def calc_len(self): """Method to get the sequence length of all sequences in the library. :return: {numpy.ndarray} sequence lengths in the attribute :py:attr:`len`. """ for l in range(self.library.shape[0]): d = GlobalDescriptor(self.library[l]) d.length() self.len.append(d.descriptor[:, 0])
def calc_charge(self, ph=7.0, amide=True): """Method to calculate the total molecular charge at a given pH for all sequences in the library. :param ph: {float} ph at which to calculate the peptide charge. :param amide: {boolean} whether the sequences have an amidated C-terminus (-> charge += 1). :return: {numpy.ndarray} calculated charges in the attribute :py:attr:`charge`. """ for l in range(self.library.shape[0]): d = GlobalDescriptor(self.library[l]) d.calculate_charge(ph=ph, amide=amide) self.charge.append(d.descriptor[:, 0])
def analyze_training(self): """ Method to analyze the distribution of the training data :return: prints out information about the length distribution of the sequences in ``self.sequences`` """ d = GlobalDescriptor(self.sequences) d.length() print("\nLENGTH DISTRIBUTION OF TRAINING DATA:\n") print("Number of sequences: \t%i" % len(self.sequences)) print("Mean sequence length: \t%.1f ± %.1f" % (np.mean(d.descriptor), np.std(d.descriptor))) print("Median sequence length: \t%i" % np.median(d.descriptor)) print("Minimal sequence length:\t%i" % np.min(d.descriptor)) print("Maximal sequence length:\t%i" % np.max(d.descriptor))
def generate_features(seq): """ expect a list of sequences (a list of one for single sequence input) return pandas dataframe containing 20 unscaled features 10 from modlamp, 10 from custom feature generateion """ from modlamp.descriptors import GlobalDescriptor custom_features = pd.Series(seq).apply(generate_custom_features) gdesc = GlobalDescriptor(seq) gdesc.calculate_all() modlamp_features = pd.DataFrame(gdesc.descriptor) modlamp_features.columns=gdesc.featurenames out = pd.concat([modlamp_features,custom_features],axis=1) return out
def calculate_peptide_props(fasta_dict): ''' Give a sequence_dictionary (made from get_sequence_dict) returns a list of dictionaries. Each dictionary has type of chemical property as the keys and the calculated value for that property as the value. Designed to be written to a csv file using DictWriter. ''' property_list = [] for header in fasta_dict: s = str(fasta_dict[header].seq) t = GlobalDescriptor([s]) t.calculate_all() d = dict(zip(t.featurenames, t.descriptor[0])) d['Peptide_name'] = header property_list.append(d) return property_list
def insert_phycs(seq_df): # Function for compute Isoelectric Point or net_charge of peptide def get_ieq_nc(seq, is_iep=True): protparam = PA(seq) return protparam.isoelectric_point( ) if is_iep else protparam.charge_at_pH(7.0) # Calculating IsoElectricPoints and NeutralCharge data_size = seq_df.size seq_df['IEP'] = list( map(get_ieq_nc, seq_df['Sequence'], [True] * data_size)) # IsoElectricPoints seq_df['Net Charge'] = list( map(get_ieq_nc, seq_df['Sequence'], [False] * data_size)) # Charge(Neutral) # Calculating hydrophobic moment (My assume all peptides are alpha-helix) descrpt = PeptideDescriptor(seq_df['Sequence'].values, 'eisenberg') descrpt.calculate_moment(window=1000, angle=100, modality='max') seq_df['Hydrophobic Moment'] = descrpt.descriptor.reshape(-1) # Calculating "Hopp-Woods" hydrophobicity descrpt = PeptideDescriptor(seq_df['Sequence'].values, 'hopp-woods') descrpt.calculate_global() seq_df['Hydrophobicity'] = descrpt.descriptor.reshape(-1) # Calculating Energy of Transmembrane Propensity descrpt = PeptideDescriptor(seq_df['Sequence'].values, 'tm_tend') descrpt.calculate_global() seq_df['Transmembrane Propensity'] = descrpt.descriptor.reshape(-1) # Calculating Levitt_alpha_helical Propensity descrpt = PeptideDescriptor(seq_df['Sequence'].values, 'levitt_alpha') descrpt.calculate_global() seq_df['Alpha Helical Propensity'] = descrpt.descriptor.reshape(-1) # Calculating Aliphatic Index descrpt = GlobalDescriptor(seq_df['Sequence'].values) descrpt.aliphatic_index() seq_df['Aliphatic Index'] = descrpt.descriptor.reshape(-1) # Calculating Boman Index descrpt = GlobalDescriptor(seq_df['Sequence'].values) descrpt.boman_index() seq_df['Boman Index'] = descrpt.descriptor.reshape(-1) return seq_df
def _read_header(self): """Priveat method called by ``__init__`` to read all file headers into the class attributes and calculate sequence dependant values. :return: headers in class attributes. """ d = GlobalDescriptor('X') # template # loop through all files in the directory for i, file in enumerate(self.filenames): with open(join( self.directory, file)) as f: # read first 4 lines as header, rest as data head = [next(f) for _ in range(4)] data = [next(f) for _ in range(4, (self.wmax - self.wmin) + 5)] # read headers into class attributes name = head[0].split('\r\n')[0] self.names.append(name) sequence = head[1].split('\r\n')[0].strip() self.sequences.append(sequence) umol = float(head[2].split('\r\n')[0]) self.conc_umol.append(umol) self.solvent.append(head[3].split('\r\n')[0]) # read CD data wlengths = [int(line.split(',')[0]) for line in data] # get rid of s***** line ends ellipts = [ float(line.split(',')[1].split('\r\n')[0]) for line in data ] self.circular_dichroism.append( np.array(list(zip(wlengths, ellipts)))) # calculate MW and transform concentration to mg/ml d.sequences = [sequence] d.calculate_MW(amide=self.amide) self.mw.append(d.descriptor[0][0]) self.conc_mgml.append(self.mw[i] * umol / 10**6) self.meanres_mw.append( self.mw[i] / (len(sequence) - 1)) # mean residue molecular weight (MW / n-1)
def test_filter_values(self): E = GlobalDescriptor( ['GLFDIVKKVVGALG', 'LLLLLL', 'KKKKKKKKKK', 'DDDDDDDDDDDD']) E.calculate_charge() E.filter_values(values=[1.], operator='>=') self.assertEqual(E.sequences, ['KKKKKKKKKK']) self.assertEqual(len(E.descriptor), 1)
