IntensityType()));
os << "Intensity ratios ( element/center, weight 1 per element):" << endl << some_statistics(it_delta_by_elems) << endl;
os << "Relative intensity error ( max{(element/center),(center/element)}, weight 1 per element):" << endl << some_statistics(it_aad_by_elems) << endl;
os << "Average relative intensity error within consensus features ( max{(element/center),(center/element)}, weight 1 per consensus features):" << endl << some_statistics(it_aad_by_cfs) << endl;
}
return EXECUTION_OK;
}
pItraq.setValue("channel_116_description", "else");
q_method->setParameters(pItraq);
IsobaricChannelExtractor ice(q_method);
// disable activation filtering
Param p = ice.getParameters();
p.setValue("select_activation", "");
ice.setParameters(p);
// extract channels
ConsensusMap cm_out;
ice.extractChannels(exp, cm_out);
// check channel meta information
TEST_EQUAL(cm_out.getFileDescriptions().size(), 4)
ABORT_IF(cm_out.getFileDescriptions().size() != 4)
TEST_EQUAL(cm_out.getFileDescriptions()[0].label, "itraq4plex_114")
TEST_EQUAL(cm_out.getFileDescriptions()[0].getMetaValue("channel_name"), 114)
TEST_EQUAL(cm_out.getFileDescriptions()[0].getMetaValue("channel_id"), 0)
TEST_EQUAL(cm_out.getFileDescriptions()[0].getMetaValue("channel_description"), "ref")
TEST_EQUAL(cm_out.getFileDescriptions()[0].getMetaValue("channel_center"), 114.1112)
TEST_EQUAL(cm_out.getFileDescriptions()[1].label, "itraq4plex_115")
TEST_EQUAL(cm_out.getFileDescriptions()[1].getMetaValue("channel_name"), 115)
TEST_EQUAL(cm_out.getFileDescriptions()[1].getMetaValue("channel_id"), 1)
TEST_EQUAL(cm_out.getFileDescriptions()[1].getMetaValue("channel_description"), "something")
TEST_EQUAL(cm_out.getFileDescriptions()[1].getMetaValue("channel_center"), 115.1082)
TEST_EQUAL(cm_out.getFileDescriptions()[2].label, "itraq4plex_116")
void LabeledPairFinder::run(const vector<ConsensusMap>& input_maps, ConsensusMap& result_map)
{
if (input_maps.size() != 1)
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__, "exactly one input map required");
if (result_map.getFileDescriptions().size() != 2)
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__, "two file descriptions required");
if (result_map.getFileDescriptions().begin()->second.filename != result_map.getFileDescriptions().rbegin()->second.filename)
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__, "the two file descriptions have to contain the same file name");
checkIds_(input_maps);
//look up the light and heavy index
Size light_index = numeric_limits<Size>::max();
Size heavy_index = numeric_limits<Size>::max();
for (ConsensusMap::FileDescriptions::const_iterator it = result_map.getFileDescriptions().begin();
it != result_map.getFileDescriptions().end();
++it)
{
if (it->second.label == "heavy")
{
heavy_index = it->first;
}
else if (it->second.label == "light")
{
light_index = it->first;
}
}
if (light_index == numeric_limits<Size>::max() || heavy_index == numeric_limits<Size>::max())
{
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__, "the input maps have to be labeled 'light' and 'heavy'");
}
result_map.clear(false);
// sort consensus features by RT (and MZ) to speed up searching afterwards
typedef ConstRefVector<ConsensusMap> RefMap;
RefMap model_ref(input_maps[0].begin(), input_maps[0].end());
model_ref.sortByPosition();
//calculate matches
ConsensusMap matches;
//settings
double rt_pair_dist = param_.getValue("rt_pair_dist");
double rt_dev_low = param_.getValue("rt_dev_low");
double rt_dev_high = param_.getValue("rt_dev_high");
double mz_dev = param_.getValue("mz_dev");
DoubleList mz_pair_dists = param_.getValue("mz_pair_dists");
