def main(commandline_args=None):
parser, opts, args = parse_command_line_parameters(**script_info)
if not opts.sff_fp:
parser.error('Required option flowgram file path (-i) not specified')
elif not files_exist(opts.sff_fp):
parser.error(
'Flowgram file path does not exist:\n %s \n Pass a valid one via -i.'
% opts.sff_fp)
#make tmp and output dir
tmp_dir = get_tmp_filename(tmp_dir=opts.output_dir + "/", suffix="/")
try:
makedirs(tmp_dir)
except OSError:
exit("Creating temporary directory failed")
if (not exists(opts.output_dir)):
try:
makedirs(opts.output_dir)
except OSError:
exit("Creating output directory failed")
#open logger
log_fh = None
if opts.verbose:
#append to the log file of the master process
log_fh = open(opts.output_dir + "/" + opts.log_fp, "a", 0)
log_fh.write("SFF file: %s\n" % opts.sff_fp)
log_fh.write("Fasta file: %s\n" % opts.fasta_fp)
log_fh.write("Output dir: %s\n" % opts.output_dir)
log_fh.write("Squeeze Seqs: %s\n" % opts.squeeze)
log_fh.write("Primer sequence: %s\n" % opts.primer)
(deprefixed_sff_fp, l, mapping, seqs) = \
preprocess(opts.sff_fp, log_fh, fasta_fp=opts.fasta_fp,
out_fp=tmp_dir,
verbose=opts.verbose, squeeze=opts.squeeze,
primer=opts.primer)
# explicitly close log file, as this file can be shared with the master
# Closing it here assures that all preprocess writes happen before the
# master writes
if log_fh:
log_fh.close()
#move files to output dir
rename(tmp_dir + "/prefix_dereplicated.sff.txt",
opts.output_dir + "/prefix_dereplicated.sff.txt")
rename(tmp_dir + "/prefix_dereplicated.fasta",
opts.output_dir + "/prefix_dereplicated.fasta")
rename(tmp_dir + "/prefix_mapping.txt",
opts.output_dir + "/prefix_mapping.txt")
rmdir(tmp_dir)
def main(commandline_args=None):
parser, opts, args = parse_command_line_parameters(**script_info)
if not opts.sff_fp:
parser.error('Required option flowgram file path (-i) not specified')
elif not files_exist(opts.sff_fp):
parser.error('Flowgram file path does not exist:\n %s \n Pass a valid one via -i.'
% opts.sff_fp)
#make tmp and output dir
tmp_dir = get_tmp_filename(tmp_dir = opts.output_dir+"/", suffix="/")
try:
makedirs(tmp_dir)
except OSError:
exit("Creating temporary directory failed")
if(not exists(opts.output_dir)):
try:
makedirs(opts.output_dir)
except OSError:
exit("Creating output directory failed")
#open logger
log_fh=None
if opts.verbose:
#append to the log file of the master process
log_fh = open(opts.output_dir+"/"+opts.log_fp, "a", 0)
log_fh.write("SFF file: %s\n" % opts.sff_fp)
log_fh.write("Fasta file: %s\n" % opts.fasta_fp)
log_fh.write("Output dir: %s\n" % opts.output_dir)
log_fh.write("Squeeze Seqs: %s\n" % opts.squeeze)
log_fh.write("Primer sequence: %s\n" % opts.primer)
(deprefixed_sff_fp, l, mapping, seqs) = \
preprocess(opts.sff_fp, log_fh, fasta_fp=opts.fasta_fp,
out_fp=tmp_dir,
verbose=opts.verbose, squeeze=opts.squeeze,
primer=opts.primer)
# explicitly close log file, as this file can be shared with the master
# Closing it here assures that all preprocess writes happen before the
# master writes
if log_fh:
log_fh.close()
#move files to output dir
rename(tmp_dir+"/prefix_dereplicated.sff.txt",
opts.output_dir+"/prefix_dereplicated.sff.txt")
rename(tmp_dir+"/prefix_dereplicated.fasta",
opts.output_dir+"/prefix_dereplicated.fasta")
rename(tmp_dir+"/prefix_mapping.txt", opts.output_dir+"/prefix_mapping.txt")
rmdir(tmp_dir)
def main(commandline_args=None):
parser, opts, args = parse_command_line_parameters(**script_info)
# make tmp and output dir
try:
tmp_dir = mkdtemp(dir=opts.output_dir, suffix="/")
except OSError:
exit("Creating temporary directory failed")
if(not exists(opts.output_dir)):
try:
makedirs(opts.output_dir)
except OSError:
exit("Creating output directory failed")
# open logger
log_fh = None
if opts.verbose:
# append to the log file of the master process
log_fh = open(opts.output_dir + "/" + opts.log_fp, "a", 0)
log_fh.write("SFF files: %s" % ', '.join(opts.sff_fps))
log_fh.write("Fasta file: %s\n" % opts.fasta_fp)
log_fh.write("Output dir: %s\n" % opts.output_dir)
log_fh.write("Squeeze Seqs: %s\n" % opts.squeeze)
log_fh.write("Primer sequence: %s\n" % opts.primer)
(deprefixed_sff_fp, l, mapping, seqs) = \
preprocess(opts.sff_fps, log_fh, fasta_fp=opts.fasta_fp,
out_fp=tmp_dir,
verbose=opts.verbose, squeeze=opts.squeeze,
primer=opts.primer)
# explicitly close log file, as this file can be shared with the master
# Closing it here assures that all preprocess writes happen before the
# master writes
if log_fh:
log_fh.close()
# move files to output dir
rename(tmp_dir + "/prefix_dereplicated.sff.txt",
opts.output_dir + "/prefix_dereplicated.sff.txt")
rename(tmp_dir + "/prefix_dereplicated.fasta",
opts.output_dir + "/prefix_dereplicated.fasta")
rename(
tmp_dir +
"/prefix_mapping.txt",
opts.output_dir +
"/prefix_mapping.txt")
rmdir(tmp_dir)
def main(commandline_args=None):
parser, opts, args = parse_command_line_parameters(**script_info)
# make tmp and output dir
try:
tmp_dir = mkdtemp(dir=opts.output_dir, suffix="/")
except OSError:
exit("Creating temporary directory failed")
if (not exists(opts.output_dir)):
try:
makedirs(opts.output_dir)
except OSError:
exit("Creating output directory failed")
# open logger
log_fh = None
if opts.verbose:
# append to the log file of the master process
log_fh = open(opts.output_dir + "/" + opts.log_fp, "a", 0)
log_fh.write("SFF files: %s" % ', '.join(opts.sff_fps))
log_fh.write("Fasta file: %s\n" % opts.fasta_fp)
log_fh.write("Output dir: %s\n" % opts.output_dir)
log_fh.write("Squeeze Seqs: %s\n" % opts.squeeze)
log_fh.write("Primer sequence: %s\n" % opts.primer)
(deprefixed_sff_fp, l, mapping, seqs) = \
preprocess(opts.sff_fps, log_fh, fasta_fp=opts.fasta_fp,
out_fp=tmp_dir,
verbose=opts.verbose, squeeze=opts.squeeze,
primer=opts.primer)
# explicitly close log file, as this file can be shared with the master
# Closing it here assures that all preprocess writes happen before the
# master writes
if log_fh:
log_fh.close()
# move files to output dir
rename(tmp_dir + "/prefix_dereplicated.sff.txt",
opts.output_dir + "/prefix_dereplicated.sff.txt")
rename(tmp_dir + "/prefix_dereplicated.fasta",
opts.output_dir + "/prefix_dereplicated.fasta")
rename(tmp_dir + "/prefix_mapping.txt",
opts.output_dir + "/prefix_mapping.txt")
rmdir(tmp_dir)
def denoise_seqs(
sff_fps, fasta_fp, tmpoutdir, preprocess_fp=None, 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, checkpoint_fp=None):
"""The main routine to denoise flowgrams"""
# abort if binary is missing
check_flowgram_ali_exe()
if verbose:
# switch of buffering for log file
log_fh = open(tmpoutdir + "/" + log_fp, "w", 0)
else:
log_fh = None
# 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("Preprocess dir: %s\n" % preprocess_fp)
if checkpoint_fp:
log_fh.write("Resuming denoiser from %s\n" % checkpoint_fp)
log_fh.write("Primer sequence: %s\n" % primer)
log_fh.write("Running on 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" % 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("Low cut-off: %.2f\n" % low_cutoff)
log_fh.write("High cut-off: %.2f\n" % high_cutoff)
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 ...
# Phase I - clean up and truncate input sff
if(checkpoint_fp):
if (preprocess_fp):
# skip preprocessing as we should have data
# we already have preprocessed data, so use it
(deprefixed_sff_fp, l, mapping,
seqs) = read_preprocessed_data(preprocess_fp)
else:
raise ApplicationError(
"Resuming from checkpoint requires --preprocess option")
else:
if(preprocess_fp):
# we already have preprocessed data, so use it
(deprefixed_sff_fp, l, mapping,
seqs) = read_preprocessed_data(preprocess_fp)
elif(cluster):
preprocess_on_cluster(sff_fps, log_fp, fasta_fp=fasta_fp,
out_fp=tmpoutdir, verbose=verbose,
squeeze=squeeze, primer=primer)
(deprefixed_sff_fp, l, mapping,
seqs) = read_preprocessed_data(tmpoutdir)
else:
(deprefixed_sff_fp, l, mapping, seqs) = \
preprocess(
sff_fps, log_fh, fasta_fp=fasta_fp, out_fp=tmpoutdir,
verbose=verbose, squeeze=squeeze, primer=primer)
# preprocessor writes into same file, so better jump to end of file
if verbose:
log_fh.close()
log_fh = open(tmpoutdir + "/" + log_fp, "a", 0)
# phase II:
# use prefix map based clustering as initial centroids and greedily
# add flowgrams to clusters with a low threshold
(new_sff_file, bestscores, mapping) = \
greedy_clustering(deprefixed_sff_fp, seqs, mapping, tmpoutdir, l,
log_fh, num_cpus=num_cpus, on_cluster=cluster,
bail_out=bail, pair_id_thresh=percent_id,
threshold=low_cutoff, verbose=verbose,
fast_method=not low_memory,
error_profile=error_profile,
max_num_rounds=max_num_rounds,
checkpoint_fp=checkpoint_fp)
# phase III phase:
# Assign seqs to nearest existing centroid with high threshold
secondary_clustering(new_sff_file, mapping, bestscores, log_fh,
verbose=verbose, threshold=high_cutoff)
remove(new_sff_file)
if (verbose):
log_fh.write("Finished clustering\n")
log_fh.write("Writing Clusters\n")
log_fh.write(make_stats(mapping) + "\n")
store_clusters(mapping, deprefixed_sff_fp, tmpoutdir)
store_mapping(mapping, tmpoutdir, "denoiser")
def denoise_seqs(sff_fps,
fasta_fp,
tmpoutdir,
preprocess_fp=None,
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,
checkpoint_fp=None):
"""The main routine to denoise flowgrams"""
# abort if binary is missing
check_flowgram_ali_exe()
if verbose:
# switch of buffering for log file
log_fh = open(tmpoutdir + "/" + log_fp, "w", 0)
else:
log_fh = None
# 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("Preprocess dir: %s\n" % preprocess_fp)
if checkpoint_fp:
log_fh.write("Resuming denoiser from %s\n" % checkpoint_fp)
log_fh.write("Primer sequence: %s\n" % primer)
log_fh.write("Running on 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" % 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("Low cut-off: %.2f\n" % low_cutoff)
log_fh.write("High cut-off: %.2f\n" % high_cutoff)
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 ...
# Phase I - clean up and truncate input sff
if (checkpoint_fp):
if (preprocess_fp):
# skip preprocessing as we should have data
# we already have preprocessed data, so use it
(deprefixed_sff_fp, l, mapping,
seqs) = read_preprocessed_data(preprocess_fp)
else:
raise ApplicationError(
"Resuming from checkpoint requires --preprocess option")
else:
if (preprocess_fp):
# we already have preprocessed data, so use it
(deprefixed_sff_fp, l, mapping,
seqs) = read_preprocessed_data(preprocess_fp)
elif (cluster):
preprocess_on_cluster(sff_fps,
log_fp,
fasta_fp=fasta_fp,
out_fp=tmpoutdir,
verbose=verbose,
squeeze=squeeze,
primer=primer)
(deprefixed_sff_fp, l, mapping,
seqs) = read_preprocessed_data(tmpoutdir)
else:
(deprefixed_sff_fp, l, mapping, seqs) = \
preprocess(
sff_fps, log_fh, fasta_fp=fasta_fp, out_fp=tmpoutdir,
verbose=verbose, squeeze=squeeze, primer=primer)
# preprocessor writes into same file, so better jump to end of file
if verbose:
log_fh.close()
log_fh = open(tmpoutdir + "/" + log_fp, "a", 0)
# phase II:
# use prefix map based clustering as initial centroids and greedily
# add flowgrams to clusters with a low threshold
(new_sff_file, bestscores, mapping) = \
greedy_clustering(deprefixed_sff_fp, seqs, mapping, tmpoutdir, l,
log_fh, num_cpus=num_cpus, on_cluster=cluster,
bail_out=bail, pair_id_thresh=percent_id,
threshold=low_cutoff, verbose=verbose,
fast_method=not low_memory,
error_profile=error_profile,
max_num_rounds=max_num_rounds,
checkpoint_fp=checkpoint_fp)
# phase III phase:
# Assign seqs to nearest existing centroid with high threshold
secondary_clustering(new_sff_file,
mapping,
bestscores,
log_fh,
verbose=verbose,
threshold=high_cutoff)
remove(new_sff_file)
if (verbose):
log_fh.write("Finished clustering\n")
log_fh.write("Writing Clusters\n")
log_fh.write(make_stats(mapping) + "\n")
store_clusters(mapping, deprefixed_sff_fp, tmpoutdir)
store_mapping(mapping, tmpoutdir, "denoiser")
