// If the score_type has a different name in the meta_values, it is not possible to find it.
// E.g. Percolator_qvalue <-> q-value.
// Improvement for the future would be to have unique names for the score_types
// LuciphorAdapter uses the same stragety to backup previous scores.
void addScoreToMetaValues_(PeptideHit& hit, const String score_type)
{
if (!hit.metaValueExists(score_type) && !hit.metaValueExists(score_type + "_score"))
{
if (score_type.hasSubstring("score"))
{
hit.setMetaValue(score_type, hit.getScore());
}
else
{
hit.setMetaValue(score_type + "_score", hit.getScore());
}
}
}
double get_score_(String& engine, const PeptideHit& hit)
{
if (engine == "OMSSA")
{
return (-1) * log10(max(hit.getScore(), smallest_e_value_));
}
else if (engine == "MyriMatch")
{
//double e_val = exp(-hit.getScore());
//double score_val = ((-1)* log10(max(e_val,smallest_e_value_)));
//printf("myri score: %e ; e_val: %e ; score_val: %e\n",hit.getScore(),e_val,score_val);
//return score_val;
return hit.getScore();
}
else if (engine.compare("XTandem") == 0)
{
return (-1) * log10(max((DoubleReal)hit.getMetaValue("E-Value"), smallest_e_value_));
}
else if (engine == "MASCOT")
{
if (hit.metaValueExists("EValue"))
{
return (-1) * log10(max((DoubleReal)hit.getMetaValue("EValue"), smallest_e_value_));
}
if (hit.metaValueExists("expect"))
{
return (-1) * log10(max((DoubleReal)hit.getMetaValue("expect"), smallest_e_value_));
}
}
else if (engine == "SpectraST")
{
return 100 * hit.getScore(); // SpectraST f-val
}
else if (engine == "SimTandem")
{
if (hit.metaValueExists("E-Value"))
{
return (-1) * log10(max((DoubleReal)hit.getMetaValue("E-Value"), smallest_e_value_));
}
}
else
{
throw Exception::UnableToFit(__FILE__, __LINE__, __PRETTY_FUNCTION__, "No parameters for chosen search engine", "The chosen search engine is currently not supported");
}
// avoid compiler warning (every code path must return a value, even if there is a throw() somewhere)
return std::numeric_limits<double>::max();
}
//Visualizing PeptideHit object
void MetaDataBrowser::visualize_(PeptideHit & meta, QTreeWidgetItem * parent)
{
PeptideHitVisualizer * visualizer = new PeptideHitVisualizer(isEditable(), this);
visualizer->load(meta);
String name = String("Pep ") + meta.getSequence().toString() + " (" + meta.getScore() + ')';
QString qs_name(name.c_str());
QStringList labels;
labels << qs_name << QString::number(ws_->addWidget(visualizer)) << QString::number(meta.getScore());
QTreeWidgetItem * item;
if (parent == nullptr)
{
item = new QTreeWidgetItem(treeview_, labels);
}
else
{
item = new QTreeWidgetItem(parent, labels);
}
visualize_(dynamic_cast<MetaInfoInterface &>(meta), item);
connectVisualizer_(visualizer);
}
void ConsensusIDAlgorithm::apply(vector<PeptideIdentification>& ids,
Size number_of_runs)
{
// abort if no IDs present
if (ids.empty())
{
return;
}
number_of_runs_ = (number_of_runs != 0) ? number_of_runs : ids.size();
// prepare data here, so that it doesn't have to happen in each algorithm:
for (vector<PeptideIdentification>::iterator pep_it = ids.begin();
pep_it != ids.end(); ++pep_it)
{
pep_it->sort();
if ((considered_hits_ > 0) &&
(pep_it->getHits().size() > considered_hits_))
{
pep_it->getHits().resize(considered_hits_);
}
}
// make sure there are no duplicated hits (by sequence):
IDFilter::removeDuplicatePeptideHits(ids, true);
SequenceGrouping results;
apply_(ids, results); // actual (subclass-specific) processing
String score_type = ids[0].getScoreType();
bool higher_better = ids[0].isHigherScoreBetter();
ids.clear();
ids.resize(1);
ids[0].setScoreType(score_type);
ids[0].setHigherScoreBetter(higher_better);
for (SequenceGrouping::iterator res_it = results.begin();
res_it != results.end(); ++res_it)
{
OPENMS_PRECONDITION(!res_it->second.second.empty(),
"Consensus score for peptide required");
PeptideHit hit;
if (res_it->second.second.size() == 2)
{
// filter by "support" value:
double support = res_it->second.second[1];
if (support < min_support_) continue;
hit.setMetaValue("consensus_support", support);
}
hit.setSequence(res_it->first);
hit.setCharge(res_it->second.first);
hit.setScore(res_it->second.second[0]);
ids[0].insertHit(hit);
#ifdef DEBUG_ID_CONSENSUS
LOG_DEBUG << " - Output hit: " << hit.getSequence() << " "
<< hit.getScore() << endl;
#endif
}
ids[0].assignRanks();
}
ExitCodes main_(int, const char**)
{
vector<ProteinIdentification> prot_ids;
vector<PeptideIdentification> pep_ids;
ProteinHit temp_protein_hit;
//-------------------------------------------------------------
// parsing parameters
//-------------------------------------------------------------
String inputfile_id = getStringOption_("id");
String inputfile_feature = getStringOption_("feature");
String inputfile_consensus = getStringOption_("consensus");
String inputfile_raw = getStringOption_("in");
String outputfile_name = getStringOption_("out");
//~ bool Ms1(getFlag_("MS1"));
//~ bool Ms2(getFlag_("MS2"));
bool remove_duplicate_features(getFlag_("remove_duplicate_features"));
//-------------------------------------------------------------