bool mrm = param_.getValue("mrm").toBool();
//estimate RT parameters
if (param_.getValue("rt_estimate") == "true")
{
//find all possible RT distances of features with the same charge and a good m/z distance
vector<double> dists;
dists.reserve(model_ref.size());
for (RefMap::const_iterator it = model_ref.begin(); it != model_ref.end(); ++it)
{
for (RefMap::const_iterator it2 = model_ref.begin(); it2 != model_ref.end(); ++it2)
{
for (DoubleList::const_iterator dist_it = mz_pair_dists.begin(); dist_it != mz_pair_dists.end(); ++dist_it)
{
double mz_pair_dist = *dist_it;
if (it2->getCharge() == it->getCharge()
&& it2->getMZ() >= it->getMZ() + mz_pair_dist / it->getCharge() - mz_dev
&& it2->getMZ() <= it->getMZ() + mz_pair_dist / it->getCharge() + mz_dev)
{
dists.push_back(it2->getRT() - it->getRT());
}
}
}
}
if (dists.empty())
{
cout << "Warning: Could not find pairs for RT distance estimation. The manual settings are used!" << endl;
}
else
{
if (dists.size() < 50)
{
cout << "Warning: Found only " << dists.size() << " pairs. The estimated shift and std deviation are probably not reliable!" << endl;
}
//--------------------------- estimate initial parameters of fit ---------------------------
GaussFitter::GaussFitResult result(-1, -1, -1);
//first estimate of the optimal shift: median of the distances
sort(dists.begin(), dists.end());
Size median_index = dists.size() / 2;
result.x0 = dists[median_index];
//create histogram of distances
//consider only the maximum of pairs, centered around the optimal shift
Size max_pairs = model_ref.size() / 2;
Size start_index = (Size) max((SignedSize)0, (SignedSize)(median_index - max_pairs / 2));
Size end_index = (Size) min((SignedSize)(dists.size() - 1), (SignedSize)(median_index + max_pairs / 2));
double start_value = dists[start_index];
double end_value = dists[end_index];
double bin_step = fabs(end_value - start_value) / 99.999; //ensure that we have 100 bins
Math::Histogram<> hist(start_value, end_value, bin_step);
//std::cout << "HIST from " << start_value << " to " << end_value << " (bin size " << bin_step << ")" << endl;
for (Size i = start_index; i <= end_index; ++i)
{
hist.inc(dists[i]);
}
//cout << hist << endl;
dists.clear();
//determine median of bins (uniform background distribution)
vector<Size> bins(hist.begin(), hist.end());
sort(bins.begin(), bins.end());
Size bin_median = bins[bins.size() / 2];
bins.clear();
//estimate scale A: maximum of the histogram
Size max_value = hist.maxValue();
result.A = max_value - bin_median;
//overwrite estimate of x0 with the position of the highest bin
for (Size i = 0; i < hist.size(); ++i)
{
if (hist[i] == max_value)
{
result.x0 = hist.centerOfBin(i);
break;
}
}
//estimate sigma: first time the count is less or equal the median count in the histogram
double pos = result.x0;
while (pos > start_value && hist.binValue(pos) > bin_median)
{
pos -= bin_step;
}
double sigma_low = result.x0 - pos;
pos = result.x0;
while (pos<end_value&& hist.binValue(pos)> bin_median)
{
pos += bin_step;
}
double sigma_high = pos - result.x0;
result.sigma = (sigma_high + sigma_low) / 6.0;
//cout << "estimated optimal RT distance (before fit): " << result.x0 << endl;
//cout << "estimated allowed deviation (before fit): " << result.sigma*3.0 << endl;
//--------------------------- do gauss fit ---------------------------
vector<DPosition<2> > points(hist.size());
for (Size i = 0; i < hist.size(); ++i)
{
points[i][0] = hist.centerOfBin(i);
points[i][1] = max(0u, hist[i]);
}
GaussFitter fitter;
fitter.setInitialParameters(result);
result = fitter.fit(points);
cout << "estimated optimal RT distance: " << result.x0 << endl;
