def test_dna_mh(track_abundance):
e1 = MinHash(n=5, ksize=4, track_abundance=track_abundance)
e2 = MinHash(n=5, ksize=4, track_abundance=track_abundance)
seq = 'ATGGCAGTGACGATGCCAG'
e1.add_sequence(seq)
for i in range(len(seq) - 3):
e2.add(seq[i:i + 4])
assert e1.get_mins() == e2.get_mins()
print(e1.get_mins())
assert 726311917625663847 in e1.get_mins()
assert 3697418565283905118 in e1.get_mins()
def test_dna_mh(track_abundance):
e1 = MinHash(n=5, ksize=4, track_abundance=track_abundance)
e2 = MinHash(n=5, ksize=4, track_abundance=track_abundance)
seq = 'ATGGCAGTGACGATGCCAG'
e1.add_sequence(seq)
for i in range(len(seq) - 3):
e2.add(seq[i:i + 4])
assert e1.get_mins() == e2.get_mins()
print(e1.get_mins())
assert 726311917625663847 in e1.get_mins()
assert 3697418565283905118 in e1.get_mins()
def test_protein_mh(track_abundance):
e1 = MinHash(n=5, ksize=6, is_protein=True,
track_abundance=track_abundance)
e2 = MinHash(n=5, ksize=6, is_protein=True,
track_abundance=track_abundance)
seq = 'ATGGCAGTGACGATGCCG'
e1.add_sequence(seq)
for i in range(len(seq) - 5):
kmer = seq[i:i + 6]
e2.add(kmer)
assert e1.get_mins() == e2.get_mins()
assert 901193879228338100 in e1.get_mins()
def test_protein_mh(track_abundance):
e1 = MinHash(n=5, ksize=6, is_protein=True,
track_abundance=track_abundance)
e2 = MinHash(n=5, ksize=6, is_protein=True,
track_abundance=track_abundance)
seq = 'ATGGCAGTGACGATGCCG'
e1.add_sequence(seq)
for i in range(len(seq) - 5):
kmer = seq[i:i + 6]
e2.add(kmer)
assert e1.get_mins() == e2.get_mins()
assert 901193879228338100 in e1.get_mins()
def test_pickle(track_abundance):
import pickle
from io import BytesIO
e1 = MinHash(n=5,
ksize=6,
is_protein=False,
track_abundance=track_abundance)
seq = 'ATGGCAGTGACGATGCCG'
e1.add_sequence(seq)
e1.add_sequence(seq)
fp = BytesIO()
pickle.dump(e1, fp)
fp2 = BytesIO(fp.getvalue())
e2 = pickle.load(fp2)
assert e1.get_mins(with_abundance=track_abundance) == \
e2.get_mins(with_abundance=track_abundance)
assert e1.num == e2.num
assert e1.ksize == e2.ksize
assert e1.is_protein == e2.is_protein
assert e1.max_hash == e2.max_hash
assert e1.seed == e2.seed
def test_set_abundance_num_hypothesis(hashes, abundances, sketch_size):
a = MinHash(sketch_size, 10, track_abundance=True)
oracle = dict(zip(hashes, abundances))
a.set_abundances(oracle)
mins = a.get_mins(with_abundance=True)
size = min(sum(1 for v in oracle.values() if v > 0), sketch_size)
assert len(mins) == size
for k, v in mins.items():
assert oracle[k] == v
def test_set_abundance_scaled_hypothesis(hashes, abundances, scaled):
a = MinHash(0, 10, track_abundance=True, scaled=scaled)
oracle = dict(zip(hashes, abundances))
a.set_abundances(oracle)
max_hash = get_max_hash_for_scaled(scaled)
below_max_hash = sum(1 for (k, v) in oracle.items()
if k <= max_hash and v > 0)
mins = a.get_mins(with_abundance=True)
assert len(mins) == below_max_hash
for k, v in mins.items():
assert oracle[k] == v
assert k <= max_hash
assert v > 0
def test_pickle(track_abundance):
import pickle
from io import BytesIO
e1 = MinHash(n=5, ksize=6, is_protein=False,
track_abundance=track_abundance)
