def test_checkpoints(self):
"""storing and loading of checkpoints works"""
self.tmpdir = get_tmp_filename(
tmp_dir="./",
suffix="_test_checkpoints/")
bestscores = dict({1: 0.9,
2: 1.1,
3: 2.3,
4: 99.93232344})
out_fp = write_checkpoint(
"Key", 99, self.mapping, [1, 2, 3, 4], bestscores,
[2, 1, 3, 4],
self.tmpdir)
observed = read_checkpoint(out_fp)
self.assertEqual(observed[0], "Key")
self.assertEqual(observed[1], 99)
self.assertEqual(observed[2], self.mapping)
self.assertEqual(observed[3], [1, 2, 3, 4])
self.assertEqual(observed[4], bestscores)
self.assertEqual(observed[5], [2, 1, 3, 4])
def test_checkpoints(self):
"""storing and loading of checkpoints works"""
self.tmpdir = mkdtemp(dir="./", suffix="_test_checkpoints/")
bestscores = dict({1: 0.9, 2: 1.1, 3: 2.3, 4: 99.93232344})
out_fp = write_checkpoint("Key", 99, self.mapping, [1, 2, 3, 4],
bestscores, [2, 1, 3, 4], self.tmpdir)
observed = read_checkpoint(out_fp)
self.assertEqual(observed[0], "Key")
self.assertEqual(observed[1], 99)
self.assertEqual(observed[2], self.mapping)
self.assertEqual(observed[3], [1, 2, 3, 4])
self.assertEqual(observed[4], bestscores)
self.assertEqual(observed[5], [2, 1, 3, 4])
def greedy_clustering(sff_fp, seqs, cluster_mapping, outdir, num_flows,
log_fh, num_cpus=1, on_cluster=False,
bail_out=1, pair_id_thresh=0.97, verbose=False,
threshold=3.75, fast_method=True,
error_profile=DENOISER_DATA_DIR +
'FLX_error_profile.dat',
max_num_rounds=None, checkpoint_fp=None):
"""second clustering phase of denoiser.
sff_fp: flowgram file
seqs: fasta seqs corresponding to sff_fp
cluster_mapping: preliminary cluster mapping from phase I
outdir: output directory
num_flows: number of flowgrams in sff_fp (need to now before parsing sff_fp)
log_fh: write verbose info to log_fh if set
num_cpus:number of cpus to use of on_cluster ==True
on_cluster: run in paralell if True
bail_out: stop clustering with first cluster having bail_out members
pair_id_thresh: always cluster flowgrams whose flowgram alignment implies a seq
identity of pair_id_thresh or higher
verbose: be verbose or not
threshold: low clustering threshold for phase II
fast_method: use more memory intensive but faster method
error_profile: path to error profile *.dat file
max_num_rounds: If set, will stop clustering after this many rounds
"""
(flowgrams, header) = lazy_parse_sff_handle(open(sff_fp))
l = num_flows
spread = [1.0 for x in range(num_cpus)]
(client_sockets, workers) = (None, None)
if on_cluster:
(client_sockets, workers, server_socket) = \
setup_cluster(num_cpus, outdir, verbose, error_profile)
if checkpoint_fp:
(checkpoint_key, round_ctr, cluster_mapping, ids, bestscores, sorted_keys) = \
read_checkpoint(checkpoint_fp)
skipping = True
else:
# ids stores all the active sequences
# we initialize it with the ids from the seqs dict here,
# as it starts with all active flows.
ids = dict.fromkeys(seqs)
sorted_keys = sort_mapping_by_size(cluster_mapping)
bestscores = {}
round_ctr = 1
# this is the main clustering loop, where most of the compute time is spent
for key in sorted_keys:
# skip until we reach the checkpoint
if checkpoint_fp:
if (checkpoint_key == key):
if log_fh:
log_fh.write("Resume denoising with %s\n" % key)
skipping = False
if (skipping):
continue
if(key not in cluster_mapping):
# this guy already has been clustered
continue
if (max_num_rounds and round_ctr > max_num_rounds):
if log_fh:
log_fh.write("Max number of rounds reached. " +
"Aborting clustering phase II and continuing with phase III.\n")
break
prefix_clustersize = len(cluster_mapping[key])
# abort greedy first phase
if(prefix_clustersize < bail_out):
break
# Do not take bad sequences as cluster seeds, as this will break the
# code
if('N' in seqs[key]):
continue
# check and delete workers if no longer needed
if on_cluster:
num_cpus = adjust_workers(l, num_cpus, client_sockets, log_fh)
# check for dead workers
check_workers(workers, client_sockets, log_fh)
if num_cpus != len(spread):
spread = [1.0 for x in range(num_cpus)]
# write checkpoint right before expensive computation starts
# Currently, write checkpint every 50 rounds,
# could easily be changed here or exposed to command line
if (round_ctr % 50) == 0:
write_checkpoint(key, round_ctr, cluster_mapping, ids, bestscores,
sorted_keys, outdir)
if log_fh:
log_fh.write("Round %d:\n" % round_ctr)
log_remaining_rounds(ids, cluster_mapping, bail_out, log_fh)
ideal_flow = seq_to_flow(seqs[key])
(new_flowgrams, newl) = filter_with_flowgram(key, ideal_flow, flowgrams, header, ids,
l, bestscores, log_fh, outdir,
on_cluster=on_cluster,
num_cpus=num_cpus,
fast_method=fast_method,
mapping=cluster_mapping,
verbose=verbose,
threshold=threshold,
pair_id_thresh=pair_id_thresh,
client_sockets=client_sockets,
error_profile=error_profile, spread=spread)
l = newl
flowgrams = new_flowgrams
round_ctr += 1
if(newl == 0):
# all flowgrams clustered
break
# JR: I think this is too much info for the regular user, I leave it in, so
# we can simply turn it on for debugging
# if log_fh:
# log_fh.write("Throughput Spread %s\n" % str(spread))
if on_cluster:
stop_workers(client_sockets, log_fh)
server_socket.close()
# write all remaining flowgrams into file for next step
# TODO: might use abstract FlowgramContainer here as well
fd, non_clustered_filename = mkstemp(dir=outdir, prefix="ff",
suffix=".sff.txt")
close(fd)
non_clustered_fh = open(non_clustered_filename, "w")
write_sff_header(header, non_clustered_fh)
for f in flowgrams:
if (f.Name in ids):
non_clustered_fh.write(f.createFlowHeader() + "\n")
return(non_clustered_filename, bestscores, cluster_mapping)
def greedy_clustering(sff_fp,
seqs,
cluster_mapping,
outdir,
num_flows,
log_fh,
num_cpus=1,
on_cluster=False,
bail_out=1,
pair_id_thresh=0.97,
verbose=False,
threshold=3.75,
fast_method=True,
error_profile=DENOISER_DATA_DIR +
'FLX_error_profile.dat',
max_num_rounds=None,
checkpoint_fp=None):
"""second clustering phase of denoiser.
