//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);
}
std::vector<PeptideIdentification> toPepVec(const QStringList& sl_pep)
{
std::vector<PeptideIdentification> pep_vec;
for (Size i = 0; i < sl_pep.size(); ++i)
{
PeptideHit hit;
hit.setSequence(AASequence::fromString(sl_pep[int(i)]));
std::vector<PeptideHit> hits;
hits.push_back(hit);
PeptideIdentification pi;
pi.setHits(hits);
pep_vec.push_back(pi);
}
return pep_vec;
}
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();
}
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();
}
// 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());
}
}
}
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 CompNovoIdentificationCID::getIdentification(PeptideIdentification & id, const PeakSpectrum & CID_spec)
{
//if (CID_spec.getPrecursors().begin()->getMZ() > 1000.0)
//{
//cerr << "Weight of precursor has been estimated to exceed 2000.0 Da which is the current limit" << endl;
//return;
//}
PeakSpectrum new_CID_spec(CID_spec);
windowMower_(new_CID_spec, 0.3, 1);
Param zhang_param;
zhang_param = zhang_.getParameters();
zhang_param.setValue("tolerance", fragment_mass_tolerance_);
zhang_param.setValue("use_gaussian_factor", "true");
zhang_param.setValue("use_linear_factor", "false");
zhang_.setParameters(zhang_param);
Normalizer normalizer;
Param n_param(normalizer.getParameters());
n_param.setValue("method", "to_one");
normalizer.setParameters(n_param);
normalizer.filterSpectrum(new_CID_spec);
Size charge(2);
double precursor_weight(0); // [M+H]+
if (!CID_spec.getPrecursors().empty())
{
// believe charge of spectrum?
if (CID_spec.getPrecursors().begin()->getCharge() != 0)
{
charge = CID_spec.getPrecursors().begin()->getCharge();
}
else
{
// TODO estimate charge state
}
precursor_weight = CID_spec.getPrecursors().begin()->getMZ() * charge - ((charge - 1) * Constants::PROTON_MASS_U);
}
//cerr << "charge=" << charge << ", [M+H]=" << precursor_weight << endl;
// now delete all peaks that are right of the estimated precursor weight
Size peak_counter(0);
for (PeakSpectrum::ConstIterator it = new_CID_spec.begin(); it != new_CID_spec.end(); ++it, ++peak_counter)
{
if (it->getPosition()[0] > precursor_weight)
{
break;
}
}
if (peak_counter < new_CID_spec.size())
{
new_CID_spec.resize(peak_counter);
}
static double oxonium_mass = EmpiricalFormula("H2O+").getMonoWeight();
Peak1D p;
p.setIntensity(1);
p.setPosition(oxonium_mass);
new_CID_spec.push_back(p);
p.setPosition(precursor_weight);
new_CID_spec.push_back(p);
// add complement to spectrum
/*
for (PeakSpectrum::ConstIterator it1 = CID_spec.begin(); it1 != CID_spec.end(); ++it1)
{
// get m/z of complement
double mz_comp = precursor_weight - it1->getPosition()[0] + Constants::PROTON_MASS_U;
// search if peaks are available that have similar m/z values
Size count(0);
bool found(false);
for (PeakSpectrum::ConstIterator it2 = CID_spec.begin(); it2 != CID_spec.end(); ++it2, ++count)
{
if (fabs(mz_comp - it2->getPosition()[0]) < fragment_mass_tolerance)
{
// add peak intensity to corresponding peak in new_CID_spec
new_CID_spec[count].setIntensity(new_CID_spec[count].getIntensity());
}
}
if (!found)
{
// infer this peak
Peak1D p;
p.setIntensity(it1->getIntensity());
p.setPosition(mz_comp);
new_CID_spec.push_back(p);
}
}*/
CompNovoIonScoringCID ion_scoring;
Param ion_scoring_param(ion_scoring.getParameters());
ion_scoring_param.setValue("fragment_mass_tolerance", fragment_mass_tolerance_);
ion_scoring_param.setValue("precursor_mass_tolerance", precursor_mass_tolerance_);
ion_scoring_param.setValue("decomp_weights_precision", decomp_weights_precision_);
ion_scoring_param.setValue("double_charged_iso_threshold", (double)param_.getValue("double_charged_iso_threshold"));
ion_scoring_param.setValue("max_isotope_to_score", param_.getValue("max_isotope_to_score"));
ion_scoring_param.setValue("max_isotope", max_isotope_);
ion_scoring.setParameters(ion_scoring_param);
Map<double, IonScore> ion_scores;
ion_scoring.scoreSpectrum(ion_scores, new_CID_spec, precursor_weight, charge);
new_CID_spec.sortByPosition();
/*
cerr << "Size of ion_scores " << ion_scores.size() << endl;
for (Map<double, IonScore>::const_iterator it = ion_scores.begin(); it != ion_scores.end(); ++it)
{
cerr << it->first << " " << it->second.score << endl;
}*/
#ifdef WRITE_SCORED_SPEC
PeakSpectrum filtered_spec(new_CID_spec);
filtered_spec.clear();
for (Map<double, CompNovoIonScoringCID::IonScore>::const_iterator it = ion_scores.begin(); it != ion_scores.end(); ++it)
{
Peak1D p;
p.setIntensity(it->second.score);
