SignalToNoiseEstimatorMeanIterative.h

Go to the documentation of this file.

// Copyright (c) 2002-present, OpenMS Inc. -- EKU Tuebingen, ETH Zurich, and FU Berlin
// SPDX-License-Identifier: BSD-3-Clause
//
// --------------------------------------------------------------------------
// $Maintainer: Chris Bielow $
// $Authors: $
// --------------------------------------------------------------------------
//
 
#pragma once
 
#include <OpenMS/PROCESSING/NOISEESTIMATION/SignalToNoiseEstimator.h>
#include <OpenMS/CONCEPT/Exception.h>
#include <OpenMS/CONCEPT/LogStream.h>
#include <OpenMS/DATASTRUCTURES/TypeAliases.h>
#include <vector>
#include <algorithm> //for std::max_element
 
namespace OpenMS
{
  template <typename Container = MSSpectrum>
  class SignalToNoiseEstimatorMeanIterative :
    public SignalToNoiseEstimator<Container>
  {
 
public:
 
    enum IntensityThresholdCalculation {MANUAL = -1, AUTOMAXBYSTDEV = 0, AUTOMAXBYPERCENT = 1};
 
    using SignalToNoiseEstimator<Container>::stn_estimates_;
    using SignalToNoiseEstimator<Container>::defaults_;
    using SignalToNoiseEstimator<Container>::param_;
 
    typedef typename SignalToNoiseEstimator<Container>::PeakIterator PeakIterator;
    typedef typename SignalToNoiseEstimator<Container>::PeakType PeakType;
 
    typedef typename SignalToNoiseEstimator<Container>::GaussianEstimate GaussianEstimate;
 
 
    inline SignalToNoiseEstimatorMeanIterative()
    {
      //set the name for DefaultParamHandler error messages
      this->setName("SignalToNoiseEstimatorMeanIterative");
 
      defaults_.setValue("max_intensity", -1, "maximal intensity considered for histogram construction. By default, it will be calculated automatically (see auto_mode)." \
                                              " Only provide this parameter if you know what you are doing (and change 'auto_mode' to '-1')!" \
                                              " All intensities EQUAL/ABOVE 'max_intensity' will not be added to the histogram." \
                                              " If you choose 'max_intensity' too small, the noise estimate might be too small as well." \
                                              " If chosen too big, the bins become quite large (which you could counter by increasing 'bin_count', which increases runtime).", {"advanced"});
      defaults_.setMinInt("max_intensity", -1);
 
      defaults_.setValue("auto_max_stdev_factor", 3.0, "parameter for 'max_intensity' estimation (if 'auto_mode' == 0): mean + 'auto_max_stdev_factor' * stdev", {"advanced"});
      defaults_.setMinFloat("auto_max_stdev_factor", 0.0);
      defaults_.setMaxFloat("auto_max_stdev_factor", 999.0);
 
 
      defaults_.setValue("auto_max_percentile", 95, "parameter for 'max_intensity' estimation (if 'auto_mode' == 1): auto_max_percentile th percentile", {"advanced"});
      defaults_.setMinInt("auto_max_percentile", 0);
      defaults_.setMaxInt("auto_max_percentile", 100);
 
      defaults_.setValue("auto_mode", 0, "method to use to determine maximal intensity: -1 --> use 'max_intensity'; 0 --> 'auto_max_stdev_factor' method (default); 1 --> 'auto_max_percentile' method", {"advanced"});
      defaults_.setMinInt("auto_mode", -1);
      defaults_.setMaxInt("auto_mode", 1);
 
      defaults_.setValue("win_len", 200.0, "window length in Thomson");
      defaults_.setMinFloat("win_len", 1.0);
 
      defaults_.setValue("bin_count", 30, "number of bins for intensity values");
      defaults_.setMinInt("bin_count", 3);
 
      defaults_.setValue("stdev_mp", 3.0, "multiplier for stdev", {"advanced"});
      defaults_.setMinFloat("stdev_mp", 0.01);
      defaults_.setMaxFloat("stdev_mp", 999.0);
 
      defaults_.setValue("min_required_elements", 10, "minimum number of elements required in a window (otherwise it is considered sparse)");
      defaults_.setMinInt("min_required_elements", 1);
 
      defaults_.setValue("noise_for_empty_window", std::pow(10.0, 20), "noise value used for sparse windows", {"advanced"});
 
      SignalToNoiseEstimator<Container>::defaultsToParam_();
    }
 
    inline SignalToNoiseEstimatorMeanIterative(const SignalToNoiseEstimatorMeanIterative & source) :
      SignalToNoiseEstimator<Container>(source)
    {
      updateMembers_();
    }
 
    inline SignalToNoiseEstimatorMeanIterative & operator=(const SignalToNoiseEstimatorMeanIterative & source)
    {
      if (&source == this) return *this;
 
      SignalToNoiseEstimator<Container>::operator=(source);
      updateMembers_();
      return *this;
    }
 
 
 
