def main():
"""Run chimera checker with given options>"""
option_parser, opts, args = parse_command_line_parameters(**script_info)
#additional option checks
if opts.chimera_detection_method == 'blast_fragments':
if not (opts.blast_db or opts.reference_seqs_fp):
option_parser.error('Must provide either --blast_db or'+\
' --reference_seqs_fp and --id_to_taxonomy_fp when'+\
' method is blast_fragments.')
if not opts.id_to_taxonomy_fp:
option_parser.error('Must provide --id_to_taxonomy_fp when method'+\
' is blast_fragments.')
if opts.num_fragments < 2:
option_parser.error('Invalid number of fragments (-n %d) Must be >= 2.' \
% opts.num_fragments)
elif opts.chimera_detection_method == 'ChimeraSlayer':
if not opts.aligned_reference_seqs_fp:
option_parser.error("Must provide --aligned_reference_seqs_fp "+\
"when using method ChimeraSlayer")
verbose = opts.verbose #not used yet ...
input_seqs_fp = opts.input_fasta_fp
id_to_taxonomy_fp = opts.id_to_taxonomy_fp
reference_seqs_fp = opts.reference_seqs_fp
chimera_detection_method = opts.chimera_detection_method
num_fragments = opts.num_fragments
output_fp = opts.output_fp
taxonomy_depth = opts.taxonomy_depth
max_e_value = opts.max_e_value
blast_db = opts.blast_db
keep_intermediates = opts.keep_intermediates
if not output_fp:
input_basename = splitext(split(input_seqs_fp)[1])[0]
output_fp = '%s_chimeric.txt' % input_basename
if chimera_detection_method == 'blast_fragments':
blast_fragments_identify_chimeras(input_seqs_fp,
id_to_taxonomy_fp,\
reference_seqs_fp,blast_db=blast_db,
num_fragments=opts.num_fragments,\
max_e_value=max_e_value,\
output_fp=output_fp,
taxonomy_depth=taxonomy_depth)
elif chimera_detection_method == 'ChimeraSlayer':
chimeraSlayer_identify_chimeras(input_seqs_fp,
output_fp=output_fp,
db_FASTA_fp=opts.reference_seqs_fp,
db_NAST_fp=opts.aligned_reference_seqs_fp,
min_div_ratio=opts.min_div_ratio,
keep_intermediates=keep_intermediates)
def main():
"""Run chimera checker with given options>"""
option_parser, opts, args = parse_command_line_parameters(**script_info)
#additional option checks
if opts.chimera_detection_method == 'blast_fragments':
if not (opts.blast_db or opts.reference_seqs_fp):
option_parser.error('Must provide either --blast_db or'+\
' --reference_seqs_fp and --id_to_taxonomy_fp when'+\
' method is blast_fragments.')
if not opts.id_to_taxonomy_fp:
option_parser.error('Must provide --id_to_taxonomy_fp when method'+\
' is blast_fragments.')
if opts.num_fragments < 2:
option_parser.error('Invalid number of fragments (-n %d) Must be >= 2.' \
% opts.num_fragments)
elif opts.chimera_detection_method == 'ChimeraSlayer':
if not opts.aligned_reference_seqs_fp:
option_parser.error("Must provide --aligned_reference_seqs_fp "+\
"when using method ChimeraSlayer")
verbose = opts.verbose #not used yet ...
