def test_sort_seqs_by_clustersize(self):
"""sort_seqs_by_clustersize works"""
seqs = {
"0": "AAA",
"1": "AAT",
"2": "ATT",
"3": "TTT",
"4": "TAA",
"5": "TTA",
"6": "CCC",
"7": "GGG",
"8": "GCG",
}
mapping = {"8": ["7", "6"], "1": ["0", "2", "5"], "4": ["3"]}
observed = list(sort_seqs_by_clustersize(seqs.iteritems(), mapping))
expected = [
("1", "AAT"),
("8", "GCG"),
("4", "TAA"),
("7", "GGG"),
("6", "CCC"),
("5", "TTA"),
("3", "TTT"),
("2", "ATT"),
("0", "AAA"),
]
self.assertEqual(observed, expected)
def test_sort_seqs_by_clustersize(self):
"""sort_seqs_by_clustersize works"""
seqs = {
'0': "AAA",
'1': "AAT",
'2': "ATT",
'3': "TTT",
'4': "TAA",
'5': "TTA",
'6': "CCC",
'7': "GGG",
'8': "GCG"
}
mapping = {"8": ["7", "6"], "1": ["0", "2", "5"], "4": ["3"]}
observed = list(sort_seqs_by_clustersize(seqs.iteritems(), mapping))
expected = [('1', "AAT"), ('8', "GCG"), ('4', 'TAA'), ('7', 'GGG'),
('6', 'CCC'), ('5', 'TTA'), ('3', 'TTT'), ('2', 'ATT'),
('0', 'AAA')]
self.assertEqual(observed, expected)
def test_sort_seqs_by_clustersize(self):
"""sort_seqs_by_clustersize works"""
seqs = {'0': "AAA",
'1': "AAT",
'2': "ATT",
'3': "TTT",
'4': "TAA",
'5': "TTA",
'6': "CCC",
'7': "GGG",
'8': "GCG"}
mapping = {"8":["7","6"],
"1":["0","2","5"],
"4":["3"]}
observed = list(sort_seqs_by_clustersize(seqs.iteritems(), mapping))
expected = [('1',"AAT"),('8',"GCG"),('4', 'TAA'), ('7', 'GGG'),
('6', 'CCC'), ('5', 'TTA'), ('3', 'TTT'), ('2', 'ATT'),
('0', 'AAA')]
self.assertEqual(observed, expected)
def denoise_per_sample(sff_fps, fasta_fp, tmpoutdir, cluster=False,
num_cpus=1, squeeze=True, percent_id=0.97, bail=1,
primer="", low_cutoff=3.75, high_cutoff=4.5,
log_fp="denoiser.log", low_memory=False, verbose=False,
error_profile=DENOISER_DATA_DIR +
'FLX_error_profile.dat',
max_num_rounds=None, titanium=False):
"""Denoise each sample separately"""
# abort early if binary is missing
check_flowgram_ali_exe()
log_fh = None
if log_fp:
# switch of buffering for global log file
log_fh = open(tmpoutdir + "/" + log_fp, "w", 0)
# overwrite settings if titanium is set
# This flag is only used from qiime. Remove after qiime integration
if titanium:
error_profile = DENOISER_DATA_DIR + "Titanium_error_profile.dat"
low_cutoff = 4
high_cutoff = 5
if verbose:
log_fh.write("Denoiser version: %s\n" % __version__)
log_fh.write("SFF files: %s\n" % ', '.join(sff_fps))
log_fh.write("Fasta file: %s\n" % fasta_fp)
log_fh.write("Cluster: %s\n" % cluster)
log_fh.write("Num CPUs: %d\n" % num_cpus)
log_fh.write("Squeeze Seqs: %s\n" % squeeze)
log_fh.write("tmpdir: %s\n\n" % tmpoutdir)
log_fh.write("percent_id threshold: %.2f\n" % percent_id)
log_fh.write("Minimal sequence coverage for first phase: %d\n" % bail)
log_fh.write("Error profile: %s\n" % error_profile)
log_fh.write("Maximal number of iteration: %s\n\n" % max_num_rounds)
