for alignment_file in args.input:
alignment_name_list = FileRoutines.split_filename(alignment_file)
output_prefix = "%s/%s.unique_positions" % (args.output_dir,
alignment_name_list[1])
unique_position_dict[alignment_name_list[
1]] = MultipleAlignmentRoutines.count_unique_positions_per_sequence_from_file(
alignment_file,
output_prefix,
format=args.format,
gap_symbol="-",
return_mode="relative",
verbose=False)
species_list = unique_position_dict.sl_keys()
data_dict = OrderedDict()
for species in species_list:
data_dict[species] = []
for alignment in unique_position_dict:
data_dict[species].append(unique_position_dict[alignment][species])
data_list = [data_dict[species] for species in data_dict]
MatplotlibRoutines.extended_percent_histogram(data_list,
args.histogram_output,
input_mode="percent",
label=species_list)
help="Directory with families of species")
"""
parser.add_argument("-o", "--output_file", action="store", dest="output", default="stdout",
help="Output file. Default: stdout")
"""
args = parser.parse_args()
# run after scripts/expansion/compare_cluster.py
# out_fd = sys.stdout if args.output == "stdout" else open(args.output, "w")
species_syn_dict = TwoLvlDict()
for species in args.species_list:
species_syn_dict[species] = read_synonyms_dict("%s%s/all.t" % (args.species_dir, species))
species_syn_dict.write("families_all_species.t", absent_symbol=".")
not_assembled = species_syn_dict.filter_by_line(is_assembled)
species_syn_dict.write("correctly_assembled_families_species.t", absent_symbol=".")
assembled_ids = IdSet(species_syn_dict.sl_keys())
assembled_ids.write("assembled_families.ids")
not_assembled_ids = IdSet(not_assembled.sl_keys())
not_assembled_ids.write("non_assembled_families.ids")
"""
if args.output != "stdout":
out_fd.close()
"""
fam_count_dict = TwoLvlDict()
species_family_dict = TwoLvlDict()
for species in args.species_set:
species_family_dict[species] = SynDict()
species_family_dict[species].read(
"%s%s%s" % (FileRoutines.check_path(args.input), species, args.suffix),
split_values=True,
values_separator=",",
separator="\t")
#print species_family_dict[species]
fam_count_dict[species] = species_family_dict[species].count_synonyms()
#print fam_count_dict[species]
species_filtered_fd_list[species] = open(
"%s%s.fam" % (args.filtered_family_dir, species), "w")
for family in fam_count_dict.sl_keys():
genes_number_list = []
number_of_species = 0
for species in species_list:
genes_number_list.append(fam_count_dict[species][family] if family in
fam_count_dict[species] else 0)
number_of_species += 1 if family in fam_count_dict[species] else 0
number_str = "\t".join(map(str, genes_number_list))
if (black_list and (family in black_list)) or (
white_list and (family not in white_list)) or (
number_of_species < args.min_species_number):
filtered_fd.write("%s\t%s\t%s\n" % (family, family, number_str))
for species in species_list:
if family in species_family_dict[species]: