def test_make_stats(self):
"""make_stats produces meaningful statistics."""
map = self.mapping
stats = """Clustersize\t#
1:\t\t2
2:\t\t1
5:\t\t1"""
self.assertEqual(make_stats(map), stats)
def test_make_stats(self):
"""make_stats produces meaningful statistics."""
map = self.mapping
stats = """Clustersize\t#
1:\t\t2
2:\t\t1
5:\t\t1"""
self.assertEqual(make_stats(map), stats)
def preprocess(sff_fps, log_fh, fasta_fp=None, out_fp="/tmp/",
verbose=False, squeeze=False,
primer=STANDARD_BACTERIAL_PRIMER):
"""Quality filtering and truncation of flowgrams, followed by denoiser phase I.
sff_fps: List of paths to flowgram files
log_fh: log messages are written to log_fh if it is set to something else than None
fasta_fp: Path to fasta file, formatted as from split_libraries.py.
This files is used to filter the flowgrams in sff_fps. Only reads in
fasta_fp are pulled from sff_fps.
out_fp: path to output directory
verbose: a binary verbose flag
squeeze: a flag that controls if sequences are squeezed before phase I.
Squeezing means consecutive identical nucs are collapsed to one.
primer: The primer sequences of the amplification process. This seq will be
removed from all reads during the preprocessing
"""
flowgrams, header = cat_sff_files(map(open, sff_fps))
if(fasta_fp):
# remove barcodes and sequences tossed by split_libraries, i.e. not in
# fasta_fp
labels = imap(lambda a_b: a_b[0], MinimalFastaParser(open(fasta_fp)))
barcode_mapping = extract_barcodes_from_mapping(labels)
(trunc_sff_fp, l) = truncate_flowgrams_in_SFF(flowgrams, header,
outdir=out_fp,
barcode_mapping=barcode_mapping,
primer=primer)
if verbose:
log_fh.write(
"Sequences in barcode mapping: %d\n" %
len(barcode_mapping))
log_fh.write("Truncated flowgrams written: %d\n" % l)
else:
# just do a simple clean and truncate
(clean_sff_fp, l) = cleanup_sff(flowgrams, header, outdir=out_fp)
if verbose:
log_fh.write("Cleaned flowgrams written: %d\n" % l)
flowgrams, header = lazy_parse_sff_handle(open(clean_sff_fp))
(trunc_sff_fp, l) = truncate_flowgrams_in_SFF(flowgrams, header,
outdir=out_fp, primer=primer)
if verbose:
log_fh.write("Truncated flowgrams written: %d\n" % l)
remove(clean_sff_fp)
if (l == 0):
raise ValueError("No flowgrams left after preprocesing.\n" +
"Check your primer sequence")
# Phase I - cluster seqs which are exact prefixe
if verbose:
log_fh.write("Filter flowgrams by prefix matching\n")
(flowgrams, header) = lazy_parse_sff_handle(open(trunc_sff_fp))
l, orig_l, mapping =\
prefix_filter_flowgrams(flowgrams, squeeze=squeeze)
averaged_sff_fp, seqs = build_averaged_flowgrams(mapping, trunc_sff_fp,
min_coverage=1,
# averaging produces too good flowgrams
# such that the greedy clustering clusters too much.
# Use the cluster centroid
# instead by using
# min_coverage 1
out_fp=out_fp + "/prefix_dereplicated.sff.txt")
remove(trunc_sff_fp)
if verbose:
log_fh.write("Prefix matching: removed %d out of %d seqs\n"
% (orig_l - l, orig_l))
log_fh.write("Remaining number of sequences: %d\n" % l)
log_fh.write(make_stats(mapping) + "\n")
# print representative sequences and mapping
print_rep_seqs(mapping, seqs, out_fp)
store_mapping(mapping, out_fp, "prefix")
return (averaged_sff_fp, l, mapping, seqs)
def preprocess(sff_fps,
log_fh,
fasta_fp=None,
out_fp="/tmp/",
verbose=False,
squeeze=False,
primer=STANDARD_BACTERIAL_PRIMER):
"""Quality filtering and truncation of flowgrams, followed by denoiser phase I.
sff_fps: List of paths to flowgram files
log_fh: log messages are written to log_fh if it is set to something else than None
fasta_fp: Path to fasta file, formatted as from split_libraries.py.
This files is used to filter the flowgrams in sff_fps. Only reads in
fasta_fp are pulled from sff_fps.
out_fp: path to output directory
verbose: a binary verbose flag
squeeze: a flag that controls if sequences are squeezed before phase I.
Squeezing means consecutive identical nucs are collapsed to one.
primer: The primer sequences of the amplification process. This seq will be
removed from all reads during the preprocessing
"""
flowgrams, header = cat_sff_files(map(open, sff_fps))
if (fasta_fp):
# remove barcodes and sequences tossed by split_libraries, i.e. not in
# fasta_fp
labels = imap(lambda a_b: a_b[0], parse_fasta(open(fasta_fp)))
barcode_mapping = extract_barcodes_from_mapping(labels)
(trunc_sff_fp,
l) = truncate_flowgrams_in_SFF(flowgrams,
header,
outdir=out_fp,
barcode_mapping=barcode_mapping,
primer=primer)
if verbose:
log_fh.write("Sequences in barcode mapping: %d\n" %
len(barcode_mapping))
log_fh.write("Truncated flowgrams written: %d\n" % l)
else:
# just do a simple clean and truncate
(clean_sff_fp, l) = cleanup_sff(flowgrams, header, outdir=out_fp)
if verbose:
log_fh.write("Cleaned flowgrams written: %d\n" % l)
flowgrams, header = lazy_parse_sff_handle(open(clean_sff_fp))
(trunc_sff_fp, l) = truncate_flowgrams_in_SFF(flowgrams,
header,
outdir=out_fp,
primer=primer)
if verbose:
log_fh.write("Truncated flowgrams written: %d\n" % l)
remove(clean_sff_fp)
if (l == 0):
raise ValueError("No flowgrams left after preprocesing.\n" +
"Check your primer sequence")
# Phase I - cluster seqs which are exact prefixe
if verbose:
log_fh.write("Filter flowgrams by prefix matching\n")
(flowgrams, header) = lazy_parse_sff_handle(open(trunc_sff_fp))
l, orig_l, mapping =\
prefix_filter_flowgrams(flowgrams, squeeze=squeeze)
averaged_sff_fp, seqs = build_averaged_flowgrams(
mapping,
trunc_sff_fp,
min_coverage=1,
# averaging produces too good flowgrams
# such that the greedy clustering clusters too much.
# Use the cluster centroid
# instead by using
# min_coverage 1
out_fp=out_fp + "/prefix_dereplicated.sff.txt")
remove(trunc_sff_fp)
if verbose:
log_fh.write("Prefix matching: removed %d out of %d seqs\n" %
(orig_l - l, orig_l))
log_fh.write("Remaining number of sequences: %d\n" % l)
log_fh.write(make_stats(mapping) + "\n")
# print representative sequences and mapping
print_rep_seqs(mapping, seqs, out_fp)
store_mapping(mapping, out_fp, "prefix")
return (averaged_sff_fp, l, mapping, seqs)
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")