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 makeintlistdic_from_allep(dir_name, run_dir): i = 1 intlistdic = {} len_ave_list, pi_ave_list, hyd_ave_list, len_var_list, pi_var_list, hyd_var_list = [ ], [], [], [], [], [] while True: if os.path.exists(dir_name + run_dir + str(i) + '.txt'): len_list_ep, pi_list_ep, hyd_list_ep = [], [], [] seq_size = 0 with open(dir_name + run_dir + str(i) + '.txt') as f: for line in f: seq = line[:-1] seq = GlobalDescriptor(seq) seq.length() len_list_ep.append(seq.descriptor[0][0]) seq.isoelectric_point() pi_list_ep.append(seq.descriptor[0][0]) seq.hydrophobic_ratio() hyd_list_ep.append(seq.descriptor[0][0]) seq_size += 1 len_ave_list.append(round(len(len_list_ep) / seq_size, 3)) pi_ave_list.append(round(len(pi_list_ep) / seq_size, 3)) hyd_ave_list.append(round(len(hyd_list_ep) / seq_size, 3)) len_var_list.append(round(statistics.pvariance(len_list_ep), 3)) pi_var_list.append(round(statistics.pvariance(pi_list_ep), 3)) hyd_var_list.append(round(statistics.pvariance(hyd_list_ep), 3)) i += 1 else: break intlistdic["len_ave"] = len_ave_list intlistdic["pi_ave"] = pi_ave_list intlistdic["hyd_ave"] = hyd_ave_list intlistdic["len_var"] = len_var_list intlistdic["pi_var"] = pi_var_list intlistdic["hyd_var"] = hyd_var_list # print(intlistdic, len(len_ave_list)) return intlistdic
def predict(): if request.method == 'POST': seq = request.form['seq'] with open("random.fasta", "w") as fp: fp.write(seq) pepdesc = PeptideDescriptor( '/home/sanika/proj/random.fasta', 'eisenberg') # use Eisenberg consensus scale globdesc = GlobalDescriptor('/home/sanika/proj/random.fasta') # --------------- Peptide Descriptor (AA scales) Calculations --------------- pepdesc.calculate_global() # calculate global Eisenberg hydrophobicity pepdesc.calculate_moment( append=True) # calculate Eisenberg hydrophobic moment # load other AA scales pepdesc.load_scale('gravy') # load GRAVY scale pepdesc.calculate_global( append=True) # calculate global GRAVY hydrophobicity pepdesc.calculate_moment( append=True) # calculate GRAVY hydrophobic moment pepdesc.load_scale('z3') # load old Z scale pepdesc.calculate_autocorr( 1, append=True) # calculate global Z scale (=window1 autocorrelation) # --------------- Global Descriptor Calculations --------------- globdesc.length() # sequence length globdesc.boman_index(append=True) # Boman index globdesc.aromaticity(append=True) # global aromaticity globdesc.aliphatic_index(append=True) # aliphatic index globdesc.instability_index(append=True) # instability index globdesc.calculate_charge(ph=7.4, amide=False, append=True) # net charge globdesc.calculate_MW(amide=False, append=True) # molecular weight f1 = pepdesc.descriptor f2 = globdesc.descriptor result = np.concatenate((f2, f1), axis=1) clf = joblib.load('ml_model.pkl') pred = clf.predict(result) proba = clf.predict_proba(result).tocoo() mc = pred.tocoo() out = mc.col res = [] labels = ['antiviral', 'antibacterial', 'antifungal'] values = proba.data plt.pie(values, labels=labels, autopct='%.0f%%', shadow=True, radius=0.5) plt.savefig('/home/sanika/proj/pie_chart.jpg') figfile = BytesIO() plt.savefig(figfile, format='png') figfile.seek(0) figdata_png = base64.b64encode(figfile.getvalue()).decode('ascii') plt.close() for i in range(len(out)): if out[i] == 0: res.append("antiviral") elif out[i] == 1: res.append("antibacterial") else: res.append("antifungal") return render_template('seq.html', seq=res, result=figdata_png) return render_template('predictor.html')
def upload(): if request.method == 'POST': # This will be executed on POST request. upfile = request.files['file'] if upfile and allowed_file(upfile.filename): filename = secure_filename(upfile.filename) upfile.save(os.path.join(app.config['UPLOAD_FOLDER'], filename)) #return render_template('upload.html') #flash("File uploaded", "success") #with open("/home/sanika/proj/uploads/aa.fasta") as f: #lines = f.readlines() #lines = [l for l in lines if "ROW" in l] #with open("/home/sanika/proj/uploads/out.fasta", "w") as f1: #f1.writelines(lines) #f = open(filename) #prot_seq = ReadFasta(f) with open(filename) as fasta_file: # Will close handle cleanly identifiers = [] sequence = [] for seq_record in SeqIO.parse(fasta_file, 'fasta'): # (generator) identifiers.append(seq_record.id) sequence.append(seq_record.seq) pepdesc = PeptideDescriptor( filename, 'eisenberg') # use Eisenberg consensus scale globdesc = GlobalDescriptor(filename) # --------------- Peptide Descriptor (AA scales) Calculations --------------- pepdesc.calculate_global( ) # calculate global Eisenberg hydrophobicity pepdesc.calculate_moment( append=True) # calculate Eisenberg hydrophobic moment # load other AA scales pepdesc.load_scale('gravy') # load GRAVY scale pepdesc.calculate_global( append=True) # calculate global GRAVY hydrophobicity pepdesc.calculate_moment( append=True) # calculate GRAVY hydrophobic moment pepdesc.load_scale('z3') # load old Z scale pepdesc.calculate_autocorr( 1, append=True ) # calculate global Z scale (=window1 autocorrelation) # --------------- Global Descriptor Calculations --------------- globdesc.length() # sequence length globdesc.boman_index(append=True) # Boman index globdesc.aromaticity(append=True) # global aromaticity globdesc.aliphatic_index(append=True) # aliphatic index globdesc.instability_index(append=True) # instability index globdesc.calculate_charge(ph=7.4, amide=False, append=True) # net charge globdesc.calculate_MW(amide=False, append=True) # molecular weight f1 = pepdesc.descriptor f2 = globdesc.descriptor result = np.concatenate((f2, f1), axis=1) rs = [] for i in range(len(result)): prt = np.reshape(result[i], (-1, 14)) clf = joblib.load('ml_model.pkl') pred = clf.predict(prt) out = pred.toarray() #print(clf.predict_proba(result)) proba = clf.predict_proba(prt).tocoo() mc = pred.tocoo() out = mc.col res = [] for i in range(len(out)): if out[i] == 0: res.append("antiviral") elif out[i] == 1: res.append("antibacterial") else: res.append("antifungal") rs.append(res) a = [] for i in range(len(rs)): a.append('-'.join(rs[i])) df = pd.DataFrame(data={ "id": identifiers, "sequence": sequence, "activity": a }, columns=['id', 'sequence', 'activity']) df.to_csv("result.csv", sep=',', index=False) os.remove(os.path.join(app.config['UPLOAD_FOLDER'], filename)) #return render_template('seq.html', seq = rs) return render_template('up.html', mimetype="text/csv") #flash("File uploaded: Thanks!", "success") else: error = "PLEASE CHECK THE FORMAT OF FILE TO UPLOAD" return render_template('upload.html', error=error) # This will be executed on GET request. return render_template('predictor.html')
