def test_filter_aa(self): D = GlobalDescriptor( ['GLFDIVKKVVGALG', 'LLLLLL', 'KKKKKKKKKK', 'DDDDDDDDDDDD']) D.calculate_charge() D.filter_aa(['D']) self.assertEqual(D.sequences, ['LLLLLL', 'KKKKKKKKKK']) self.assertEqual(len(D.descriptor), 2)
def analyze_generated(self, num, fname='analysis.txt', plot=False): """ Method to analyze the generated sequences located in `self.generated`. :param num: {int} wanted number of sequences to sample :param fname: {str} filename to save analysis info to :param plot: {bool} whether to plot an overview of descriptors :return: file with analysis info (distances) """ with open(fname, 'w') as f: print("Analyzing...") f.write("ANALYSIS OF SAMPLED SEQUENCES\n==============================\n\n") f.write("Nr. of duplicates in generated sequences: %i\n" % (len(self.generated) - len(set(self.generated)))) count = len(set(self.generated) & set(self.sequences)) # get shared entries in both lists f.write("%.1f percent of generated sequences are present in the training data.\n" % ((count / len(self.generated)) * 100)) d = GlobalDescriptor(self.generated) len1 = len(d.sequences) d.filter_aa('B') len2 = len(d.sequences) d.length() f.write("\n\nLENGTH DISTRIBUTION OF GENERATED DATA:\n\n") f.write("Number of sequences too short:\t%i\n" % (num - len1)) f.write("Number of invalid (with 'B'):\t%i\n" % (len1 - len2)) f.write("Number of valid unique seqs:\t%i\n" % len2) f.write("Mean sequence length: \t\t%.1f ± %.1f\n" % (np.mean(d.descriptor), np.std(d.descriptor))) f.write("Median sequence length: \t\t%i\n" % np.median(d.descriptor)) f.write("Minimal sequence length: \t\t%i\n" % np.min(d.descriptor)) f.write("Maximal sequence length: \t\t%i\n" % np.max(d.descriptor)) descriptor = 'pepcats' seq_desc = PeptideDescriptor([s[1:].rstrip() for s in self.sequences], descriptor) seq_desc.calculate_autocorr(7) gen_desc = PeptideDescriptor(d.sequences, descriptor) gen_desc.calculate_autocorr(7) # random comparison set self.ran = Random(len(self.generated), np.min(d.descriptor), np.max(d.descriptor)) # generate rand seqs probas = count_aas(''.join(seq_desc.sequences)).values() # get the aa distribution of training seqs self.ran.generate_sequences(proba=probas) ran_desc = PeptideDescriptor(self.ran.sequences, descriptor) ran_desc.calculate_autocorr(7) # amphipathic helices comparison set self.hel = Helices(len(self.generated), np.min(d.descriptor), np.max(d.descriptor)) self.hel.generate_sequences() hel_desc = PeptideDescriptor(self.hel.sequences, descriptor) hel_desc.calculate_autocorr(7) # distance calculation f.write("\n\nDISTANCE CALCULATION IN '%s' DESCRIPTOR SPACE\n\n" % descriptor.upper()) desc_dist = distance.cdist(gen_desc.descriptor, seq_desc.descriptor, metric='euclidean') f.write("Average euclidean distance of sampled to training data:\t%.3f +/- %.3f\n" % (np.mean(desc_dist), np.std(desc_dist))) ran_dist = distance.cdist(ran_desc.descriptor, seq_desc.descriptor, metric='euclidean') f.write("Average euclidean distance if randomly sampled seqs:\t%.3f +/- %.3f\n" % (np.mean(ran_dist), np.std(ran_dist))) hel_dist = distance.cdist(hel_desc.descriptor, seq_desc.descriptor, metric='euclidean') f.write("Average euclidean distance if amphipathic helical seqs:\t%.3f +/- %.3f\n" % (np.mean(hel_dist), np.std(hel_dist))) # more simple descriptors g_seq = GlobalDescriptor(seq_desc.sequences) g_gen = GlobalDescriptor(gen_desc.sequences) g_ran = GlobalDescriptor(ran_desc.sequences) g_hel = GlobalDescriptor(hel_desc.sequences) g_seq.calculate_all() g_gen.calculate_all() g_ran.calculate_all() g_hel.calculate_all() sclr = StandardScaler() sclr.fit(g_seq.descriptor) f.write("\n\nDISTANCE CALCULATION FOR SCALED GLOBAL DESCRIPTORS\n\n") desc_dist = distance.cdist(sclr.transform(g_gen.descriptor), sclr.transform(g_seq.descriptor), metric='euclidean') f.write("Average euclidean distance of sampled to training data:\t%.2f +/- %.2f\n" % (np.mean(desc_dist), np.std(desc_dist))) ran_dist = distance.cdist(sclr.transform(g_ran.descriptor), sclr.transform(g_seq.descriptor), metric='euclidean') f.write("Average euclidean distance if randomly sampled seqs:\t%.2f +/- %.2f\n" % (np.mean(ran_dist), np.std(ran_dist))) hel_dist = distance.cdist(sclr.transform(g_hel.descriptor), sclr.transform(g_seq.descriptor), metric='euclidean') f.write("Average euclidean distance if amphipathic helical seqs:\t%.2f +/- %.2f\n" % (np.mean(hel_dist), np.std(hel_dist))) # hydrophobic moments uh_seq = PeptideDescriptor(seq_desc.sequences, 'eisenberg') uh_seq.calculate_moment() uh_gen = PeptideDescriptor(gen_desc.sequences, 'eisenberg') uh_gen.calculate_moment() uh_ran = PeptideDescriptor(ran_desc.sequences, 'eisenberg') uh_ran.calculate_moment() uh_hel = PeptideDescriptor(hel_desc.sequences, 'eisenberg') uh_hel.calculate_moment() f.write("\n\nHYDROPHOBIC MOMENTS\n\n") f.write("Hydrophobic moment of training seqs:\t%.3f +/- %.3f\n" % (np.mean(uh_seq.descriptor), np.std(uh_seq.descriptor))) f.write("Hydrophobic moment of sampled seqs:\t\t%.3f +/- %.3f\n" % (np.mean(uh_gen.descriptor), np.std(uh_gen.descriptor))) f.write("Hydrophobic moment of random seqs:\t\t%.3f +/- %.3f\n" % (np.mean(uh_ran.descriptor), np.std(uh_ran.descriptor))) f.write("Hydrophobic moment of amphipathic seqs:\t%.3f +/- %.3f\n" % (np.mean(uh_hel.descriptor), np.std(uh_hel.descriptor))) if plot: if self.refs: a = GlobalAnalysis([uh_seq.sequences, uh_gen.sequences, uh_hel.sequences, uh_ran.sequences], ['training', 'sampled', 'hel', 'ran']) else: a = GlobalAnalysis([uh_seq.sequences, uh_gen.sequences], ['training', 'sampled']) a.plot_summary(filename=fname[:-4] + '.png')