p.setPosition(it->first);
filtered_spec.push_back(p);
}
DTAFile().store("spec_scored.dta", filtered_spec);
#endif
set<String> sequences;
getDecompositionsDAC_(sequences, 0, new_CID_spec.size() - 1, precursor_weight, new_CID_spec, ion_scores);
#ifdef SPIKE_IN
sequences.insert("AFCVDGEGR");
sequences.insert("APEFAAPWPDFVPR");
sequences.insert("AVKQFEESQGR");
sequences.insert("CCTESLVNR");
sequences.insert("DAFLGSFLYEYSR");
sequences.insert("DAIPENLPPLTADFAEDK");
sequences.insert("DDNKVEDIWSFLSK");
sequences.insert("DDPHACYSTVFDK");
sequences.insert("DEYELLCLDGSR");
sequences.insert("DGAESYKELSVLLPNR");
sequences.insert("DGASCWCVDADGR");
sequences.insert("DLFIPTCLETGEFAR");
sequences.insert("DTHKSEIAHR");
sequences.insert("DVCKNYQEAK");
sequences.insert("EACFAVEGPK");
sequences.insert("ECCHGDLLECADDR");
sequences.insert("EFLGDKFYTVISSLK");
sequences.insert("EFTPVLQADFQK");
sequences.insert("ELFLDSGIFQPMLQGR");
sequences.insert("ETYGDMADCCEK");
sequences.insert("EVGCPSSSVQEMVSCLR");
sequences.insert("EYEATLEECCAK");
sequences.insert("FADLIQSGTFQLHLDSK");
sequences.insert("FFSASCVPGATIEQK");
sequences.insert("FLANVSTVLTSK");
sequences.insert("FLSGSDYAIR");
sequences.insert("FTASCPPSIK");
sequences.insert("GAIEWEGIESGSVEQAVAK");
sequences.insert("GDVAFIQHSTVEENTGGK");
sequences.insert("GEPPSCAEDQSCPSER");
sequences.insert("GEYVPTSLTAR");
sequences.insert("GQEFTITGQKR");
sequences.insert("GTFAALSELHCDK");
sequences.insert("HLVDEPQNLIK");
sequences.insert("HQDCLVTTLQTQPGAVR");
sequences.insert("HTTVNENAPDQK");
sequences.insert("ILDCGSPDTEVR");
sequences.insert("KCPSPCQLQAER");
sequences.insert("KGTEFTVNDLQGK");
sequences.insert("KQTALVELLK");
sequences.insert("KVPQVSTPTLVEVSR");
sequences.insert("LALQFTTNAKR");
sequences.insert("LCVLHEKTPVSEK");
sequences.insert("LFTFHADICTLPDTEK");
sequences.insert("LGEYGFQNALIVR");
sequences.insert("LHVDPENFK");
sequences.insert("LKECCDKPLLEK");
sequences.insert("LKHLVDEPQNLIK");
sequences.insert("LKPDPNTLCDEFK");
sequences.insert("LLGNVLVVVLAR");
sequences.insert("LLVVYPWTQR");
sequences.insert("LRVDPVNFK");
sequences.insert("LTDEELAFPPLSPSR");
sequences.insert("LVNELTEFAK");
sequences.insert("MFLSFPTTK");
sequences.insert("MPCTEDYLSLILNR");
sequences.insert("NAPYSGYSGAFHCLK");
sequences.insert("NECFLSHKDDSPDLPK");
sequences.insert("NEPNKVPACPGSCEEVK");
sequences.insert("NLQMDDFELLCTDGR");
sequences.insert("QAGVQAEPSPK");
sequences.insert("RAPEFAAPWPDFVPR");
sequences.insert("RHPEYAVSVLLR");
sequences.insert("RPCFSALTPDETYVPK");
sequences.insert("RSLLLAPEEGPVSQR");
sequences.insert("SAFPPEPLLCSVQR");
sequences.insert("SAGWNIPIGTLLHR");
sequences.insert("SCWCVDEAGQK");
sequences.insert("SGNPNYPHEFSR");
sequences.insert("SHCIAEVEK");
sequences.insert("SISSGFFECER");
sequences.insert("SKYLASASTMDHAR");
sequences.insert("SLHTLFGDELCK");
sequences.insert("SLLLAPEEGPVSQR");
sequences.insert("SPPQCSPDGAFRPVQCK");
sequences.insert("SREGDPLAVYLK");
sequences.insert("SRQIPQCPTSCER");
sequences.insert("TAGTPVSIPVCDDSSVK");
sequences.insert("TCVADESHAGCEK");
sequences.insert("TQFGCLEGFGR");
sequences.insert("TVMENFVAFVDK");
sequences.insert("TYFPHFDLSHGSAQVK");
sequences.insert("TYMLAFDVNDEK");
sequences.insert("VDEVGGEALGR");
sequences.insert("VDLLIGSSQDDGLINR");
sequences.insert("VEDIWSFLSK");
sequences.insert("VGGHAAEYGAEALER");
sequences.insert("VGTRCCTKPESER");
sequences.insert("VKVDEVGGEALGR");
sequences.insert("VKVDLLIGSSQDDGLINR");
sequences.insert("VLDSFSNGMK");
sequences.insert("VLSAADKGNVK");
sequences.insert("VPQVSTPTLVEVSR");
sequences.insert("VTKCCTESLVNR");
sequences.insert("VVAASDASQDALGCVK");
sequences.insert("VVAGVANALAHR");
sequences.insert("YICDNQDTISSK");
sequences.insert("YLASASTMDHAR");
sequences.insert("YNGVFQECCQAEDK");
#endif
SpectrumAlignmentScore spectra_zhang;
spectra_zhang.setParameters(zhang_param);
vector<PeptideHit> hits;
Size missed_cleavages = param_.getValue("missed_cleavages");
for (set<String>::const_iterator it = sequences.begin(); it != sequences.end(); ++it)
{
Size num_missed = countMissedCleavagesTryptic_(*it);
if (missed_cleavages < num_missed)
{
//cerr << "Two many missed cleavages: " << *it << ", found " << num_missed << ", allowed " << missed_cleavages << endl;
continue;
}
PeakSpectrum CID_sim_spec;
getCIDSpectrum_(CID_sim_spec, *it, charge);
//normalizer.filterSpectrum(CID_sim_spec);
double cid_score = zhang_(CID_sim_spec, CID_spec);
PeptideHit hit;
hit.setScore(cid_score);
hit.setSequence(getModifiedAASequence_(*it));
hit.setCharge((Int)charge); //TODO unify charge interface: int or size?