cout << "estimated allowed deviation: " << fabs(result.sigma) * 3.0 << endl;
rt_pair_dist = result.x0;
rt_dev_low = fabs(result.sigma) * 3.0;
rt_dev_high = fabs(result.sigma) * 3.0;
}
}
// check each feature
for (RefMap::const_iterator it = model_ref.begin(); it != model_ref.end(); ++it)
{
for (DoubleList::const_iterator dist_it = mz_pair_dists.begin(); dist_it != mz_pair_dists.end(); ++dist_it)
{
double mz_pair_dist = *dist_it;
RefMap::const_iterator it2 = lower_bound(model_ref.begin(), model_ref.end(), it->getRT() + rt_pair_dist - rt_dev_low, ConsensusFeature::RTLess());
while (it2 != model_ref.end() && it2->getRT() <= it->getRT() + rt_pair_dist + rt_dev_high)
{
// if in mrm mode, we need to compare precursor mass difference and fragment mass difference, charge remains the same
double prec_mz_diff(0);
if (mrm)
{
prec_mz_diff = fabs((double)it2->getMetaValue("MZ") - (double)it->getMetaValue("MZ"));
if (it->getCharge() != 0)
{
prec_mz_diff = fabs(prec_mz_diff - mz_pair_dist / it->getCharge());
}
else
{
prec_mz_diff = fabs(prec_mz_diff - mz_pair_dist);
}
}
bool mrm_correct_dist(false);
double frag_mz_diff = fabs(it->getMZ() - it2->getMZ());
//cerr << it->getRT() << " charge1=" << it->getCharge() << ", charge2=" << it2->getCharge() << ", prec_diff=" << prec_mz_diff << ", frag_diff=" << frag_mz_diff << endl;
if (mrm &&
it2->getCharge() == it->getCharge() &&
prec_mz_diff < mz_dev &&
(frag_mz_diff < mz_dev || fabs(frag_mz_diff - mz_pair_dist) < mz_dev))
{
mrm_correct_dist = true;
//cerr << "mrm_correct_dist" << endl;
}
if ((mrm && mrm_correct_dist) || (!mrm &&
it2->getCharge() == it->getCharge() &&
it2->getMZ() >= it->getMZ() + mz_pair_dist / it->getCharge() - mz_dev &&
it2->getMZ() <= it->getMZ() + mz_pair_dist / it->getCharge() + mz_dev
))
{
//cerr << "dist correct" << endl;
double score = sqrt(
PValue_(it2->getMZ() - it->getMZ(), mz_pair_dist / it->getCharge(), mz_dev, mz_dev) *
PValue_(it2->getRT() - it->getRT(), rt_pair_dist, rt_dev_low, rt_dev_high)
);
// Note: we used to copy the id from the light feature here, but that strategy does not generalize to more than two labels.
// We might want to report consensus features where the light one is missing but more than one heavier variant was found.
// Also, the old strategy is inconsistent with what was done in the unlabeled case. Thus now we assign a new unique id here.
matches.push_back(ConsensusFeature());
matches.back().setUniqueId();
matches.back().insert(light_index, *it);
matches.back().clearMetaInfo();
matches.back().insert(heavy_index, *it2);
matches.back().setQuality(score);
matches.back().setCharge(it->getCharge());
matches.back().computeMonoisotopicConsensus();
}
++it2;
}
}
}
//compute best pairs
// - sort matches by quality
// - take highest-quality matches first (greedy) and mark them as used
set<Size> used_features;
matches.sortByQuality(true);
for (ConsensusMap::const_iterator match = matches.begin(); match != matches.end(); ++match)
{
//check if features are not used yet
if (used_features.find(match->begin()->getUniqueId()) == used_features.end() &&
used_features.find(match->rbegin()->getUniqueId()) == used_features.end()
)
{
//if unused, add it to the final set of elements
result_map.push_back(*match);
used_features.insert(match->begin()->getUniqueId());
used_features.insert(match->rbegin()->getUniqueId());
}
}
//Add protein identifications to result map
for (Size i = 0; i < input_maps.size(); ++i)
{
result_map.getProteinIdentifications().insert(result_map.getProteinIdentifications().end(), input_maps[i].getProteinIdentifications().begin(), input_maps[i].getProteinIdentifications().end());
}
//Add unassigned peptide identifications to result map