class TestGlobalDescriptor(unittest.TestCase): G = GlobalDescriptor( ['GLFDIVKKVVGALG', 'LLLLLL', 'KKKKKKKKKK', 'DDDDDDDDDDDD']) G2 = GlobalDescriptor(join(dirname(__file__), 'files/lib.fasta')) G3 = GlobalDescriptor(join(dirname(__file__), 'files/lib.csv')) def test_load(self): self.assertEqual('GLFDIVKKVVGALG', self.G.sequences[0]) self.assertEqual('LASKSTSGIGVFGRIRAGLKLKST', self.G2.sequences[2]) self.assertEqual('NPGKSTTRRI', self.G3.sequences[-1]) def test_charge(self): self.G.calculate_charge() self.assertAlmostEqual(self.G.descriptor[0, 0], 0.996, 3) self.G.calculate_charge(amide=True) self.assertAlmostEqual(self.G.descriptor[0, 0], 1.996, 3) self.G.calculate_charge(ph=9.84) self.assertAlmostEqual(self.G.descriptor[0, 0], -0.000, 3) def test_isoelectric(self): self.G.isoelectric_point() self.assertAlmostEqual(self.G.descriptor[0, 0], 9.840, 3) self.G.isoelectric_point(amide=True) self.assertAlmostEqual(self.G.descriptor[0, 0], 10.7090, 4) def test_charge_density(self): self.G.charge_density() self.assertAlmostEqual(self.G.descriptor[0, 0], 0.00070, 4) self.G.charge_density(amide=True) def test_aliphatic_index(self): self.G.aliphatic_index() self.assertAlmostEqual(self.G.descriptor[0, 0], 152.857, 3) def test_boman_index(self): self.G.boman_index() self.assertAlmostEqual(self.G.descriptor[0, 0], -1.0479, 4) 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 test_filter_values(self): E = GlobalDescriptor( ['GLFDIVKKVVGALG', 'LLLLLL', 'KKKKKKKKKK', 'DDDDDDDDDDDD']) E.calculate_charge() E.filter_values(values=[1.], operator='>=') self.assertEqual(E.sequences, ['KKKKKKKKKK']) self.assertEqual(len(E.descriptor), 1) def test_instability_index(self): self.G.instability_index() self.assertAlmostEqual(self.G.descriptor[0, 0], -8.214, 3) def test_length(self): self.G.length() self.assertEqual(self.G.descriptor[0, 0], 14) def test_molweight(self): self.G.calculate_MW() self.assertEqual(self.G.descriptor[0, 0], 1415.72) def test_featurescaling(self): self.G.calculate_charge() self.G.calculate_MW(append=True) self.G.feature_scaling() self.assertAlmostEqual(-5.55111512e-17, np.mean(self.G.descriptor, axis=0).tolist()[0]) self.assertAlmostEqual(1., np.std(self.G.descriptor, axis=0).tolist()[0]) def test_hydroratio(self): self.G.hydrophobic_ratio() self.assertAlmostEqual(0.57142857, self.G.descriptor[0][0]) def test_aromaticity(self): self.G.aromaticity() self.assertAlmostEqual(0.07142857142857142, self.G.descriptor[0][0]) def test_formula(self): self.G.formula(amide=True, append=True) self.assertEqual('C67 H115 N17 O16', self.G.descriptor[0, -1])
#!/usr/bin/env python # -*- coding: utf-8 -*- """ Script to calculate different peptide descriptors for a given sequences.fasta file and save them to two files. """ from modlamp.descriptors import PeptideDescriptor, GlobalDescriptor # Load sequence file into descriptor object pepdesc = PeptideDescriptor('/path/to/sequences.fasta', 'Eisenberg') # use Eisenberg consensus scale globdesc = GlobalDescriptor('/path/to/sequences.fasta') # --------------- Peptide Descriptor (AA scales) Calculations --------------- pepdesc.calculate_global() # calculate global Eisenberg hydrophobicity pepdesc.calculate_moment(append=True) # calculate Eisenberg hydrophobic moment # load other AA scales pepdesc.load_scale('gravy') # load GRAVY scale pepdesc.calculate_global(append=True) # calculate global GRAVY hydrophobicity pepdesc.calculate_moment(append=True) # calculate GRAVY hydrophobic moment pepdesc.load_scale('z3') # load old Z scale pepdesc.calculate_autocorr( 1, append=True) # calculate global Z scale (=window1 autocorrelation) # save descriptor data to .csv file col_names1 = 'ID,Sequence,H_Eisenberg,uH_Eisenberg,H_GRAVY,uH_GRAVY,Z3_1,Z3_2,Z3_3' pepdesc.save_descriptor('/path/to/descriptors1.csv', header=col_names1) # --------------- Global Descriptor Calculations --------------- globdesc.length() # sequence length
ch_den=[] ip=[] ii=[] bi=[] hr=[] ar=[] al=[] for i in arr_motifs: print(i[0]) motif.append(i[0]) arr_len.append(len(i[0])) # charge for i,j in zip(arr_motifs, arr_len): desc = GlobalDescriptor(i[0]) desc.calculate_charge(ph=7.4, amide=True) ch.append(desc.descriptor/j) #hydrophobic ratio for i,j in zip(arr_motifs, arr_len): desc = GlobalDescriptor(i[0]) desc.hydrophobic_ratio() hr.append(desc.descriptor/j) # aromaticity for i,j in zip(arr_motifs, arr_len): desc = GlobalDescriptor(i[0]) desc.aromaticity() ar.append(desc.descriptor/j)
def describe_sequences(): aa_letters = ['A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'Y'] di_letters = ["%s%s" % (a, b) for a in aa_letters for b in aa_letters] letters = {1 : aa_letters, 2 : di_letters} def counter(string, seq_type): ''' A function for counting the number of letters present. Returns a list of (letter, #occurances) tuples. ''' l = len(string) d = {i : 0 for i in letters[seq_type]} if seq_type == 1: for s in string: try: d[s] += 1.0 except KeyError: d[s] = 1.0 d = {k : d[k]/l for k in d} if seq_type == 2: for a in range(l-1): s = string[a:a+seq_type] try: d[s] += 1.0 except KeyError: d[s] = 1.0 d = {k : d[k]/(l-1) for k in d} return d def residue_distribution(all_residues, seq_type): ''' Takes as arguments a string with letters, and the type of sequence represented. Returns an alphabetically ordered string of relative frequencies, correct to three decimal places. ''' d = counter(all_residues, seq_type) residue_counts = list(sorted([(i, d[i]) for i in letters[seq_type] ])) ##Removes ambiguous letters r_c = [i[1] for i in residue_counts] dis = np.array([r_c,]) return dis peptides = [{"seq" : "FLPILASLAAKFGPKLFCLVTKKC", "cTer" : None, "activity" : "YES"}, {"seq" : "ILGPVISTIGGVLGGLLKNL", "cTer" : "Amidation", "activity" : "YES"}, {"seq": "GIGGKILSGLKTALKGAAKELASTYLH", "cTer" : None, "activity" : "NO"}, {"seq": "GIGSAILSAGKSALKGLAKGLAEHFAN", "cTer" : None, "activity" : "NO"}, {"seq": "FLSLIPHAINAVSAIAKHF", "cTer" : "Amidation", "activity" : "NO"}, ] for peptide in peptides: #print(peptide["id"]) #print(peptide["seq"]) globdesc = GlobalDescriptor(peptide["seq"]) globdesc.calculate_all(amide = peptide["cTer"] == "Amidation") #peptide["GlobalDescriptor"] = globdesc #print(peptide["GlobalDescriptor"].descriptor) #Eisenberg hydrophobicity consensus #Take most of the values from here pepdesc = PeptideDescriptor(peptide["seq"], "eisenberg") pepdesc.calculate_global() pepdesc.calculate_moment(append=True) #pepdesc.calculate_profile(append=True, prof_type = "uH") pepdesc.load_scale("Ez") pepdesc.calculate_global(append=True) pepdesc.load_scale("charge_phys") pepdesc.calculate_moment(append=True) pepdesc.calculate_global(append=True) pepdesc.load_scale("flexibility") pepdesc.calculate_moment(append=True) pepdesc.calculate_global(append=True) pepdesc.load_scale("polarity") pepdesc.calculate_moment(append=True) pepdesc.calculate_global(append=True) pepdesc.load_scale("isaeci") pepdesc.calculate_global(append=True) pepdesc.load_scale("refractivity") pepdesc.calculate_moment(append=True) pepdesc.calculate_global(append=True) pepdesc.load_scale("z5") pepdesc.calculate_global(append=True) #peptide["PeptideDescriptor"] = pepdesc peptide["TotalDescriptor"] = str(np.concatenate((pepdesc.descriptor, globdesc.descriptor), axis=1)) try: pepid = np.array([[int(peptide["id"].replace("HEMOLYTIK",""))]]) except KeyError: pepid = np.array([[0]]) freq_1d = residue_distribution(peptide["seq"], 1) freq_2d = residue_distribution(peptide["seq"], 2) len_peptide = np.array([[len(peptide["seq"])]]) if peptide["activity"] == "YES": pepact = 1 else: pepact = 0 pepact = np.array([[pepact]]) peptide_di2 = di2(peptide["seq"]) peptide["array"] = np.concatenate((pepid, pepdesc.descriptor, globdesc.descriptor, len_peptide, freq_1d, #freq_2d, #peptide_di2, pepact,), axis=1) #print(peptide["TotalDescriptor"]) x = np.concatenate([peptide["array"] for peptide in peptides], axis=0) print(x) np.save("hemolytik_array_custom_tests", x, allow_pickle=False)
from modlamp.descriptors import GlobalDescriptor sequences = [] MIC = [] units = [] actives = {} # read the file with 3 columns containing MIC values with open('Saureus.csv', 'r') as f: for line in f: sequences.append(line.split(',')[0]) MIC.append(line.split(',')[1]) units.append(line.split(',')[2]) D = GlobalDescriptor(sequences) D.calculate_MW() MW = D.descriptor.tolist() for i, u in enumerate(units): if u == 'ug/ml\r\n': # find MIC values in ug/mL if '+' in MIC[i]: mic = float(MIC[i].split('+')[0]) + float(MIC[i].split('+')[1]) # if with stdev, take upper bound actives[sequences[i]] = round((mic / float(MW[i][0])) * 1000., 1) # convert ug/mL to uM elif '-' in MIC[i]: mic = float(MIC[i].split('-')[1]) # if with stdev, be conservative and take upper bound actives[sequences[i]] = round((mic / float(MW[i][0])) * 1000., 1) # convert ug/mL to uM else: actives[sequences[i]] = round((float(MIC[i]) / float(MW[i][0])) * 1000., 1) # convert ug/mL to uM s_inactive = [s for s, v in actives.items() if v > 100.0]
charges = coll.defaultdict(list) charges_long = [] charge_densities = coll.defaultdict(list) charge_densities_long = [] polarities = coll.defaultdict(list) polarities_long = [] gravy = coll.defaultdict(list) gravy_long = [] for gp in peptides: # eisenbergs[gp] = get_peptide_values(peptides[gp], 'eisenberg') for val in eisenbergs[gp]: eisenbergs_long.append([gp, val]) # properties = GlobalDescriptor(peptides[gp]) properties.calculate_charge(ph=7.4, amide=True) charges[gp] = [x[0] for x in properties.descriptor] for val in charges[gp]: charges_long.append([gp, val]) # properties = GlobalDescriptor(peptides[gp]) properties.charge_density(ph=7.4, amide=True) charge_densities[gp] = [x[0] for x in properties.descriptor] for val in charge_densities[gp]: charge_densities_long.append([gp, val]) # polarities[gp] = get_peptide_values(peptides[gp], 'polarity') for val in polarities[gp]: polarities_long.append([gp, val]) #
def _add_features_to_peptide_series(self, peptide, index, n_cluster=-1, lpvs=None): # primary intensity weights d = delta, pd = penalty delta # TODO only d_start and d_stop depends on impval, pd_start and pd_stop does not because # they are always between a d_start and d_stop, and should thus be above imp_val! # therefore we can write out d_start as and d_stop as: # [before_start, after_start], [befrore_stop, after_stop] # thus if we have # raw data = [0, 0, 5, 5, 7, 7, 5, 5, 0, 0] # then for the peptide 3--------------8 # before_start, after_start = [ 0, 5 ] # but for the peptide 5--6 # before_start, after_start = [ 5, 7 ] # by making a none linear model we could formulate the w_start parameter as follows: # w_start * (after_start - max(before_start, imp_val)) # which is consistent with how we currently do the grid search (imp_val=4): # d_start = 5 - max(0, 4) = 1 # d_start = 7 - max(5, 4) = 2 if lpvs is None: lpvs = set() i_start = peptide.start.index i_stop = peptide.stop.index # MS Delta series = pd.Series(np.zeros(len(index)) * np.nan, index=index) ms_int = self.ms_intensity_features.type series[ms_int, 'start'] = self.start_scores[i_start] series[ms_int, 'stop'] = self.stop_scores[i_stop] if 4 < len(peptide): penalty = SequenceRange(peptide.start + 1, peptide.stop - 1, validate=False) series[ms_int, 'penalty_start'] = self.start_scores[penalty.slice].sum() series[ms_int, 'penalty_stop'] = self.stop_scores[penalty.slice].sum() else: series[ms_int, 'penalty_start'] = series[ms_int, 'penalty_stop'] = 0 # MS Bool b_obs, f_obs = self._calc_observed(peptide) series[self.ms_bool_features.type, "first"] = self.h_first[i_start] series[self.ms_bool_features.type, "last"] = self.h_last[i_stop] series[self.ms_bool_features.type, "observed"] = b_obs # MS Frequency # ptm weights # TODO: should it get extra penalties if there are PTM's between start and end? ms_freq = self.ms_frequency_features.type series[ms_freq, 'acetylation'] = self.ac_freq[i_start] series[ms_freq, 'amidation'] = self.am_freq[i_stop] series[ms_freq, 'start'] = self.h_start_freq[i_start] series[ms_freq, 'stop'] = self.h_stop_freq[i_stop] series[ms_freq, 'observed'] = f_obs series[ms_freq, 'sample'] = self.h_sample[peptide.slice].min() series[ms_freq, 'ladder'] = \ self.h_ladder_start[i_start] * self.h_ladder_stop[i_stop] series[ms_freq, 'protein_coverage'] = self.protein_coverage series[ms_freq, 'cluster_coverage'] = self.cluster_coverage[n_cluster] # thise are good features, but there may be better ways to extract them series[ms_freq, 'bond'] = self.h_bond[self.get_bond_slice(peptide)].min() # MS Counts ms_count = self.ms_count_features.type series[ms_count, 'start'] = self.start_counts[peptide.start] series[ms_count, 'stop'] = self.stop_counts[peptide.stop] # series[ms_count, 'ladder'] = \ # self.h_ladder_start[i_start] + self.h_ladder_stop[i_stop] ############################################################ # Chemical sequence = self.protein_sequence[peptide.slice] peptide_features = GlobalDescriptor(sequence) is_amidated = series[ms_freq, 'amidation'] > 0.05 peptide_features.calculate_all(amide=is_amidated) chem = self.chemical_features.type for i, name in enumerate(peptide_features.featurenames): if name in self.chemical_features.features: series[chem, name] = peptide_features.descriptor[0, i] eisenberg = PeptideDescriptor(sequence, 'eisenberg') eisenberg.calculate_moment() series[chem, 'eisenberg'] = eisenberg.descriptor.flatten()[0] # Annotations series[self.annotations.type, "Known"] = peptide in self.known_peptides # series[self.annotations.type, "Type"] = peptide in self.known_peptides series[self.annotations.type, "Cluster"] = n_cluster series[self.annotations.type, "Sequence"] = peptide.seq series[self.annotations.type, "LPV"] = False # TODO! series[self.annotations.type, "N Flanking"] = \ self.get_nflanking_region(peptide.start, self.protein_sequence) series[self.annotations.type, "C Flanking"] = \ self.get_cflanking_region(peptide.stop, self.protein_sequence) series[self.annotations.type, "LPV"] = peptide in lpvs if f_obs != 0: _pep_index = (slice(None), slice(None), peptide.start.pos, peptide.stop.pos) series[self.annotations.type, "Intensity"] = self.df.loc[_pep_index, :].sum().sum() return series
def describe_sequences(): path = r"C:\Users\Patrick\OneDrive - University College Dublin\Bioinformatics\HemolyticStudies\BOTH_peptides.json" aa_letters = [ 'A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'Y' ] di_letters = ["%s%s" % (a, b) for a in aa_letters for b in aa_letters] tri_letters = [ "%s%s%s" % (a, b, c) for a in aa_letters for b in aa_letters for c in aa_letters ] conjoint_letters = ["A", "I", "Y", "H", "R", "D", "C"] letters = { 1: aa_letters, 2: di_letters, 3: tri_letters, 4: conjoint_letters } #Conjoint src = https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-015-0828-1 conjoint_dict = { "A": "A", "G": "A", "V": "A", "I": "I", "L": "I", "F": "I", "P": "I", "Y": "Y", "M": "Y", "T": "Y", "S": "Y", "H": "H", "N": "H", "Q": "H", "W": "H", "R": "R", "K": "R", "D": "D", "E": "D", "C": "C", } def counter(string, seq_type): ''' A function for counting the number of letters present. Returns a list of (letter, #occurances) tuples. ''' l = len(string) d = {i: 0 for i in letters[seq_type]} if seq_type == 1: for s in string: try: d[s] += 1.0 except KeyError: d[s] = 1.0 d = {k: d[k] / l for k in d} if seq_type == 2: for a in range(l - 1): s = string[a:a + seq_type] try: d[s] += 1.0 except KeyError: d[s] = 1.0 d = {k: d[k] / (l - 1) for k in d} if seq_type == 3: for a in range(l - 2): s = string[a:a + seq_type] try: d[s] += 1.0 except KeyError: d[s] = 1.0 d = {k: d[k] / (l - 2) for k in d} return d def counter_boolean(string, seq_type): ''' A function for counting the number of letters present. Returns a list of (letter, #occurances) tuples. ''' l = len(string) d = {i: 0 for i in letters[seq_type]} if seq_type == 1: for s in string: try: d[s] = 1.0 except KeyError: d[s] = 1.0 if seq_type == 2: for a in range(l - 1): s = string[a:a + seq_type] try: d[s] = 1.0 except KeyError: d[s] = 1.0 return d def counter_abs(string, seq_type): ''' A function for counting the number of letters present. Returns a list of (letter, #occurances) tuples. ''' l = len(string) d = {i: 0 for i in letters[seq_type]} if seq_type == 1: for s in string: try: d[s] = d[s] + 1.0 except KeyError: d[s] = 1.0 if seq_type == 2: for a in range(l - 1): s = string[a:a + seq_type] try: d[s] = d[s] + 1.0 except KeyError: d[s] = 1.0 return d def residue_distribution(all_residues, seq_type, dp): ''' Takes as arguments a string with letters, and the type of sequence represented. Returns an alphabetically ordered string of relative frequencies, correct to three decimal places. ''' d = counter(all_residues, seq_type) if seq_type == 1: residue_counts = list( sorted([(i, d[i]) for i in letters[seq_type] ])) ##Removes ambiguous letters elif seq_type == 2: residue_counts = list( sorted([(i, d[i]) for i in letters[seq_type] if dp[i] >= 50])) elif seq_type == 3: residue_counts = list( sorted([(i, d[i]) for i in letters[seq_type] if tp[i] >= 20])) elif seq_type == 4: residue_counts = list( sorted([(i, d[i]) for i in letters[seq_type]])) r_c = [i[1] for i in residue_counts] dis = np.array([ r_c, ]) return dis def residue_boolean(all_residues, seq_type, dp): ''' Takes as arguments a string with letters, and the type of sequence represented. Returns an alphabetically ordered string of relative frequencies, correct to three decimal places. ''' d = counter_boolean(all_residues, seq_type) if seq_type == 1: residue_counts = list( sorted([(i, d[i]) for i in letters[seq_type] ])) ##Removes ambiguous letters elif seq_type == 2: residue_counts = list( sorted([(i, d[i]) for i in letters[seq_type] if dp[i] >= 50])) r_c = [i[1] for i in residue_counts] dis = np.array([ r_c, ]) return dis def residue_abs(all_residues, seq_type, dp): ''' Takes as arguments a string with letters, and the type of sequence represented. Returns an alphabetically ordered string of relative frequencies, correct to three decimal places. ''' d = counter_abs(all_residues, seq_type) if seq_type == 1: residue_counts = list( sorted([(i, d[i]) for i in letters[seq_type] ])) ##Removes ambiguous letters elif seq_type == 2: residue_counts = list( sorted([(i, d[i]) for i in letters[seq_type] if dp[i] >= 50])) r_c = [i[1] for i in residue_counts] dis = np.array([ r_c, ]) return dis with open(path, "r") as f: text = f.read() peptides = eval(text)["Peptides"] train_peptides, test_peptides = train_test_split(peptides, test_size=0.15, random_state=42) train_peptides_seqs = [peptide["seq"] for peptide in train_peptides] for peptide in peptides: if peptide["seq"] in train_peptides_seqs: peptide["train"] = True else: peptide["train"] = False print(len([p for p in peptides if p["train"] == True])) print(len([p for p in peptides if p["train"] == False])) new_peptides = [] for peptide in peptides: if peptide["train"] == True: new_peptide = peptide.copy() new_seq = ''.join(reversed(peptide["seq"])) new_peptide["seq"] = new_seq new_peptides.append(new_peptide) #peptides.extend(new_peptides) random.shuffle(peptides) print(len([p for p in peptides if