def __init__(self, cpus=1):
"""Initialization."""
self.logger = logging.getLogger('timestamp')
self.cpus = cpus
check_on_path('mafft')
def __init__(self, cpus):
"""Initialization."""
self.logger = logging.getLogger('timestamp')
self.cpus = cpus
if self.cpus > 1:
check_on_path('raxmlHPC-PTHREADS-SSE3')
else:
check_on_path('raxmlHPC-SSE3')
def __init__(self, multithreaded=True):
"""Initialization."""
self.logger = logging.getLogger('timestamp')
self.multithreaded = multithreaded
if self.multithreaded:
check_on_path('FastTreeMP')
else:
check_on_path('FastTree')
def __init__(self, cpus=1):
"""Initialization.
Parameters
----------
cpus : int
Number of cpus to use.
"""
self.logger = logging.getLogger('timestamp')
check_on_path('diamond')
self.cpus = cpus
def __init__(self, cpus):
"""Initialization.
Parameters
----------
cpus : int
Maximum number of cpus/threads to use.
"""
self.logger = logging.getLogger('timestamp')
self.cpus = cpus
check_on_path('ani_calculator')
def __init__(self, mode="dom"):
self.logger = logging.getLogger('timestamp')
# make sure HMMER is installed
check_on_path('hmmsearch')
# set the mode
if mode == "dom":
self.mode = 'domtblout'
elif mode == "tbl":
self.mode = 'tblout'
elif mode == 'align':
self.mode = 'align'
elif mode == 'fetch':
self.mode = 'fetch'
else:
raise HMMMERModeError("Mode %s not understood" % mode)
def __init__(self, cpus, verbose=True):
"""Initialization.
Parameters
----------
cpus : int
Number of cpus to use.
verbose : boolean
Flag indicating if progress should be reported.
"""
self.logger = logging.getLogger('timestamp')
check_on_path('prodigal')
self.cpus = cpus
self.verbose = verbose
def bootstrap(self, input_tree, msa_file, model_str, num_replicates, output_dir, cpus):
"""Perform non-parametric bootstrapping.
Parameters
----------
input_tree : str
File containing newick tree to decorate with bootstraps.
msa_file : str
Fasta file containing multiple sequence alignment.
model_str : str
Specified either the 'WAG' or 'LG' model.
num_replicates : int
Number of replicates to perform.
output_dir: str
Output directory to contain bootstrap trees.
cpus : int
Number of cpus to use.
"""
check_on_path('seqmagick')
assert(model_str.upper() in ['WAG', 'LG'])
self.output_dir = output_dir
self.model = model_str
self.msa = seq_io.read(msa_file)
# calculate replicates
parallel = Parallel(cpus)
replicate_numbers = list(range(num_replicates))
parallel.run(self._bootstrap, None, replicate_numbers, None)
# calculate support values
rep_tree_files = []
for rep_index in replicate_numbers:
rep_tree_files.append(os.path.join(output_dir, 'rep_%d' % rep_index, 'RAxML_bestTree.support'))
tree_name = os.path.splitext(os.path.basename(input_tree))[0]
output_tree = os.path.join(output_dir, tree_name + '.bootstrap.tree')
bootstrap_support(input_tree, rep_tree_files, output_tree)
return output_tree
def __init__(self, cpus=1):
"""Initialization.
Parameters
----------
cpus : int
Number of cpus to use.
"""
self.logger = logging.getLogger('timestamp')
check_on_path('diamond')
self.cpus = cpus
self.output_fmt = {
'diamond_daa':
'100',
'standard':
'6',
'custom':
'6 qseqid qlen sseqid stitle slen length pident evalue bitscore'
}
def __init__(self):
"""Initialization."""
self.logger = logging.getLogger()
execute.check_on_path('ktImportText')
def __init__(self):
"""Initialization."""
self.logger = logging.getLogger('timestamp')
check_on_path('muscle')