// fetch vocabularies
//------------------------------------------------------------
ControlledVocabulary cv;
cv.loadFromOBO("PSI-MS", File::find("/CV/psi-ms.obo"));
cv.loadFromOBO("QC", File::find("/CV/qc-cv.obo"));
QcMLFile qcmlfile;
//-------------------------------------------------------------
// MS aqiusition
//------------------------------------------------------------
String base_name = QFileInfo(QString::fromStdString(inputfile_raw)).baseName();
cout << "Reading mzML file..." << endl;
MzMLFile mz_data_file;
MSExperiment<Peak1D> exp;
MzMLFile().load(inputfile_raw, exp);
//---prep input
exp.sortSpectra();
UInt min_mz = std::numeric_limits<UInt>::max();
UInt max_mz = 0;
std::map<Size, UInt> mslevelcounts;
qcmlfile.registerRun(base_name,base_name); //TODO use UIDs
//---base MS aquisition qp
String msaq_ref = base_name + "_msaq";
QcMLFile::QualityParameter qp;
qp.id = msaq_ref; ///< Identifier
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000004";
try
{
//~ const ControlledVocabulary::CVTerm& test = cv.getTermByName("MS aquisition result details");
//~ cout << test.name << test.id << endl;
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
//~ const ControlledVocabulary::CVTerm& term = cv.getTerm("0000004");
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "mzML file"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
//---file origin qp
qp = QcMLFile::QualityParameter();
qp.name = "mzML file"; ///< Name
qp.id = base_name + "_run_name"; ///< Identifier
qp.cvRef = "MS"; ///< cv reference
qp.cvAcc = "MS:1000577";
qp.value = base_name;
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.name = "instrument model"; ///< Name
qp.id = base_name + "_instrument_name"; ///< Identifier
qp.cvRef = "MS"; ///< cv reference
qp.cvAcc = "MS:1000031";
qp.value = exp.getInstrument().getName();
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.name = "completion time"; ///< Name
qp.id = base_name + "_date"; ///< Identifier
qp.cvRef = "MS"; ///< cv reference
qp.cvAcc = "MS:1000747";
qp.value = exp.getDateTime().getDate();
qcmlfile.addRunQualityParameter(base_name, qp);
//---precursors at
QcMLFile::Attachment at;
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000044";
at.qualityRef = msaq_ref;
at.id = base_name + "_precursors"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "precursors"; ///< Name
}
at.colTypes.push_back("MS:1000894_[sec]"); //RT
at.colTypes.push_back("MS:1000040"); //MZ
for (Size i = 0; i < exp.size(); ++i)
{
mslevelcounts[exp[i].getMSLevel()]++;
if (exp[i].getMSLevel() == 2)
{
if (exp[i].getPrecursors().front().getMZ() < min_mz)
{
min_mz = exp[i].getPrecursors().front().getMZ();
}
if (exp[i].getPrecursors().front().getMZ() > max_mz)
{
max_mz = exp[i].getPrecursors().front().getMZ();
}
std::vector<String> row;
row.push_back(exp[i].getRT());
row.push_back(exp[i].getPrecursors().front().getMZ());
at.tableRows.push_back(row);
}
}
qcmlfile.addRunAttachment(base_name, at);
//---aquisition results qp
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000006"; ///< cv accession for "aquisition results"
qp.id = base_name + "_ms1aquisition"; ///< Identifier
qp.value = String(mslevelcounts[1]);
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "number of ms1 spectra"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000007"; ///< cv accession for "aquisition results"
qp.id = base_name + "_ms2aquisition"; ///< Identifier
qp.value = String(mslevelcounts[2]);
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "number of ms2 spectra"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000008"; ///< cv accession for "aquisition results"
qp.id = base_name + "_Chromaquisition"; ///< Identifier
qp.value = String(exp.getChromatograms().size());
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "number of chromatograms"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000009";
at.qualityRef = msaq_ref;
at.id = base_name + "_mzrange"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "MS MZ aquisition ranges"; ///< Name
}
at.colTypes.push_back("QC:0000010"); //MZ
at.colTypes.push_back("QC:0000011"); //MZ
std::vector<String> rowmz;
rowmz.push_back(String(min_mz));
rowmz.push_back(String(max_mz));
at.tableRows.push_back(rowmz);
qcmlfile.addRunAttachment(base_name, at);
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000012";
at.qualityRef = msaq_ref;
at.id = base_name + "_rtrange"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "MS RT aquisition ranges"; ///< Name
}
at.colTypes.push_back("QC:0000013"); //MZ
at.colTypes.push_back("QC:0000014"); //MZ
std::vector<String> rowrt;
rowrt.push_back(String(exp.begin()->getRT()));
rowrt.push_back(String(exp.getSpectra().back().getRT()));
at.tableRows.push_back(rowrt);
qcmlfile.addRunAttachment(base_name, at);
//---ion current stability ( & tic ) qp
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000022";
at.qualityRef = msaq_ref;
at.id = base_name + "_tics"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "MS TICs"; ///< Name
}
at.colTypes.push_back("MS:1000894_[sec]");