p["train"] == True])) print(len([p for p in peptides if p["train"] == False])) print("doubling complete") dp = {i: 0 for i in letters[2]} tp = {i: 0 for i in letters[3]} name_i = 0 for peptide in peptides: temp_set = set() seq = peptide["seq"] l = len(seq) for a in range(l - 1): s = seq[a:a + 2] temp_set.add(s) for s in temp_set: dp[s] = dp[s] + 1 for peptide in peptides: temp_set = set() seq = peptide["seq"] l = len(seq) for a in range(l - 2): s = seq[a:a + 3] temp_set.add(s) for s in temp_set: tp[s] = tp[s] + 1 for peptide in peptides: peptide["conjoint_seq"] = "".join( [conjoint_dict[letter] for letter in peptide["seq"]]) for peptide in peptides: globdesc = GlobalDescriptor(peptide["seq"]) globdesc.calculate_all(amide=peptide["cTer"] == "Amidation") ctdc = CTD.CalculateC(peptide["seq"]) ctdc_keys = list(sorted(list([key for key in ctdc]))) ctdc_vals = np.array([[ctdc[key] for key in ctdc_keys]]) conjointtriad = ConjointTriad.CalculateConjointTriad(peptide["seq"]) conjointtriad_keys = list(sorted(list([key for key in conjointtriad]))) conjointtriad_vals = np.array( [[conjointtriad[key] for key in conjointtriad_keys]]) conjoint_dis = residue_distribution(peptide["conjoint_seq"], 4, None) #peptide["GlobalDescriptor"] = globdesc #print(peptide["GlobalDescriptor"].descriptor) #Eisenberg hydrophobicity consensus #Take most of the values from here pepdesc = PeptideDescriptor(peptide["seq"], "eisenberg") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) #pepdesc.calculate_profile(append=True, prof_type = "uH") pepdesc.load_scale("Ez") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("aasi") pepdesc.calculate_global(append=True) pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.load_scale("abhprk") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("charge_acid") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.load_scale("cougar") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("gravy") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.load_scale("hopp-woods") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.load_scale("kytedoolittle") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.load_scale("ppcali") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("msw") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("charge_phys") pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("flexibility") pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("bulkiness") pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("TM_tend") pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("mss") pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("t_scale") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("peparc") pepdesc.calculate_arc(modality="max", append=True) pepdesc.calculate_arc(modality="mean", append=True) pepdesc.load_scale("msw") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("polarity") pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("pepcats") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("isaeci") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("refractivity") pepdesc.calculate_moment(modality="max", append=True) pepdesc.calculate_moment(modality="mean", append=True) pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("z3") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) pepdesc.load_scale("z5") pepdesc.calculate_global(modality="mean", append=True) pepdesc.calculate_global(modality="max", append=True) #pepdesc.load_scale("PPCALI") #pepdesc.calculate_autocorr(2) #peptide["PeptideDescriptor"] = pepdesc protein = PyPro() protein.ReadProteinSequence(peptide["seq"]) paac = protein.GetPAAC(lamda=1, weight=0.05) paac2 = [[ paac[a] for a in list( sorted([k for k in paac], key=lambda x: int(x.replace("PAAC", "")))) ]] cTer = np.array([[1 if peptide["cTer"] == "Amidation" else 0]]) paac = np.array(paac2) analysed_seq = ProteinAnalysis(peptide["seq"]) secondary_structure_fraction = np.array( [analysed_seq.secondary_structure_fraction()]) peptide["TotalDescriptor"] = str( np.concatenate((pepdesc.descriptor, globdesc.descriptor), axis=1)) try: pepid = np.array([[ int(peptide["id"].replace("HEMOLYTIK", "").replace( "DRAMP", "").replace("DBAASP", "")) ]]) except KeyError: pepid = 0 pep_train = np.array([[1 if peptide["train"] == True else 0]]) freq_1d = residue_distribution(peptide["seq"], 1, dp) freq_2d = residue_distribution(peptide["seq"], 2, dp) freq_3d = residue_distribution(peptide["seq"], 3, dp) freq_1dbool = residue_boolean(peptide["seq"], 1, dp) freq_2dbool = residue_boolean(peptide["seq"], 2, dp) freq_1dabs = residue_abs(peptide["seq"], 1, dp) freq_2dabs = residue_abs(peptide["seq"], 2, dp) len_peptide = np.array([[len(peptide["seq"])]]) if peptide["activity"] == "YES": pepact = 1 else: pepact = 0 pepact = np.array([[pepact]]) peptide_di2 = di2(peptide["seq"]) peptide_di3 = di3(peptide["conjoint_seq"]) ####################### AAindex ######################### to_get = [ ("CHAM810101", "mean"), #Steric Hinderance ("CHAM810101", "total"), #Steric Hinderance ("KYTJ820101", "mean"), #Hydropathy ("KLEP840101", "total"), #Charge ("KLEP840101", "mean"), #Charge ("MITS020101", "mean"), #Amphiphilicity ("FAUJ830101", "mean"), #Hydrophobic parameter pi ("GOLD730102", "total"), #Residue volume ("MEEJ800101", "mean"), #Retention coefficient in HPLC ("OOBM850105", "mean"), #Optimized side chain interaction parameter ("OOBM850105", "total"), #Optimized side chain interaction parameter ("VELV850101", "total"), #Electron-ion interaction parameter ("VELV850101", "mean"), #Electron-ion interaction parameter ("PUNT030102", "mean"), #Knowledge-based membrane-propensity scale from 3D_Helix ("BHAR880101", "mean"), #Average flexibility indeces ("KRIW790102", "mean"), #Fraction of site occupied by water ("PLIV810101", "mean"), #Partition coefficient ("ZIMJ680102", "mean"), #Bulkiness ("ZIMJ680102", "total"), #Bulkiness ("ZHOH040101", "mean"), #Stability scale ("CHAM820102", "total"), #Free energy solubility in water #From HemoPi: src = https://github.com/riteshcanfly/Hemopi/blob/master/pcCalculator.java ("HOPT810101", "mean"), #Hydrophilicity ("EISD840101", "mean"), #Hydrophobicity ("FAUJ880109", "total"), #Net Hydrogen ("EISD860101", "mean"), #Solvation ] tetra_peptides = [ "KLLL", # src = https://github.com/riteshcanfly/Hemopi/blob/master/tetrapos.txt "GCSC", "AAAK", "KLLS", "LGKL", "VLKA", "LLGK", "LVGA", "LSDF", "SDFK", "SWLR", "WLRD", ] tp_bin = [] for t_p in tetra_peptides: if t_p in peptide["seq"]: tp_bin.append(1) else: tp_bin.append(0) tp_bin = np.array([tp_bin]) for identifier, mode in to_get: x = aaf(peptide["seq"], identifier, mode) aminoacidindeces = np.array([[ aaf(peptide["seq"], identifier, mode) for identifier, mode in to_get ]]) peptide["array"] = np.concatenate( ( pepid, pep_train, pepdesc.descriptor, globdesc.descriptor, len_peptide, cTer, secondary_structure_fraction, aminoacidindeces, ctdc_vals, conjointtriad_vals, tp_bin, freq_1d, freq_2d, freq_3d, freq_1dbool, freq_2dbool, freq_1dabs, freq_2dabs, peptide_di2, peptide_di3, #Conjoint Alphabet paac, pepact, ), axis=1) #print(peptide["TotalDescriptor"]) x = np.concatenate([peptide["array"] for peptide in peptides], axis=0) np.save("peptides_array", x, allow_pickle=False)