sff_fp: flowgram file
seqs: fasta seqs corresponding to sff_fp
cluster_mapping: preliminary cluster mapping from phase I
outdir: output directory
num_flows: number of flowgrams in sff_fp (need to now before parsing sff_fp)
log_fh: write verbose info to log_fh if set
num_cpus:number of cpus to use of on_cluster ==True
on_cluster: run in paralell if True
bail_out: stop clustering with first cluster having bail_out members
pair_id_thresh: always cluster flowgrams whose flowgram alignment implies a seq
identity of pair_id_thresh or higher
verbose: be verbose or not
threshold: low clustering threshold for phase II
fast_method: use more memory intensive but faster method
error_profile: path to error profile *.dat file
max_num_rounds: If set, will stop clustering after this many rounds
"""
(flowgrams, header) = lazy_parse_sff_handle(open(sff_fp))
l = num_flows
spread = [1.0 for x in range(num_cpus)]
(client_sockets, workers) = (None, None)
if on_cluster:
(client_sockets, workers, server_socket) = \
setup_cluster(num_cpus, outdir, verbose, error_profile)
if checkpoint_fp:
(checkpoint_key, round_ctr, cluster_mapping, ids, bestscores, sorted_keys) = \
read_checkpoint(checkpoint_fp)
skipping = True
else:
# ids stores all the active sequences
# we initialize it with the ids from the seqs dict here,
# as it starts with all active flows.
ids = dict.fromkeys(seqs)
sorted_keys = sort_mapping_by_size(cluster_mapping)
bestscores = {}
round_ctr = 1
# this is the main clustering loop, where most of the compute time is spent
for key in sorted_keys:
# skip until we reach the checkpoint
if checkpoint_fp:
if (checkpoint_key == key):
if log_fh:
log_fh.write("Resume denoising with %s\n" % key)
skipping = False
if (skipping):
continue
if (key not in cluster_mapping):
# this guy already has been clustered
continue
if (max_num_rounds and round_ctr > max_num_rounds):
if log_fh:
log_fh.write(
"Max number of rounds reached. " +
"Aborting clustering phase II and continuing with phase III.\n"
)
break
prefix_clustersize = len(cluster_mapping[key])
# abort greedy first phase
if (prefix_clustersize < bail_out):
break
# Do not take bad sequences as cluster seeds, as this will break the
# code
if ('N' in seqs[key]):
continue
# check and delete workers if no longer needed
if on_cluster:
num_cpus = adjust_workers(l, num_cpus, client_sockets, log_fh)
# check for dead workers
check_workers(workers, client_sockets, log_fh)
if num_cpus != len(spread):
spread = [1.0 for x in range(num_cpus)]
# write checkpoint right before expensive computation starts
# Currently, write checkpint every 50 rounds,
# could easily be changed here or exposed to command line
if (round_ctr % 50) == 0:
write_checkpoint(key, round_ctr, cluster_mapping, ids, bestscores,
sorted_keys, outdir)
if log_fh:
log_fh.write("Round %d:\n" % round_ctr)
log_remaining_rounds(ids, cluster_mapping, bail_out, log_fh)
ideal_flow = seq_to_flow(seqs[key])
(new_flowgrams,
newl) = filter_with_flowgram(key,
ideal_flow,
flowgrams,
header,
ids,
l,
bestscores,
log_fh,
outdir,
on_cluster=on_cluster,
num_cpus=num_cpus,
fast_method=fast_method,
mapping=cluster_mapping,
verbose=verbose,
threshold=threshold,
pair_id_thresh=pair_id_thresh,
client_sockets=client_sockets,
error_profile=error_profile,
spread=spread)
l = newl
flowgrams = new_flowgrams
round_ctr += 1
if (newl == 0):
# all flowgrams clustered
break
# JR: I think this is too much info for the regular user, I leave it in, so
# we can simply turn it on for debugging
# if log_fh:
# log_fh.write("Throughput Spread %s\n" % str(spread))
if on_cluster:
stop_workers(client_sockets, log_fh)
server_socket.close()
# write all remaining flowgrams into file for next step
# TODO: might use abstract FlowgramContainer here as well
fd, non_clustered_filename = mkstemp(dir=outdir,
prefix="ff",
suffix=".sff.txt")
close(fd)
non_clustered_fh = open(non_clustered_filename, "w")
write_sff_header(header, non_clustered_fh)
for f in flowgrams:
if (f.Name in ids):
non_clustered_fh.write(f.createFlowHeader() + "\n")
return (non_clustered_filename, bestscores, cluster_mapping)