at.colTypes.push_back("MS:1000285");
UInt max = 0;
Size below_10k = 0;
for (Size i = 0; i < exp.size(); ++i)
{
if (exp[i].getMSLevel() == 1)
{
UInt sum = 0;
for (Size j = 0; j < exp[i].size(); ++j)
{
sum += exp[i][j].getIntensity();
}
if (sum > max)
{
max = sum;
}
if (sum < 10000)
{
++below_10k;
}
std::vector<String> row;
row.push_back(exp[i].getRT());
row.push_back(sum);
at.tableRows.push_back(row);
}
}
qcmlfile.addRunAttachment(base_name, at);
qp = QcMLFile::QualityParameter();
qp.id = base_name + "_ticslump"; ///< Identifier
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000023";
qp.value = String((100 / exp.size()) * below_10k);
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "percentage of tic slumps"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
//-------------------------------------------------------------
// MS id
//------------------------------------------------------------
if (inputfile_id != "")
{
IdXMLFile().load(inputfile_id, prot_ids, pep_ids);
cerr << "idXML read ended. Found " << pep_ids.size() << " peptide identifications." << endl;
ProteinIdentification::SearchParameters params = prot_ids[0].getSearchParameters();
vector<String> var_mods = params.variable_modifications;
//~ boost::regex re("(?<=[KR])(?=[^P])");
String msid_ref = base_name + "_msid";
QcMLFile::QualityParameter qp;
qp.id = msid_ref; ///< Identifier
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000025";
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "MS identification result details"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000026";
at.qualityRef = msid_ref;
at.id = base_name + "_idsetting"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "MS id settings"; ///< Name
}
at.colTypes.push_back("MS:1001013"); //MS:1001013 db name MS:1001016 version MS:1001020 taxonomy
at.colTypes.push_back("MS:1001016");
at.colTypes.push_back("MS:1001020");
std::vector<String> row;
row.push_back(String(prot_ids.front().getSearchParameters().db));
row.push_back(String(prot_ids.front().getSearchParameters().db_version));
row.push_back(String(prot_ids.front().getSearchParameters().taxonomy));
at.tableRows.push_back(row);
qcmlfile.addRunAttachment(base_name, at);
UInt spectrum_count = 0;
Size peptide_hit_count = 0;
UInt runs_count = 0;
Size protein_hit_count = 0;
set<String> peptides;
set<String> proteins;
Size missedcleavages = 0;
for (Size i = 0; i < pep_ids.size(); ++i)
{
if (!pep_ids[i].empty())
{
++spectrum_count;
peptide_hit_count += pep_ids[i].getHits().size();
const vector<PeptideHit>& temp_hits = pep_ids[i].getHits();
for (Size j = 0; j < temp_hits.size(); ++j)
{
peptides.insert(temp_hits[j].getSequence().toString());
}
}
}
for (set<String>::iterator it = peptides.begin(); it != peptides.end(); ++it)
{
for (String::const_iterator st = it->begin(); st != it->end() - 1; ++st)
{
if (*st == 'K' || *st == 'R')
{
++missedcleavages;
}
}
}
for (Size i = 0; i < prot_ids.size(); ++i)
{
++runs_count;
protein_hit_count += prot_ids[i].getHits().size();
const vector<ProteinHit>& temp_hits = prot_ids[i].getHits();
for (Size j = 0; j < temp_hits.size(); ++j)
{
proteins.insert(temp_hits[j].getAccession());
}
}
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000037"; ///< cv accession
qp.id = base_name + "_misscleave"; ///< Identifier
qp.value = missedcleavages;
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of missed cleavages"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000032"; ///< cv accession
qp.id = base_name + "_totprot"; ///< Identifier
qp.value = protein_hit_count;
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of identified proteins"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000033"; ///< cv accession
qp.id = base_name + "_totuniqprot"; ///< Identifier
qp.value = String(proteins.size());
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of uniquely identified proteins"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000029"; ///< cv accession
qp.id = base_name + "_psms"; ///< Identifier
qp.value = String(spectrum_count);
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of PSM"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000030"; ///< cv accession
qp.id = base_name + "_totpeps"; ///< Identifier
qp.value = String(peptide_hit_count);
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of identified peptides"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000031"; ///< cv accession
qp.id = base_name + "_totuniqpeps"; ///< Identifier
qp.value = String(peptides.size());
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "total number of uniquely identified peptides"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000038";
at.qualityRef = msid_ref;
at.id = base_name + "_massacc"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "delta ppm tables";
}
//~ delta ppm QC:0000039 RT MZ uniqueness ProteinID MS:1000885 target/decoy Score PeptideSequence MS:1000889 Annots string Similarity Charge UO:0000219 TheoreticalWeight UO:0000221 Oxidation_(M)
at.colTypes.push_back("RT");
at.colTypes.push_back("MZ");
