default="./",
help="Directory to write output")
parser.add_argument("-m",
"--min_len",
action="store",
dest="min_len",
type=int,
default=1,
help="Minimum length of read to output")
args = parser.parse_args()
n_regexp = re.compile("N+$")
if args.input_se:
se_directory, se_prefix, se_extension = split_filename(args.input_se)
se_in_fd = open(args.input_se, "r")
se_out_file = "%s%s.filtered%s" % (check_path(
args.out_dir), se_prefix, se_extension)
se_out_fd = open(se_out_file, "w")
while True:
name, sequence, separator, quality = read_entry(se_in_fd)
if name is None:
break
match = n_regexp.search(sequence)
if match is None:
se_out_fd.write("%s\n%s\n%s\n%s\n" %
(name, sequence, separator, quality))
elif match.start() >= args.min_len:
se_out_fd.write("%s\n%s\n%s\n%s\n" %
help="Remove nucleotide substitutions from output(preserve only AA substitutions)")
parser.add_argument("-c", "--convert_aa_to_single_letter", action="store_true", dest="convert_to_single_letter",
help="Convert aminoacids to single letters")
args = parser.parse_args()
args.input = make_list_of_path_to_files(args.input)
gene_alias_dict = SynDict()
if args.gene_alias_file:
gene_alias_dict.read(args.gene_alias_file, split_values=False)
out_fd = sys.stdout if args.output == "stdout" else open(args.output, "w")
summary_dict = TwoLvlDict()
for filename in args.input:
directory, prefix, extension = split_filename(filename)
if args.write_dir_path and args.write_ext:
name = filename
elif args.write_dir_path:
name = (directory + prefix) if directory else prefix
elif args.write_ext:
name = prefix + extension
else:
name = prefix
if args.suffix_to_remove in name:
name = name.replace(args.suffix_to_remove, "")
summary_dict[name] = OrderedDict()
with open(filename, "r") as file_fd:
file_fd.readline()
for line in file_fd:
if args.threads == 1:
TRF.search_tandem_repeats(
args.input_file,
matching_weight=args.matching_weight,
mismatching_penalty=args.mismatching_penalty,
indel_penalty=args.indel_penalty,
match_probability=args.matching_probability,
indel_probability=args.indel_probability,
min_alignment_score=args.min_score,
max_period=args.max_period_size,
report_flanking_sequences=args.report_flanking_sequences,
make_dat_file=True,
disable_html_output=args.enable_html_output)
trf_report = "%s.%i.%i.%i.%i.%i.%i.%i.dat" % (
split_filename(args.input_file)[1] +
split_filename(args.input_file)[2], args.matching_weight,
args.mismatching_penalty, args.indel_penalty,
args.matching_probability, args.indel_probability, args.min_score,
args.max_period_size)
TRF.convert_trf_report(trf_report, args.output_prefix)
else:
TRF.parallel_search_tandem_repeat(
args.input_file,
args.output_prefix,
matching_weight=args.matching_weight,
mismatching_penalty=args.mismatching_penalty,
indel_penalty=args.indel_penalty,
match_probability=args.matching_probability,
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--tree_dir", action="store", dest="tree_dir", required=True, type=check_path,
help="Directory with trees")
parser.add_argument("-f", "--tree_format", action="store", dest="tree_format", default=1, type=int,
help="Format of input trees")
parser.add_argument("-o", "--output_file", action="store", dest="output_file", default="stdout",
help="Output file with leaves of trees. Default: stdout")
args = parser.parse_args()
out_fd = sys.stdout if args.output_file == "stdout" else open(args.output_file, "w")
tree_files_list = os.listdir(args.tree_dir)
names_dict = SynDict()
for tree_file in tree_files_list:
tree_name = split_filename(tree_file)[1]
with open("%s%s" % (args.tree_dir, tree_file), "r") as tree_fd:
tree = Tree(tree_fd.readline().strip(), format=args.tree_format)
leaves_list = []
for node in tree.traverse():
if node.is_leaf():
leaves_list.append(node.name)
names_dict[tree_name] = leaves_list
names_dict.write(args.outp_fd, splited_values=True)
if args.output_file != "stdout":
out_fd.close()
abs_path_source_reads.append("%s/%s" % (working_dir, filename))
"""
for iteration_index in range(1, args.number_of_iterations):
os.chdir(working_dir)
iteration = "iteration_%i" % iteration_index
iteration_dir = "%s/%s" % (working_dir, iteration)
iteration_ref = "%s/%s_reference.fasta" % (iteration_dir, iteration)
iteration_ref_index = "%s/%s_reference.idx" % (iteration_dir, iteration)
base_prefix = "%s/%s_reference_with_rev_com" % (iteration_dir, iteration)
iteration_ref_with_rev_com = "%s/%s_reference_with_rev_com.fasta" % (iteration_dir, iteration)
kmer_file = "%s_%i_mer.kmer" % (base_prefix, args.kmer_length)
masurca_config_file = "masurca_%s.config" % iteration
left_reads_prefix = split_filename(abs_path_left_source_reads)[1]
right_reads_prefix = split_filename(abs_path_right_source_reads)[1]
left_reads_se = "%s.se.fastq" % left_reads_prefix
right_reads_se = "%s.se.fastq" % right_reads_prefix
left_reads_filtered = "%s.filtered.fastq" % left_reads_prefix
right_reads_filtered = "%s.filtered.fastq" % right_reads_prefix
try:
os.mkdir(iteration_dir)
except OSError:
pass
shutil.copyfile(iteration_reference_file, iteration_ref)
os.chdir(iteration_dir)
iteration_reference_dict = SeqIO.index_db(iteration_ref_index, iteration_ref, format="fasta")
help="Suffix of fam files. Default: .fam")
parser.add_argument("-o",
"--output",
action="store",
dest="output",
default="stdout",
help="Suffix of fam files")
args = parser.parse_args()
out_fd = sys.stdout if args.output == "stdout" else open(args.output, "w")
species_list = []
suffix_list = []
if args.use_basename:
for filename in sorted(os.listdir(args.input)):
dir, basename, ext = split_filename(filename)
species_list.append(basename)
suffix_list.append("%s" % ext)
else:
species_list = sorted(args.species_set)
suffix_list = [args.suffix for i in range(0, len(species_list))]
out_fd.write("#species\tnumber_of_families\tnumber_of_proteins\n")
for species, suffix in zip(species_list, suffix_list):
fam_dict = SynDict()
fam_dict.read("%s%s%s" % (args.input, species, suffix),
separator="\t",
split_values=True,
values_separator=",",
key_index=0,
value_index=1)