def __init__(self, title=None): if title: self.title = title else: self.title = [] self.result = [] self._keggdb = dbutils.keggdb()
def dist_from_annot_file(handle): dist = Dist() mykeggdb = dbutils.keggdb() for l in handle: if l[0] == '#': continue query, kos = parse_annot(l) if not kos: continue for ko in kos: paths = mykeggdb.get_ko3s(ko) for path in paths: dist[path] = query return dist
def dist_from_annot_file(handle): dist = Dist() mykeggdb = dbutils.keggdb() for l in handle: if l[0] == "#": continue query, kos = parse_annot(l) if not kos: continue for ko in kos: paths = mykeggdb.get_ko3s(ko) for path in paths: dist[path] = query return dist
def arg2dist(arg): """ get dist dict in term of arg, abbrev for genome or used defined annot """ kobasrc = config.getrc() if len(arg) == 3: keggdb = dbutils.keggdb() distfile = os.path.join(kobasrc["kobas_home"], "gene_dist", keggdb.get_species_name(arg.lower())) dist_dict = discover.dist_from_distfile(open(distfile)) else: if not os.access(arg, os.F_OK): print "File: %s not exist" % arg sys.exit(0) dist_dict = discover.dist_from_annot_file(open(arg, 'r')) dist_size = dist_dict.size() return (dist_dict, dist_size)
def arg2dist(arg): """ get dist dict in term of arg, abbrev for genome or used defined annot """ kobasrc = config.getrc() if len(arg) == 3: keggdb = dbutils.keggdb() distfile = os.path.join( kobasrc["kobas_home"], "gene_dist", keggdb.get_species_name(arg.lower())) dist_dict = discover.dist_from_distfile(open(distfile)) else: if not os.access(arg, os.F_OK): print "File: %s not exist" % arg sys.exit(0) dist_dict = discover.dist_from_annot_file(open(arg, 'r')) dist_size = dist_dict.size() return (dist_dict, dist_size)
def annot2dist(handle): """ convert annotation to term distribution, besides total size """ dist_dict = {} dist_size = 0 mykeggdb = dbutils.keggdb() for l in handle: terms = [] if l[0] == "#": continue query, kos = parse_annot(l) if kos: dist_size += 1 [terms.extend(mykeggdb.get_ko3s(koid)) for koid in kos] term_freq(dist_dict, [(term, 1) for term in terms]) return (dist_dict, dist_size)
def annot2dist(handle): """ convert annotation to term distribution, besides total size """ dist_dict = {} dist_size = 0 mykeggdb = dbutils.keggdb() for l in handle: terms = [] if l[0] == '#': continue query, kos = parse_annot(l) if kos: dist_size += 1 [terms.extend(mykeggdb.get_ko3s(koid)) for koid in kos] term_freq(dist_dict, [(term, 1) for term in terms]) return (dist_dict, dist_size)
opt_parser,opt,args = config_option() if len(args) != 1: opt_parser.print_help() sys.exit(1) # Blast environment configuration kobasrc = config.getrc() # Integrate command line switches into environments if opt.rank: kobasrc["rank"] = opt.rank if opt.evalue: kobasrc["evalue"] = opt.evalue keggdb = dbutils.keggdb(kobasrc['kobasdb']) if opt.intype == "fasta": # verify fasta file try: try: f = open(args[0]) fasta.verify(f) finally: f.close() except exception.FastaIOError, msg: exception.error(msg) sys.exit(1) annotator = annot.Annotator( reader = annot.BlastProgReader( kobasrc['blast'], opt.blast_prog, kobasrc['blastdb'], args[0],
opt_parser, opt, args = config_option() if len(args) != 1: opt_parser.print_help() sys.exit(1) # Blast environment configuration kobasrc = config.getrc() # Integrate command line switches into environments if opt.rank: kobasrc["rank"] = opt.rank if opt.evalue: kobasrc["evalue"] = opt.evalue keggdb = dbutils.keggdb(kobasrc['kobasdb']) if opt.intype == "fasta": # verify fasta file try: try: f = open(args[0]) fasta.verify(f) finally: f.close() except exception.FastaIOError, msg: exception.error(msg) sys.exit(1) annotator = annot.Annotator( reader=annot.BlastProgReader(kobasrc['blast'], opt.blast_prog,
def setUp(self): self._keggdb = dbutils.keggdb()
global similarity return record.get_similarity() >= similarity def usage(): print >> sys.stderr, __doc__ sys.exit(1) if __name__ == "__main__": opts, args = getopt.getopt(sys.argv[1:], 'e:hi:o:r:s:t:') if len(args) != 1: usage() f = open(args[0], 'r') annot_iter = annot.Iterator(f) keggdb = dbutils.keggdb() # kobasrc = config.getrc() # evalue = float(kobasrc['evalue']) # rank = int(kobasrc['rank']) output = 't' for o, a in opts: if o == '-e': evalue = float(a) elif o == '-i': similarity = float(a) elif o == '-r': rank = int(a) elif o == '-o': if a == 'o': output = 'o'
def usage(): print >> sys.stderr, __doc__ sys.exit(1) if __name__ == "__main__": opts, args = getopt.getopt(sys.argv[1:], 'e:hi:o:r:s:t:') if len(args) != 1: usage() f = open(args[0], 'r') annot_iter = annot.Iterator(f) keggdb = dbutils.keggdb() # kobasrc = config.getrc() # evalue = float(kobasrc['evalue']) # rank = int(kobasrc['rank']) output = 't' for o, a in opts: if o == '-e': evalue = float(a) elif o == '-i': similarity = float(a) elif o == '-r': rank = int(a) elif o == '-o': if a == 'o': output = 'o'