def set_defaults(self):
"""Set default values to run programs
For LTR,
min_dist: minimum distance(bp) between LTRs.
max_dist: maximum distance(bp) between LTRS
min_len_ltr: minimum length(bp) of LTR.
max_len_ltr: maximum length(bp) of LTR.
ltr_sim_condition: minimum similarity(%) for LTRs in an element.
cluster_sim_condition: minimum similarity(%) for LTRs in a cluster
len_condition: minimum length(bp) for LTRs aligned in local alignment.
"""
if self.data_dir:
self.data_dir = utils.create_directory(self.data_dir, False)
else:
self.data_dir = \
utils.create_directory(utils.get_abspath(self.default_output_path))
self.hmmerv = 3
self.min_dist = 2000
self.max_dist = 20000
self.min_len_ltr = 130
self.max_len_ltr = 2000
self.ltr_sim_condition = 70
self.cluster_sim_condition = 70
self.len_condition = 70
self.sw_rm = "No" # or Yes
self.scaffold = "" # or directory
def set_defaults(self):
"""Set default values to run programs
For LTR,
min_dist: minimum distance(bp) between LTRs.
max_dist: maximum distance(bp) between LTRS
min_len_ltr: minimum length(bp) of LTR.
max_len_ltr: maximum length(bp) of LTR.
ltr_sim_condition: minimum similarity(%) for LTRs in an element.
cluster_sim_condition: minimum similarity(%) for LTRs in a cluster
len_condition: minimum length(bp) for LTRs aligned in local alignment.
"""
if self.data_dir:
self.data_dir = utils.create_directory(self.data_dir, False)
else:
self.data_dir = \
utils.create_directory(utils.get_abspath(self.default_output_path))
self.hmmerv = 3
self.min_dist = 2000
self.max_dist = 20000
self.min_len_ltr = 130
self.max_len_ltr = 2000
self.ltr_sim_condition = 70
self.cluster_sim_condition = 70
self.len_condition = 70
self.sw_rm = "No" # or Yes
self.scaffold = "" # or directory
def reverse_complement(self, directory):
mypath = self.genome_path
for (dirpath, dirnames, filenames) in os.walk(mypath):
break
utils.create_directory(directory, False)
for name in filenames:
file_path = utils.get_abspath(dirpath + "/" + name)
reverse_complement_fasta(file_path, directory)
def reverse_complement(self, directory):
mypath = self.genome_path
for (dirpath, dirnames, filenames) in os.walk(mypath):
break
utils.create_directory(directory, False)
for name in filenames:
file_path = utils.get_abspath(dirpath + "/" + name)
reverse_complement_fasta(file_path, directory)
def split_files(self, dirpath=None, output_path=None):
if not dirpath:
dirpath = self.input_file
if not output_path:
output_path = self.result_path
utils.create_directory(output_path,False)
onlyfiles = [ f for f in listdir(dirpath) if isfile(join(dirpath,f)) ]
for file in onlyfiles:
self.split_file(dirpath + "/" + file, output_path)
def forward(self):
utils.create_directory(self.output_path, False)
if self.nmpi:
#cmd = self._padding("mpirun", self.p_np, self.p_mpi_option,
cmd = self._padding("mpirun", "-n " + str(int(math.ceil(1.0*int(self.nmpi)/2))), self.p_mpi_option,
self.p_mgescan_mpi_cmd, self.p_prg, self.p_genome_f,
self.p_data_f, self.p_hmmerv)
self.run_cmd(cmd)
else:
mypath = self.genome_path
for f in os.listdir(mypath):
fpath = os.path.join(mypath, f)
if os.path.isfile(fpath):
#p = Process(target=self.run_hmm, args=("forward", fpath,))
#p.start()
self.run_hmm("forward", fpath)
def forward(self):
utils.create_directory(self.output_path, False)
if self.nmpi:
#cmd = self._padding("mpirun", self.p_np, self.p_mpi_option,
cmd = self._padding(
"mpirun",
"-n " + str(int(math.ceil(1.0 * int(self.nmpi) / 2))),
self.p_mpi_option, self.p_mgescan_mpi_cmd, self.p_prg,
self.p_genome_f, self.p_data_f, self.p_hmmerv)
self.run_cmd(cmd)
else:
mypath = self.genome_path
for f in os.listdir(mypath):
fpath = os.path.join(mypath, f)
if os.path.isfile(fpath):
#p = Process(target=self.run_hmm, args=("forward", fpath,))
#p.start()
self.run_hmm("forward", fpath)
def set_defaults(self):
"""Set default values to run programs"""
if self.result_path:
self.result_path = utils.create_directory(self.result_path, False)
else:
self.result_path = utils.create_directory(self.default_output)