at.colTypes.push_back("Score");
at.colTypes.push_back("PeptideSequence");
at.colTypes.push_back("Charge");
at.colTypes.push_back("TheoreticalWeight");
at.colTypes.push_back("delta_ppm");
for (UInt w = 0; w < var_mods.size(); ++w)
{
at.colTypes.push_back(String(var_mods[w]).substitute(' ', '_'));
}
std::vector<double> deltas;
//~ prot_ids[0].getSearchParameters();
for (vector<PeptideIdentification>::iterator it = pep_ids.begin(); it != pep_ids.end(); ++it)
{
if (it->getHits().size() > 0)
{
std::vector<String> row;
row.push_back(it->getRT());
row.push_back(it->getMZ());
PeptideHit tmp = it->getHits().front(); //TODO depends on score & sort
vector<UInt> pep_mods;
for (UInt w = 0; w < var_mods.size(); ++w)
{
pep_mods.push_back(0);
}
for (AASequence::ConstIterator z = tmp.getSequence().begin(); z != tmp.getSequence().end(); ++z)
{
Residue res = *z;
String temp;
if (res.getModification().size() > 0 && res.getModification() != "Carbamidomethyl")
{
temp = res.getModification() + " (" + res.getOneLetterCode() + ")";
//cout<<res.getModification()<<endl;
for (UInt w = 0; w < var_mods.size(); ++w)
{
if (temp == var_mods[w])
{
//cout<<temp;
pep_mods[w] += 1;
}
}
}
}
row.push_back(tmp.getScore());
row.push_back(tmp.getSequence().toString().removeWhitespaces());
row.push_back(tmp.getCharge());
row.push_back(String((tmp.getSequence().getMonoWeight() + tmp.getCharge() * Constants::PROTON_MASS_U) / tmp.getCharge()));
double dppm = /* std::abs */ (getMassDifference(((tmp.getSequence().getMonoWeight() + tmp.getCharge() * Constants::PROTON_MASS_U) / tmp.getCharge()), it->getMZ(), true));
row.push_back(String(dppm));
deltas.push_back(dppm);
for (UInt w = 0; w < var_mods.size(); ++w)
{
row.push_back(pep_mods[w]);
}
at.tableRows.push_back(row);
}
}
qcmlfile.addRunAttachment(base_name, at);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000040"; ///< cv accession
qp.id = base_name + "_mean_delta"; ///< Identifier
qp.value = String(OpenMS::Math::mean(deltas.begin(), deltas.end()));
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "mean delta ppm"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000041"; ///< cv accession
qp.id = base_name + "_median_delta"; ///< Identifier
qp.value = String(OpenMS::Math::median(deltas.begin(), deltas.end(), false));
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "median delta ppm"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000035"; ///< cv accession
qp.id = base_name + "_ratio_id"; ///< Identifier
qp.value = String(double(pep_ids.size()) / double(mslevelcounts[2]));
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "id ratio"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
}
//-------------------------------------------------------------
// MS quantitation
//------------------------------------------------------------
FeatureMap map;
String msqu_ref = base_name + "_msqu";
if (inputfile_feature != "")
{
FeatureXMLFile f;
f.load(inputfile_feature, map);
cout << "Read featureXML file..." << endl;
//~ UInt fiter = 0;
map.sortByRT();
map.updateRanges();
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000045"; ///< cv accession
qp.id = msqu_ref; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "MS quantification result details"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
qp = QcMLFile::QualityParameter();
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:0000046"; ///< cv accession
qp.id = base_name + "_feature_count"; ///< Identifier
qp.value = String(map.size());
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(qp.cvAcc);
qp.name = term.name; ///< Name
}
catch (...)
{
qp.name = "number of features"; ///< Name
}
qcmlfile.addRunQualityParameter(base_name, qp);
}
if (inputfile_feature != "" && !remove_duplicate_features)
{
QcMLFile::Attachment at;
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000047";
at.qualityRef = msqu_ref;
at.id = base_name + "_features"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "features"; ///< Name
}
at.colTypes.push_back("MZ");
at.colTypes.push_back("RT");
at.colTypes.push_back("Intensity");
at.colTypes.push_back("Charge");
at.colTypes.push_back("Quality");
at.colTypes.push_back("FWHM");
at.colTypes.push_back("IDs");
UInt fiter = 0;
map.sortByRT();
//ofstream out(outputfile_name.c_str());
while (fiter < map.size())
{
std::vector<String> row;
row.push_back(map[fiter].getMZ());
row.push_back(map[fiter].getRT());
row.push_back(map[fiter].getIntensity());
row.push_back(map[fiter].getCharge());
row.push_back(map[fiter].getOverallQuality());
row.push_back(map[fiter].getWidth());
row.push_back(map[fiter].getPeptideIdentifications().size());
fiter++;
at.tableRows.push_back(row);
}
qcmlfile.addRunAttachment(base_name, at);
}
else if (inputfile_feature != "" && remove_duplicate_features)
{
QcMLFile::Attachment at;
at = QcMLFile::Attachment();
at.cvRef = "QC"; ///< cv reference
at.cvAcc = "QC:0000047";
at.qualityRef = msqu_ref;
at.id = base_name + "_features"; ///< Identifier
try
{
const ControlledVocabulary::CVTerm& term = cv.getTerm(at.cvAcc);
at.name = term.name; ///< Name
}
catch (...)
