def test_selection_with_preferred_sources():
readset = string_to_readset("""
1 1
""", source_id=3)
more_reads = string_to_readset("""
1111
111
1111
""",
source_id=1)
for read in more_reads:
readset.add(read)
selected_reads = readselection(readset,
max_cov=2,
preferred_source_ids=None,
bridging=True)
assert selected_reads == set([1, 2, 3]), str(selected_reads)
selected_reads = readselection(readset,
max_cov=2,
preferred_source_ids=set([3]),
bridging=True)
assert selected_reads == set([0, 1, 3]), str(selected_reads)
def test_selection():
reads = string_to_readset("""
1 1
00
0 1
10 1
1 1
11
0 1
1 1
""")
selected_reads = readselection(reads,
max_cov=1,
preferred_source_ids=None,
bridging=False)
assert selected_reads == set([1, 5])
selected_reads = readselection(reads,
max_cov=2,
preferred_source_ids=None,
bridging=False)
assert selected_reads == set([1, 3, 5]), str(selected_reads)
selected_reads = readselection(reads,
max_cov=3,
preferred_source_ids=None,
bridging=False)
assert selected_reads == set([1, 3, 5, 7]), str(selected_reads)
selected_reads = readselection(reads,
max_cov=3,
preferred_source_ids=None,
bridging=True)
#Here the assert is wrong, because the bridging doesn't come into account , because in the slice_read the selected
# reads have already coverage 3 by set ([1,3,5,7]) because first each position has to covered at least once before
#the bridging starts
assert selected_reads == set([1, 3, 5, 7]), str(selected_reads)
def test_components_of_readselection():
reads = string_to_readset("""
111
000
00
00
1 1
""")
selected_reads = readselection(reads, max_cov=2, bridging=False)
assert selected_reads == set([0, 1, 2, 3]), str(selected_reads)
# assert len(set(new_components.values())) == 2
selected_reads = readselection(reads, max_cov=2, bridging=True)
assert selected_reads == set([0, 1, 4]), str(selected_reads)
def test_bridging():
reads = string_to_readset("""
11
00
11
00
11
00
1 1
""")
selected_reads = readselection(reads, max_cov=2, bridging=False)
assert selected_reads == set([0, 1, 2, 3, 4, 5])
selected_reads = readselection(reads, max_cov=2, bridging=True)
#Not sure why 0 is there selected and not 1...
assert selected_reads == set([0, 3, 5, 6])
def test_selection2():
reads = string_to_readset("""
1111
111
1 111
1 11
1 11
""")
selected_reads = readselection(reads, max_cov=4, bridging=False)
assert selected_reads == set([0, 1, 2, 3]), str(selected_reads)
def select_reads(readset, max_coverage, preferred_source_ids):
logger.info(
"Reducing coverage to at most %dX by selecting most informative reads ...", max_coverage,
)
selected_indices = readselection(readset, max_coverage, preferred_source_ids)
selected_reads = readset.subset(selected_indices)
logger.info(
"Selected %d reads covering %d variants",
len(selected_reads),
len(selected_reads.get_positions()),
)
return selected_reads
def eprint(*args, **kwargs):
print(*args, file=sys.stderr, **kwargs)
#print('INPUT READ SET')
gfa_filename = sys.argv[1]
max_gap = int(sys.argv[2])
max_coverage = int(sys.argv[3])
readset = gfa_to_readset(gfa_filename, max_gap)
readset = readset.subset(
[i for i, read in enumerate(readset) if len(read) >= 2])
selected_indices = readselection(readset, max_coverage)
selected_reads = readset.subset(selected_indices)
readset_length = 0
for read in selected_reads:
readset_length += len(read)
#print(selected_reads)
def bipartition(reads):
positions = reads.get_positions()
# create genotypes over your variants: all heterozygous (=1)
genotypes = canonic_index_list_to_biallelic_gt_list([1] * len(positions))
# genotype likelihoods are None
genotype_likelihoods = [None] * len(positions)