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;
}
void LabeledPairFinder::run(const vector<ConsensusMap>& input_maps, ConsensusMap& result_map)
{
if (input_maps.size() != 1)
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__, "exactly one input map required");
if (result_map.getFileDescriptions().size() != 2)
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__, "two file descriptions required");
if (result_map.getFileDescriptions().begin()->second.filename != result_map.getFileDescriptions().rbegin()->second.filename)
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__, "the two file descriptions have to contain the same file name");
checkIds_(input_maps);
//look up the light and heavy index
Size light_index = numeric_limits<Size>::max();
Size heavy_index = numeric_limits<Size>::max();
for (ConsensusMap::FileDescriptions::const_iterator it = result_map.getFileDescriptions().begin();
it != result_map.getFileDescriptions().end();
++it)
{
if (it->second.label == "heavy")
{
heavy_index = it->first;
}
else if (it->second.label == "light")
{
light_index = it->first;
}
}
if (light_index == numeric_limits<Size>::max() || heavy_index == numeric_limits<Size>::max())
{
throw Exception::IllegalArgument(__FILE__, __LINE__, __PRETTY_FUNCTION__, "the input maps have to be labeled 'light' and 'heavy'");
}
result_map.clear(false);
// sort consensus features by RT (and MZ) to speed up searching afterwards
typedef ConstRefVector<ConsensusMap> RefMap;
RefMap model_ref(input_maps[0].begin(), input_maps[0].end());
model_ref.sortByPosition();
//calculate matches
ConsensusMap matches;
//settings
double rt_pair_dist = param_.getValue("rt_pair_dist");
double rt_dev_low = param_.getValue("rt_dev_low");
double rt_dev_high = param_.getValue("rt_dev_high");
double mz_dev = param_.getValue("mz_dev");
DoubleList mz_pair_dists = param_.getValue("mz_pair_dists");
bool mrm = param_.getValue("mrm").toBool();
//estimate RT parameters
if (param_.getValue("rt_estimate") == "true")
{
//find all possible RT distances of features with the same charge and a good m/z distance
vector<double> dists;
dists.reserve(model_ref.size());
for (RefMap::const_iterator it = model_ref.begin(); it != model_ref.end(); ++it)
{
for (RefMap::const_iterator it2 = model_ref.begin(); it2 != model_ref.end(); ++it2)
{
for (DoubleList::const_iterator dist_it = mz_pair_dists.begin(); dist_it != mz_pair_dists.end(); ++dist_it)
{
double mz_pair_dist = *dist_it;
if (it2->getCharge() == it->getCharge()
&& it2->getMZ() >= it->getMZ() + mz_pair_dist / it->getCharge() - mz_dev
&& it2->getMZ() <= it->getMZ() + mz_pair_dist / it->getCharge() + mz_dev)
{
dists.push_back(it2->getRT() - it->getRT());
}
}
}
}
if (dists.empty())
{
cout << "Warning: Could not find pairs for RT distance estimation. The manual settings are used!" << endl;
}
else
{
if (dists.size() < 50)
{
cout << "Warning: Found only " << dists.size() << " pairs. The estimated shift and std deviation are probably not reliable!" << endl;
}
//--------------------------- estimate initial parameters of fit ---------------------------
GaussFitter::GaussFitResult result(-1, -1, -1);
//first estimate of the optimal shift: median of the distances
sort(dists.begin(), dists.end());
Size median_index = dists.size() / 2;
result.x0 = dists[median_index];
//create histogram of distances
//consider only the maximum of pairs, centered around the optimal shift
Size max_pairs = model_ref.size() / 2;
Size start_index = (Size) max((SignedSize)0, (SignedSize)(median_index - max_pairs / 2));
Size end_index = (Size) min((SignedSize)(dists.size() - 1), (SignedSize)(median_index + max_pairs / 2));
double start_value = dists[start_index];
double end_value = dists[end_index];
double bin_step = fabs(end_value - start_value) / 99.999; //ensure that we have 100 bins
Math::Histogram<> hist(start_value, end_value, bin_step);
//std::cout << "HIST from " << start_value << " to " << end_value << " (bin size " << bin_step << ")" << endl;
for (Size i = start_index; i <= end_index; ++i)
{
hist.inc(dists[i]);
}
//cout << hist << endl;
dists.clear();
//determine median of bins (uniform background distribution)
vector<Size> bins(hist.begin(), hist.end());
sort(bins.begin(), bins.end());
Size bin_median = bins[bins.size() / 2];
bins.clear();
//estimate scale A: maximum of the histogram
Size max_value = hist.maxValue();
result.A = max_value - bin_median;
//overwrite estimate of x0 with the position of the highest bin
for (Size i = 0; i < hist.size(); ++i)
{
if (hist[i] == max_value)
{
result.x0 = hist.centerOfBin(i);
break;
}
}
//estimate sigma: first time the count is less or equal the median count in the histogram
double pos = result.x0;
while (pos > start_value && hist.binValue(pos) > bin_median)
{
pos -= bin_step;
}
double sigma_low = result.x0 - pos;
