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; }
DPosition<2> p1(11.0f,12.1f); TEST_REAL_SIMILAR(p1[0],11.0f); TEST_REAL_SIMILAR(p1[1],12.1f); DPosition<2> p(12.34,56.78); TEST_REAL_SIMILAR(p[0], 12.34) TEST_REAL_SIMILAR(p[1], 56.78) END_SECTION START_SECTION((CoordinateType getX() const)) DPosition<2> p1(11.0f,12.1f); TEST_REAL_SIMILAR(p1.getX(),11.0f); END_SECTION START_SECTION((CoordinateType getY() const)) DPosition<2> p1(11.0f,12.1f); TEST_REAL_SIMILAR(p1.getY(),12.1f); END_SECTION START_SECTION((void setX(CoordinateType c))) DPosition<2> p1(11.0f,12.1f); p1.setX(5.0f); TEST_REAL_SIMILAR(p1[0],5.0f); TEST_REAL_SIMILAR(p1[1],12.1f); END_SECTION START_SECTION((void setY(CoordinateType c))) DPosition<2> p1(11.0f,12.1f); p1.setY(5.0f); TEST_REAL_SIMILAR(p1[0],11.0f); TEST_REAL_SIMILAR(p1[1],5.0f); END_SECTION