void ElutionPeakDetection::smoothData(MassTrace& mt, int win_size) const
{
// alternative smoothing using SavitzkyGolay
// looking at the unit test, this method gives better fits than lowess smoothing
// reference paper uses lowess smoothing
MSSpectrum<PeakType> spectrum;
spectrum.insert(spectrum.begin(), mt.begin(), mt.end());
SavitzkyGolayFilter sg;
Param param;
param.setValue("polynomial_order", 2);
param.setValue("frame_length", std::max(3, win_size)); // frame length must be at least polynomial_order+1, otherwise SG will fail
sg.setParameters(param);
sg.filter(spectrum);
MSSpectrum<PeakType>::iterator iter = spectrum.begin();
std::vector<double> smoothed_intensities;
for (; iter != spectrum.end(); ++iter)
{
smoothed_intensities.push_back(iter->getIntensity());
}
mt.setSmoothedIntensities(smoothed_intensities);
//alternative end
// std::cout << "win_size elution: " << scan_time << " " << win_size << std::endl;
// if there is no previous FWHM estimation... do it now
// if (win_size == 0)
// {
// mt.estimateFWHM(false); // estimate FWHM
// win_size = mt.getFWHMScansNum();
// }
// use one global window size for all mass traces to smooth
// std::vector<double> rts, ints;
//
// for (MassTrace::const_iterator c_it = mt.begin(); c_it != mt.end(); ++c_it)
// {
// rts.push_back(c_it->getRT());
// ints.push_back(c_it->getIntensity());
// }
// LowessSmoothing lowess_smooth;
// Param lowess_params;
// lowess_params.setValue("window_size", win_size);
// lowess_smooth.setParameters(lowess_params);
// std::vector<double> smoothed_data;
// lowess_smooth.smoothData(rts, ints, smoothed_data);
// mt.setSmoothedIntensities(smoothed_data);
}
void ElutionPeakDetection::detectElutionPeaks_(MassTrace & mt, std::vector<MassTrace> & single_mtraces)
{
std::vector<DoubleReal> rts, ints;
for (MassTrace::const_iterator c_it = mt.begin(); c_it != mt.end(); ++c_it)
{
rts.push_back(c_it->getRT());
ints.push_back(c_it->getIntensity());
}
std::vector<DoubleReal> smoothed_data;
LowessSmoothing lowess_smooth;
Param lowess_params;
// use dynamically computed window sizes
// Size win_size = mt.getFWHMScansNum();
// use one global window size for all mass traces to smooth
DoubleReal scan_time(mt.getScanTime());
Size win_size = std::ceil(chrom_fwhm_ / scan_time);
// std::cout << "win_size elution: " << scan_time << " " << win_size << std::endl;
// if there is no previous FWHM estimation... do it now
// if (win_size == 0)
// {
// mt.estimateFWHM(false); // estimate FWHM
// win_size = mt.getFWHMScansNum();
// }
lowess_params.setValue("window_size", win_size);
lowess_smooth.setParameters(lowess_params);
lowess_smooth.smoothData(rts, ints, smoothed_data);
mt.setSmoothedIntensities(smoothed_data);
// debug intensities
// Size i = 0;
// std::cout << "*****" << std::endl;
// for (MassTrace::const_iterator mt_it = mt.begin(); mt_it != mt.end(); ++mt_it)
// {
// std::cout << mt_it->getIntensity() << " " << smoothed_data[i] << std::endl;
// ++i;
// }
//std::cout << "*****" << std::endl;
std::vector<Size> maxes, mins;
// mt.findLocalExtrema(win_size / 2, maxes, mins);
findLocalExtrema(mt, win_size/2, maxes, mins);
// if only one maximum exists: finished!