for (Size i = 0; i < input_maps.size(); ++i)
{
result_map.getUnassignedPeptideIdentifications().insert(result_map.getUnassignedPeptideIdentifications().end(), input_maps[i].getUnassignedPeptideIdentifications().begin(), input_maps[i].getUnassignedPeptideIdentifications().end());
}
// Very useful for checking the results, and the ids have no real meaning anyway
result_map.sortByMZ();
}
void EDTAFile::load(const String& filename, ConsensusMap& consensus_map)
{
// load input
TextFile input(filename);
TextFile::ConstIterator input_it = input.begin();
// reset map
consensus_map = ConsensusMap();
consensus_map.setUniqueId();
char separator = ' ';
if (input_it->hasSubstring("\t"))
separator = '\t';
else if (input_it->hasSubstring(" "))
separator = ' ';
else if (input_it->hasSubstring(","))
separator = ',';
// parsing header line
std::vector<String> headers;
input_it->split(separator, headers);
int offset = 0;
for (Size i = 0; i < headers.size(); ++i)
{
headers[i].trim();
}
String header_trimmed = *input.begin();
header_trimmed.trim();
enum
{
TYPE_UNDEFINED,
TYPE_OLD_NOCHARGE,
TYPE_OLD_CHARGE,
TYPE_CONSENSUS
}
input_type = TYPE_UNDEFINED;
Size input_features = 1;
double rt = 0.0;
double mz = 0.0;
double it = 0.0;
Int ch = 0;
if (headers.size() <= 2)
{
throw Exception::ParseError(__FILE__, __LINE__, __PRETTY_FUNCTION__, "", String("Failed parsing in line 1: not enough columns! Expected at least 3 columns!\nOffending line: '") + header_trimmed + "' (line 1)\n");
}
else if (headers.size() == 3)
input_type = TYPE_OLD_NOCHARGE;
else if (headers.size() == 4)
input_type = TYPE_OLD_CHARGE;
// see if we have a header
try
{
// try to convert... if not: thats a header
rt = headers[0].toDouble();
mz = headers[1].toDouble();
it = headers[2].toDouble();
}
catch (Exception::BaseException&)
{
offset = 1;
++input_it;
LOG_INFO << "Detected a header line.\n";
}
if (headers.size() >= 5)
{
if (String(headers[4].trim()).toUpper() == "RT1")
input_type = TYPE_CONSENSUS;
else
input_type = TYPE_OLD_CHARGE;
}
if (input_type == TYPE_CONSENSUS)
{
// Every consensus style line includes features with four columns.
// The remainder is meta data
input_features = headers.size() / 4;
}
if (offset == 0 && (input_type == TYPE_OLD_CHARGE || input_type == TYPE_CONSENSUS))
{
throw Exception::ParseError(__FILE__, __LINE__, __PRETTY_FUNCTION__, "", String("Failed parsing in line 1: No HEADER provided. This is only allowed for three columns. You have more!\nOffending line: '") + header_trimmed + "' (line 1)\n");
}
SignedSize input_size = input.end() - input.begin();
ConsensusMap::FileDescription desc;
desc.filename = filename;
desc.size = (input_size) - offset;
consensus_map.getFileDescriptions()[0] = desc;
// parsing features
consensus_map.reserve(input_size);
for (; input_it != input.end(); ++input_it)
{
//do nothing for empty lines
String line_trimmed = *input_it;
line_trimmed.trim();
if (line_trimmed == "")
{
if ((input_it - input.begin()) < input_size - 1) LOG_WARN << "Notice: Empty line ignored (line " << ((input_it - input.begin()) + 1) << ").";
continue;
}
//split line to tokens
std::vector<String> parts;
input_it->split(separator, parts);
//abort if line does not contain enough fields
if (parts.size() < 3)
{
throw Exception::ParseError(__FILE__, __LINE__, __PRETTY_FUNCTION__, "",
String("Failed parsing in line ")
+ String((input_it - input.begin()) + 1)
+ ": At least three columns are needed! (got "
+ String(parts.size())
+ ")\nOffending line: '"
+ line_trimmed
+ "' (line "
+ String((input_it - input.begin()) + 1)
+ ")\n");
}
ConsensusFeature cf;
cf.setUniqueId();
try
{
// Convert values. Will return -1 if not available.