import pandas as pd import sys from modlamp.descriptors import PeptideDescriptor, GlobalDescriptor database = pd.read_csv(sys.argv[1]) path_output = sys.argv[2] print("Estimate formula") #get formula for each sequence formula_array = [] for i in range(len(database)): try: desc = GlobalDescriptor([database['Sequence'][i]]) desc.formula(amide=True) for v in desc.descriptor: formula_array.append(v[0]) except: formula_array.append('') database['formula'] = formula_array print("Estimate molecular_weigth") #get MW for each sequence molecular_weigth_array = [] for i in range(len(database)): try: desc = GlobalDescriptor([database['Sequence'][i]])
def propi(): des_fis = GlobalDescriptor(seq) des_fis.calculate_all() prop_fis = des_fis.descriptor # Composición de aminoácidos amino_comp = map(AC.CalculateAAComposition, seq) # AA dipep_comp = map(AC.CalculateDipeptideComposition, seq) # Dipéptidos # Autocorrelación moreau_auto = map(auto.CalculateNormalizedMoreauBrotoAutoTotal, seq) # Moreau moran_auto = map(auto.CalculateMoranAutoTotal, seq) # Moran geary_auto = map(auto.CalculateGearyAutoTotal, seq) # Geary # Composition - Distribution - Transition ctd = map(CTD.CalculateCTD, seq) # QuasiSequence sqa = map(lambda p: qua.GetQuasiSequenceOrder(p, maxlag=5, weight=0.1), seq) secq = map(lambda p: qua.GetSequenceOrderCouplingNumber(p, d=1), seq) amino_comp = pd.DataFrame.from_dict(amino_comp) amino_comp.reset_index(drop=True, inplace=True) dipep_comp = pd.DataFrame.from_dict(dipep_comp) dipep_comp.reset_index(drop=True, inplace=True) moreau_auto = pd.DataFrame.from_dict(moreau_auto) moreau_auto.reset_index(drop=True, inplace=True) moran_auto = pd.DataFrame.from_dict(moran_auto) moran_auto.reset_index(drop=True, inplace=True) geary_auto = pd.DataFrame.from_dict(geary_auto) geary_auto.reset_index(drop=True, inplace=True) ctd = pd.DataFrame.from_dict(ctd) ctd.reset_index(drop=True, inplace=True) # PseudoAAC - Tipo I Hydrophobicity = PAAC._Hydrophobicity hydrophilicity = PAAC._hydrophilicity residuemass = PAAC._residuemass pK1 = PAAC._pK1 pK2 = PAAC._pK2 pI = PAAC._pI clasI_pse = map( lambda p: PAAC.GetPseudoAAC( p, lamda=3, weight=0.7, AAP=[Hydrophobicity, hydrophilicity, residuemass, pK1, pK2, pI]), seq) clasI_pse = pd.DataFrame.from_dict(clasI_pse) clasI_pse.reset_index(drop=True, inplace=True) sqa = pd.DataFrame.from_dict(sqa) sqa.reset_index(drop=True, inplace=True) secq = pd.DataFrame.from_dict(secq) secq.reset_index(drop=True, inplace=True) prop_fis = pd.DataFrame(prop_fis) prop_fis.columns = [ 'Longitud', 'MW', 'Carga', 'DensCarga', 'pIso', 'InestInd', 'Aroma', 'Alifa', 'Boman', 'HidroRa' ] var = pd.concat([ amino_comp, dipep_comp, moreau_auto, moran_auto, ctd, clasI_pse, sqa, secq, geary_auto, prop_fis ], axis=1) return var
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')
def exec(peptide, time_node): file = open("../src/public/jobs/service1/service1.fasta", "w") file.write(peptide) file.close() fasta = SeqIO.parse("../src/public/jobs/service1/service1.fasta", "fasta") if(any(fasta) == False): #False when `fasta` is empty return "error" cantidad = 0 for record in SeqIO.parse("../src/public/jobs/service1/service1.fasta", "fasta"): cantidad = cantidad+1 if (cantidad == 1): properties = {} for record in SeqIO.parse("../src/public/jobs/service1/service1.fasta", "fasta"): properties[str(record.id)] = {} #save properties properties[str(record.id)]["length"] = len(record.seq) #formula try: desc = GlobalDescriptor(str(record.seq)) desc.formula(amide=True) properties[str(record.id)]["formula"] = desc.descriptor[0][0] except: properties[str(record.id)]["formula"] = "-" #molecular weigth try: desc = GlobalDescriptor(str(record.seq)) desc.calculate_MW(amide=True) properties[str(record.id)]["molecular_weigth"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["molecular_weigth"] = "-" #boman_index try: desc = GlobalDescriptor(str(record.seq)) desc.boman_index() properties[str(record.id)]["boman_index"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["boman_index"] = "-" #charge try: desc = GlobalDescriptor(str(record.seq)) desc.calculate_charge(ph=7, amide=True) properties[str(record.id)]["charge"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["charge"] = "-" #charge density try: desc = GlobalDescriptor(str(record.seq)) desc.charge_density(ph=7, amide=True) properties[str(record.id)]["charge_density"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["charge_density"] = "-" #estimate isoelectric point try: desc = GlobalDescriptor(str(record.seq)) desc.isoelectric_point() properties[str(record.id)]["isoelectric_point"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["isoelectric_point"] = "-" #estimate inestability index try: desc = GlobalDescriptor(str(record.seq)) desc.instability_index() properties[str(record.id)]["instability_index"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["instability_index"] = "-" #estimate aromaticity try: desc = GlobalDescriptor(str(record.seq)) desc.aromaticity() properties[str(record.id)]["aromaticity"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["aromaticity"] = "-" #estimate aliphatic_index try: desc = GlobalDescriptor(str(record.seq)) desc.aliphatic_index() properties[str(record.id)]["aliphatic_index"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["aliphatic_index"] = "-" #estimate hydrophobic_ratio try: desc = GlobalDescriptor(str(record.seq)) desc.hydrophobic_ratio() properties[str(record.id)]["hydrophobic_ratio"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["hydrophobic_ratio"] = "-" #profile hydrophobicity try: desc = PeptideDescriptor(str(record.seq), scalename='Eisenberg') desc.calculate_profile(prof_type='H') properties[str(record.id)]["hydrophobicity_profile"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["hydrophobicity_profile"] = "-" #profile hydrophobic try: desc = PeptideDescriptor(str(record.seq), scalename='Eisenberg') desc.calculate_profile(prof_type='uH') properties[str(record.id)]["hydrophobic_profile"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["hydrophobic_profile"] = "-" #moment try: desc = PeptideDescriptor(str(record.seq), scalename='Eisenberg') desc.calculate_moment() properties[str(record.id)]["calculate_moment"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["calculate_moment"] = "-" try: os.mkdir("../src/public/jobs/service1/"+time_node) except: print("Error") #generate plot profile plot_profile(str(record.seq), scalename='eisenberg', filename= "../src/public/jobs/service1/"+time_node+"/profile.png") #generate helical wheel helical_wheel(str(record.seq), colorcoding='charge', lineweights=False, filename= "../src/public/jobs/service1/"+time_node+"/helical.png") return(properties) if (cantidad > 1): properties = {} for record in SeqIO.parse("../src/public/jobs/service1/service1.fasta", "fasta"): properties[str(record.id)] = {} properties[str(record.id)]["length"] = len(record.seq) #formula try: desc = GlobalDescriptor(str(record.seq)) desc.formula(amide=True) properties[str(record.id)]["formula"] = desc.descriptor[0][0] except: properties[str(record.id)]["formula"] = "-" #molecular weigth try: desc = GlobalDescriptor(str(record.seq)) desc.calculate_MW(amide=True) properties[str(record.id)]["molecular_weigth"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["molecular_weigth"] = "-" #boman_index try: desc = GlobalDescriptor(str(record.seq)) desc.boman_index() properties[str(record.id)]["boman_index"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["boman_index"] = "-" #charge try: desc = GlobalDescriptor(str(record.seq)) desc.calculate_charge(ph=7, amide=True) properties[str(record.id)]["charge"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["charge"] = "-" #charge density try: desc = GlobalDescriptor(str(record.seq)) desc.charge_density(ph=7, amide=True) properties[str(record.id)]["charge_density"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["charge_density"] = "-" #estimate isoelectric point try: desc = GlobalDescriptor(str(record.seq)) desc.isoelectric_point() properties[str(record.id)]["isoelectric_point"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["isoelectric_point"] = "-" #estimate inestability index try: desc = GlobalDescriptor(str(record.seq)) desc.instability_index() properties[str(record.id)]["instability_index"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["instability_index"] = "-" #estimate aromaticity try: desc = GlobalDescriptor(str(record.seq)) desc.aromaticity() properties[str(record.id)]["aromaticity"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["aromaticity"] = "-" #estimate aliphatic_index try: desc = GlobalDescriptor(str(record.seq)) desc.aliphatic_index() properties[str(record.id)]["aliphatic_index"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["aliphatic_index"] = "-" #estimate hydrophobic_ratio try: desc = GlobalDescriptor(str(record.seq)) desc.hydrophobic_ratio() properties[str(record.id)]["hydrophobic_ratio"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["hydrophobic_ratio"] = "-" #profile hydrophobicity try: desc = PeptideDescriptor(str(record.seq), scalename='Eisenberg') desc.calculate_profile(prof_type='H') properties[str(record.id)]["hydrophobicity_profile"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["hydrophobicity_profile"] = "-" #profile hydrophobic try: desc = PeptideDescriptor(str(record.seq), scalename='Eisenberg') desc.calculate_profile(prof_type='uH') properties[str(record.id)]["hydrophobic_profile"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["hydrophobic_profile"] = "-" #moment try: desc = PeptideDescriptor(str(record.seq), scalename='Eisenberg') desc.calculate_moment() properties[str(record.id)]["calculate_moment"] = float("%.4f" % desc.descriptor[0][0]) except: properties[str(record.id)]["calculate_moment"] = "-" return(properties)
len_list = [] aacomp_diclist = [] pi_list = [] hyd_list = [] ctd_diclist = [] header_list = [] # row_list.append("\n") row_list.append("\n" + run_dir + file_name) for line in f: seq = line[:-1] DesObject = PyPro.GetProDes(seq) if do_length: len_list.append(len(seq)) if do_pi: glob_seq = GlobalDescriptor(seq) glob_seq.isoelectric_point() pi_list.append(glob_seq.descriptor[0][0]) if do_hyd: glob_seq = GlobalDescriptor(seq) glob_seq.hydrophobic_ratio() hyd_list.append(glob_seq.descriptor[0][0]) if do_aacomp: aacomp_diclist.append(DesObject.GetAAComp()) if do_ctd: # calculate 147 CTD descriptors # Default: False ctd_diclist.append(DesObject.GetCTD()) if file_name == real_file: run_dir = real_file + "/"
"""Some more features other than amino acid composition of each amino acid in sequence""" newFeatures = [ 'MW', 'ChargeDensity', 'pI', 'InstabilityInd', 'Aromaticity', 'AliphaticInd', 'BomanInd', 'HydRatio' ] #writing feature names in excel sheet for i in range(cols + len(aminoAcid) + 1, cols + len(aminoAcid) + len(newFeatures) + 1): writingSheet.cell( row=1, column=i).value = newFeatures[i - (cols + len(aminoAcid) + 1)] for i in range(2, rows + 1): #filling feature value in excel sheet pepSequencee = readingSheet.cell(row=i, column=cols).value desc = GlobalDescriptor(pepSequencee) desc.calculate_all(amide=True) array = desc.descriptor.tolist() countt = 1 for j in range(cols + len(aminoAcid) + 1, cols + len(aminoAcid) + 1 + len(newFeatures)): writingSheet.cell(row=i, column=j).value = float(array[0][countt]) countt += 1 writingBook.save(str(outputFile)) #saving all data to output file ##################################################################TESTING DATA#################################################### trainingData = pd.read_csv(r"test.csv") #reading CSV training data trainingData.to_excel(r"test.xlsx", index=None, header=True) #converting CSV to Excel