if (maxes.size() == 1)
{
bool pw_ok = true;
bool snr_ok = true;
// check mass trace filter criteria (if enabled)
if (pw_filtering_ == "fixed")
{
DoubleReal act_fwhm(mt.estimateFWHM(true));
// std::cout << "act_fwhm: " << act_fwhm << " ";
if (act_fwhm < min_fwhm_ || act_fwhm > max_fwhm_)
{
pw_ok = false;
}
// std::cout << pw_ok << std::endl;
}
if (mt_snr_filtering_)
{
if (computeApexSNR(mt) < chrom_peak_snr_)
{
snr_ok = false;
}
}
if (pw_ok && snr_ok)
{
mt.updateSmoothedMaxRT();
if (pw_filtering_ != "fixed")
{
mt.estimateFWHM(true);
}
// check for minimum/maximum trace length
// DoubleReal mt_length(std::fabs(mt.rbegin()->getRT() - mt.begin()->getRT()));
// if ((mt_length >= min_trace_length_) && (mt_length <= max_trace_length_))
// if (mt_quality >= 1.2)
// {
#ifdef _OPENMP
#pragma omp critical
#endif
single_mtraces.push_back(mt);
}
}
else if (maxes.empty())
{
return;
}
else // split mt to subtraces
{
MassTrace::const_iterator cp_it = mt.begin();
Size last_idx(0);
for (Size min_idx = 0; min_idx < mins.size(); ++min_idx)
{
// copy subtrace between cp_it and splitpoint
std::vector<PeakType> tmp_mt;
std::vector<DoubleReal> smoothed_tmp;
while (last_idx <= mins[min_idx])
{
tmp_mt.push_back(*cp_it);
smoothed_tmp.push_back(mt.getSmoothedIntensities()[last_idx]);
++cp_it;
++last_idx;
}
// check if
// if (tmp_mt.size() >= win_size / 2)
// {
DoubleReal scantime(mt.getScanTime());
MassTrace new_mt(tmp_mt, scantime);
// copy smoothed ints
new_mt.setSmoothedIntensities(smoothed_tmp);
// check filter criteria
bool pw_ok = true;
bool snr_ok = true;
// check mass trace filter criteria (if enabled)
if (pw_filtering_ == "fixed")
{
DoubleReal act_fwhm(new_mt.estimateFWHM(true));
// std::cout << "act_fwhm: " << act_fwhm << " ";
if (act_fwhm < min_fwhm_ || act_fwhm > max_fwhm_)
{
pw_ok = false;
}
// std::cout << pw_ok << std::endl;
}
if (mt_snr_filtering_)
{
if (computeApexSNR(mt) < chrom_peak_snr_)
{
snr_ok = false;
}
}
if (pw_ok && snr_ok)
{
// set label of subtrace
String tr_num;
std::stringstream read_in;
read_in << (min_idx + 1);
tr_num = "." + read_in.str();
new_mt.setLabel(mt.getLabel() + tr_num);
//new_mt.updateWeightedMeanRT();
new_mt.updateSmoothedMaxRT();
//new_mt.updateSmoothedWeightedMeanRT();
new_mt.updateWeightedMeanMZ();
new_mt.updateWeightedMZsd();
if (pw_filtering_ != "fixed")
{
new_mt.estimateFWHM(true);
}
// DoubleReal mt_quality(computeApexSNR(new_mt));
// DoubleReal new_mt_length(std::fabs(new_mt.rbegin()->getRT() - new_mt.begin()->getRT()));
// if ((new_mt_length >= min_trace_length_) && (new_mt_length <= max_trace_length_))
//{
#ifdef _OPENMP
#pragma omp critical
#endif
single_mtraces.push_back(new_mt);
}
// }
}
// don't forget the trailing trace
std::vector<PeakType> tmp_mt;
std::vector<DoubleReal> smoothed_tmp;
while (last_idx < mt.getSize())
{
tmp_mt.push_back(*cp_it);
smoothed_tmp.push_back(mt.getSmoothedIntensities()[last_idx]);
++cp_it;
++last_idx;
}
// if (tmp_mt.size() >= win_size / 2)
// {
DoubleReal scantime(mt.getScanTime());
MassTrace new_mt(tmp_mt, scantime);
// copy smoothed ints
new_mt.setSmoothedIntensities(smoothed_tmp);
// check filter criteria
bool pw_ok = true;
bool snr_ok = true;
// check mass trace filter criteria (if enabled)
if (pw_filtering_ == "fixed")
{
DoubleReal act_fwhm(new_mt.estimateFWHM(true));
// std::cout << "act_fwhm: " << act_fwhm << " ";
if (act_fwhm < min_fwhm_ || act_fwhm > max_fwhm_)
{
pw_ok = false;
}
// std::cout << pw_ok << std::endl;
}
if (mt_snr_filtering_)
{
if (computeApexSNR(mt) < chrom_peak_snr_)
{
snr_ok = false;
}
}
if (pw_ok && snr_ok)
{
// set label of subtrace
String tr_num;
std::stringstream read_in;
read_in << (mins.size() + 1);
tr_num = "." + read_in.str();
new_mt.setLabel(mt.getLabel() + tr_num);
new_mt.updateSmoothedMaxRT();
new_mt.updateWeightedMeanMZ();
new_mt.updateWeightedMZsd();
if (pw_filtering_ != "fixed")
{
new_mt.estimateFWHM(true);
}
// DoubleReal mt_quality(computeApexSNR(new_mt));
// DoubleReal mt_length(std::fabs(new_mt.rbegin()->getRT() - new_mt.begin()->getRT()));
// if ((mt_length >= min_trace_length_) && (mt_length <= max_trace_length_))
// {
#ifdef _OPENMP
#pragma omp critical
#endif
single_mtraces.push_back(new_mt);
}
// }
}
return;
}