rt = checkedToDouble_(parts, 0);
mz = checkedToDouble_(parts, 1);
it = checkedToDouble_(parts, 2);
ch = checkedToInt_(parts, 3);
cf.setRT(rt);
cf.setMZ(mz);
cf.setIntensity(it);
if (input_type != TYPE_OLD_NOCHARGE)
cf.setCharge(ch);
}
catch (Exception::BaseException&)
{
throw Exception::ParseError(__FILE__, __LINE__, __PRETTY_FUNCTION__, "", String("Failed parsing in line ") + String((input_it - input.begin()) + 1) + ": Could not convert the first three columns to a number!\nOffending line: '" + line_trimmed + "' (line " + String((input_it - input.begin()) + 1) + ")\n");
}
// Check all features in one line
for (Size j = 1; j < input_features; ++j)
{
try
{
Feature f;
f.setUniqueId();
// Convert values. Will return -1 if not available.
rt = checkedToDouble_(parts, j * 4 + 0);
mz = checkedToDouble_(parts, j * 4 + 1);
it = checkedToDouble_(parts, j * 4 + 2);
ch = checkedToInt_(parts, j * 4 + 3);
// Only accept features with at least RT and MZ set
if (rt != -1 && mz != -1)
{
f.setRT(rt);
f.setMZ(mz);
f.setIntensity(it);
f.setCharge(ch);
cf.insert(j - 1, f);
}
}
catch (Exception::BaseException&)
{
throw Exception::ParseError(__FILE__, __LINE__, __PRETTY_FUNCTION__, "", String("Failed parsing in line ") + String((input_it - input.begin()) + 1) + ": Could not convert one of the four sub-feature columns (starting at column " + (j * 4 + 1) + ") to a number! Is the correct separator specified?\nOffending line: '" + line_trimmed + "' (line " + String((input_it - input.begin()) + 1) + ")\n");
}
}
//parse meta data
for (Size j = input_features * 4; j < parts.size(); ++j)
{
String part_trimmed = parts[j];
part_trimmed.trim();
if (part_trimmed != "")
{
//check if column name is ok
if (headers.size() <= j || headers[j] == "")
{
throw Exception::ParseError(__FILE__, __LINE__, __PRETTY_FUNCTION__, "",
String("Error: Missing meta data header for column ") + (j + 1) + "!"
+ String("Offending header line: '") + header_trimmed + "' (line 1)");
}
//add meta value
cf.setMetaValue(headers[j], part_trimmed);
}
}
//insert feature to map
consensus_map.push_back(cf);
}
// register FileDescriptions
ConsensusMap::FileDescription fd;
fd.filename = filename;
fd.size = consensus_map.size();
Size maps = std::max(input_features - 1, Size(1)); // its either a simple feature or a consensus map
// (in this case the 'input_features' includes the centroid, which we do not count)
for (Size i = 0; i < maps; ++i)
{
fd.label = String("EDTA_Map ") + String(i);
consensus_map.getFileDescriptions()[i] = fd;
}
}
START_SECTION((void load(const String &filename, ConsensusMap & map)))
ConsensusMap map;
ConsensusXMLFile file;
file.load(OPENMS_GET_TEST_DATA_PATH("ConsensusXMLFile_1.consensusXML"), map);
//test DocumentIdentifier addition
TEST_STRING_EQUAL(map.getLoadedFilePath(), OPENMS_GET_TEST_DATA_PATH("ConsensusXMLFile_1.consensusXML"));
TEST_STRING_EQUAL(FileTypes::typeToName(map.getLoadedFileType()), "consensusXML");
//meta data
TEST_EQUAL(map.getIdentifier(), "lsid")
TEST_EQUAL(map.getExperimentType() == "label-free", true)
TEST_EQUAL(map.getMetaValue("name1") == DataValue("value1"), true)
TEST_EQUAL(map.getMetaValue("name2") == DataValue(2), true)
//file descriptions