seq = 'ATGGCAGTGACGATGCCG'
e1.add_sequence(seq)
e1.add_sequence(seq)
fp = BytesIO()
pickle.dump(e1, fp)
fp2 = BytesIO(fp.getvalue())
e2 = pickle.load(fp2)
assert e1.get_mins(with_abundance=track_abundance) == \
e2.get_mins(with_abundance=track_abundance)
assert e1.num == e2.num
assert e1.ksize == e2.ksize
assert e1.is_protein == e2.is_protein
assert e1.max_hash == e2.max_hash
assert e1.seed == e2.seed
def main(argv):
p = argparse.ArgumentParser(description=__doc__)
p.add_argument('catlas_prefix', help='catlas prefix')
p.add_argument('mh_index_picklefile', help='pickled hashval index')
p.add_argument('hashval_list', help='file with list of hashvals')
p.add_argument('output')
p.add_argument('-k',
'--ksize',
default=31,
type=int,
help='k-mer size (default: 31)')
p.add_argument('--scaled',
default=1000,
type=float,
help="scaled value for contigs minhash output")
p.add_argument('-v', '--verbose', action='store_true')
args = p.parse_args(argv)
# create output directory if it doesn't exist.
outdir = args.output
notify('putting output in {}', outdir)
os.makedirs(os.path.join(outdir, "contigs"), exist_ok=True)
if not os.path.isdir(outdir):
error("output '{}' is not a directory and cannot be made", outdir)
sys.exit(-1)
# load picklefile
with open(args.mh_index_picklefile, 'rb') as fp:
hashval_to_contig_id = pickle.load(fp)
notify('loaded {} hash value -> cdbg_id mappings from {}',
len(hashval_to_contig_id), args.mh_index_picklefile)
# load list of desired hashvals
hashvals = [int(x.strip()) for x in open(args.hashval_list, 'rt')]
hashvals = set(hashvals)
notify('loaded {} search hashvalues from {}', len(hashvals),
args.hashval_list)
if not len(hashvals):
print('No hash values to search!', file=sys.stderr)
sys.exit(-1)
# load catlas DAG
catlas = CAtlas(args.catlas_prefix)
notify('loaded {} nodes from catlas {}', len(catlas), args.catlas_prefix)
notify('loaded {} layer 1 catlas nodes', len(catlas.layer1_to_cdbg))
# find the contigs filename
contigs_file = os.path.join(args.catlas_prefix, 'contigs.fa.gz')
# get a single ksize & scaled
ksize = int(args.ksize)
scaled = int(args.scaled)
# record command line
with open(os.path.join(outdir, 'command.txt'), 'wt') as fp:
fp.write(str(sys.argv))
fp.write("\n")
# output results.csv in the output directory:
csvoutfp = open(os.path.join(outdir, 'hashval_results.csv'), 'wt')
csv_writer = csv.writer(csvoutfp)
csv_writer.writerow(['hashval', 'bp', 'contigs'])
# iterate over each query, do the thing.
n_found = 0
for hashval in hashvals:
notify('----')
notify('QUERY HASHVAL: {}', hashval)
mh = MinHash(0, ksize, scaled=scaled)
result = execute_query(hashval, catlas, hashval_to_contig_id, mh=mh)
notify('done searching!')
if not result:
notify("no result for hashval {}", hashval)
continue
result.retrieve_contigs(contigs_file)
result.write(csv_writer, csvoutfp, outdir)
assert hashval in mh.get_mins()
n_found += 1
# end main loop!
notify('----')
notify("Done! Found {} hashvals of {} in {} with k={}", n_found,
len(hashvals), args.catlas_prefix, ksize)
notify("Results are in directory '{}'", outdir)
return 0