{
at.name = "features"; ///< Name
}
at.colTypes.push_back("MZ");
at.colTypes.push_back("RT");
at.colTypes.push_back("Intensity");
at.colTypes.push_back("Charge");
FeatureMap map, map_out;
FeatureXMLFile f;
f.load(inputfile_feature, map);
UInt fiter = 0;
map.sortByRT();
while (fiter < map.size())
{
FeatureMap map_tmp;
for (UInt k = fiter; k <= map.size(); ++k)
{
if (abs(map[fiter].getRT() - map[k].getRT()) < 0.1)
{
//~ cout << fiter << endl;
map_tmp.push_back(map[k]);
}
else
{
fiter = k;
break;
}
}
map_tmp.sortByMZ();
UInt retif = 1;
map_out.push_back(map_tmp[0]);
while (retif < map_tmp.size())
{
if (abs(map_tmp[retif].getMZ() - map_tmp[retif - 1].getMZ()) > 0.01)
{
cout << "equal RT, but mass different" << endl;
map_out.push_back(map_tmp[retif]);
}
retif++;
}
}
qcmlfile.addRunAttachment(base_name, at);
}
if (inputfile_consensus != "")
{
cout << "Reading consensusXML file..." << endl;
ConsensusXMLFile f;
ConsensusMap map;
f.load(inputfile_consensus, map);
//~ String CONSENSUS_NAME = "_consensus.tsv";
//~ String combined_out = outputfile_name + CONSENSUS_NAME;
//~ ofstream out(combined_out.c_str());
at = QcMLFile::Attachment();
qp.name = "consensuspoints"; ///< Name
//~ qp.id = base_name + "_consensuses"; ///< Identifier
qp.cvRef = "QC"; ///< cv reference
qp.cvAcc = "QC:xxxxxxxx"; ///< cv accession "featuremapper results"
at.colTypes.push_back("Native_spectrum_ID");
at.colTypes.push_back("DECON_RT_(sec)");
at.colTypes.push_back("DECON_MZ_(Th)");
at.colTypes.push_back("DECON_Intensity");
at.colTypes.push_back("Feature_RT_(sec)");
at.colTypes.push_back("Feature_MZ_(Th)");
at.colTypes.push_back("Feature_Intensity");
at.colTypes.push_back("Feature_Charge");
for (ConsensusMap::const_iterator cmit = map.begin(); cmit != map.end(); ++cmit)
{
const ConsensusFeature& CF = *cmit;
for (ConsensusFeature::const_iterator cfit = CF.begin(); cfit != CF.end(); ++cfit)
{
std::vector<String> row;
FeatureHandle FH = *cfit;
row.push_back(CF.getMetaValue("spectrum_native_id"));
row.push_back(CF.getRT()); row.push_back(CF.getMZ());
row.push_back(CF.getIntensity());
row.push_back(FH.getRT());
row.push_back(FH.getMZ());
row.push_back(FH.getCharge());
at.tableRows.push_back(row);
}
}
qcmlfile.addRunAttachment(base_name, at);
}
//-------------------------------------------------------------
// finalize
//------------------------------------------------------------
qcmlfile.store(outputfile_name);
return EXECUTION_OK;
}
void IDDecoyProbability::apply_(vector<PeptideIdentification> & ids, const vector<double> & rev_scores, const vector<double> & fwd_scores, const vector<double> & all_scores)
{
Size number_of_bins(param_.getValue("number_of_bins"));
// normalize distribution to [0, 1]
vector<double> fwd_scores_normalized(number_of_bins, 0.0), rev_scores_normalized(number_of_bins, 0.0), diff_scores(number_of_bins, 0.0), all_scores_normalized(number_of_bins, 0.0);
Transformation_ rev_trafo, fwd_trafo, all_trafo;
normalizeBins_(rev_scores, rev_scores_normalized, rev_trafo);
normalizeBins_(fwd_scores, fwd_scores_normalized, fwd_trafo);
normalizeBins_(all_scores, all_scores_normalized, all_trafo);
// rev scores fitting
vector<DPosition<2> > rev_data;
for (Size i = 0; i < number_of_bins; ++i)
{
DPosition<2> pos;
pos.setX(((double)i) / (double)number_of_bins + 0.0001); // necessary????
