def main(args): graph_type = 'nodegraph' report_on_config(args, graphtype=graph_type) base = args.output_filename filenames = args.input_filenames for fname in args.input_filenames: check_input_files(fname, args.force) graphsize = calculate_graphsize(args, graph_type) space_needed = (args.n_tables * graphsize / khmer._buckets_per_byte[graph_type]) check_space_for_graph(args.output_filename, space_needed, args.force) print('Saving k-mer nodegraph to %s' % base, file=sys.stderr) print('Loading kmers from sequences in %s' % repr(filenames), file=sys.stderr) if args.no_build_tagset: print('We WILL NOT build the tagset.', file=sys.stderr) else: print('We WILL build the tagset (for partitioning/traversal).', file=sys.stderr) print('making nodegraph', file=sys.stderr) nodegraph = khmer_args.create_nodegraph(args) oxfuncs.build_graph(filenames, nodegraph, args.threads, not args.no_build_tagset) print('Total number of unique k-mers: {0}'.format( nodegraph.n_unique_kmers()), file=sys.stderr) print('saving k-mer nodegraph in', base, file=sys.stderr) nodegraph.save(base) if not args.no_build_tagset: print('saving tagset in', base + '.tagset', file=sys.stderr) nodegraph.save_tagset(base + '.tagset') info_fp = open(base + '.info', 'w') info_fp.write('%d unique k-mers' % nodegraph.n_unique_kmers()) fp_rate = \ khmer.calc_expected_collisions( nodegraph, args.force, max_false_pos=.15) # 0.18 is ACTUAL MAX. Do not change. print('false positive rate estimated to be %1.3f' % fp_rate, file=sys.stderr) print('\nfalse positive rate estimated to be %1.3f' % fp_rate, file=info_fp) print('wrote to ' + base + '.info and ' + base, file=sys.stderr) if not args.no_build_tagset: print('and ' + base + '.tagset', file=sys.stderr) sys.exit(0)
def main(args): info('build-graph.py', ['graph', 'SeqAn']) report_on_config(args, hashtype='nodegraph') base = args.output_filename filenames = args.input_filenames for fname in args.input_filenames: check_input_files(fname, args.force) # if optimization args are given, do optimization args = functions.do_sanity_checking(args, 0.01) check_space(args.input_filenames, args.force) check_space_for_hashtable(args, 'nodegraph', args.force) print('Saving k-mer presence table to %s' % base, file=sys.stderr) print('Loading kmers from sequences in %s' % repr(filenames), file=sys.stderr) if args.no_build_tagset: print('We WILL NOT build the tagset.', file=sys.stderr) else: print('We WILL build the tagset (for partitioning/traversal).', file=sys.stderr) print('making nodegraph', file=sys.stderr) htable = khmer_args.create_nodegraph(args) functions.build_graph(filenames, htable, args.threads, not args.no_build_tagset) print('Total number of unique k-mers: {0}'.format(htable.n_unique_kmers()), file=sys.stderr) print('saving k-mer presence table in', base + '.pt', file=sys.stderr) htable.save(base + '.pt') if not args.no_build_tagset: print('saving tagset in', base + '.tagset', file=sys.stderr) htable.save_tagset(base + '.tagset') info_fp = open(base + '.info', 'w') info_fp.write('%d unique k-mers' % htable.n_unique_kmers()) fp_rate = \ khmer.calc_expected_collisions(htable, args.force, max_false_pos=.15) # 0.18 is ACTUAL MAX. Do not change. print('false positive rate estimated to be %1.3f' % fp_rate, file=sys.stderr) print('\nfalse positive rate estimated to be %1.3f' % fp_rate, file=info_fp) print('wrote to', base + '.info and', base + '.pt', file=sys.stderr) if not args.no_build_tagset: print('and ' + base + '.tagset', file=sys.stderr) sys.exit(0)
def main(args): info('build-graph.py', ['graph', 'SeqAn']) report_on_config(args, hashtype='hashbits') base = args.output_filename filenames = args.input_filenames for fname in args.input_filenames: check_input_files(fname, args.force) check_space(args.input_filenames, args.force) check_space_for_hashtable( (float(args.n_tables * args.min_tablesize) / 8.), args.force) print >>sys.stderr, 'Saving k-mer presence table to %s' % base print >>sys.stderr, 'Loading kmers from sequences in %s' % repr(filenames) if args.no_build_tagset: print >>sys.stderr, 'We WILL NOT build the tagset.' else: print >>sys.stderr, 'We WILL build the tagset', \ ' (for partitioning/traversal).' print >>sys.stderr, 'making k-mer presence table' htable = khmer.new_hashbits(args.ksize, args.min_tablesize, args.n_tables) functions.build_graph(filenames, htable, args.threads, not