def init(): global html_path html_path = "../results" global compound2smiles compound2smiles = util.parse_dat("../metacyc/compounds.dat", "UNIQUE-ID", "SMILES") global atom_types atom_types = ['C', 'N', 'O', 'P', 'S'] #global bond_types; bond_types = range(5) global bond_types bond_types = range(4) global motif_sizes motif_sizes = range(2, 7) global log_zero log_zero = -800.0 global compound2graph compound2graph = {} for compound in compound2smiles.keys(): try: compound2graph[compound] = chemconvert.molfile2graph("../mol/" + compound + ".mol") except Exception: pass return
def convert_compounds_hash(compound_dat_filename): compound2hash = util.parse_dat(compound_dat_filename, "UNIQUE-ID", "HASH") util._mkdir("../mol") for (key, smiles) in compound2hash.iteritems(): mol_filename = "../mol/" + key + ".mol" if (not os.path.exists(mol_filename)): print "Writing a MOL file to: " + mol_filename if (len(smiles) > 0): mol = chemconvert.hash2graph(smiles[0]).to_mol() mol_file = open(mol_filename, "w") mol_file.write(mol) mol_file.close() else: print "Found the MOL file: " + mol_filename return
def main(): import argparse parser = argparse.ArgumentParser() parser.add_argument('identifier', help='Identifier name e.g. cne.100899.FST.') parser.add_argument('-f', '--file', nargs='?', type=argparse.FileType('r'), default=sys.stdin, help='Input file e.g. d2z.dat.') parser.add_argument('--extra_data', type=argparse.FileType('r'), default='hg18.toDanRer5.seqs.txt', help='Extra data file e.g. hg18.toDanRer5.seqs.txt.') parser.add_argument('--valid', type=int, default=9, help='Field number of valid test coordinates.') OPTS = parser.parse_args() cne_dict = parse_dat(read_fields(f=OPTS.file)) line_tups = read_fields(f=OPTS.extra_data) cne_valids = {} for l in line_tups: danrer_co, valid_co = parse_coords(l[4]), parse_coords(l[OPTS.valid-1]) valid_indices = (valid_co['start'] - danrer_co['start'], valid_co['end'] - danrer_co['start']) cne_valids[l[0]] = valid_indices plot_cne(OPTS.identifier, cne_dict[OPTS.identifier], cne_valids[OPTS.identifier])
def main(): import argparse parser = argparse.ArgumentParser() parser.add_argument('-f', '--file', nargs='?', type=argparse.FileType('r'), default=sys.stdin, help='Input file e.g. d2z.dat.') parser.add_argument('--extra_data', type=argparse.FileType('r'), default='hg18.toDanRer5.seqs.txt', help='Extra data file e.g. hg18.toDanRer5.seqs.txt.') parser.add_argument('scoring', choices=['ranked_peaks', 'overlap']) OPTS = parser.parse_args() line_tups = read_fields(f=OPTS.file) cne_dict = parse_dat(line_tups) extra = parse_extra_data(read_fields(f=OPTS.extra_data)) if OPTS.scoring == 'ranked_peaks': results = ranked_peaks(cne_dict, extra) elif OPTS.scoring == 'overlap': results = overlap(cne_dict, extra) for cne, result in sorted(results.iteritems()): sys.stdout.write('\t'.join([cne, str(result['rank']), str(result['places'])]) + '\n')
def init(): global html_path; html_path = "../results" global compound2smiles; compound2smiles = util.parse_dat("../metacyc/compounds.dat", "UNIQUE-ID", "SMILES") global atom_types; atom_types = ['C', 'N', 'O', 'P', 'S'] #global bond_types; bond_types = range(5) global bond_types; bond_types = range(4) global motif_sizes; motif_sizes = range(2, 7) global log_zero; log_zero = -800.0 global compound2graph; compound2graph = {} for compound in compound2smiles.keys(): try: compound2graph[compound] = chemconvert.molfile2graph("../mol/" + compound + ".mol") except Exception: pass return