hits.push_back(hit);
//cerr << getModifiedAASequence_(*it) << " " << cid_score << " " << endl;
}
// rescore the top hits
id.setHits(hits);
id.assignRanks();
hits = id.getHits();
SpectrumAlignmentScore alignment_score;
Param align_param(alignment_score.getParameters());
align_param.setValue("tolerance", fragment_mass_tolerance_);
align_param.setValue("use_linear_factor", "true");
alignment_score.setParameters(align_param);
for (vector<PeptideHit>::iterator it = hits.begin(); it != hits.end(); ++it)
{
//cerr << "Pre: " << it->getRank() << " " << it->getSequence() << " " << it->getScore() << " " << endl;
}
Size number_of_prescoring_hits = param_.getValue("number_of_prescoring_hits");
if (hits.size() > number_of_prescoring_hits)
{
hits.resize(number_of_prescoring_hits);
}
for (vector<PeptideHit>::iterator it = hits.begin(); it != hits.end(); ++it)
{
PeakSpectrum CID_sim_spec;
getCIDSpectrum_(CID_sim_spec, getModifiedStringFromAASequence_(it->getSequence()), charge);
normalizer.filterSpectrum(CID_sim_spec);
//DTAFile().store("sim_specs/" + it->getSequence().toUnmodifiedString() + "_sim_CID.dta", CID_sim_spec);
//double cid_score = spectra_zhang(CID_sim_spec, CID_spec);
double cid_score = alignment_score(CID_sim_spec, CID_spec);
//cerr << "Final: " << it->getSequence() << " " << cid_score << endl;
it->setScore(cid_score);
}
id.setHits(hits);
id.assignRanks();
hits = id.getHits();
for (vector<PeptideHit>::iterator it = hits.begin(); it != hits.end(); ++it)
{
//cerr << "Fin: " << it->getRank() << " " << it->getSequence() << " " << it->getScore() << " " << endl;
}
Size number_of_hits = param_.getValue("number_of_hits");
if (id.getHits().size() > number_of_hits)
{
hits.resize(number_of_hits);
}
id.setHits(hits);
id.assignRanks();
return;
}
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();
}
ExitCodes main_(int, const char**)
{
//-------------------------------------------------------------
// parameter handling
//-------------------------------------------------------------
StringList in_spec = getStringList_("in");
StringList out = getStringList_("out");
String in_lib = getStringOption_("lib");
String compare_function = getStringOption_("compare_function");
Int precursor_mass_multiplier = getIntOption_("round_precursor_to_integer");
float precursor_mass_tolerance = getDoubleOption_("precursor_mass_tolerance");
//Int min_precursor_charge = getIntOption_("min_precursor_charge");
//Int max_precursor_charge = getIntOption_("max_precursor_charge");
float remove_peaks_below_threshold = getDoubleOption_("filter:remove_peaks_below_threshold");
UInt min_peaks = getIntOption_("filter:min_peaks");
UInt max_peaks = getIntOption_("filter:max_peaks");
Int cut_peaks_below = getIntOption_("filter:cut_peaks_below");
StringList fixed_modifications = getStringList_("fixed_modifications");
StringList variable_modifications = getStringList_("variable_modifications");
Int top_hits = getIntOption_("top_hits");
if (top_hits < -1)
{
writeLog_("top_hits (should be >= -1 )");
return ILLEGAL_PARAMETERS;
}
//-------------------------------------------------------------
// loading input
//-------------------------------------------------------------
if (out.size() != in_spec.size())
{
writeLog_("out (should be as many as input files)");
return ILLEGAL_PARAMETERS;
}
time_t prog_time = time(NULL);
MSPFile spectral_library;
RichPeakMap query, library;
//spectrum which will be identified
MzMLFile spectra;
spectra.setLogType(log_type_);
time_t start_build_time = time(NULL);
//-------------------------------------------------------------
//building map for faster search
//-------------------------------------------------------------
//library containing already identified peptide spectra
vector<PeptideIdentification> ids;
spectral_library.load(in_lib, ids, library);
map<Size, vector<PeakSpectrum> > MSLibrary;
{
RichPeakMap::iterator s;
vector<PeptideIdentification>::iterator i;
ModificationsDB* mdb = ModificationsDB::getInstance();
for (s = library.begin(), i = ids.begin(); s < library.end(); ++s, ++i)
{
double precursor_MZ = (*s).getPrecursors()[0].getMZ();
Size MZ_multi = (Size)precursor_MZ * precursor_mass_multiplier;
map<Size, vector<PeakSpectrum> >::iterator found;
found = MSLibrary.find(MZ_multi);
PeakSpectrum librar;
bool variable_modifications_ok = true;
bool fixed_modifications_ok = true;
const AASequence& aaseq = i->getHits()[0].getSequence();
//variable fixed modifications
if (!fixed_modifications.empty())
{
for (Size i = 0; i < aaseq.size(); ++i)
{
const Residue& mod = aaseq.getResidue(i);
for (Size s = 0; s < fixed_modifications.size(); ++s)
{
if (mod.getOneLetterCode() == mdb->getModification(fixed_modifications[s]).getOrigin() && fixed_modifications[s] != mod.getModification())
{
fixed_modifications_ok = false;
break;
}
}
}
}
//variable modifications
if (aaseq.isModified() && (!variable_modifications.empty()))
{
for (Size i = 0; i < aaseq.size(); ++i)
{
if (aaseq.isModified(i))
{
const Residue& mod = aaseq.getResidue(i);
for (Size s = 0; s < variable_modifications.size(); ++s)
{
if (mod.getOneLetterCode() == mdb->getModification(variable_modifications[s]).getOrigin() && variable_modifications[s] != mod.getModification())
{
variable_modifications_ok = false;
break;
}
}
}
}
}
if (variable_modifications_ok && fixed_modifications_ok)
{
PeptideIdentification& translocate_pid = *i;
librar.getPeptideIdentifications().push_back(translocate_pid);
librar.setPrecursors(s->getPrecursors());
//library entry transformation
for (UInt l = 0; l < s->size(); ++l)
{
Peak1D peak;
if ((*s)[l].getIntensity() > remove_peaks_below_threshold)
{
const String& info = (*s)[l].getMetaValue("MSPPeakInfo");
if (info[0] == '?')