input_seqs_fp = opts.input_fasta_fp
id_to_taxonomy_fp = opts.id_to_taxonomy_fp
reference_seqs_fp = opts.reference_seqs_fp
chimera_detection_method = opts.chimera_detection_method
num_fragments = opts.num_fragments
output_fp = opts.output_fp
taxonomy_depth = opts.taxonomy_depth
max_e_value = opts.max_e_value
blast_db = opts.blast_db
keep_intermediates = opts.keep_intermediates
if not output_fp:
input_basename = splitext(split(input_seqs_fp)[1])[0]
output_fp = '%s_chimeric.txt' % input_basename
if chimera_detection_method == 'blast_fragments':
blast_fragments_identify_chimeras(input_seqs_fp,
id_to_taxonomy_fp,\
reference_seqs_fp,blast_db=blast_db,
num_fragments=opts.num_fragments,\
max_e_value=max_e_value,\
output_fp=output_fp,
taxonomy_depth=taxonomy_depth)
elif chimera_detection_method == 'ChimeraSlayer':
chimeraSlayer_identify_chimeras(input_seqs_fp,
output_fp=output_fp,
db_FASTA_fp=opts.reference_seqs_fp,
db_NAST_fp=opts.aligned_reference_seqs_fp,
min_div_ratio=opts.min_div_ratio,
keep_intermediates=keep_intermediates)
def main():
"""Run chimera checker with given options>"""
option_parser, opts, args = parse_command_line_parameters(**script_info)
#additional option checks
if opts.chimera_detection_method == 'blast_fragments':
if not (opts.blast_db or opts.reference_seqs_fp):
option_parser.error('Must provide either --blast_db or'+\
' --reference_seqs_fp and --id_to_taxonomy_fp when'+\
' method is blast_fragments.')
if not opts.id_to_taxonomy_fp:
option_parser.error('Must provide --id_to_taxonomy_fp when method'+\
' is blast_fragments.')
if opts.num_fragments < 2:
option_parser.error('Invalid number of fragments (-n %d) Must be >= 2.' \
% opts.num_fragments)
elif opts.chimera_detection_method == 'ChimeraSlayer':
if not opts.aligned_reference_seqs_fp:
option_parser.error("Must provide --aligned_reference_seqs_fp "
"when using method ChimeraSlayer")
elif opts.chimera_detection_method == 'usearch61':
if opts.suppress_usearch61_ref and opts.suppress_usearch61_denovo:
option_parser.error("Supressing both de novo and reference "
"chimera detection not allowed.")
if not opts.reference_seqs_fp and not opts.suppress_usearch61_ref:
option_parser.error("--reference_seqs_fp required for reference "
"based chimera detection, suppress reference based chimera "
"detection with --suppress_usearch61_ref")
if opts.reference_seqs_fp:
try:
temp_f = open(opts.reference_seqs_fp, "U")
temp_f.close()
except IOError:
raise IOError,("Unable to open --reference_seqs_fp, please "
"check filepath and permissions.")
if opts.non_chimeras_retention not in ['intersection', 'union']:
option_parser.error("--non_chimeras_retention must be either "
"'union' or 'intersection'")
if opts.usearch61_xn <= 1:
option_parser.error("--usearch61_xn must be > 1")
if opts.usearch61_dn <= 0:
option_parser.error("--usearch61_dn must be > 0")
if opts.usearch61_mindiffs <= 0:
option_parser.error("--usearch61_mindiffs must be > 0")
if opts.usearch61_mindiv <= 0:
option_parser.error("--usearch61_mindiv must be > 0")
if opts.usearch61_abundance_skew <= 0:
option_parser.error("--usearch61_abundance_skew must be > 0")
verbose = opts.verbose #not used yet ...
input_seqs_fp = opts.input_fasta_fp
id_to_taxonomy_fp = opts.id_to_taxonomy_fp
reference_seqs_fp = opts.reference_seqs_fp
chimera_detection_method = opts.chimera_detection_method
num_fragments = opts.num_fragments
output_fp = opts.output_fp
taxonomy_depth = opts.taxonomy_depth
max_e_value = opts.max_e_value
blast_db = opts.blast_db
keep_intermediates = opts.keep_intermediates
threads = opts.threads
# calculate threads as 1 per CPU, or use float of input value
if threads == 'one_per_cpu':
threads = float(1/cpu_count())
else:
# Make sure input is a float
try:
threads = float(threads)
except ValueError:
option_parser.error("--threads must be a float value if "
"default 'one_per_cpu' value overridden.")