# here we go ...
sff_files = split_sff(map(open, sff_fps), open(fasta_fp), tmpoutdir)
combined_mapping = {}
result_centroids = []
result_singletons_files = []
# denoise each sample separately
for i, sff_file in enumerate(sff_files):
if not exists(tmpoutdir + ("/%d" % i)):
makedirs(tmpoutdir + ("/%d" % i))
out_fp = tmpoutdir + ("/%d/" % i)
denoise_seqs([sff_file], fasta_fp, out_fp, None, cluster,
num_cpus, squeeze, percent_id, bail, primer,
low_cutoff, high_cutoff, log_fp, low_memory,
verbose, error_profile, max_num_rounds)
# collect partial results
this_rounds_mapping = read_denoiser_mapping(
open(out_fp + "/denoiser_mapping.txt"))
combined_mapping.update(this_rounds_mapping)
result_centroids.append(
parse_fasta(open(out_fp + "/centroids.fasta")))
result_singletons_files.append(out_fp + "/singletons.fasta")
# write the combined files
store_mapping(combined_mapping, tmpoutdir, "denoiser")
seqs = chain(*result_centroids)
fasta_fh = open(tmpoutdir + "/denoised.fasta", "w")
# write centroids sorted by clustersize
write_Fasta_from_name_seq_pairs(
sort_seqs_by_clustersize(seqs, combined_mapping),
fasta_fh)
for singleton_file in result_singletons_files:
write_Fasta_from_name_seq_pairs(
parse_fasta(open(singleton_file, "r")),
fasta_fh)
fasta_fh.close()
# return outdir for tests/test_denoiser
return tmpoutdir
def denoise_per_sample(sff_fps,
fasta_fp,
tmpoutdir,
cluster=False,
num_cpus=1,
squeeze=True,
percent_id=0.97,
bail=1,
primer="",
low_cutoff=3.75,
high_cutoff=4.5,
log_fp="denoiser.log",
low_memory=False,
verbose=False,
error_profile=DENOISER_DATA_DIR +
'FLX_error_profile.dat',
max_num_rounds=None,
titanium=False):
"""Denoise each sample separately"""
# abort early if binary is missing
check_flowgram_ali_exe()
log_fh = None
if log_fp:
# switch of buffering for global log file
log_fh = open(tmpoutdir + "/" + log_fp, "w", 0)
# overwrite settings if titanium is set
# This flag is only used from qiime. Remove after qiime integration
if titanium:
error_profile = DENOISER_DATA_DIR + "Titanium_error_profile.dat"
low_cutoff = 4
high_cutoff = 5
if verbose:
log_fh.write("Denoiser version: %s\n" % __version__)
log_fh.write("SFF files: %s\n" % ', '.join(sff_fps))
log_fh.write("Fasta file: %s\n" % fasta_fp)
log_fh.write("Cluster: %s\n" % cluster)
log_fh.write("Num CPUs: %d\n" % num_cpus)
log_fh.write("Squeeze Seqs: %s\n" % squeeze)
log_fh.write("tmpdir: %s\n\n" % tmpoutdir)
log_fh.write("percent_id threshold: %.2f\n" % percent_id)
log_fh.write("Minimal sequence coverage for first phase: %d\n" % bail)
log_fh.write("Error profile: %s\n" % error_profile)
log_fh.write("Maximal number of iteration: %s\n\n" % max_num_rounds)
# here we go ...
sff_files = split_sff(map(open, sff_fps), open(fasta_fp), tmpoutdir)
combined_mapping = {}
result_centroids = []
result_singletons_files = []
# denoise each sample separately
for i, sff_file in enumerate(sff_files):
if not exists(tmpoutdir + ("/%d" % i)):
makedirs(tmpoutdir + ("/%d" % i))
out_fp = tmpoutdir + ("/%d/" % i)
denoise_seqs([sff_file], fasta_fp, out_fp, None, cluster, num_cpus,
squeeze, percent_id, bail, primer, low_cutoff,
high_cutoff, log_fp, low_memory, verbose, error_profile,
max_num_rounds)
# collect partial results
this_rounds_mapping = read_denoiser_mapping(
open(out_fp + "/denoiser_mapping.txt"))
combined_mapping.update(this_rounds_mapping)
result_centroids.append(parse_fasta(open(out_fp + "/centroids.fasta")))
result_singletons_files.append(out_fp + "/singletons.fasta")
# write the combined files
store_mapping(combined_mapping, tmpoutdir, "denoiser")
seqs = chain(*result_centroids)
fasta_fh = open(tmpoutdir + "/denoised.fasta", "w")
# write centroids sorted by clustersize
write_Fasta_from_name_seq_pairs(
sort_seqs_by_clustersize(seqs, combined_mapping), fasta_fh)
for singleton_file in result_singletons_files:
write_Fasta_from_name_seq_pairs(parse_fasta(open(singleton_file, "r")),
fasta_fh)
fasta_fh.close()
# return outdir for tests/test_denoiser
return tmpoutdir
