def test_two_groupings(self):
"""Tests two groupings of input sequences in which the first
grouping has two sequences and the second grouping has one
sequence.
Note that this test is dependent on the default values for
generating candidate probes: probe length of 100 bp with a stride
of 50 bp.
"""
seqs = [[genome.Genome.from_one_seq('A' * 200),
genome.Genome.from_one_seq('B' * 150)],
[genome.Genome.from_one_seq('C' * 300)]]
desired_candidate_probes = \
['A' * 100, 'A' * 100, 'A' * 100, 'B' * 100, 'B' * 100,
'C' * 100, 'C' * 100, 'C' * 100, 'C' * 100, 'C' * 100]
desired_candidate_probes = \
[probe.Probe.from_str(s) for s in desired_candidate_probes]
desired_final_probes = ['A' * 100, 'B' * 100, 'C' * 100]
desired_final_probes = \
[probe.Probe.from_str(s) for s in desired_final_probes]
df = duplicate_filter.DuplicateFilter()
pb = probe_designer.ProbeDesigner(seqs, [df], probe_length=100,
probe_stride=50)
pb.design()
self.assertEqual(pb.candidate_probes, desired_candidate_probes)
self.assertEqual(pb.final_probes, desired_final_probes)
def test_one_filter1(self):
"""A basic test with a duplicate filter and one input sequence.
Note that this test is dependent on the default values for
generating candidate probes: probe length of 100 bp with a stride
of 50 bp.
"""
seqs = [
[genome.Genome.from_one_seq('A' * 100 + 'B' * 100 + 'A' * 100)]]
desired_candidate_probes = \
['A' * 100, 'A' * 50 + 'B' * 50, 'B' * 100, 'B' * 50 + 'A' * 50,
'A' * 100]
desired_candidate_probes = \
[probe.Probe.from_str(s) for s in desired_candidate_probes]
desired_final_probes = ['A' * 100, 'A' * 50 + 'B' * 50, 'B' * 100,
'B' * 50 + 'A' * 50]
desired_final_probes = \
[probe.Probe.from_str(s) for s in desired_final_probes]
df = duplicate_filter.DuplicateFilter()
pb = probe_designer.ProbeDesigner(seqs, [df], probe_length=100,
probe_stride=50)
pb.design()
self.assertEqual(pb.candidate_probes, desired_candidate_probes)
self.assertEqual(pb.final_probes, desired_final_probes)
def test_with_small_sequences(self):
"""A test with a duplicate filter and input sequences that are smaller
than the probe length.
"""
seqs = [[genome.Genome.from_one_seq('ABCDEFGHIJKLMN'),
genome.Genome.from_one_seq('ABCDEFGHIXKLMN'),
genome.Genome.from_one_seq('XYZAB')]]
desired_candidate_probes = \
['ABCDEF', 'DEFGHI', 'GHIJKL', 'IJKLMN',
'ABCDEF', 'DEFGHI', 'GHIXKL', 'IXKLMN',
'XYZAB']
desired_candidate_probes = \
[probe.Probe.from_str(s) for s in desired_candidate_probes]
desired_final_probes = ['ABCDEF', 'DEFGHI', 'GHIJKL', 'IJKLMN',
'GHIXKL', 'IXKLMN', 'XYZAB']
desired_final_probes = \
[probe.Probe.from_str(s) for s in desired_final_probes]
df = duplicate_filter.DuplicateFilter()
pb = probe_designer.ProbeDesigner(seqs, [df], probe_length=6,
probe_stride=3,
allow_small_seqs=5)
pb.design()
self.assertEqual(pb.candidate_probes, desired_candidate_probes)
self.assertEqual(pb.final_probes, desired_final_probes)
def test_one_filter2(self):
"""A basic test with a duplicate filter and one input sequence.
Note that this test uses a probe length of 75 bp and a stride of
25 bp.