    ~SignalToNoiseEstimatorMeanIterative() override
    {}
 
 
protected:
 
 
    void computeSTN_(const Container& c) override
    {
      //first element in the scan
      PeakIterator scan_first_ = c.begin();
      //last element in the scan
      PeakIterator scan_last_ = c.end();
 
      // reset counter for sparse windows
      double sparse_window_percent = 0;
 
      // reset the results
      stn_estimates_.clear();
      stn_estimates_.resize(c.size());
 
      // maximal range of histogram needs to be calculated first
      if (auto_mode_ == AUTOMAXBYSTDEV)
      {
        // use MEAN+auto_max_intensity_*STDEV as threshold
        GaussianEstimate gauss_global = SignalToNoiseEstimator<Container>::estimate_(scan_first_, scan_last_);
        max_intensity_ = gauss_global.mean + std::sqrt(gauss_global.variance) * auto_max_stdev_Factor_;
      }
      else if (auto_mode_ == AUTOMAXBYPERCENT)
      {
        // get value at "auto_max_percentile_"th percentile
        // we use a histogram approach here as well.
        if ((auto_max_percentile_ < 0) || (auto_max_percentile_ > 100))
        {
          std::string s = StringUtils::toStr(auto_max_percentile_);
          throw Exception::InvalidValue(__FILE__,
                                        __LINE__,
                                        OPENMS_PRETTY_FUNCTION,
                                        "auto_mode is on AUTOMAXBYPERCENT! auto_max_percentile is not in [0,100]. Use setAutoMaxPercentile(<value>) to change it!",
                                        s);
        }
 
        if (c.empty())
        {
          return;
        }
 
        std::vector<int> histogram_auto(100, 0);
 
        // find maximum of current scan
        auto maxIt = std::max_element(c.begin(), c.end() ,[](const PeakType& a, const PeakType& b){ return a.getIntensity() < b.getIntensity();});
        typename PeakType::IntensityType maxInt = maxIt->getIntensity();
 
        double bin_size = maxInt > 0 ? static_cast<double>(maxInt) / 100.0 : 1.0;
 
        // fill histogram
        for (const auto& peak : c)
        {
          const int bin = (int) std::max(0.0, std::min(peak.getIntensity() / bin_size, 99.0));
          ++histogram_auto[bin];
        }
 
        // add up element counts in histogram until ?th percentile is reached
        int elements_below_percentile = std::max(1, (int) (auto_max_percentile_ * c.size() / 100));
        int elements_seen = 0;
        int i = -1;
 
        while (i < 99 && elements_seen < elements_below_percentile)
        {
          ++i;
          elements_seen += histogram_auto[i];
        }
 
        max_intensity_ = (((double)i) + 0.5) * bin_size;
      }
      else   //if (auto_mode_ == MANUAL)
      {
        if (max_intensity_ <= 0)
        {
          std::string s = StringUtils::toStr(max_intensity_);
          throw Exception::InvalidValue(__FILE__,
                                        __LINE__,
                                        OPENMS_PRETTY_FUNCTION,
                                        "auto_mode is on MANUAL! max_intensity is <=0. Needs to be positive! Use setMaxIntensity(<value>) or enable auto_mode!",
                                        s);
        }
      }
 
      if (max_intensity_ < 0)
      {
        OPENMS_LOG_WARN << "SignalToNoiseEstimatorMeanIterative: the max_intensity_ value should be positive! " << max_intensity_ << std::endl;
        return;
      }
 
      PeakIterator window_pos_center  = scan_first_;
      PeakIterator window_pos_borderleft = scan_first_;
      PeakIterator window_pos_borderright = scan_first_;
 
      double window_half_size = win_len_ / 2;
      double bin_size = std::max(1.0, max_intensity_ / bin_count_);   // at least size of 1 for intensity bins
 
      std::vector<int> histogram(bin_count_, 0);
      std::vector<double> bin_value(bin_count_, 0);
      // calculate average intensity that is represented by a bin
      for (int bin = 0; bin < bin_count_; bin++)
      {
        histogram[bin] = 0;
        bin_value[bin] = (bin + 0.5) * bin_size;
      }
      // index of last valid bin during iteration
      int hist_rightmost_bin;
      // bin in which a datapoint would fall
      int to_bin;
      // mean & stdev of the histogram
      double hist_mean;
      double hist_stdev;
 
      // tracks elements in current window, which may vary because of unevenly spaced data
      int elements_in_window = 0;
      int window_count = 0;
 
      double noise;      // noise value of a datapoint
 
      SignalToNoiseEstimator<Container>::startProgress(0, c.size(), "noise estimation of data");
 