if not output_fp:
if chimera_detection_method == "usearch61":
output_dir = "usearch61_chimeras/"
create_dir(output_dir, fail_on_exist=False)
else:
input_basename = splitext(split(input_seqs_fp)[1])[0]
output_fp = '%s_chimeric.txt' % input_basename
elif chimera_detection_method == "usearch61":
output_dir = output_fp
create_dir(output_dir, fail_on_exist=False)
if chimera_detection_method == 'blast_fragments':
blast_fragments_identify_chimeras(input_seqs_fp,
id_to_taxonomy_fp,\
reference_seqs_fp,blast_db=blast_db,
num_fragments=opts.num_fragments,\
max_e_value=max_e_value,\
output_fp=output_fp,
taxonomy_depth=taxonomy_depth)
elif chimera_detection_method == 'ChimeraSlayer':
chimeraSlayer_identify_chimeras(input_seqs_fp,
output_fp=output_fp,
db_FASTA_fp=opts.reference_seqs_fp,
db_NAST_fp=opts.aligned_reference_seqs_fp,
min_div_ratio=opts.min_div_ratio,
keep_intermediates=keep_intermediates)
elif chimera_detection_method == 'usearch61':
usearch61_chimera_check(input_seqs_fp,
output_dir=output_dir,
reference_seqs_fp=reference_seqs_fp,
suppress_usearch61_intermediates=opts.suppress_usearch61_intermediates,
suppress_usearch61_ref = opts.suppress_usearch61_ref,
suppress_usearch61_denovo = opts.suppress_usearch61_denovo,
split_by_sampleid = opts.split_by_sampleid,
non_chimeras_retention = opts.non_chimeras_retention,
usearch61_minh = opts.usearch61_minh,
usearch61_xn = opts.usearch61_xn,
usearch61_dn = opts.usearch61_dn,
usearch61_mindiffs = opts.usearch61_mindiffs,
usearch61_mindiv = opts.usearch61_mindiv,
usearch61_abundance_skew = opts.usearch61_abundance_skew,
percent_id_usearch61 = opts.percent_id_usearch61,
minlen = opts.minlen,
word_length = opts.word_length,
max_accepts = opts.max_accepts,
max_rejects = opts.max_rejects,
verbose = opts.verbose,
threads = threads)
def main():
"""Run chimera checker with given options>"""
option_parser, opts, args = parse_command_line_parameters(**script_info)
#additional option checks
if opts.chimera_detection_method == 'blast_fragments':
if not (opts.blast_db or opts.reference_seqs_fp):
option_parser.error('Must provide either --blast_db or'+\
' --reference_seqs_fp and --id_to_taxonomy_fp when'+\
' method is blast_fragments.')
if not opts.id_to_taxonomy_fp:
option_parser.error('Must provide --id_to_taxonomy_fp when method'+\
' is blast_fragments.')
if opts.num_fragments < 2:
option_parser.error('Invalid number of fragments (-n %d) Must be >= 2.' \
% opts.num_fragments)
elif opts.chimera_detection_method == 'ChimeraSlayer':
if not opts.aligned_reference_seqs_fp:
option_parser.error("Must provide --aligned_reference_seqs_fp "
"when using method ChimeraSlayer")
elif opts.chimera_detection_method == 'usearch61':
if opts.suppress_usearch61_ref and opts.suppress_usearch61_denovo:
option_parser.error("Supressing both de novo and reference "
"chimera detection not allowed.")
if not opts.reference_seqs_fp and not opts.suppress_usearch61_ref:
option_parser.error(
"--reference_seqs_fp required for reference "
"based chimera detection, suppress reference based chimera "
"detection with --suppress_usearch61_ref")
if opts.reference_seqs_fp:
try:
temp_f = open(opts.reference_seqs_fp, "U")
temp_f.close()
except IOError:
raise IOError, ("Unable to open --reference_seqs_fp, please "
"check filepath and permissions.")
