def test_read_in_clade_definitions_simple():
clades = read_in_clade_definitions("tests/data/clades/simple_clades.tsv")
assert clades == {
'Clade_1': [('ctpE', 80, 'D')],
'Clade_2': [('nuc', 30641, 'T')],
'Clade_3': [('nuc', 444295, 'A'), ('pks8', 633, 'T')]
}
def test_read_in_clade_definitions_inherit_chained():
clades = read_in_clade_definitions("tests/data/clades/inherit_chained_clades.tsv")
assert clades == {
'Clade_1': [('ctpE', 80, 'D')],
'Clade_2': [('ctpE', 80, 'D'),('nuc', 30641, 'T')],
'Clade_3': [('ctpE', 80, 'D'),('nuc', 30641, 'T'), ('pks8', 633, 'T')]
}
default=10,
type=int,
help="don't clean up")
parser.add_argument("--nthreads",
default=1,
type=int,
help="Number of threads to use in alignment")
args = parser.parse_args()
#refname = f"config/reference.gb"
refname = args.gbk
features = load_features(refname)
seqs = SeqIO.parse(args.sequences, 'fasta')
ref = SeqIO.read(refname, 'genbank')
#clade_designations = read_in_clade_definitions(f"config/clades.tsv")
clade_designations = read_in_clade_definitions(args.clade)
log_fname = "clade_assignment.log"
in_fname = "clade_assignment_tmp.fasta"
out_fname = "clade_assignment_tmp_alignment.fasta"
output = open(args.output, 'w')
print('name\tclade\tparent clades', file=output)
# break the sequences into chunks, align each to the reference, and assign clades one-by-one
done = False
while not done:
# generate a chunk with chunk-size sequences
chunk = []
while len(chunk) < args.chunk_size and (not done):
try:
parser = argparse.ArgumentParser(
description="Assign clades to sequences",
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument("--sequences",
required=True,
help="FASTA file of HA sequences")
parser.add_argument("--lineage",
required=True,
help="lineage of the sequences supplied")
args = parser.parse_args()
refname = f"config/reference_{args.lineage}_ha.gb"
seqs = SeqIO.parse(args.sequences, 'fasta')
ref = SeqIO.read(refname, 'genbank')
features = load_features(refname)
clade_designations = read_in_clade_definitions(
f"config/clades_{args.lineage}_ha.tsv")
# get sequence as string, CDS seq, amino acid sequence, and start/end pos
refstr, refCDS, refAA, cds_start, cds_end = get_cds(ref)
alignment = []
for seq in seqs:
seq_container = tmpNode()
seq_aln = codon_align(seq, refstr, refAA, cds_start, cds_end)
if seq_aln is None:
print(f"{seq.id}\tnot translatable", file=sys.stdout)
continue
seq_container.sequences['nuc'] = {i: c for i, c in enumerate(seq_aln)}
for fname, feat in features.items():
if feat.type != 'source':
help="process this many sequences at once")
parser.add_argument("--nthreads",
default=1,
type=int,
help="Number of threads to use in alignment")
args = parser.parse_args()
refname = f"defaults/reference_seq.gb"
features = load_features(refname)
if args.sequences:
seqs = SeqIO.parse(args.sequences, 'fasta')
else:
alignment = SeqIO.parse(args.alignment, 'fasta')
ref = SeqIO.read(refname, 'genbank')
clade_designations = read_in_clade_definitions(f"defaults/clades.tsv")
log_fname = "clade_assignment.log"
in_fname = "clade_assignment_tmp.fasta"
out_fname = "clade_assignment_tmp_alignment.fasta"
output = open(args.output, 'w')
print('name\tclade\tparent clades', file=output)
# break the sequences into chunks, align each to the reference, and assign clades one-by-one
done = False
while not done:
# if not aligned, align
if args.sequences:
# generate a chunk with chunk-size sequences
chunk = []
group.add_argument("--alignment", help="*aligned* FASTA file of SARS-CoV-2 sequences relative to Wuhan-HU-1 with insertions removed")
parser.add_argument("--output", type=str, default='clade_assignment.tsv', help="tsv file to write clade definitions to")
parser.add_argument("--keep-temporary-files", action='store_true', help="don't clean up")
parser.add_argument("--chunk-size", default=10, type=int, help="process this many sequences at once")
parser.add_argument("--nthreads", default=1, type=int, help="Number of threads to use in alignment")
args = parser.parse_args()
refname = f"config/reference.gb"
features = load_features(refname)
if args.sequences:
seqs = SeqIO.parse(args.sequences, 'fasta')
else:
alignment = SeqIO.parse(args.alignment, 'fasta')
ref = SeqIO.read(refname, 'genbank')
clade_designations = read_in_clade_definitions(f"config/clades.tsv")
log_fname = "clade_assignment.log"
in_fname = "clade_assignment_tmp.fasta"
out_fname = "clade_assignment_tmp_alignment.fasta"
output = open(args.output, 'w')
print('name\tclade\tparent clades', file=output)
# break the sequences into chunks, align each to the reference, and assign clades one-by-one
done = False
while not done:
# if not aligned, align
if args.sequences:
# generate a chunk with chunk-size sequences
def test_read_in_clade_definitions_inheritance_from_self_error():
with pytest.raises(ValueError):
read_in_clade_definitions("tests/data/clades/self_inherit_clades.tsv")
def test_read_in_clade_definitions_inheritance_from_nonexistent_clade_error():
with pytest.raises(ValueError):
read_in_clade_definitions("tests/data/clades/nonexistent_clade_inheritance_clades.tsv")
def test_read_in_clade_definitions_multiple_inheritance_error():
with pytest.raises(ValueError):
read_in_clade_definitions("tests/data/clades/multiple_inheritance_clades.tsv")
def test_read_in_clade_definitions_inherit_cycle_error():
with pytest.raises(ValueError):
read_in_clade_definitions("tests/data/clades/inherit_cycle_clades.tsv")