      // MAIN LOOP
      while (window_pos_center != scan_last_)
      {
        // erase all elements from histogram that will leave the window on the LEFT side
        while ((*window_pos_borderleft).getMZ() <  (*window_pos_center).getMZ() - window_half_size)
        {
          //std::cout << "S: " << (*window_pos_borderleft).getMZ()  <<  " " << ( (*window_pos_center).getMZ() - window_half_size ) << "\n";
          to_bin = (int) ((std::max((*window_pos_borderleft).getIntensity(), 0.0f)) / bin_size);
          if (to_bin < bin_count_)
          {
            --histogram[to_bin];
            --elements_in_window;
          }
          ++window_pos_borderleft;
        }
 
        //std::printf("S1: %E %E\n", (*window_pos_borderright).getMZ(), (*window_pos_center).getMZ() + window_half_size);
 
 
        // add all elements to histogram that will enter the window on the RIGHT side
        while ((window_pos_borderright != scan_last_)
              && ((*window_pos_borderright).getMZ() < (*window_pos_center).getMZ() + window_half_size))
        {
          //std::printf("Sb: %E %E %E\n", (*window_pos_borderright).getMZ(), (*window_pos_center).getMZ() + window_half_size, (*window_pos_borderright).getMZ() - ((*window_pos_center).getMZ() + window_half_size));
 
          to_bin = (int) ((std::max((*window_pos_borderright).getIntensity(), 0.0f)) / bin_size);
          if (to_bin < bin_count_)
          {
            ++histogram[to_bin];
            ++elements_in_window;
          }
          ++window_pos_borderright;
        }
 
        if (elements_in_window < min_required_elements_)
        {
          noise = noise_for_empty_window_;
          ++sparse_window_percent;
        }
        else
        {
 
          hist_rightmost_bin = bin_count_;
 
          // do iteration on histogram and find threshold
          for (int i = 0; i < 3; ++i)
          {
            // mean
            hist_mean = 0;
            for (int bin = 0; bin < hist_rightmost_bin; ++bin)
            {
              //std::cout << "V: " << bin << " " << hist_mean << " " << histogram[bin] << " " << elements_in_window << " " << bin_value[bin] << "\n";
              // immediate division is numerically more stable
              hist_mean += histogram[bin] / (double) elements_in_window * bin_value[bin];
            }
            //hist_mean = hist_mean / elements_in_window;
 
            // stdev
            hist_stdev = 0;
            for (int bin = 0; bin < hist_rightmost_bin; ++bin)
            {
              double tmp(bin_value[bin] - hist_mean);
              hist_stdev += histogram[bin] / (double) elements_in_window * tmp * tmp;
            }
            hist_stdev = std::sqrt(hist_stdev);
 
            //determine new threshold (i.e. the rightmost bin we consider)
            int estimate = (int) ((hist_mean + hist_stdev * stdev_ - 1) / bin_size + 1);
            //std::cout << "E: " << hist_mean << " " << hist_stdev << " " << stdev_ << " " << bin_size<< " " << estimate << "\n";
            hist_rightmost_bin = std::min(estimate, bin_count_);
          }
 
          // just avoid division by 0
          noise = std::max(1.0, hist_mean);
        }
 
        // store result
        stn_estimates_[window_count] = (*window_pos_center).getIntensity() / noise;
 
 
 
        // advance the window center by one datapoint
        ++window_pos_center;
        ++window_count;
        // update progress
        SignalToNoiseEstimator<Container>::setProgress(window_count);
 
      }   // end while
 
      SignalToNoiseEstimator<Container>::endProgress();
 
      sparse_window_percent = sparse_window_percent * 100 / window_count;
      // warn if percentage of sparse windows is above 20%
      if (sparse_window_percent > 20)
      {
        OPENMS_LOG_WARN << "WARNING in SignalToNoiseEstimatorMeanIterative: "
                        << sparse_window_percent
                        << "% of all windows were sparse. You should consider increasing 'win_len' or increasing 'min_required_elements'"
                        << " You should also check the MaximalIntensity value (or the parameters for its heuristic estimation)"
                        << " If it is too low, then too many high intensity peaks will be discarded, which leads to a sparse window!"
                        << std::endl;
      }
 
      return;
 
    }   // end of shiftWindow_
 
    void updateMembers_() override
    {
      max_intensity_         = (double)param_.getValue("max_intensity");
      auto_max_stdev_Factor_ = (double)param_.getValue("auto_max_stdev_factor");
      auto_max_percentile_   = param_.getValue("auto_max_percentile");
      auto_mode_             = param_.getValue("auto_mode");
      win_len_               = (double)param_.getValue("win_len");
      bin_count_             = param_.getValue("bin_count");
      stdev_                 = (double)param_.getValue("stdev_mp");
      min_required_elements_ = param_.getValue("min_required_elements");
      noise_for_empty_window_ = (double)param_.getValue("noise_for_empty_window");
      stn_estimates_.clear();
    }
 
    double max_intensity_;
    double auto_max_stdev_Factor_;
    double auto_max_percentile_;
    int    auto_mode_;
    double win_len_;
    int    bin_count_;
    double stdev_;
    int min_required_elements_;
    double noise_for_empty_window_;
 
 
 
 
  };
 
} // namespace OpenMS