TEST_EQUAL(map.getFileDescriptions()[0].filename == "data/MapAlignmentFeatureMap1.xml", true)
TEST_EQUAL(map.getFileDescriptions()[0].label, "label")
TEST_EQUAL(map.getFileDescriptions()[0].size, 144)
TEST_EQUAL(map.getFileDescriptions()[0].getMetaValue("name3") == DataValue("value3"), true)
TEST_EQUAL(map.getFileDescriptions()[0].getMetaValue("name4") == DataValue(4), true)
TEST_STRING_EQUAL(map.getFileDescriptions()[1].filename, "data/MapAlignmentFeatureMap2.xml")
TEST_EQUAL(map.getFileDescriptions()[1].label, "")
TEST_EQUAL(map.getFileDescriptions()[1].size, 0)
TEST_EQUAL(map.getFileDescriptions()[1].getMetaValue("name5") == DataValue("value5"), true)
TEST_EQUAL(map.getFileDescriptions()[1].getMetaValue("name6") == DataValue(6.0), true)
//data processing
TEST_EQUAL(map.getDataProcessing().size(), 2)
TEST_STRING_EQUAL(map.getDataProcessing()[0].getSoftware().getName(), "Software1")
TEST_STRING_EQUAL(map.getDataProcessing()[0].getSoftware().getVersion(), "0.91a")
TEST_EQUAL(map.getDataProcessing()[0].getProcessingActions().size(), 1)
TEST_EQUAL(map.getDataProcessing()[0].getProcessingActions().count(DataProcessing::DEISOTOPING), 1)
FGA* nullPointer = 0;
START_SECTION((FeatureGroupingAlgorithm()))
ptr = new FGA();
TEST_NOT_EQUAL(ptr, nullPointer)
END_SECTION
START_SECTION((virtual ~FeatureGroupingAlgorithm()))
delete ptr;
END_SECTION
START_SECTION((virtual void group(const vector< FeatureMap > &maps, ConsensusMap &out)=0))
FGA fga;
vector< FeatureMap > in;
ConsensusMap map;
fga.group(in,map);
TEST_EQUAL(map.getFileDescriptions()[0].filename, "bla")
END_SECTION
START_SECTION((static void registerChildren()))
{
TEST_STRING_EQUAL(Factory<FeatureGroupingAlgorithm>::registeredProducts()[0],FeatureGroupingAlgorithmLabeled::getProductName());
TEST_STRING_EQUAL(Factory<FeatureGroupingAlgorithm>::registeredProducts()[1],FeatureGroupingAlgorithmUnlabeled::getProductName());
TEST_EQUAL(Factory<FeatureGroupingAlgorithm>::registeredProducts().size(), 3)
}
END_SECTION
START_SECTION((void transferSubelements(const vector<ConsensusMap>& maps, ConsensusMap& out) const))
{
vector<ConsensusMap> maps(2);
maps[0].getFileDescriptions()[0].filename = "file1";
maps[0].getFileDescriptions()[0].size = 1;
void group(const vector< FeatureMap >&, ConsensusMap& map)
{
map.getFileDescriptions()[0].filename = "bla";
map.getFileDescriptions()[0].size = 5;
}
void ProteinInference::infer_(ConsensusMap & consensus_map,
const size_t protein_idenfication_index,
const UInt reference_map)
{
ProteinIdentification & protein_ident = consensus_map.getProteinIdentifications()[protein_idenfication_index];
for (size_t i = 0; i < protein_ident.getHits().size(); ++i)
{
// Protein Accession
String accession = protein_ident.getHits()[i].getAccession();
// consensus feature -> peptide hit
Map<size_t, PeptideHit> consensus_to_peptide;
// search for it in consensus elements:
for (size_t i_cm = 0; i_cm < consensus_map.size(); ++i_cm)
{
std::vector<PeptideHit> peptide_hits;
for (std::vector<PeptideIdentification>::iterator it_pepid = consensus_map[i_cm].getPeptideIdentifications().begin();
it_pepid != consensus_map[i_cm].getPeptideIdentifications().end();
++it_pepid)
{
// are Protein- and PeptideIdentification from the same search engine run?