{
peak.setIntensity(sqrt(0.2 * (*s)[l].getIntensity()));
}
else
{
peak.setIntensity(sqrt((*s)[l].getIntensity()));
}
peak.setMZ((*s)[l].getMZ());
peak.setPosition((*s)[l].getPosition());
librar.push_back(peak);
}
}
if (found != MSLibrary.end())
{
found->second.push_back(librar);
}
else
{
vector<PeakSpectrum> tmp;
tmp.push_back(librar);
MSLibrary.insert(make_pair(MZ_multi, tmp));
}
}
}
}
time_t end_build_time = time(NULL);
cout << "Time needed for preprocessing data: " << (end_build_time - start_build_time) << "\n";
//compare function
PeakSpectrumCompareFunctor* comparor = Factory<PeakSpectrumCompareFunctor>::create(compare_function);
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
double score;
StringList::iterator in, out_file;
for (in = in_spec.begin(), out_file = out.begin(); in < in_spec.end(); ++in, ++out_file)
{
time_t start_time = time(NULL);
spectra.load(*in, query);
//Will hold valuable hits
vector<PeptideIdentification> peptide_ids;
vector<ProteinIdentification> protein_ids;
// Write parameters to ProteinIdentifcation
ProteinIdentification prot_id;
//Parameters of identificaion
prot_id.setIdentifier("test");
prot_id.setSearchEngineVersion("SpecLibSearcher");
prot_id.setDateTime(DateTime::now());
prot_id.setScoreType(compare_function);
ProteinIdentification::SearchParameters searchparam;
searchparam.precursor_tolerance = precursor_mass_tolerance;
prot_id.setSearchParameters(searchparam);
/***********SEARCH**********/
for (UInt j = 0; j < query.size(); ++j)
{
//Set identifier for each identifications
PeptideIdentification pid;
pid.setIdentifier("test");
pid.setScoreType(compare_function);
ProteinHit pr_hit;
pr_hit.setAccession(j);
prot_id.insertHit(pr_hit);
//RichPeak1D to Peak1D transformation for the compare function query
PeakSpectrum quer;
bool peak_ok = true;
query[j].sortByIntensity(true);
double min_high_intensity = 0;
if (query[j].empty() || query[j].getMSLevel() != 2)
{
continue;
}
if (query[j].getPrecursors().empty())
{
writeLog_("Warning MS2 spectrum without precursor information");
continue;
}
min_high_intensity = (1 / cut_peaks_below) * query[j][0].getIntensity();
query[j].sortByPosition();
for (UInt k = 0; k < query[j].size() && k < max_peaks; ++k)
{
if (query[j][k].getIntensity() > remove_peaks_below_threshold && query[j][k].getIntensity() >= min_high_intensity)
{
Peak1D peak;
peak.setIntensity(sqrt(query[j][k].getIntensity()));
peak.setMZ(query[j][k].getMZ());
peak.setPosition(query[j][k].getPosition());
quer.push_back(peak);
}
}
if (quer.size() >= min_peaks)
{
peak_ok = true;
}
else
{
peak_ok = false;
}
double query_MZ = query[j].getPrecursors()[0].getMZ();
if (peak_ok)
{
bool charge_one = false;
Int percent = (Int) Math::round((query[j].size() / 100.0) * 3.0);
Int margin = (Int) Math::round((query[j].size() / 100.0) * 1.0);
for (vector<RichPeak1D>::iterator peak = query[j].end() - 1; percent >= 0; --peak, --percent)
{
if (peak->getMZ() < query_MZ)
{
break;
}
}
if (percent > margin)
{
charge_one = true;
}
float min_MZ = (query_MZ - precursor_mass_tolerance) * precursor_mass_multiplier;
float max_MZ = (query_MZ + precursor_mass_tolerance) * precursor_mass_multiplier;
for (Size mz = (Size)min_MZ; mz <= ((Size)max_MZ) + 1; ++mz)
{
map<Size, vector<PeakSpectrum> >::iterator found;
found = MSLibrary.find(mz);
if (found != MSLibrary.end())
{
vector<PeakSpectrum>& library = found->second;
for (Size i = 0; i < library.size(); ++i)
{
float this_MZ = library[i].getPrecursors()[0].getMZ() * precursor_mass_multiplier;
if (this_MZ >= min_MZ && max_MZ >= this_MZ && ((charge_one == true && library[i].getPeptideIdentifications()[0].getHits()[0].getCharge() == 1) || charge_one == false))
{
PeptideHit hit = library[i].getPeptideIdentifications()[0].getHits()[0];
PeakSpectrum& librar = library[i];
//Special treatment for SpectraST score as it computes a score based on the whole library
if (compare_function == "SpectraSTSimilarityScore")
