def test_compute_min_alignment_length(self):
"""compute_min_alignment_length: returns n std devs below mean seq len
"""
self.assertEqual(compute_min_alignment_length(\
self.min_length_computation_seqs),16)
self.assertEqual(compute_min_alignment_length(\
self.min_length_computation_seqs,0.60),13)
def test_compute_min_alignment_length(self):
"""compute_min_alignment_length: returns n std devs below mean seq len
"""
self.assertEqual(compute_min_alignment_length(
self.min_length_computation_seqs), 16)
self.assertEqual(compute_min_alignment_length(
self.min_length_computation_seqs, 0.60), 13)
def _precommand_initiation(self,input_fp,output_dir,working_dir,params):
if not params['blast_db']:
# Build the blast database from the reference_seqs_fp -- all procs
# will then access one db rather than create one per proc
blast_db, db_files_to_remove = \
build_blast_db_from_fasta_path(params['template_fp'])
self.files_to_remove += db_files_to_remove
params['blast_db'] = blast_db
if params['min_length'] < 0:
params['min_length'] = compute_min_alignment_length(\
open(input_fp,'U'))
def _precommand_initiation(self,input_fp,output_dir,working_dir,params):
if not params['blast_db']:
# Build the blast database from the reference_seqs_fp -- all procs
# will then access one db rather than create one per proc
blast_db, db_files_to_remove = \
build_blast_db_from_fasta_path(params['template_fp'])
self.files_to_remove += db_files_to_remove
params['blast_db'] = blast_db
if params['min_length'] < 0:
params['min_length'] = compute_min_alignment_length(\
open(input_fp,'U'))
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
if opts.min_percent_id <= 1.0:
opts.min_percent_id *= 100
if not (1.0 <= opts.min_percent_id <= 100.0):
option_parser.error('Minimum percent sequence identity must be' +
' between 1.0 and 100.0: %2.2f' % opts.min_percent_id)
if not opts.template_fp and opts.alignment_method == 'pynast':
option_parser.error(
'PyNAST requires a template alignment to be passed via -t')
input_seqs_filepath = opts.input_fasta_fp
alignment_method = opts.alignment_method
output_dir = opts.output_dir or alignment_method + '_aligned'
create_dir(output_dir, fail_on_exist=False)
# compute the minimum alignment length if a negative value was
# provided (the default)
min_length = opts.min_length
if min_length < 0:
min_length = compute_min_alignment_length(
open(input_seqs_filepath, 'U'))
fpath, ext = splitext(input_seqs_filepath)
input_dir, fname = split(fpath)
result_path = output_dir + '/' + fname + "_aligned.fasta"
log_path = output_dir + '/' + fname + "_log.txt"
failure_path = output_dir + '/' + fname + "_failures.fasta"
if alignment_method in alignment_method_constructors:
# try/except was causing problems here, so replacing with
# an explicit check
# define the aligner params
aligner_constructor =\
alignment_method_constructors[alignment_method]
aligner_type = alignment_method
params = {'min_len': min_length,
'min_pct': opts.min_percent_id,
'template_filepath': opts.template_fp,
'blast_db': opts.blast_db,
'pairwise_alignment_method': opts.pairwise_alignment_method}
# build the aligner object
aligner = aligner_constructor(params)
# apply the aligner
aligner(input_seqs_filepath, result_path=result_path,
log_path=log_path, failure_path=failure_path)
else:
# define the aligner params
aligner = CogentAligner({
'Module': alignment_module_names.get(alignment_method, 'Unknown'),
'Method': alignment_method
})
if alignment_method == "muscle":
if opts.muscle_max_memory is not None:
aligner.Params["-maxmb"] = str(opts.muscle_max_memory)
# build the aligner
aligner_type = 'Cogent'
# apply the aligner
aligner(result_path, seq_path=input_seqs_filepath,
log_path=log_path)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
if opts.min_percent_id <= 1.0:
opts.min_percent_id *= 100
if not (1.0 <= opts.min_percent_id <= 100.0):
option_parser.error('Minimum percent sequence identity must be' +
' between 1.0 and 100.0: %2.2f' %
opts.min_percent_id)
if not opts.template_fp and opts.alignment_method == 'pynast':
option_parser.error(
'PyNAST requires a template alignment to be passed via -t')
input_seqs_filepath = opts.input_fasta_fp
alignment_method = opts.alignment_method
output_dir = opts.output_dir or alignment_method + '_aligned'
create_dir(output_dir, fail_on_exist=False)
# compute the minimum alignment length if a negative value was
# provided (the default)
min_length = opts.min_length
if min_length < 0:
min_length = compute_min_alignment_length(
open(input_seqs_filepath, 'U'))
fpath, ext = splitext(input_seqs_filepath)
input_dir, fname = split(fpath)
result_path = output_dir + '/' + fname + "_aligned.fasta"
log_path = output_dir + '/' + fname + "_log.txt"
failure_path = output_dir + '/' + fname + "_failures.fasta"
if alignment_method in alignment_method_constructors:
# try/except was causing problems here, so replacing with
# an explicit check
# define the aligner params
aligner_constructor =\
alignment_method_constructors[alignment_method]
aligner_type = alignment_method
params = {
'min_len': min_length,
'min_pct': opts.min_percent_id,
'template_filepath': opts.template_fp,
'blast_db': opts.blast_db,
'pairwise_alignment_method': opts.pairwise_alignment_method
}
# build the aligner object
aligner = aligner_constructor(params)
# apply the aligner
aligner(input_seqs_filepath,
result_path=result_path,
log_path=log_path,
failure_path=failure_path)
else:
# define the aligner params
aligner = CogentAligner({
'Module':
alignment_module_names.get(alignment_method, 'Unknown'),
'Method':
alignment_method
})
if alignment_method == "muscle":
if opts.muscle_max_memory is not None:
aligner.Params["-maxmb"] = str(opts.muscle_max_memory)
# build the aligner
aligner_type = 'Cogent'
# apply the aligner
aligner(result_path, seq_path=input_seqs_filepath, log_path=log_path)
def _precommand_initiation(self, input_fp, output_dir, working_dir,
params):
if params['min_length'] < 0:
params['min_length'] = compute_min_alignment_length(
open(input_fp, 'U'))
def _precommand_initiation(
self, input_fp, output_dir, working_dir, params):
if params['min_length'] < 0:
params['min_length'] = compute_min_alignment_length(
open(input_fp, 'U'))