pos.setY(rev_scores_normalized[i]);
rev_data.push_back(pos);
#ifdef IDDECOYPROBABILITY_DEBUG
cerr << pos.getX() << " " << pos.getY() << endl;
#endif
}
Math::GammaDistributionFitter gdf;
Math::GammaDistributionFitter::GammaDistributionFitResult result_gamma_1st (1.0, 3.0);
gdf.setInitialParameters(result_gamma_1st);
// TODO heuristic for good start parameters
Math::GammaDistributionFitter::GammaDistributionFitResult result_gamma = gdf.fit(rev_data);
#ifdef IDDECOYPROBABILITY_DEBUG
cerr << gdf.getGnuplotFormula() << endl;
String rev_filename = param_.getValue("rev_filename");
generateDistributionImage_(rev_scores_normalized, gdf.getGnuplotFormula(), rev_filename);
#endif
// generate diffs of distributions
// get the fwd and rev distribution, apply all_trafo and calculate the diff
vector<Size> fwd_bins(number_of_bins, 0), rev_bins(number_of_bins, 0);
double min(all_trafo.min_score), diff(all_trafo.diff_score);
Size max_bin(0);
for (vector<double>::const_iterator it = fwd_scores.begin(); it != fwd_scores.end(); ++it)
{
Size bin = (Size)((*it - min) / diff * (double)(number_of_bins - 1));
++fwd_bins[bin];
if (fwd_bins[bin] > max_bin)
{
max_bin = fwd_bins[bin];
}
}
Size max_reverse_bin(0), max_reverse_bin_value(0);
//min = rev_trafo.min_score;
//diff = rev_trafo.diff_score;
for (vector<double>::const_iterator it = rev_scores.begin(); it != rev_scores.end(); ++it)
{
Size bin = (Size)((*it - min) / diff * (double)number_of_bins);
++rev_bins[bin];
if (rev_bins[bin] > max_bin)
{
max_bin = rev_bins[bin];
}
if (rev_bins[bin] > max_reverse_bin_value)
{
max_reverse_bin = bin;
max_reverse_bin_value = rev_bins[bin];
}
}
#ifdef IDDECOYPROBABILITY_DEBUG
cerr << "Trying to get diff scores" << endl;
#endif
// get diff of fwd and rev
for (Size i = 0; i < number_of_bins; ++i)
{
Size fwd(0), rev(0);
fwd = fwd_bins[i];
rev = rev_bins[i];
if ((double)fwd > (double)(1.3 * rev) && max_reverse_bin < i)
{
diff_scores[i] = (double)(fwd - rev) / (double)max_bin;
}
else
{
diff_scores[i] = 0.0;
}
}
#ifdef IDDECOYPROBABILITY_DEBUG
cerr << "Gauss Fitting values size of diff scores=" << diff_scores.size() << endl;
#endif
// diff scores fitting
vector<DPosition<2> > diff_data;
double gauss_A(0), gauss_x0(0), norm_factor(0);
for (Size i = 0; i < number_of_bins; ++i)
{
DPosition<2> pos;
pos.setX((double)i / (double)number_of_bins);
pos.setY(diff_scores[i]);
if (pos.getY() > gauss_A)
{
gauss_A = pos.getY();
}
gauss_x0 += pos.getX() * pos.getY();
norm_factor += pos.getY();
diff_data.push_back(pos);
}
double gauss_sigma(0);
gauss_x0 /= (double)diff_data.size();
gauss_x0 /= norm_factor;
for (Size i = 0; i <= number_of_bins; ++i)
{
gauss_sigma += fabs(gauss_x0 - (double)i / (double)number_of_bins);
}
gauss_sigma /= (double)diff_data.size();
#ifdef IDDECOYPROBABILITY_DEBUG
cerr << "setting initial parameters: " << endl;
#endif
Math::GaussFitter gf;
Math::GaussFitter::GaussFitResult result_1st(gauss_A, gauss_x0, gauss_sigma);
gf.setInitialParameters(result_1st);
#ifdef IDDECOYPROBABILITY_DEBUG
cerr << "Initial Gauss guess: A=" << gauss_A << ", x0=" << gauss_x0 << ", sigma=" << gauss_sigma << endl;
#endif
//TODO: fail-to-fit correction was done using the GNUPlotFormula. Seemed to be a hack.
//Changed it to try-catch-block but I am not sure if this correction should be made
//at all. Can someone please verify?
Math::GaussFitter::GaussFitResult result_gauss (gauss_A, gauss_x0, gauss_sigma);
try{
result_gauss = gf.fit(diff_data);
}
catch(Exception::UnableToFit& /* e */)
{
result_gauss.A = gauss_A;
result_gauss.x0 = gauss_x0;
result_gauss.sigma = gauss_sigma;
}
// // fit failed?
