def test_convert_tree_tips(self):
"""Convert tree tips to phylip labels"""
# convert tree tips to PHYLIP labels
tree = convert_tree_tips(self.align_map, self.tmp_tree_fname)
self.assertEqual(tree.getNewick(with_distances=True), PHYLIP_TREE)
def test_convert_tree_tips(self):
"""Convert tree tips to phylip labels"""
# convert tree tips to PHYLIP labels
tree = convert_tree_tips(self.align_map, self.tmp_tree_fname)
self.assertEqual(tree.getNewick(with_distances=True), PHYLIP_TREE)
def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
parameters = {}
# get the tree insertion method to use
module = opts.insertion_method
# create output directory
output_dir = opts.output_dir
create_dir(output_dir)
# list of tree insertion methods
tree_insertion_module_names = \
{'raxml_v730': brokit.raxml_v730,
'parsinsert': brokit.parsinsert,
'pplacer': brokit.pplacer}
# load input sequences and convert to phylip since the tools require
# the query sequences to phylip-compliant names
load_aln = parse_fasta(open(opts.input_fasta_fp, 'U'))
aln = DenseAlignment(load_aln)
seqs, align_map = aln.toPhylip()
if opts.method_params_fp:
param_dict = parse_qiime_parameters(open(opts.method_params_fp, 'U'))
if module == 'raxml_v730':
# load the reference sequences
load_ref_aln = \
DenseAlignment(parse_fasta(open(opts.refseq_fp, 'U')))
# combine and load the reference plus query
combined_aln = parse_fasta(StringIO(load_ref_aln.toFasta() +
'\n' + aln.toFasta()))
# overwrite the alignment map
aln = DenseAlignment(combined_aln)
seqs, align_map = aln.toPhylip()
try:
parameters = param_dict['raxml']
except:
parameters = {}
tree = convert_tree_tips(align_map, opts.starting_tree_fp)
# write out the tree with phylip labels
updated_tree_fp = join(output_dir,
'%s_phylip_named_tree.tre' % (module))
write_updated_tree_file(updated_tree_fp, tree)
# set the primary parameters for raxml
parameters['-w'] = abspath(output_dir) + '/'
parameters["-n"] = split(splitext(get_tmp_filename())[0])[-1]
parameters["-t"] = updated_tree_fp
if "-f" not in parameters:
parameters["-f"] = 'v'
if "-m" not in parameters:
parameters["-m"] = 'GTRGAMMA'
elif module == 'pplacer':
try:
parameters = param_dict['pplacer']
except:
parameters = {}
# make sure stats file is passed
if not opts.stats_fp:
raise IOError(
'When using pplacer, the RAxML produced info file is required.')
# set the primary parameters for pplacer - allow for user-defined
parameters['--out-dir'] = abspath(output_dir) + '/'
parameters["-t"] = opts.starting_tree_fp
parameters['-r'] = opts.refseq_fp
parameters['-s'] = opts.stats_fp
elif module == 'parsinsert':
try:
parameters = param_dict['parsinsert']
except:
parameters = {}
# define log fp
log_fp = join(output_dir, 'parsinsert.log')
# define tax assignment values fp
tax_assign_fp = join(output_dir, 'parsinsert_assignments.log')
parameters["-l"] = log_fp
parameters["-o"] = tax_assign_fp
parameters["-s"] = opts.refseq_fp
parameters["-t"] = opts.starting_tree_fp
# call the module and return a tree object
result = \
tree_insertion_module_names[module].insert_sequences_into_tree(seqs,
moltype=DNA, params=parameters)
result_tree = strip_and_rename_unwanted_labels_from_tree(align_map, result)
# write out the resulting tree
final_tree = join(output_dir, '%s_final_placement.tre' % (module))
write_updated_tree_file(final_tree, result)
def main():
option_parser, opts, args =\
parse_command_line_parameters(**script_info)
parameters = {}
# get the tree insertion method to use
module = opts.insertion_method
# create output directory
output_dir = opts.output_dir
create_dir(output_dir)
# list of tree insertion methods
tree_insertion_module_names = \
{'raxml_v730':cogent.app.raxml_v730,
'parsinsert':cogent.app.parsinsert,
'pplacer':cogent.app.pplacer}
# load input sequences and convert to phylip since the tools require
# the query sequences to phylip-compliant names
load_aln = MinimalFastaParser(open(opts.input_fasta_fp, 'U'))
aln = DenseAlignment(load_aln)
seqs, align_map = aln.toPhylip()
if opts.method_params_fp:
param_dict = parse_qiime_parameters(open(opts.method_params_fp, 'U'))
if module == 'raxml_v730':
# load the reference sequences
load_ref_aln = \
DenseAlignment(MinimalFastaParser(open(opts.refseq_fp,'U')))
# combine and load the reference plus query
combined_aln = MinimalFastaParser(StringIO(load_ref_aln.toFasta() + \
'\n' + aln.toFasta()))
# overwrite the alignment map
aln = DenseAlignment(combined_aln)
seqs, align_map = aln.toPhylip()
try:
parameters = param_dict['raxml']
except:
parameters = {}
tree = convert_tree_tips(align_map, opts.starting_tree_fp)
# write out the tree with phylip labels
updated_tree_fp = join(output_dir, \
'%s_phylip_named_tree.tre' % (module))
write_updated_tree_file(updated_tree_fp, tree)
# set the primary parameters for raxml
parameters['-w'] = abspath(output_dir) + '/'
parameters["-n"] = split(splitext(get_tmp_filename())[0])[-1]
parameters["-t"] = updated_tree_fp
if "-f" not in parameters:
parameters["-f"] = 'v'
if "-m" not in parameters:
parameters["-m"] = 'GTRGAMMA'
elif module == 'pplacer':
try:
parameters = param_dict['pplacer']
except:
parameters = {}
# make sure stats file is passed
if not opts.stats_fp:
raise IOError, \
'When using pplacer, the RAxML produced info file is required.'
