def windowed_spectrum(mz_array, intensity_array, window_size=1.): mz_min = mz_array.min() mz_max = mz_array.max() step_size = window_size / 2. center_mz = mz_min + step_size center_i = get_nearest(mz_array, center_mz, 1) windows = [] niter = 0 while center_mz < mz_max: lo_mz = center_mz - step_size hi_mz = center_mz + step_size lo_i = get_nearest(mz_array, lo_mz, center_i) hi_i = get_nearest(mz_array, hi_mz, center_i) win = Window(mz_array[lo_i:hi_i + 1], intensity_array[lo_i:hi_i + 1], lo_i, hi_i) win.center_mz = center_mz windows.append(win) center_mz = center_mz + window_size center_i = get_nearest(mz_array, center_mz, center_i) niter += 1 return windows
def find_intersects(self, fit_bin=0): starts = [] ends = [] bin_fit = self.binned_fits[fit_bin] for i, feat_fit in enumerate(self.fits): baseline = self.baselines[i] xs = feat_fit.xs ys = feat_fit.compute_fitted() center_ix = search.get_nearest(xs, bin_fit.center, 0) left_ix = self.find_left_intersect(ys, baseline, center_ix) right_ix = self.find_right_intersect(ys, baseline, center_ix) starts.append(xs[left_ix]) ends.append(xs[right_ix]) return starts, ends
def find_intersects(self, fit_bin=0): starts = [] ends = [] bin_fit = self.binned_fits[fit_bin] for i, feat_fit in enumerate(self.fits): baseline = self.baselines[i] xs = feat_fit.xs ys = feat_fit.compute_fitted() center_ix = search.get_nearest(xs, bin_fit.center, 0) left_ix = self.find_left_intersect(ys, baseline, center_ix) right_ix = self.find_right_intersect(ys, baseline, center_ix) starts.append(xs[left_ix]) ends.append(xs[right_ix]) return starts, ends
def set_up_peak_fit(self, ys=None, min_height=0, peak_count=0): xs = self.xs if ys is None: ys = self.ys params = self.shape_fitter.guess(xs, ys) params_dict = self.shape_fitter.params_to_dict(params) # If the guessed amplitude is less than 0, we are virtually guaranteed to never # improve. if params_dict['amplitude'] < 1: params_dict['amplitude'] = 1 indices = peak_indices(ys, min_height) if len(indices) > 0: center = xs[max(indices, key=lambda x: ys[x])] else: center = xs[len(xs) // 2] params_dict['center'] = center fit = self.shape_fitter.leastsq(xs, ys, list(params_dict.values())) params = fit[0] params_dict = self.shape_fitter.wrap_parameters(params) self.params_dict_list.append(params_dict) residuals = self.shape_fitter.error(params, xs, ys) fitted_apex_index = search.get_nearest(xs, params_dict['center'], 0) fitted_apex = ys[fitted_apex_index] new_min_height = fitted_apex * self.relative_peak_height_threshold if new_min_height < min_height: min_height *= 0.85 else: min_height = new_min_height indices = peak_indices(residuals, min_height) peak_count += 1 if indices.size and peak_count < self.max_peaks: residuals, params_dict = self.set_up_peak_fit( residuals, min_height, peak_count=peak_count) return residuals, params_dict
def set_up_peak_fit(self, ys=None, min_height=0, peak_count=0): xs = self.xs if ys is None: ys = self.ys params = self.shape_fitter.guess(xs, ys) params_dict = self.shape_fitter.params_to_dict(params) indices = peak_indices(ys, min_height) if len(indices) > 0: center = xs[max(indices, key=lambda x: ys[x])] else: center = xs[len(xs) / 2] params_dict['center'] = center fit = leastsq(self.shape_fitter.fit, params_dict.values(), (xs, ys)) params = fit[0] params_dict = FittedPeakShape(self.shape_fitter.params_to_dict(params), self.shape_fitter) self.params_list.append(params) self.params_dict_list.append(params_dict) residuals = self.shape_fitter.fit(params, xs, ys) fitted_apex_index = search.get_nearest(xs, params_dict['center'], 0) fitted_apex = ys[fitted_apex_index] new_min_height = fitted_apex * 0.5 if new_min_height < min_height: min_height *= 0.85 else: min_height = new_min_height indices = peak_indices(residuals, min_height) peak_count += 1 if indices.size and peak_count < self.max_peaks: residuals, params_dict = self.set_up_peak_fit( residuals, min_height, peak_count=peak_count) return residuals, params_dict
def set_up_peak_fit(self, ys=None, min_height=0, peak_count=0): xs = self.xs if ys is None: ys = self.ys params = self.shape_fitter.guess(xs, ys) params_dict = self.shape_fitter.params_to_dict(params) indices = peak_indices(ys, min_height) if len(indices) > 0: center = xs[max(indices, key=lambda x: ys[x])] else: center = xs[len(xs) / 2] params_dict['center'] = center fit = leastsq(self.shape_fitter.fit, params_dict.values(), (xs, ys)) params = fit[0] params_dict = FittedPeakShape(self.shape_fitter.params_to_dict(params), self.shape_fitter) self.params_list.append(params) self.params_dict_list.append(params_dict) residuals = self.shape_fitter.fit(params, xs, ys) fitted_apex_index = search.get_nearest(xs, params_dict['center'], 0) fitted_apex = ys[fitted_apex_index] new_min_height = fitted_apex * 0.5 if new_min_height < min_height: min_height *= 0.85 else: min_height = new_min_height indices = peak_indices(residuals, min_height) peak_count += 1 if indices.size and peak_count < self.max_peaks: residuals, params_dict = self.set_up_peak_fit(residuals, min_height, peak_count=peak_count) return residuals, params_dict
def average_profile_scans(scan_arrays, width=0.01): groups = [[arr.astype(float) for arr in group] for group in scan_arrays] mzs = set() for mz_array, intensity_array in groups: mzs.update(mz_array) mzs = sorted(mzs) mz_out = [] intensity_out = [] _abs = abs _len = len for mz in mzs: cluster_mzs = [] cluster_intensities = [] for group in groups: mz_array, intensity_array = group left_ix = search.get_nearest(mz_array, mz - width, 0) left_mz = mz_array[left_ix] err = (left_mz - (mz - width)) abs_err = _abs(err) if abs_err > width: if err > 0 and left_ix != 0: left_ix -= 1 elif left_ix != _len(mz_array) - 1: left_ix += 1 left_mz = mz_array[left_ix] err = (left_mz - (mz - width)) if _abs(err) > (2 * width): continue right_ix = search.get_nearest(mz_array, mz + width, 0) right_mz = mz_array[right_ix] err = (right_mz - (mz + width)) abs_err = _abs(err) if abs_err > width: if err > 0: right_ix -= 1 elif right_ix != _len(mz_array) - 1: right_ix += 1 right_mz = mz_array[right_ix] err = (right_mz - (mz + width)) abs_err = _abs(err) if abs_err > (2 * width): continue mz_values = mz_array[left_ix:(right_ix + 1)] intensity_values = intensity_array[left_ix:(right_ix + 1)] cluster_mzs.extend(mz_values) cluster_intensities.extend(intensity_values) cluster_mzs = np.array(cluster_mzs) cluster_intensities = np.array(cluster_intensities) ix = np.argsort(cluster_mzs) cluster_mzs = cluster_mzs[ix] cluster_intensities = cluster_intensities[ix] u = np.mean(cluster_mzs) sd = np.std(cluster_mzs) gauss_weights = np.exp(-((cluster_mzs - u) ** 2) / (2 * (sd ** 2))) intensity = (gauss_weights * cluster_intensities).sum() / \ gauss_weights.sum() mz_out.append(mz) intensity_out.append(intensity) return np.array(mz_out, dtype=np.float64), np.array(intensity_out, dtype=np.float64)