// if (gf.getGnuplotFormula() == "")
// {
// result_gauss.A = gauss_A;
// result_gauss.x0 = gauss_x0;
// result_gauss.sigma = gauss_sigma;
// }
#ifdef IDDECOYPROBABILITY_DEBUG
cerr << gf.getGnuplotFormula() << endl;
String fwd_filename = param_.getValue("fwd_filename");
if (gf.getGnuplotFormula() == "")
{
String formula("f(x)=" + String(gauss_A) + " * exp(-(x - " + String(gauss_x0) + ") ** 2 / 2 / (" + String(gauss_sigma) + ") ** 2)");
generateDistributionImage_(diff_scores, formula, fwd_filename);
}
else
{
generateDistributionImage_(diff_scores, gf.getGnuplotFormula(), fwd_filename);
}
#endif
#ifdef IDDECOYPROBABILITY_DEBUG
//all_trafo.diff_score + all_trafo.min_score
String gauss_formula("f(x)=" + String(result_gauss.A / all_trafo.max_intensity) + " * exp(-(x - " + String(result_gauss.x0 * all_trafo.diff_score + all_trafo.min_score) + ") ** 2 / 2 / (" + String(result_gauss.sigma * all_trafo.diff_score) + ") ** 2)");
String b_str(result_gamma.b), p_str(result_gamma.p);
String gamma_formula = "g(x)=(" + b_str + " ** " + p_str + ") / gamma(" + p_str + ") * x ** (" + p_str + " - 1) * exp(- " + b_str + " * x)";
generateDistributionImage_(all_scores_normalized, all_trafo, gauss_formula, gamma_formula, (String)param_.getValue("fwd_filename"));
#endif
vector<PeptideIdentification> new_prob_ids;
// calculate the probabilities and write them to the IDs
for (vector<PeptideIdentification>::const_iterator it = ids.begin(); it != ids.end(); ++it)
{
if (it->getHits().size() > 0)
{
vector<PeptideHit> hits;
String score_type = it->getScoreType() + "_score";
for (vector<PeptideHit>::const_iterator pit = it->getHits().begin(); pit != it->getHits().end(); ++pit)
{
PeptideHit hit = *pit;
double score = hit.getScore();
if (!it->isHigherScoreBetter())
{
score = -log10(score);
}
hit.setMetaValue(score_type, hit.getScore());
hit.setScore(getProbability_(result_gamma, rev_trafo, result_gauss, fwd_trafo, score));
hits.push_back(hit);
}
PeptideIdentification id = *it;
id.setHigherScoreBetter(true);
id.setScoreType(id.getScoreType() + "_DecoyProbability");
id.setHits(hits);
new_prob_ids.push_back(id);
}
}
ids = new_prob_ids;
}
double getScore_(String& engine, const PeptideHit& hit)
{
if (engine == "OMSSA")
{
return (-1) * log10(max(hit.getScore(), smallest_e_value_));
}
else if (engine == "MyriMatch")
{
//double e_val = exp(-hit.getScore());
//double score_val = ((-1)* log10(max(e_val,smallest_e_value_)));
//printf("myri score: %e ; e_val: %e ; score_val: %e\n",hit.getScore(),e_val,score_val);
//return score_val;
return hit.getScore();
}
else if (engine.compare("XTandem") == 0)
{
return (-1) * log10(max((double)hit.getMetaValue("E-Value"), smallest_e_value_));
}
else if (engine == "MASCOT")
{
// issue #740: unable to fit data with score 0
if (hit.getScore() == 0.0)
{
return numeric_limits<double>::quiet_NaN();
}
// end issue #740
if (hit.metaValueExists("EValue"))
{
return (-1) * log10(max((double)hit.getMetaValue("EValue"), smallest_e_value_));
}
if (hit.metaValueExists("expect"))
{
return (-1) * log10(max((double)hit.getMetaValue("expect"), smallest_e_value_));
}
}
else if (engine == "SpectraST")
{
return 100 * hit.getScore(); // SpectraST f-val
}
else if (engine == "SimTandem")
{
if (hit.metaValueExists("E-Value"))
{
return (-1) * log10(max((double)hit.getMetaValue("E-Value"), smallest_e_value_));
}
}
else if ((engine == "MSGFPlus") || (engine == "MS-GF+"))
{
if (hit.metaValueExists("MS:1002053")) // name: MS-GF:EValue
{
return (-1) * log10(max((double)hit.getMetaValue("MS:1002053"), smallest_e_value_));
}
else if (hit.metaValueExists("expect"))
{
return (-1) * log10(max((double)hit.getMetaValue("expect"), smallest_e_value_));
}
}
else if (engine == "Comet")
{
if (hit.metaValueExists("MS:1002257")) // name: Comet:expectation value
{
return (-1) * log10(max((double)hit.getMetaValue("MS:1002257"), smallest_e_value_));
}
else if (hit.metaValueExists("expect"))
{
return (-1) * log10(max((double)hit.getMetaValue("expect"), smallest_e_value_));
}
}
else
{
throw Exception::UnableToFit(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION, "No parameters for chosen search engine", "The chosen search engine is currently not supported");
}
// avoid compiler warning (every code path must return a value, even if there is a throw() somewhere)
return std::numeric_limits<double>::max();
}
String describeHit_(const PeptideHit& hit)
{
return "peptide hit with sequence '" + hit.getSequence().toString() +
"', charge " + String(hit.getCharge()) + ", score " +
String(hit.getScore());