"""
seqs = [
[genome.Genome.from_one_seq('A' * 100 + 'B' * 100 + 'A' * 100)]]
desired_candidate_probes = \
['A' * 75, 'A' * 75, 'A' * 50 + 'B' * 25, 'A' * 25 + 'B' * 50,
'B' * 75, 'B' * 75, 'B' * 50 + 'A' * 25, 'B' * 25 + 'A' * 50,
'A' * 75, 'A' * 75]
desired_candidate_probes = \
[probe.Probe.from_str(s) for s in desired_candidate_probes]
desired_final_probes = ['A' * 75, 'A' * 50 + 'B' * 25,
'A' * 25 + 'B' * 50, 'B' * 75,
'B' * 50 + 'A' * 25, 'B' * 25 + 'A' * 50]
desired_final_probes = \
[probe.Probe.from_str(s) for s in desired_final_probes]
df = duplicate_filter.DuplicateFilter()
pb = probe_designer.ProbeDesigner(seqs, [df], probe_length=75,
probe_stride=25)
pb.design()
self.assertEqual(pb.candidate_probes, desired_candidate_probes)
self.assertEqual(pb.final_probes, desired_final_probes)
def main(args):
# Read the FASTA sequences
ds = args.dataset
try:
if os.path.isfile(ds):
# Process a custom fasta file with sequences
seqs = [seq_io.read_genomes_from_fasta(ds)]
else:
dataset = importlib.import_module(
'catch.datasets.' + ds)
seqs = [seq_io.read_dataset_genomes(dataset)]
except ImportError:
raise ValueError("Unknown file or dataset '%s'" % ds)
if (args.limit_target_genomes and
args.limit_target_genomes_randomly_with_replacement):
raise Exception(("Cannot --limit-target-genomes and "
"--limit-target-genomes-randomly-with-replacement at "
"the same time"))
elif args.limit_target_genomes:
seqs = [genomes[:args.limit_target_genomes] for genomes in seqs]
elif args.limit_target_genomes_randomly_with_replacement:
k = args.limit_target_genomes_randomly_with_replacement
seqs = [random.choices(genomes, k=k) for genomes in seqs]
# Setup the filters needed for replication
filters = []
# The filters we use are, in order:
# Duplicate filter (df) -- condense all candidate probes that
# are identical down to one; this is not necessary for
# correctness, as the naive redundant filter achieves the same
# task implicitly, but it does significantly lower runtime by
# decreasing the input size to the naive redundant filter
df = duplicate_filter.DuplicateFilter()
filters += [df]
if args.naive_redundant_filter and args.dominating_set_filter:
raise Exception(("Cannot use both 'naive_redundant_filter' and "
"'dominating_set_filter' at the same time. (You could "
"of course do one after the other, but it was probably "
"a mistake to specify both.)"))
elif args.naive_redundant_filter or args.dominating_set_filter:
if args.naive_redundant_filter:
# Naive redundant filter -- execute a greedy algorithm to
# condense 'similar' probes down to one
mismatches, lcf_thres = args.naive_redundant_filter
filt_class = naive_redundant_filter.NaiveRedundantFilter
if args.dominating_set_filter:
# Dominating set filter (dsf) -- construct a graph where each
# node is a probe and edges connect 'similar' probes; then
# approximate the smallest dominating set
mismatches, lcf_thres = args.dominating_set_filter
filt_class = dominating_set_filter.DominatingSetFilter
# Construct a function to determine whether two probes are
# redundant, and then instantiate the appropriate filter
redundant_fn = naive_redundant_filter.redundant_longest_common_substring(
mismatches, lcf_thres)
filt = filt_class(redundant_fn)
filters += [filt]
if args.add_reverse_complements:
# Reverse complement (rc) -- add the reverse complement of
# each probe as a candidate
rc = reverse_complement_filter.ReverseComplementFilter()
filters += [rc]
# Design the probes
pb = probe_designer.ProbeDesigner(seqs, filters,
probe_length=args.probe_length,
probe_stride=args.probe_stride)
pb.design()
if args.print_analysis:
if args.naive_redundant_filter or args.dominating_set_filter:
mismatch_thres = mismatches
else:
mismatch_thres = 0
analyzer = coverage_analysis.Analyzer(pb.final_probes,
mismatch_thres,
args.probe_length,
seqs,
[args.dataset])
analyzer.run()
analyzer.print_analysis()
else:
# Just print the number of probes
print(len(pb.final_probes))
def main(args):
logger = logging.getLogger(__name__)
# Set NCBI API key
if args.ncbi_api_key:
ncbi_neighbors.ncbi_api_key = args.ncbi_api_key
# Read the genomes from FASTA sequences
genomes_grouped = []
genomes_grouped_names = []
for ds in args.dataset:
if ds.startswith('collection:'):
# Process a collection of datasets
collection_name = ds[len('collection:'):]
try:
collection = importlib.import_module(
'catch.datasets.collections.' + collection_name)
except ImportError:
raise ValueError("Unknown dataset collection %s" %
collection_name)
for name, dataset in collection.import_all():