{
SpectraSTSimilarityScore* sp = static_cast<SpectraSTSimilarityScore*>(comparor);
BinnedSpectrum quer_bin = sp->transform(quer);
BinnedSpectrum librar_bin = sp->transform(librar);
score = (*sp)(quer, librar); //(*sp)(quer_bin,librar_bin);
double dot_bias = sp->dot_bias(quer_bin, librar_bin, score);
hit.setMetaValue("DOTBIAS", dot_bias);
}
else
{
score = (*comparor)(quer, librar);
}
DataValue RT(library[i].getRT());
DataValue MZ(library[i].getPrecursors()[0].getMZ());
hit.setMetaValue("RT", RT);
hit.setMetaValue("MZ", MZ);
hit.setScore(score);
PeptideEvidence pe;
pe.setProteinAccession(pr_hit.getAccession());
hit.addPeptideEvidence(pe);
pid.insertHit(hit);
}
}
}
}
}
pid.setHigherScoreBetter(true);
pid.sort();
if (compare_function == "SpectraSTSimilarityScore")
{
if (!pid.empty() && !pid.getHits().empty())
{
vector<PeptideHit> final_hits;
final_hits.resize(pid.getHits().size());
SpectraSTSimilarityScore* sp = static_cast<SpectraSTSimilarityScore*>(comparor);
Size runner_up = 1;
for (; runner_up < pid.getHits().size(); ++runner_up)
{
if (pid.getHits()[0].getSequence().toUnmodifiedString() != pid.getHits()[runner_up].getSequence().toUnmodifiedString() || runner_up > 5)
{
break;
}
}
double delta_D = sp->delta_D(pid.getHits()[0].getScore(), pid.getHits()[runner_up].getScore());
for (Size s = 0; s < pid.getHits().size(); ++s)
{
final_hits[s] = pid.getHits()[s];
final_hits[s].setMetaValue("delta D", delta_D);
final_hits[s].setMetaValue("dot product", pid.getHits()[s].getScore());
final_hits[s].setScore(sp->compute_F(pid.getHits()[s].getScore(), delta_D, pid.getHits()[s].getMetaValue("DOTBIAS")));
//final_hits[s].removeMetaValue("DOTBIAS");
}
pid.setHits(final_hits);
pid.sort();
pid.setMZ(query[j].getPrecursors()[0].getMZ());
pid.setRT(query_MZ);
}
}
if (top_hits != -1 && (UInt)top_hits < pid.getHits().size())
{
vector<PeptideHit> hits;
hits.resize(top_hits);
for (Size i = 0; i < (UInt)top_hits; ++i)
{
hits[i] = pid.getHits()[i];
}
pid.setHits(hits);
}
peptide_ids.push_back(pid);
}
protein_ids.push_back(prot_id);
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
IdXMLFile id_xml_file;
id_xml_file.store(*out_file, protein_ids, peptide_ids);
time_t end_time = time(NULL);
cout << "Search time: " << difftime(end_time, start_time) << " seconds for " << *in << "\n";
}
time_t end_time = time(NULL);
cout << "Total time: " << difftime(end_time, prog_time) << " secconds\n";
return EXECUTION_OK;
}
String describeHit_(const PeptideHit& hit)
{
return "peptide hit with sequence '" + hit.getSequence().toString() +
"', charge " + String(hit.getCharge()) + ", score " +
String(hit.getScore());
}
PeptideHit AScore::compute(const PeptideHit & hit, PeakSpectrum & real_spectrum, double fragment_mass_tolerance, bool fragment_mass_unit_ppm, Size max_peptide_len, Size max_num_perm)
{
PeptideHit phospho = hit;
//reset phospho
phospho.setScore(-1);
if (real_spectrum.empty())
{
return phospho;
}
String sequence_str = phospho.getSequence().toString();
Size number_of_phosphorylation_events = numberOfPhosphoEvents_(sequence_str);
AASequence seq_without_phospho = removePhosphositesFromSequence_(sequence_str);
if (seq_without_phospho.toUnmodifiedString().size() > max_peptide_len)
{
LOG_DEBUG << "\tcalculation aborted: peptide too long: " << seq_without_phospho.toString() << std::endl;
return phospho;
}
// determine all phospho sites
vector<Size> sites(getSites_(seq_without_phospho));
Size number_of_STY = sites.size();
if (number_of_phosphorylation_events == 0 || number_of_STY == 0 || number_of_STY == number_of_phosphorylation_events)
{
return phospho;
}
vector<vector<Size> > permutations(computePermutations_(sites, (Int)number_of_phosphorylation_events));
LOG_DEBUG << "\tnumber of permutations: " << permutations.size() << std::endl;
// TODO: using a heuristic to calculate the best phospho sites if the number of permutations are exceeding the maximum.