if opts.non_chimeras_retention not in ['intersection', 'union']:
option_parser.error("--non_chimeras_retention must be either "
"'union' or 'intersection'")
if opts.usearch61_xn <= 1:
option_parser.error("--usearch61_xn must be > 1")
if opts.usearch61_dn <= 0:
option_parser.error("--usearch61_dn must be > 0")
if opts.usearch61_mindiffs <= 0:
option_parser.error("--usearch61_mindiffs must be > 0")
if opts.usearch61_mindiv <= 0:
option_parser.error("--usearch61_mindiv must be > 0")
if opts.usearch61_abundance_skew <= 0:
option_parser.error("--usearch61_abundance_skew must be > 0")
verbose = opts.verbose #not used yet ...
input_seqs_fp = opts.input_fasta_fp
id_to_taxonomy_fp = opts.id_to_taxonomy_fp
reference_seqs_fp = opts.reference_seqs_fp
chimera_detection_method = opts.chimera_detection_method
num_fragments = opts.num_fragments
output_fp = opts.output_fp
taxonomy_depth = opts.taxonomy_depth
max_e_value = opts.max_e_value
blast_db = opts.blast_db
keep_intermediates = opts.keep_intermediates
threads = opts.threads
# calculate threads as 1 per CPU, or use float of input value
if threads == 'one_per_cpu':
threads = float(1 / cpu_count())
else:
# Make sure input is a float
try:
threads = float(threads)
except ValueError:
option_parser.error("--threads must be a float value if "
"default 'one_per_cpu' value overridden.")
if not output_fp:
if chimera_detection_method == "usearch61":
output_dir = "usearch61_chimeras/"
create_dir(output_dir, fail_on_exist=False)
else:
input_basename = splitext(split(input_seqs_fp)[1])[0]
output_fp = '%s_chimeric.txt' % input_basename
elif chimera_detection_method == "usearch61":
output_dir = output_fp
create_dir(output_dir, fail_on_exist=False)
if chimera_detection_method == 'blast_fragments':
blast_fragments_identify_chimeras(input_seqs_fp,
id_to_taxonomy_fp,\
reference_seqs_fp,blast_db=blast_db,
num_fragments=opts.num_fragments,\
max_e_value=max_e_value,\
output_fp=output_fp,
taxonomy_depth=taxonomy_depth)
elif chimera_detection_method == 'ChimeraSlayer':
chimeraSlayer_identify_chimeras(
input_seqs_fp,
output_fp=output_fp,
db_FASTA_fp=opts.reference_seqs_fp,
db_NAST_fp=opts.aligned_reference_seqs_fp,
min_div_ratio=opts.min_div_ratio,
keep_intermediates=keep_intermediates)
elif chimera_detection_method == 'usearch61':
usearch61_chimera_check(
input_seqs_fp,
output_dir=output_dir,
reference_seqs_fp=reference_seqs_fp,
suppress_usearch61_intermediates=opts.
suppress_usearch61_intermediates,
suppress_usearch61_ref=opts.suppress_usearch61_ref,
suppress_usearch61_denovo=opts.suppress_usearch61_denovo,
split_by_sampleid=opts.split_by_sampleid,
non_chimeras_retention=opts.non_chimeras_retention,
usearch61_minh=opts.usearch61_minh,
usearch61_xn=opts.usearch61_xn,
usearch61_dn=opts.usearch61_dn,
usearch61_mindiffs=opts.usearch61_mindiffs,
usearch61_mindiv=opts.usearch61_mindiv,
usearch61_abundance_skew=opts.usearch61_abundance_skew,
percent_id_usearch61=opts.percent_id_usearch61,
minlen=opts.minlen,
word_length=opts.word_length,
max_accepts=opts.max_accepts,
max_rejects=opts.max_rejects,
verbose=opts.verbose,
threads=threads)