genomes_grouped += [seq_io.read_dataset_genomes(dataset)]
genomes_grouped_names += [name]
elif ds.startswith('download:'):
# Download a FASTA for an NCBI taxonomic ID
taxid = ds[len('download:'):]
if args.write_taxid_acc:
taxid_fn = os.path.join(args.write_taxid_acc,
str(taxid) + '.txt')
else:
taxid_fn = None
if '-' in taxid:
taxid, segment = taxid.split('-')
else:
segment = None
ds_fasta_tf = ncbi_neighbors.construct_fasta_for_taxid(
taxid, segment=segment, write_to=taxid_fn)
genomes_grouped += [
seq_io.read_genomes_from_fasta(ds_fasta_tf.name)
]
genomes_grouped_names += ['taxid:' + str(taxid)]
ds_fasta_tf.close()
elif os.path.isfile(ds):
# Process a custom fasta file with sequences
genomes_grouped += [seq_io.read_genomes_from_fasta(ds)]
genomes_grouped_names += [os.path.basename(ds)]
else:
# Process an individual dataset
try:
dataset = importlib.import_module('catch.datasets.' + ds)
except ImportError:
raise ValueError("Unknown file or dataset '%s'" % ds)
genomes_grouped += [seq_io.read_dataset_genomes(dataset)]
genomes_grouped_names += [ds]
if (args.limit_target_genomes
and args.limit_target_genomes_randomly_with_replacement):
raise Exception(("Cannot --limit-target-genomes and "
"--limit-target-genomes-randomly-with-replacement at "
"the same time"))
elif args.limit_target_genomes:
genomes_grouped = [
genomes[:args.limit_target_genomes] for genomes in genomes_grouped
]
elif args.limit_target_genomes_randomly_with_replacement:
k = args.limit_target_genomes_randomly_with_replacement
genomes_grouped = [
random.choices(genomes, k=k) for genomes in genomes_grouped
]
# Store the FASTA paths of blacklisted genomes
blacklisted_genomes_fasta = []
if args.blacklist_genomes:
for bg in args.blacklist_genomes:
if os.path.isfile(bg):
# Process a custom fasta file with sequences
blacklisted_genomes_fasta += [bg]
else:
# Process an individual dataset
try:
dataset = importlib.import_module('catch.datasets.' + bg)
except ImportError:
raise ValueError("Unknown file or dataset '%s'" % bg)
for fp in dataset.fasta_paths:
blacklisted_genomes_fasta += [fp]
# Setup and verify parameters related to probe length
if not args.lcf_thres:
args.lcf_thres = args.probe_length
if args.probe_stride > args.probe_length:
logger.warning(("PROBE_STRIDE (%d) is greater than PROBE_LENGTH "
"(%d), which is usually undesirable and may lead "
"to undefined behavior"), args.probe_stride,
args.probe_length)
if args.lcf_thres > args.probe_length:
logger.warning(("LCF_THRES (%d) is greater than PROBE_LENGTH "
"(%d), which is usually undesirable and may lead "
"to undefined behavior"), args.lcf_thres,
args.probe_length)
if args.island_of_exact_match > args.probe_length:
logger.warning(("ISLAND_OF_EXACT_MATCH (%d) is greater than "
"PROBE_LENGTH (%d), which is usually undesirable "
"and may lead to undefined behavior"),
args.island_of_exact_match, args.probe_length)
# Setup and verify parameters related to k-mer length in probe map
if args.kmer_probe_map_k:
# Check that k is sufficiently small
if args.kmer_probe_map_k > args.probe_length:
raise Exception(("KMER_PROBE_MAP_K (%d) exceeds PROBE_LENGTH "
"(%d), which is not permitted") %
(args.kmer_probe_map_k, args.probe_length))
# Use this value for the SetCoverFilter, AdapterFilter, and
# the Analyzer
kmer_probe_map_k_scf = args.kmer_probe_map_k
kmer_probe_map_k_af = args.kmer_probe_map_k
kmer_probe_map_k_analyzer = args.kmer_probe_map_k
else:
if args.probe_length <= 20:
logger.warning(("PROBE_LENGTH (%d) is small; you may want to "
"consider setting --kmer-probe-map-k to be "
"small as well in order to be more sensitive "
"in mapping candidate probes to target sequence"),
args.probe_length)
# Use a default k of 20 for the SetCoverFilter and AdapterFilter,
# and 10 for the Analyzer since we would like to be more sensitive
# (potentially at the cost of slower runtime) for the latter
kmer_probe_map_k_scf = 20
kmer_probe_map_k_af = 20
kmer_probe_map_k_analyzer = 10
# Set the maximum number of processes in multiprocessing pools
if args.max_num_processes:
probe.set_max_num_processes_for_probe_finding_pools(
args.max_num_processes)
cluster.set_max_num_processes_for_creating_distance_matrix(
args.max_num_processes)
# Raise exceptions or warn based on use of adapter arguments
if args.add_adapters:
if not (args.adapter_a or args.adapter_b):
logger.warning(("Adapter sequences will be added, but default "
"sequences will be used; to provide adapter "
"sequences, use --adapter-a and --adapter-b"))
else:
if args.adapter_a or args.adapter_b:
raise Exception(
("Adapter sequences were provided with "
"--adapter-a and --adapter-b, but --add-adapters is required "
"to add adapter sequences onto the ends of probes"))
# Do not allow both --small-seq-skip and --small-seq-min, since they
# have different intentions
if args.small_seq_skip is not None and args.small_seq_min is not None:
raise Exception(("Both --small-seq-skip and --small-seq-min were "
"specified, but both cannot be used together"))
# Check arguments involving clustering
if args.cluster_and_design_separately and args.identify:
raise Exception(
("Cannot use --cluster-and-design-separately with "
"--identify, because clustering collapses genome groupings into "
"one"))
if args.cluster_from_fragments and not args.cluster_and_design_separately:
raise Exception(("Cannot use --cluster-from-fragments without also "
"setting --cluster-and-design-separately"))
# Check for whether a custom hybridization function was provided
if args.custom_hybridization_fn:
custom_cover_range_fn = tuple(args.custom_hybridization_fn)
else:
custom_cover_range_fn = None
if args.custom_hybridization_fn_tolerant:
custom_cover_range_tolerant_fn = tuple(
args.custom_hybridization_fn_tolerant)
else:
custom_cover_range_tolerant_fn = None
# Setup the filters
# The filters we use are, in order:
filters = []
# [Optional]
# Fasta filter (ff) -- leave out candidate probes
if args.filter_from_fasta:
ff = fasta_filter.FastaFilter(args.filter_from_fasta,
skip_reverse_complements=True)
filters += [ff]
# [Optional]
# Poly(A) filter (paf) -- leave out probes with stretches of 'A' or 'T'
if args.filter_polya:
polya_length, polya_mismatches = args.filter_polya
if polya_length > args.probe_length:
logger.warning(("Length of poly(A) stretch to filter (%d) is "
"greater than PROBE_LENGTH (%d), which is usually "
"undesirable"), polya_length, args.probe_length)
if polya_length < 10:
logger.warning(("Length of poly(A) stretch to filter (%d) is "
"short, and may lead to many probes being "
"filtered"), polya_length)
if polya_mismatches > 10:
logger.warning(("Number of mismatches to tolerate when searching "
"for poly(A) stretches (%d) is high, and may "
"lead to many probes being filtered"),
polya_mismatches)
paf = polya_filter.PolyAFilter(polya_length, polya_mismatches)
filters += [paf]
# Duplicate filter (df) -- condense all candidate probes that
# are identical down to one; this is not necessary for
# correctness, as the set cover filter achieves the same task
# implicitly, but it does significantly lower runtime by
# decreasing the input size to the set cover filter
# Near duplicate filter (ndf) -- condense candidate probes that
# are near-duplicates down to one using locality-sensitive
# hashing; like the duplicate filter, this is not necessary
# but can significantly lower runtime and reduce memory usage
# (even more than the duplicate filter)
if (args.filter_with_lsh_hamming is not None
and args.filter_with_lsh_minhash is not None):
raise Exception(("Cannot use both --filter-with-lsh-hamming "
"and --filter-with-lsh-minhash"))
if args.filter_with_lsh_hamming is not None:
if args.filter_with_lsh_hamming > args.mismatches:
logger.warning(
("Setting FILTER_WITH_LSH_HAMMING (%d) to be greater "
"than MISMATCHES (%d) may cause the probes to achieve less "
"than the desired coverage"), args.filter_with_lsh_hamming,
args.mismatches)
ndf = near_duplicate_filter.NearDuplicateFilterWithHammingDistance(
args.filter_with_lsh_hamming, args.probe_length)
filters += [ndf]
elif args.filter_with_lsh_minhash is not None:
ndf = near_duplicate_filter.NearDuplicateFilterWithMinHash(
args.filter_with_lsh_minhash)
filters += [ndf]
else:
df = duplicate_filter.DuplicateFilter()
filters += [df]
# Set cover filter (scf) -- solve the problem by treating it as
# an instance of the set cover problem
scf = set_cover_filter.SetCoverFilter(
mismatches=args.mismatches,
lcf_thres=args.lcf_thres,
island_of_exact_match=args.island_of_exact_match,
mismatches_tolerant=args.mismatches_tolerant,
lcf_thres_tolerant=args.lcf_thres_tolerant,
island_of_exact_match_tolerant=args.island_of_exact_match_tolerant,
custom_cover_range_fn=custom_cover_range_fn,
custom_cover_range_tolerant_fn=custom_cover_range_tolerant_fn,
identify=args.identify,
blacklisted_genomes=blacklisted_genomes_fasta,
coverage=args.coverage,
cover_extension=args.cover_extension,
cover_groupings_separately=args.cover_groupings_separately,
kmer_probe_map_k=kmer_probe_map_k_scf,
kmer_probe_map_use_native_dict=args.