// A heuristic could be to calculate the best site for the first phosphorylation and based on this the best site for the second
// phosphorylation and so on until every site is determined
if (permutations.size() > max_num_perm)
{
LOG_DEBUG << "\tcalculation aborted: number of permutations exceeded" << std::endl;
return phospho;
}
vector<PeakSpectrum> th_spectra(createTheoreticalSpectra_(permutations, seq_without_phospho));
// prepare real spectrum windows
if (!real_spectrum.isSorted())
{
real_spectrum.sortByPosition();
}
vector<PeakSpectrum> windows_top10(peakPickingPerWindowsInSpectrum_(real_spectrum));
// calculate peptide score for each possible phospho site permutation
vector<vector<double> > peptide_site_scores(calculatePermutationPeptideScores_(th_spectra, windows_top10, fragment_mass_tolerance, fragment_mass_unit_ppm));
// rank peptide permutations ascending
multimap<double, Size> ranking(rankWeightedPermutationPeptideScores_(peptide_site_scores));
multimap<double, Size>::reverse_iterator rev = ranking.rbegin();
String seq1 = th_spectra[rev->second].getName();
phospho.setSequence(AASequence::fromString(seq1));
phospho.setMetaValue("search_engine_sequence", hit.getSequence().toString());
double peptide1_score = rev->first;
phospho.setMetaValue("AScore_pep_score", peptide1_score); // initialize score with highest peptide score (aka highest weighted score)
++rev;
String seq2 = th_spectra[rev->second].getName();
double peptide2_score = rev->first;
vector<ProbablePhosphoSites> phospho_sites;
determineHighestScoringPermutations_(peptide_site_scores, phospho_sites, permutations, ranking);
Int rank = 1;
double best_Ascore = std::numeric_limits<double>::max(); // the lower the better
for (vector<ProbablePhosphoSites>::iterator s_it = phospho_sites.begin(); s_it != phospho_sites.end(); ++s_it)
{
double Ascore = 0;
if (peptide1_score == peptide2_score) // set Ascore = 0 for each phosphorylation site
{
LOG_DEBUG << "\tscore of best (" << seq1 << ") and second best peptide (" << seq2 << ") are equal (" << peptide1_score << ")" << std::endl;
}
else
{
vector<PeakSpectrum> site_determining_ions;
computeSiteDeterminingIons_(th_spectra, *s_it, site_determining_ions, fragment_mass_tolerance, fragment_mass_unit_ppm);
Size N = site_determining_ions[0].size(); // all possibilities have the same number so take the first one
double p = static_cast<double>(s_it->peak_depth) / 100.0;
Size n_first = 0; // number of matching peaks for first peptide
for (Size window_idx = 0; window_idx != windows_top10.size(); ++window_idx) // for each 100 m/z window
{
n_first += numberOfMatchedIons_(site_determining_ions[0], windows_top10[window_idx], s_it->peak_depth, fragment_mass_tolerance, fragment_mass_unit_ppm);
}
double P_first = computeCumulativeScore_(N, n_first, p);
Size n_second = 0; // number of matching peaks for second peptide
for (Size window_idx = 0; window_idx < windows_top10.size(); ++window_idx) //each 100 m/z window
{
n_second += numberOfMatchedIons_(site_determining_ions[1], windows_top10[window_idx], s_it->peak_depth, fragment_mass_tolerance, fragment_mass_unit_ppm);
}
Size N2 = site_determining_ions[1].size(); // all possibilities have the same number so take the first one
double P_second = computeCumulativeScore_(N2, n_second, p);
//abs is used to avoid -0 score values
double score_first = abs(-10 * log10(P_first));
double score_second = abs(-10 * log10(P_second));
LOG_DEBUG << "\tfirst - N: " << N << ",p: " << p << ",n: " << n_first << ", score: " << score_first << std::endl;
LOG_DEBUG << "\tsecond - N: " << N2 << ",p: " << p << ",n: " << n_second << ", score: " << score_second << std::endl;
Ascore = score_first - score_second;
LOG_DEBUG << "\tAscore_" << rank << ": " << Ascore << std::endl;
}
if (Ascore < best_Ascore)
{
best_Ascore = Ascore;
}
phospho.setMetaValue("AScore_" + String(rank), Ascore);
++rank;
}
phospho.setScore(best_Ascore);
return phospho;
}
ExitCodes main_(int, const char **)
{
//-------------------------------------------------------------
// parsing parameters
//-------------------------------------------------------------
StringList id_in(getStringList_("id_in"));
StringList in_raw(getStringList_("in"));
Size number_of_bins((UInt)getIntOption_("number_of_bins"));
bool precursor_error_ppm(getFlag_("precursor_error_ppm"));
bool fragment_error_ppm(getFlag_("fragment_error_ppm"));
bool generate_gnuplot_scripts(DataValue(getStringOption_("generate_gnuplot_scripts")).toBool());
if (in_raw.size() != id_in.size())
{
writeLog_("Number of spectrum files and identification files differs...");
return ILLEGAL_PARAMETERS;
}
//-------------------------------------------------------------
// reading input
//-------------------------------------------------------------
vector<vector<PeptideIdentification> > pep_ids;