if (it_pepid->getIdentifier() != protein_ident.getIdentifier())
continue;
std::vector<PeptideHit> peptide_hits_local;
it_pepid->getReferencingHits(accession, peptide_hits_local);
if (peptide_hits_local.empty())
continue;
if (sortByUnique_(peptide_hits_local, it_pepid->isHigherScoreBetter())) // we found a unique peptide
{
peptide_hits.push_back(peptide_hits_local[0]);
}
}
// if several PeptideIdentifications (==Spectra) were assigned to current ConsensusElement
// --> take the best (as above), e.g. in SILAC this could happen
// TODO: better idea?
if (!peptide_hits.empty())
{
if (sortByUnique_(peptide_hits, consensus_map[i_cm].getPeptideIdentifications()[0].isHigherScoreBetter())) //found a unique peptide for current ConsensusElement
{
consensus_to_peptide[i_cm] = peptide_hits[0];
#ifdef DEBUG_INFERENCE
std::cout << "assign peptide " << peptide_hits[0].getSequence() << " to Protein " << accession << std::endl;
#endif
}
}
} // ! ConsensusMap loop
// no peptides found that match current Protein
if (consensus_to_peptide.empty())
continue;
// Use all matching ConsensusElements to derive a quantitation for current protein
// build up ratios for every map vs reference
double coverage = 0;
Map<Size, std::vector<IntensityType> > ratios;
// number of unique peptides pointing to current protein
UInt coverage_count = (UInt)consensus_to_peptide.size();
for (Map<size_t, PeptideHit>::iterator it_pephits = consensus_to_peptide.begin();
it_pephits != consensus_to_peptide.end();
++it_pephits)
{
coverage += it_pephits->second.getSequence().size();
const ConsensusFeature::HandleSetType & handles = consensus_map[it_pephits->first].getFeatures();
//search if reference is present
ConsensusFeature::HandleSetType::const_iterator it_ref = handles.end();
for (ConsensusFeature::HandleSetType::const_iterator it = handles.begin();
it != handles.end();
++it)
{
if (it->getMapIndex() == reference_map)
{
it_ref = it;
break;
}
}
// did not find a reference
// TODO assume intensity==0 instead??
if (it_ref == handles.end())
continue;
for (ConsensusFeature::HandleSetType::const_iterator it = handles.begin();
it != handles.end();
++it)
{
ratios[it->getMapIndex()].push_back(it->getIntensity() / it_ref->getIntensity());
}
}
// sort ratios map-wise and take median
for (ConsensusMap::FileDescriptions::const_iterator it_file = consensus_map.getFileDescriptions().begin();
it_file != consensus_map.getFileDescriptions().end();
++it_file)
{
if (ratios.has(it_file->first))
{
//sort intensity ratios for map #it_file->first
std::sort(ratios[it_file->first].begin(), ratios[it_file->first].end());
//take median
IntensityType protein_ratio = ratios[it_file->first][ratios[it_file->first].size() / 2];
//TODO if ratios have high variance emit a warning!