use_native_dict_when_finding_tolerant_coverage)
filters += [scf]
# [Optional]
# Adapter filter (af) -- add adapters to both the 5' and 3' ends
# of each probe
if args.add_adapters:
# Set default adapter sequences, if not provided
if args.adapter_a:
adapter_a = tuple(args.adapter_a)
else:
adapter_a = ('ATACGCCATGCTGGGTCTCC', 'CGTACTTGGGAGTCGGCCAT')
if args.adapter_b:
adapter_b = tuple(args.adapter_b)
else:
adapter_b = ('AGGCCCTGGCTGCTGATATG', 'GACCTTTTGGGACAGCGGTG')
af = adapter_filter.AdapterFilter(adapter_a,
adapter_b,
mismatches=args.mismatches,
lcf_thres=args.lcf_thres,
island_of_exact_match=\
args.island_of_exact_match,
custom_cover_range_fn=\
custom_cover_range_fn,
kmer_probe_map_k=kmer_probe_map_k_af)
filters += [af]
# [Optional]
# N expansion filter (nef) -- expand Ns in probe sequences
# to avoid ambiguity
if args.expand_n is not None:
nef = n_expansion_filter.NExpansionFilter(
limit_n_expansion_randomly=args.expand_n)
filters += [nef]
# [Optional]
# Reverse complement (rc) -- add the reverse complement of each
# probe that remains
if args.add_reverse_complements:
rc = reverse_complement_filter.ReverseComplementFilter()
filters += [rc]
# If requested, don't apply the set cover filter
if args.skip_set_cover:
filter_before_scf = filters[filters.index(scf) - 1]
filters.remove(scf)
# Define parameters for clustering sequences
if args.cluster_and_design_separately:
cluster_threshold = args.cluster_and_design_separately
if args.skip_set_cover:
cluster_merge_after = filter_before_scf
else:
cluster_merge_after = scf
cluster_fragment_length = args.cluster_from_fragments
else:
cluster_threshold = None
cluster_merge_after = None
cluster_fragment_length = None
# Design the probes
pb = probe_designer.ProbeDesigner(
genomes_grouped,
filters,
probe_length=args.probe_length,
probe_stride=args.probe_stride,
allow_small_seqs=args.small_seq_min,
seq_length_to_skip=args.small_seq_skip,
cluster_threshold=cluster_threshold,
cluster_merge_after=cluster_merge_after,
cluster_fragment_length=cluster_fragment_length)
pb.design()
# Write the final probes to the file args.output_probes
seq_io.write_probe_fasta(pb.final_probes, args.output_probes)
if (args.print_analysis or args.write_analysis_to_tsv
or args.write_sliding_window_coverage
or args.write_probe_map_counts_to_tsv):
analyzer = coverage_analysis.Analyzer(
pb.final_probes,
args.mismatches,
args.lcf_thres,
genomes_grouped,
genomes_grouped_names,
island_of_exact_match=args.island_of_exact_match,
custom_cover_range_fn=custom_cover_range_fn,
cover_extension=args.cover_extension,
kmer_probe_map_k=kmer_probe_map_k_analyzer,
rc_too=args.add_reverse_complements)
analyzer.run()
if args.write_analysis_to_tsv:
analyzer.write_data_matrix_as_tsv(args.write_analysis_to_tsv)
if args.write_sliding_window_coverage:
analyzer.write_sliding_window_coverage(
args.write_sliding_window_coverage)
if args.write_probe_map_counts_to_tsv:
analyzer.write_probe_map_counts(args.write_probe_map_counts_to_tsv)
if args.print_analysis:
analyzer.print_analysis()
else:
# Just print the number of probes
print(len(pb.final_probes))