vector<vector<ProteinIdentification> > prot_ids;
pep_ids.resize(id_in.size());
prot_ids.resize(id_in.size());
IdXMLFile idxmlfile;
for (Size i = 0; i != id_in.size(); ++i)
{
String doc_id;
idxmlfile.load(id_in[i], prot_ids[i], pep_ids[i], doc_id);
}
// read mzML files
vector<RichPeakMap> maps_raw;
maps_raw.resize(in_raw.size());
MzMLFile mzml_file;
for (Size i = 0; i != in_raw.size(); ++i)
{
mzml_file.load(in_raw[i], maps_raw[i]);
}
//-------------------------------------------------------------
// calculations
//-------------------------------------------------------------
// mapping ids
IDMapper mapper;
for (Size i = 0; i != maps_raw.size(); ++i)
{
mapper.annotate(maps_raw[i], pep_ids[i], prot_ids[i]);
}
// normalize the spectra
Normalizer normalizer;
for (vector<RichPeakMap>::iterator it1 = maps_raw.begin(); it1 != maps_raw.end(); ++it1)
{
for (RichPeakMap::Iterator it2 = it1->begin(); it2 != it1->end(); ++it2)
{
normalizer.filterSpectrum(*it2);
}
}
// generate precursor statistics
vector<MassDifference> precursor_diffs;
if (getStringOption_("precursor_out") != "")
{
for (Size i = 0; i != maps_raw.size(); ++i)
{
for (Size j = 0; j != maps_raw[i].size(); ++j)
{
if (maps_raw[i][j].getPeptideIdentifications().empty())
{
continue;
}
for (vector<PeptideIdentification>::const_iterator it = maps_raw[i][j].getPeptideIdentifications().begin(); it != maps_raw[i][j].getPeptideIdentifications().end(); ++it)
{
if (it->getHits().size() > 0)
{
PeptideHit hit = *it->getHits().begin();
MassDifference md;
Int charge = hit.getCharge();
if (charge == 0)
{
charge = 1;
}
md.exp_mz = it->getMZ();
md.theo_mz = (hit.getSequence().getMonoWeight() + (double)charge * Constants::PROTON_MASS_U) / (double)charge;
md.charge = charge;
precursor_diffs.push_back(md);
}
}
}
}
}
// generate fragment ions statistics
vector<MassDifference> fragment_diffs;
TheoreticalSpectrumGenerator tsg;
SpectrumAlignment sa;
double fragment_mass_tolerance(getDoubleOption_("fragment_mass_tolerance"));
Param sa_param(sa.getParameters());
sa_param.setValue("tolerance", fragment_mass_tolerance);
sa.setParameters(sa_param);
if (getStringOption_("fragment_out") != "")
{
for (Size i = 0; i != maps_raw.size(); ++i)
{
for (Size j = 0; j != maps_raw[i].size(); ++j)
{
if (maps_raw[i][j].getPeptideIdentifications().empty())
{
continue;
}
for (vector<PeptideIdentification>::const_iterator it = maps_raw[i][j].getPeptideIdentifications().begin(); it != maps_raw[i][j].getPeptideIdentifications().end(); ++it)
{
if (it->getHits().size() > 0)
{
PeptideHit hit = *it->getHits().begin();
RichPeakSpectrum theo_spec;
tsg.addPeaks(theo_spec, hit.getSequence(), Residue::YIon);
tsg.addPeaks(theo_spec, hit.getSequence(), Residue::BIon);
vector<pair<Size, Size> > pairs;
sa.getSpectrumAlignment(pairs, theo_spec, maps_raw[i][j]);
//cerr << hit.getSequence() << " " << hit.getSequence().getSuffix(1).getFormula() << " " << hit.getSequence().getSuffix(1).getFormula().getMonoWeight() << endl;
for (vector<pair<Size, Size> >::const_iterator pit = pairs.begin(); pit != pairs.end(); ++pit)
{
MassDifference md;
md.exp_mz = maps_raw[i][j][pit->second].getMZ();
md.theo_mz = theo_spec[pit->first].getMZ();
//cerr.precision(15);
//cerr << md.exp_mz << " " << md.theo_mz << " " << md.exp_mz - md.theo_mz << endl;
md.intensity = maps_raw[i][j][pit->second].getIntensity();
md.charge = hit.getCharge();
fragment_diffs.push_back(md);
}
}
}
}
}
}
//-------------------------------------------------------------
// writing output
//-------------------------------------------------------------
String precursor_out_file(getStringOption_("precursor_out"));
if (precursor_out_file != "")
{
vector<double> errors;
ofstream precursor_out(precursor_out_file.c_str());
double min_diff(numeric_limits<double>::max()), max_diff(numeric_limits<double>::min());
for (Size i = 0; i != precursor_diffs.size(); ++i)
{
double diff = getMassDifference(precursor_diffs[i].theo_mz, precursor_diffs[i].exp_mz, precursor_error_ppm);
precursor_out << diff << "\n";
errors.push_back(diff);
if (diff > max_diff)
{
max_diff = diff;
}
if (diff < min_diff)
{
min_diff = diff;
}
}
precursor_out.close();
// fill histogram with the collected values
double bin_size = (max_diff - min_diff) / (double)number_of_bins;
Histogram<double, double> hist(min_diff, max_diff, bin_size);
for (Size i = 0; i != errors.size(); ++i)
{
hist.inc(errors[i], 1.0);
}
writeDebug_("min_diff=" + String(min_diff) + ", max_diff=" + String(max_diff) + ", number_of_bins=" + String(number_of_bins), 1);
// transform the histogram into a vector<DPosition<2> > for the fitting
vector<DPosition<2> > values;
for (Size i = 0; i != hist.size(); ++i)
{
DPosition<2> p;
p.setX((double)i / (double)number_of_bins * (max_diff - min_diff) + min_diff);
p.setY(hist[i]);
values.push_back(p);
}
double mean = Math::mean(errors.begin(), errors.end());
