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" %
(name, sequence[:match.start() + 1], separator,
quality[:match.start() + 1]))
else:
return False
if first_list[-1][1:] != second_list[-1][1:]:
return False
if first_list[-1][0] != "1" or second_list[-1][0] != "2":
return False
return True
parser = argparse.ArgumentParser()
parser.add_argument("-d",
"--sample_directory",
action="store",
dest="samples_dir",
required=True,
type=lambda s: check_path(os.path.abspath(s)),
help="Directory with samples")
parser.add_argument(
"-s",
"--samples",
action="store",
dest="samples",
help="Comma-separated list of subdirectories(one per sample) to handle. "
"If not set all subdirectories will be considered as containing samples."
"In sample directory should one(in case SE reads) or two(in case PE reads) files."
"Filenames should should contain '_1.fq' or '_1.fastq' for forward(left) reads, "
" '_2.fq' or '_2.fastq' for reverse(right) reads and '.fq' or '.fastq' for SE reads"
)
parser.add_argument("-o",
"--output",
action="store",
parser.add_argument("-b", "--count_both_strands", action="store_true", dest="count_both_strands",
help="Count kmers in both strands. NOTICE: only mer or its reverse-complement, whichever "
"comes first lexicographically, is stored and the count value is the number of "
"occurrences of both. So this option is not suitable for generating sets of forward "
"and reverse-complement kmers. For this case use -r/--add_reverse_complement option. "
"Not compatible with -r/--add_reverse_complement option.")
parser.add_argument("-r", "--add_reverse_complement", action="store_true", dest="add_rev_com",
help="Add reverse-complement sequences before counting kmers. "
"Works only for fasta sequences. "
"Not compatible with -b/--count_both_strands option")
parser = argparse.ArgumentParser()
args = parser.parse_args()
args.path_to_mavr = check_path(args.path_to_mavr)
MaSuRCA.threads = args.threads
Jellyfish.threads = args.threads
Jellyfish.path = args.jellyfish_path if args.jellyfish_path else ""
iteration_reference_file = args.initial_sequences
working_dir = os.getcwd()
abs_path_left_source_reads = os.path.abspath(args.left_source_reads)
abs_path_right_source_reads = os.path.abspath(args.right_source_reads)
"""
for filename in args.source_reads:
ab
if os.path.isabs(filename):
abs_path_source_reads.append(filename)
call_hcluster(args.input, *arg_list)
"""
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--hclust_input_file", action="store", dest="hclust_input", required=True,
help="File with input graph for hclust")
parser.add_argument("-c", "--families_file", action="store", dest="fam_file", required=True,
help="File with families")
parser.add_argument("-o", "--output_dir", action="store", dest="output_dir",
help="Directory to write output")
parser.add_argument("-t", "--threads", action="store", dest="threads", type=int, default=1,
help="Number of threads to use")
args = parser.parse_args()
args.output_dir = check_path(args.output_dir)
def check_edge_strict(nodes_list, id_list):
for node in nodes_list:
if node not in id_list:
return False
return True
def check_edge_soft(nodes_list, id_list):
for node in nodes_list:
if node in id_list:
return True
return False
def write_splited(self, out_dir="./", extension="t", value_separator=","):
from RouToolPa.Routines.File import check_path
for fl_key in self:
with open("%s%s.%s" % (check_path(out_dir), fl_key, extension), "w") as out_fd:
for sl_key in self[fl_key]:
out_fd.write("%s\t%s\n" % (sl_key, value_separator.join(self[fl_key][sl_key])))