}
ExitCodes main_(int, const char **)
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
//input/output files
StringList in(getStringList_("in"));
StringList id_in(getStringList_("id_in"));
String trained_model_file(getStringOption_("trained_model_file"));
String model_file(getStringOption_("model_file"));
bool score_filtering(getFlag_("score_filtering"));
double score_threshold(getDoubleOption_("score_threshold"));
Int min_charge(getIntOption_("min_charge"));
Int max_charge(getIntOption_("max_charge"));
if (in.empty())
{
writeLog_("For 'training' mode spectra and identifications are needed.");
return INCOMPATIBLE_INPUT_DATA;
}
//bool duplicates_by_tic(getFlag_("duplicates_by_tic"));
//bool base_model_from_file(getFlag_("base_model_from_file"));
// create model, either read from a model file, or initialize with default parameters
PILISModel model;
if (model_file != "")
{
writeDebug_("Reading model from file '" + model_file + "'", 1);
model.readFromFile(model_file);
}
else
{
writeDebug_("Initializing model", 1);
model.setParameters(getParam_().copy("PILIS_parameters:", true));
model.init();
}
Param pilis_param(model.getParameters());
ModificationDefinitionsSet mod_set(pilis_param.getValue("fixed_modifications"), pilis_param.getValue("variable_modifications"));
// read spectra file (if available)
vector<RichPeakMap> exp;
vector<vector<ProteinIdentification> > prot_ids;
vector<vector<PeptideIdentification> > pep_ids;
if (!in.empty())
{
FileTypes::Type in_file_type = FileHandler().getType(in[0]);
writeDebug_("File type of parameter 'in' estimated as '" + FileTypes::typeToName(in_file_type) + "'", 1);
// TODO check all types
if (in_file_type == FileTypes::MSP)
{
writeDebug_("Reading MSP file", 1);
MSPFile f;
exp.resize(in.size());
pep_ids.resize(in.size());
for (Size i = 0; i != in.size(); ++i)
{
f.load(in[i], pep_ids[i], exp[i]);
for (Size j = 0; j != exp[i].size(); ++j)
{
exp[i][j].getPeptideIdentifications().push_back(pep_ids[i][j]);
}
}
}
if (in_file_type == FileTypes::MZML)
{
MzMLFile f;
f.setLogType(log_type_);
exp.resize(in.size());
for (Size i = 0; i != in.size(); ++i)
{
f.load(in[i], exp[i]);
}
}
}
if (!id_in.empty())
{
prot_ids.resize(id_in.size());
pep_ids.resize(id_in.size());
IdXMLFile f;
for (Size i = 0; i != id_in.size(); ++i)
{
f.load(id_in[i], prot_ids[i], pep_ids[i]);
}
}
if (!id_in.empty() && !in.empty())
{
// map the
if (id_in.size() != in.size())
{
writeLog_("If in parameter contains mzML files and id_in contains idXML files, the number should be equal to allow mapping of the identification to the spectra");
return INCOMPATIBLE_INPUT_DATA;
}
// map the ids to the spectra
IDMapper id_mapper;
for (Size i = 0; i != exp.size(); ++i)
{
id_mapper.annotate(exp[i], pep_ids[i], prot_ids[i]);
}
}
// get the peptides and spectra
vector<PILISCrossValidation::Peptide> peptides;
for (vector<RichPeakMap>::const_iterator it1 = exp.begin(); it1 != exp.end(); ++it1)
{
for (RichPeakMap::ConstIterator it2 = it1->begin(); it2 != it1->end(); ++it2)
{
if (it2->getPeptideIdentifications().empty())
{
continue;
}
PeptideHit hit;
if (it2->getPeptideIdentifications().begin()->getHits().size() > 0)
{
hit = *it2->getPeptideIdentifications().begin()->getHits().begin();
}
else
{
continue;
}
// check whether the sequence contains a modification not modelled
if (!mod_set.isCompatible(hit.getSequence()) || hit.getSequence().size() > (UInt)pilis_param.getValue("visible_model_depth"))
{
continue;
}
if (score_filtering &&
((hit.getScore() < score_threshold && it2->getPeptideIdentifications().begin()->isHigherScoreBetter()) ||
(hit.getScore() > score_threshold && !it2->getPeptideIdentifications().begin()->isHigherScoreBetter())))
{
continue;
}
PILISCrossValidation::Peptide pep_struct;
pep_struct.sequence = hit.getSequence();
pep_struct.charge = hit.getCharge();
pep_struct.spec = *it2;
pep_struct.hits = it2->getPeptideIdentifications().begin()->getHits();
// check charges
if (pep_struct.charge < min_charge || pep_struct.charge > max_charge)
{
continue;
}
peptides.push_back(pep_struct);
}
}
getUniquePeptides(peptides);
writeDebug_("Number of (unique) peptides for training: " + String(peptides.size()), 1);
//model.writeToFile("pilis_tmp.dat");
model.setParameters(pilis_param);
for (vector<PILISCrossValidation::Peptide>::const_iterator it = peptides.begin(); it != peptides.end(); ++it)
{
model.train(it->spec, it->sequence, it->charge);
}
model.evaluate();
if (trained_model_file != "")
{
model.writeToFile(trained_model_file);
}
return EXECUTION_OK;
}