pos = result.x0;
while (pos<end_value&& hist.binValue(pos)> bin_median)
{
pos += bin_step;
}
double sigma_high = pos - result.x0;
result.sigma = (sigma_high + sigma_low) / 6.0;
//cout << "estimated optimal RT distance (before fit): " << result.x0 << endl;
//cout << "estimated allowed deviation (before fit): " << result.sigma*3.0 << endl;
//--------------------------- do gauss fit ---------------------------
vector<DPosition<2> > points(hist.size());
for (Size i = 0; i < hist.size(); ++i)
{
points[i][0] = hist.centerOfBin(i);
points[i][1] = max(0u, hist[i]);
}
GaussFitter fitter;
fitter.setInitialParameters(result);
result = fitter.fit(points);
cout << "estimated optimal RT distance: " << result.x0 << endl;
cout << "estimated allowed deviation: " << fabs(result.sigma) * 3.0 << endl;
rt_pair_dist = result.x0;
rt_dev_low = fabs(result.sigma) * 3.0;
rt_dev_high = fabs(result.sigma) * 3.0;
}
}
// check each feature
for (RefMap::const_iterator it = model_ref.begin(); it != model_ref.end(); ++it)
{
for (DoubleList::const_iterator dist_it = mz_pair_dists.begin(); dist_it != mz_pair_dists.end(); ++dist_it)
{
double mz_pair_dist = *dist_it;
RefMap::const_iterator it2 = lower_bound(model_ref.begin(), model_ref.end(), it->getRT() + rt_pair_dist - rt_dev_low, ConsensusFeature::RTLess());
while (it2 != model_ref.end() && it2->getRT() <= it->getRT() + rt_pair_dist + rt_dev_high)
{
// if in mrm mode, we need to compare precursor mass difference and fragment mass difference, charge remains the same
double prec_mz_diff(0);
if (mrm)
{
prec_mz_diff = fabs((double)it2->getMetaValue("MZ") - (double)it->getMetaValue("MZ"));
if (it->getCharge() != 0)
{
prec_mz_diff = fabs(prec_mz_diff - mz_pair_dist / it->getCharge());
}
else
{
prec_mz_diff = fabs(prec_mz_diff - mz_pair_dist);
}
}
bool mrm_correct_dist(false);
double frag_mz_diff = fabs(it->getMZ() - it2->getMZ());
//cerr << it->getRT() << " charge1=" << it->getCharge() << ", charge2=" << it2->getCharge() << ", prec_diff=" << prec_mz_diff << ", frag_diff=" << frag_mz_diff << endl;
if (mrm &&
it2->getCharge() == it->getCharge() &&
prec_mz_diff < mz_dev &&
(frag_mz_diff < mz_dev || fabs(frag_mz_diff - mz_pair_dist) < mz_dev))
{
mrm_correct_dist = true;
//cerr << "mrm_correct_dist" << endl;
}
if ((mrm && mrm_correct_dist) || (!mrm &&
it2->getCharge() == it->getCharge() &&
it2->getMZ() >= it->getMZ() + mz_pair_dist / it->getCharge() - mz_dev &&
it2->getMZ() <= it->getMZ() + mz_pair_dist / it->getCharge() + mz_dev
))
{
//cerr << "dist correct" << endl;
double score = sqrt(
PValue_(it2->getMZ() - it->getMZ(), mz_pair_dist / it->getCharge(), mz_dev, mz_dev) *
PValue_(it2->getRT() - it->getRT(), rt_pair_dist, rt_dev_low, rt_dev_high)
);
// Note: we used to copy the id from the light feature here, but that strategy does not generalize to more than two labels.
// We might want to report consensus features where the light one is missing but more than one heavier variant was found.
// Also, the old strategy is inconsistent with what was done in the unlabeled case. Thus now we assign a new unique id here.
matches.push_back(ConsensusFeature());
matches.back().setUniqueId();
matches.back().insert(light_index, *it);
matches.back().clearMetaInfo();
matches.back().insert(heavy_index, *it2);
matches.back().setQuality(score);
matches.back().setCharge(it->getCharge());
matches.back().computeMonoisotopicConsensus();
}
++it2;
}
}
}
//compute best pairs
// - sort matches by quality
// - take highest-quality matches first (greedy) and mark them as used
set<Size> used_features;
matches.sortByQuality(true);
for (ConsensusMap::const_iterator match = matches.begin(); match != matches.end(); ++match)
{
//check if features are not used yet
if (used_features.find(match->begin()->getUniqueId()) == used_features.end() &&
used_features.find(match->rbegin()->getUniqueId()) == used_features.end()
)
{
//if unused, add it to the final set of elements
result_map.push_back(*match);
used_features.insert(match->begin()->getUniqueId());
used_features.insert(match->rbegin()->getUniqueId());
}
}
//Add protein identifications to result map
for (Size i = 0; i < input_maps.size(); ++i)
{
result_map.getProteinIdentifications().insert(result_map.getProteinIdentifications().end(), input_maps[i].getProteinIdentifications().begin(), input_maps[i].getProteinIdentifications().end());
}
//Add unassigned peptide identifications to result map
for (Size i = 0; i < input_maps.size(); ++i)
{
result_map.getUnassignedPeptideIdentifications().insert(result_map.getUnassignedPeptideIdentifications().end(), input_maps[i].getUnassignedPeptideIdentifications().begin(), input_maps[i].getUnassignedPeptideIdentifications().end());
}
// Very useful for checking the results, and the ids have no real meaning anyway
result_map.sortByMZ();
}