protein_ident.getHits()[i].setMetaValue(String("ratio_") + String(it_file->first), protein_ratio);
}
} // ! map loop
// % coverage of protein by peptides
coverage /= DoubleReal(protein_ident.getHits()[i].getSequence().size()) / 100;
protein_ident.getHits()[i].setMetaValue("coverage", coverage);
protein_ident.getHits()[i].setMetaValue("hits", coverage_count);
} // ! Protein loop
// protein_to_peptides now contains the Protein -> Peptides mapping
// lets estimate the
}
void FeatureGroupingAlgorithmUnlabeled::group(const std::vector<FeatureMap> & maps, ConsensusMap & out)
{
// check that the number of maps is ok
if (maps.size() < 2)
{
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__, "At least two maps must be given!");
}
// define reference map (the one with most peaks)
Size reference_map_index = 0;
Size max_count = 0;
for (Size m = 0; m < maps.size(); ++m)
{
if (maps[m].size() > max_count)
{
max_count = maps[m].size();
reference_map_index = m;
}
}
std::vector<ConsensusMap> input(2);
// build a consensus map of the elements of the reference map (contains only singleton consensus elements)
MapConversion::convert(reference_map_index, maps[reference_map_index],
input[0]);
// loop over all other maps, extend the groups
StablePairFinder pair_finder;
pair_finder.setParameters(param_.copy("", true));
for (Size i = 0; i < maps.size(); ++i)
{
if (i != reference_map_index)
{
MapConversion::convert(i, maps[i], input[1]);
// compute the consensus of the reference map and map i
ConsensusMap result;
pair_finder.run(input, result);
input[0].swap(result);
}
}
// replace result with temporary map
out.swap(input[0]);
// copy back the input maps (they have been deleted while swapping)
out.getFileDescriptions() = input[0].getFileDescriptions();
// add protein IDs and unassigned peptide IDs to the result map here,
// to keep the same order as the input maps (useful for output later)
for (std::vector<FeatureMap>::const_iterator map_it = maps.begin();
map_it != maps.end(); ++map_it)
{
// add protein identifications to result map
out.getProteinIdentifications().insert(
out.getProteinIdentifications().end(),
map_it->getProteinIdentifications().begin(),
map_it->getProteinIdentifications().end());
// add unassigned peptide identifications to result map
out.getUnassignedPeptideIdentifications().insert(
out.getUnassignedPeptideIdentifications().end(),
map_it->getUnassignedPeptideIdentifications().begin(),
map_it->getUnassignedPeptideIdentifications().end());
}
// canonical ordering for checking the results, and the ids have no real meaning anyway
#if 1 // the way this was done in DelaunayPairFinder and StablePairFinder
out.sortByMZ();
#else
out.sortByQuality();
out.sortByMaps();
out.sortBySize();
#endif
return;
}
ExitCodes main_(int, const char **)
{
String in = getStringOption_("in");
StringList out = getStringList_("out");
SeedListGenerator seed_gen;
// results (actually just one result, except for consensusXML input):
Map<UInt64, SeedListGenerator::SeedList> seed_lists;
Size num_maps = 0;
FileTypes::Type in_type = FileHandler::getType(in);
if (in_type == FileTypes::CONSENSUSXML)
{
ConsensusMap consensus;
ConsensusXMLFile().load(in, consensus);
num_maps = consensus.getFileDescriptions().size();
if (out.size() != num_maps)
{
writeLog_("Error: expected " + String(num_maps) +
" output filenames");
return ILLEGAL_PARAMETERS;
}
seed_gen.generateSeedLists(consensus, seed_lists);
}
else if (out.size() > 1)
{
writeLog_("Error: expected only one output filename");
return ILLEGAL_PARAMETERS;
}
else if (in_type == FileTypes::MZML)
{
MSExperiment<> experiment;
MzMLFile().load(in, experiment);
seed_gen.generateSeedList(experiment, seed_lists[0]);
}
else if (in_type == FileTypes::IDXML)
{
vector<ProteinIdentification> proteins;
vector<PeptideIdentification> peptides;
IdXMLFile().load(in, proteins, peptides);
seed_gen.generateSeedList(peptides, seed_lists[0],
getFlag_("use_peptide_mass"));
}
else if (in_type == FileTypes::FEATUREXML)
{
FeatureMap features;
FeatureXMLFile().load(in, features);
seed_gen.generateSeedList(
features.getUnassignedPeptideIdentifications(), seed_lists[0]);
}
// output:
num_maps = 0;
for (Map<UInt64, SeedListGenerator::SeedList>::Iterator it =
seed_lists.begin(); it != seed_lists.end(); ++it, ++num_maps)
{
FeatureMap features;
seed_gen.convertSeedList(it->second, features);
//annotate output with data processing info:
addDataProcessing_(features, getProcessingInfo_(
DataProcessing::DATA_PROCESSING));
FeatureXMLFile().store(out[num_maps], features);
}
return EXECUTION_OK;
}