# set the primary parameters for pplacer - allow for user-defined
parameters['--out-dir'] = abspath(output_dir) + '/'
parameters["-t"] = opts.starting_tree_fp
parameters['-r'] = opts.refseq_fp
parameters['-s'] = opts.stats_fp
elif module == 'parsinsert':
try:
parameters = param_dict['parsinsert']
except:
parameters = {}
# define log fp
log_fp = join(output_dir, 'parsinsert.log')
# define tax assignment values fp
tax_assign_fp = join(output_dir, 'parsinsert_assignments.log')
parameters["-l"] = log_fp
parameters["-o"] = tax_assign_fp
parameters["-s"] = opts.refseq_fp
parameters["-t"] = opts.starting_tree_fp
# call the module and return a tree object
result = \
tree_insertion_module_names[module].insert_sequences_into_tree(seqs,
moltype=DNA, params=parameters)
result_tree = strip_and_rename_unwanted_labels_from_tree(align_map, result)
# write out the resulting tree
final_tree = join(output_dir, '%s_final_placement.tre' % (module))
write_updated_tree_file(final_tree, result)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
parameters = {}
# get the tree insertion method to use
module = opts.insertion_method
# create output directory
output_dir = opts.output_dir
create_dir(output_dir)
# list of tree insertion methods
tree_insertion_module_names = {
"raxml_v730": qiime.pycogent_backports.raxml_v730,
"parsinsert": qiime.pycogent_backports.parsinsert,
"pplacer": qiime.pycogent_backports.pplacer,
}
# load input sequences and convert to phylip since the tools require
# the query sequences to phylip-compliant names
load_aln = MinimalFastaParser(open(opts.input_fasta_fp, "U"))
aln = DenseAlignment(load_aln)
seqs, align_map = aln.toPhylip()
if opts.method_params_fp:
param_dict = parse_qiime_parameters(open(opts.method_params_fp, "U"))
if module == "raxml_v730":
# load the reference sequences
load_ref_aln = DenseAlignment(MinimalFastaParser(open(opts.refseq_fp, "U")))
# combine and load the reference plus query
combined_aln = MinimalFastaParser(StringIO(load_ref_aln.toFasta() + "\n" + aln.toFasta()))
# overwrite the alignment map
aln = DenseAlignment(combined_aln)
seqs, align_map = aln.toPhylip()
try:
parameters = param_dict["raxml"]
except:
parameters = {}
tree = convert_tree_tips(align_map, opts.starting_tree_fp)
# write out the tree with phylip labels
updated_tree_fp = join(output_dir, "%s_phylip_named_tree.tre" % (module))
write_updated_tree_file(updated_tree_fp, tree)
# set the primary parameters for raxml
parameters["-w"] = abspath(output_dir) + "/"
parameters["-n"] = split(splitext(get_tmp_filename())[0])[-1]
parameters["-t"] = updated_tree_fp
if "-f" not in parameters:
parameters["-f"] = "v"
if "-m" not in parameters:
parameters["-m"] = "GTRGAMMA"
elif module == "pplacer":
try:
parameters = param_dict["pplacer"]
except:
parameters = {}
# make sure stats file is passed
if not opts.stats_fp:
raise IOError, "When using pplacer, the RAxML produced info file is required."
# set the primary parameters for pplacer - allow for user-defined
parameters["--out-dir"] = abspath(output_dir) + "/"
parameters["-t"] = opts.starting_tree_fp
parameters["-r"] = opts.refseq_fp
parameters["-s"] = opts.stats_fp
elif module == "parsinsert":
try:
parameters = param_dict["parsinsert"]
except:
parameters = {}
# define log fp
log_fp = join(output_dir, "parsinsert.log")
# define tax assignment values fp
tax_assign_fp = join(output_dir, "parsinsert_assignments.log")
parameters["-l"] = log_fp
parameters["-o"] = tax_assign_fp
parameters["-s"] = opts.refseq_fp
parameters["-t"] = opts.starting_tree_fp
# call the module and return a tree object
result = tree_insertion_module_names[module].insert_sequences_into_tree(seqs, moltype=DNA, params=parameters)
result_tree = strip_and_rename_unwanted_labels_from_tree(align_map, result)
# write out the resulting tree
final_tree = join(output_dir, "%s_final_placement.tre" % (module))
write_updated_tree_file(final_tree, result)
