Esempio n. 1
0
// approximately unimodal under most pictures of the world
// scan at maximum and build up a picture of the likelihood using log(n)*constant measurements, interpolate to linearize
void PosteriorInference::InterpolateFrequencyScan(ShortStack &total_theory, bool update_frequency, int strand_key) {
  
  unsigned int num_reads = ResizeToMatch(total_theory);
  
  float fnum_reads = (float) num_reads;

  UpdateMaxFreqFromResponsibility(total_theory, strand_key);

  int eval_start = (int)(max_freq * num_reads);
  vector<unsigned int> samples;
  FibInterval(samples, eval_start, num_reads);
  unsigned int i_last = 0;
  eval_at_frequency[i_last] = (float)i_last / fnum_reads;
  log_posterior_by_frequency[i_last] = total_theory.PosteriorFrequencyLogLikelihood(eval_at_frequency[i_last], data_reliability, strand_key);
  int bottom = log_posterior_by_frequency[i_last];
  int top = bottom;
  for (unsigned int i_dx = 1; i_dx < samples.size(); i_dx++) {
    unsigned int i_eval = samples[i_dx];
    eval_at_frequency[i_eval] = (float)i_eval / fnum_reads;
    log_posterior_by_frequency[i_eval] = total_theory.PosteriorFrequencyLogLikelihood(eval_at_frequency[i_eval],data_reliability, strand_key);
    top = log_posterior_by_frequency[i_eval];
    for (unsigned int i_mid = i_last + 1; i_mid < i_eval; i_mid++) {
      int delta_low = i_mid - i_last;
      int delta_hi = i_eval - i_last;
      eval_at_frequency[i_mid] = (float)i_mid / fnum_reads;
      log_posterior_by_frequency[i_mid] = (top * delta_low + bottom * delta_hi) / (delta_low + delta_hi);
    }
    bottom = top;
    i_last = i_eval;

  }
  FindMaxFrequency(update_frequency);
  scan_done = true;

};
Esempio n. 2
0
// do a hard classification as though the reads were independent
// i.e. look more like the data in the BAM file
void PosteriorInference::StartAtHardClassify(ShortStack &total_theory, bool update_frequency, float start_frequency) {
  // just to allocate
  ResizeToMatch(total_theory);
  if (update_frequency) {
    max_freq = start_frequency;
    max_ll = total_theory.PosteriorFrequencyLogLikelihood(max_freq, data_reliability, ALL_STRAND_KEY);
  } 
  total_theory.UpdateResponsibility(max_freq, data_reliability);
}
Esempio n. 3
0
void PosteriorInference::DoPosteriorFrequencyScan(ShortStack &total_theory, bool update_frequency, int strand_key) {
//cout << "ScanningFrequency" << endl;
// posterior frequency inference given current data/likelihood pairing
  unsigned int num_reads = ResizeToMatch(total_theory);

  float fnum_reads = (float) num_reads;
  for (unsigned int i_eval = 0; i_eval < eval_at_frequency.size(); i_eval++) {
    eval_at_frequency[i_eval] = (float)i_eval / fnum_reads;
    log_posterior_by_frequency[i_eval] = total_theory.PosteriorFrequencyLogLikelihood(eval_at_frequency[i_eval], data_reliability, strand_key);
  }
  // if doing monomorphic eval, set frequency to begin with and don't update
  FindMaxFrequency(update_frequency);
  scan_done = true;
// log_posterior now contains all frequency information inferred from the data
}
Esempio n. 4
0
void PosteriorInference::UpdateMaxFreqFromResponsibility(ShortStack &total_theory, int strand_key) {
  // skip time consuming scan and use responsibilities as cluster entry
  float max_freq = total_theory.FrequencyFromResponsibility(strand_key);
  max_ll = total_theory.PosteriorFrequencyLogLikelihood(max_freq, data_reliability, strand_key);
  scan_done = false; // didn't come from scan
}