double abs_dev = Math::absdev(errors.begin(), errors.end(), mean);
double sdv = Math::sd(errors.begin(), errors.end(), mean);
sort(errors.begin(), errors.end());
double median = errors[(Size)(errors.size() / 2.0)];
writeDebug_("Precursor mean error: " + String(mean), 1);
writeDebug_("Precursor abs. dev.: " + String(abs_dev), 1);
writeDebug_("Precursor std. dev.: " + String(sdv), 1);
writeDebug_("Precursor median error: " + String(median), 1);
// calculate histogram for gauss fitting
GaussFitter gf;
GaussFitter::GaussFitResult init_param (hist.maxValue(), median, sdv/500.0);
gf.setInitialParameters(init_param);
try
{
gf.fit(values);
// write gnuplot scripts
if (generate_gnuplot_scripts)
{
ofstream out(String(precursor_out_file + "_gnuplot.dat").c_str());
for (vector<DPosition<2> >::const_iterator it = values.begin(); it != values.end(); ++it)
{
out << it->getX() << " " << it->getY() << endl;
}
out.close();
ofstream gpl_out(String(precursor_out_file + "_gnuplot.gpl").c_str());
gpl_out << "set terminal png" << endl;
gpl_out << "set output \"" << precursor_out_file << "_gnuplot.png\"" << endl;
if (precursor_error_ppm)
{
gpl_out << "set xlabel \"error in ppm\"" << endl;
}
else
{
gpl_out << "set xlabel \"error in Da\"" << endl;
}
gpl_out << "set ylabel \"frequency\"" << endl;
gpl_out << "plot '" << precursor_out_file << "_gnuplot.dat' title 'Precursor mass error distribution' w boxes, f(x) w lp title 'Gaussian fit of the error distribution'" << endl;
gpl_out.close();
}
}
catch (Exception::UnableToFit)
{
writeLog_("Unable to fit a Gaussian distribution to the precursor mass errors");
}
}
String fragment_out_file(getStringOption_("fragment_out"));
if (fragment_out_file != "")
{
vector<double> errors;
ofstream fragment_out(fragment_out_file.c_str());
double min_diff(numeric_limits<double>::max()), max_diff(numeric_limits<double>::min());
for (Size i = 0; i != fragment_diffs.size(); ++i)
{
double diff = getMassDifference(fragment_diffs[i].theo_mz, fragment_diffs[i].exp_mz, fragment_error_ppm);
fragment_out << diff << endl;
errors.push_back(diff);
if (diff > max_diff)
{
max_diff = diff;
}
if (diff < min_diff)
{
min_diff = diff;
}
}
fragment_out.close();
// fill histogram with the collected values
// here we use the intensities to scale the error
// low intensity peaks are likely to be random matches
double bin_size = (max_diff - min_diff) / (double)number_of_bins;
Histogram<double, double> hist(min_diff, max_diff, bin_size);
for (Size i = 0; i != fragment_diffs.size(); ++i)
{
double diff = getMassDifference(fragment_diffs[i].theo_mz, fragment_diffs[i].exp_mz, fragment_error_ppm);
hist.inc(diff, fragment_diffs[i].intensity);
}
writeDebug_("min_diff=" + String(min_diff) + ", max_diff=" + String(max_diff) + ", number_of_bins=" + String(number_of_bins), 1);
// transform the histogram into a vector<DPosition<2> > for the fitting
vector<DPosition<2> > values;
for (Size i = 0; i != hist.size(); ++i)
{
DPosition<2> p;
p.setX((double)i / (double)number_of_bins * (max_diff - min_diff) + min_diff);
p.setY(hist[i]);
values.push_back(p);
}
double mean = Math::mean(errors.begin(), errors.end());
double abs_dev = Math::absdev(errors.begin(), errors.end(), mean);
double sdv = Math::sd(errors.begin(), errors.end(), mean);
sort(errors.begin(), errors.end());
double median = errors[(Size)(errors.size() / 2.0)];
writeDebug_("Fragment mean error: " + String(mean), 1);
writeDebug_("Fragment abs. dev.: " + String(abs_dev), 1);
writeDebug_("Fragment std. dev.: " + String(sdv), 1);
writeDebug_("Fragment median error: " + String(median), 1);
// calculate histogram for gauss fitting
GaussFitter gf;
GaussFitter::GaussFitResult init_param (hist.maxValue(), median, sdv / 100.0);
gf.setInitialParameters(init_param);
try
{
gf.fit(values);
// write gnuplot script
if (generate_gnuplot_scripts)
{
ofstream out(String(fragment_out_file + "_gnuplot.dat").c_str());
for (vector<DPosition<2> >::const_iterator it = values.begin(); it != values.end(); ++it)
{
out << it->getX() << " " << it->getY() << endl;
}
out.close();
ofstream gpl_out(String(fragment_out_file + "_gnuplot.gpl").c_str());
gpl_out << "set terminal png" << endl;
gpl_out << "set output \"" << fragment_out_file << "_gnuplot.png\"" << endl;
if (fragment_error_ppm)
{
gpl_out << "set xlabel \"error in ppm\"" << endl;
}
else
{
gpl_out << "set xlabel \"error in Da\"" << endl;
}
gpl_out << "set ylabel \"frequency\"" << endl;
gpl_out << "plot '" << fragment_out_file << "_gnuplot.dat' title 'Fragment mass error distribution' w boxes, f(x) w lp title 'Gaussian fit of the error distribution'" << endl;
gpl_out.close();
}
}
catch (Exception::UnableToFit)
{
writeLog_("Unable to fit a Gaussian distribution to the fragment mass errors");
}
}
return EXECUTION_OK;
}
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;
}