args.no_build_tagset) print >> sys.stderr, 'Total number of unique k-mers: {0}'.format( htable.n_unique_kmers()) print >>sys.stderr, 'saving k-mer presence table in', base + '.pt' htable.save(base + '.pt') if not args.no_build_tagset: print >>sys.stderr, 'saving tagset in', base + '.tagset' htable.save_tagset(base + '.tagset') info_fp = open(base + '.info', 'w') info_fp.write('%d unique k-mers' % htable.n_unique_kmers()) fp_rate = \ khmer.calc_expected_collisions(htable, args.force, max_false_pos=.15) # 0.18 is ACTUAL MAX. Do not change. print >>sys.stderr, 'false positive rate estimated to be %1.3f' % fp_rate print >>info_fp, '\nfalse positive rate estimated to be %1.3f' % fp_rate print >> sys.stderr, 'wrote to', base + '.info and', base + '.pt' if not args.no_build_tagset: print >> sys.stderr, 'and ' + base + '.tagset' sys.exit(0)
def main(args): info("build-graph.py", ["graph", "SeqAn"]) report_on_config(args, graphtype="nodegraph") base = args.output_filename filenames = args.input_filenames for fname in args.input_filenames: check_input_files(fname, args.force) graphsize = calculate_graphsize(args, "nodegraph") check_space_for_graph(args.output_filename, graphsize, args.force) print("Saving k-mer nodegraph to %s" % base, file=sys.stderr) print("Loading kmers from sequences in %s" % repr(filenames), file=sys.stderr) if args.no_build_tagset: print("We WILL NOT build the tagset.", file=sys.stderr) else: print("We WILL build the tagset (for partitioning/traversal).", file=sys.stderr) print("making nodegraph", file=sys.stderr) nodegraph = khmer_args.create_nodegraph(args) oxfuncs.build_graph(filenames, nodegraph, args.threads, not args.no_build_tagset) print("Total number of unique k-mers: {0}".format(nodegraph.n_unique_kmers()), file=sys.stderr) print("saving k-mer nodegraph in", base, file=sys.stderr) nodegraph.save(base) if not args.no_build_tagset: print("saving tagset in", base + ".tagset", file=sys.stderr) nodegraph.save_tagset(base + ".tagset") info_fp = open(base + ".info", "w") info_fp.write("%d unique k-mers" % nodegraph.n_unique_kmers()) fp_rate = khmer.calc_expected_collisions(nodegraph, args.force, max_false_pos=0.15) # 0.18 is ACTUAL MAX. Do not change. print("false positive rate estimated to be %1.3f" % fp_rate, file=sys.stderr) print("\nfalse positive rate estimated to be %1.3f" % fp_rate, file=info_fp) print("wrote to " + base + ".info and " + base, file=sys.stderr) if not args.no_build_tagset: print("and " + base + ".tagset", file=sys.stderr) sys.exit(0)
def main(args): info("build-graph.py", ["graph", "SeqAn"]) report_on_config(args, hashtype="hashbits") base = args.output_filename filenames = args.input_filenames for fname in args.input_filenames: check_input_files(fname, args.force) check_space(args.input_filenames, args.force) check_space_for_hashtable((float(args.n_tables * args.min_tablesize) / 8.0), args.force) print("Saving k-mer presence table to %s" % base, file=sys.stderr) print("Loading kmers from sequences in %s" % repr(filenames), file=sys.stderr) if args.no_build_tagset: print("We WILL NOT build the tagset.", file=sys.stderr) else: print("We WILL build the tagset (for partitioning/traversal).", file=sys.stderr) print("making k-mer presence table", file=sys.stderr) htable = khmer.new_hashbits(args.ksize, args.min_tablesize, args.n_tables) functions.build_graph(filenames, htable, args.threads, not args.no_build_tagset) print("Total number of unique k-mers: {0}".format(htable.n_unique_kmers()), file=sys.stderr) print("saving k-mer presence table in", base + ".pt", file=sys.stderr) htable.save(base + ".pt") if not args.no_build_tagset: print("saving tagset in", base + ".tagset", file=sys.stderr) htable.save_tagset(base + ".tagset") info_fp = open(base + ".info", "w") info_fp.write("%d unique k-mers" % htable.n_unique_kmers()) fp_rate = khmer.calc_expected_collisions(htable, args.force, max_false_pos=0.15) # 0.18 is ACTUAL MAX. Do not change. print("false positive rate estimated to be %1.3f" % fp_rate, file=sys.stderr) print("\nfalse positive rate estimated to be %1.3f" % fp_rate, file=info_fp) print("wrote to", base + ".info and", base + ".pt", file=sys.stderr) if not args.no_build_tagset: print("and " + base + ".tagset", file=sys.stderr) sys.exit(0)