def setup(self):
self.reference_filepath = "src/mykrobe/data/NC_000962.3.fasta"
self.reference = os.path.basename(
self.reference_filepath).split('.fa')[0]
self.aa2dna = GeneAminoAcidChangeToDNAVariants(
"src/mykrobe/data/NC_000962.3.fasta",
"src/mykrobe/data/NC_000962.3.gb")
def test_gene_muts(self):
self.gm = GeneAminoAcidChangeToDNAVariants(
reference="src/mykrobe/data/NC_000962.3.fasta",
genbank="src/mykrobe/data/NC_000962.3.gb")
assert self.gm.get_alts("K") == ['AAA', 'AAG']
# GAT -> ['GCA', 'GCT', 'GCC', 'GCG'], positions 759813,14,15
assert sorted(self.gm.get_variant_names("rpoB", "D3A")) == sorted(
['GAT759813GCA', 'GAT759813GCT', 'GAT759813GCC', 'GAT759813GCG'])
# GAT -> ['GCA', 'GCT', 'GCC', 'GCG'], positions 759813,14,15
assert sorted(self.gm.get_variant_names("rpoB", "D3X")) == sorted([
'GAT759813GCA', 'GAT759813GCT', 'GAT759813GCC', 'GAT759813GCG',
'GAT759813TGT', 'GAT759813TGC', 'GAT759813GAA', 'GAT759813GAG',
'GAT759813GGA', 'GAT759813GGT', 'GAT759813GGC', 'GAT759813GGG',
'GAT759813TTT', 'GAT759813TTC', 'GAT759813ATA', 'GAT759813ATT',
'GAT759813ATC', 'GAT759813CAT', 'GAT759813CAC', 'GAT759813AAA',
'GAT759813AAG', 'GAT759813ATG', 'GAT759813TTA', 'GAT759813TTG',
'GAT759813CTA', 'GAT759813CTT', 'GAT759813CTC', 'GAT759813CTG',
'GAT759813AAT', 'GAT759813AAC', 'GAT759813CAA', 'GAT759813CAG',
'GAT759813CCA', 'GAT759813CCT', 'GAT759813CCC', 'GAT759813CCG',
'GAT759813AGT', 'GAT759813AGC', 'GAT759813TCA', 'GAT759813TCT',
'GAT759813TCC', 'GAT759813TCG', 'GAT759813AGA', 'GAT759813AGG',
'GAT759813CGA', 'GAT759813CGT', 'GAT759813CGC', 'GAT759813CGG',
'GAT759813ACA', 'GAT759813ACT', 'GAT759813ACC', 'GAT759813ACG',
'GAT759813TGG', 'GAT759813GTA', 'GAT759813GTT', 'GAT759813GTC',
'GAT759813GTG', 'GAT759813TAT', 'GAT759813TAC'
])
DB.drop_database('mykrobe-test')
def test_gene_muts2(self):
self.gm = GeneAminoAcidChangeToDNAVariants(
reference=f"{DATA_DIR}/NC_000962.3.fasta",
genbank=f"{DATA_DIR}/NC_000962.3.gb")
assert self.gm.get_alts("K") == ['AAA', 'AAG']
# AGC -> ['CTT', 'CTC', 'CTA', 'CTG']
# # GAG -> ['GCA', 'GCT', 'GCC', 'GCG']
# RC : CTC -> ['TGC',...] position2156103
assert sorted(self.gm.get_variant_names("katG", "E3A")) == sorted(
['CTC2156103TGC', 'CTC2156103AGC', 'CTC2156103GGC', 'CTC2156103CGC'])
DB.drop_database('mykrobe-test')
def setup(self):
DB.drop_database('mykrobe-test')
with open("src/mykrobe/data/NC_000962.3.fasta", 'r') as infile:
self.reference_seq = list(SeqIO.parse(infile, "fasta"))[0].seq
self.gm = GeneAminoAcidChangeToDNAVariants(
reference="src/mykrobe/data/NC_000962.3.fasta",
genbank="src/mykrobe/data/NC_000962.3.gb")
self.reference_set = ReferenceSet().create_and_save(name="ref_set")
self.variant_set = VariantSet.create_and_save(
name="this_vcf_file", reference_set=self.reference_set)
self.variant_sets = [self.variant_set]
self.reference_id = Reference().create_and_save(
name="ref", md5checksum="sre", reference_sets=[self.reference_set])
def test_gene_muts(self):
self.gm = GeneAminoAcidChangeToDNAVariants(
reference=f"{DATA_DIR}/NC_000962.3.fasta",
genbank=f"{DATA_DIR}/NC_000962.3.gb",
)
assert self.gm.get_alts("K") == ["AAA", "AAG"]
# GAT -> ['GCA', 'GCT', 'GCC', 'GCG'], positions 759813,14,15
assert sorted(self.gm.get_variant_names("rpoB", "D3A")) == sorted(
["GAT759813GCA", "GAT759813GCT", "GAT759813GCC", "GAT759813GCG"])
# GAT -> ['GCA', 'GCT', 'GCC', 'GCG'], positions 759813,14,15
assert sorted(self.gm.get_variant_names("rpoB", "D3X")) == sorted([
"GAT759813GCA",
"GAT759813GCT",
"GAT759813GCC",
"GAT759813GCG",
"GAT759813TGT",
"GAT759813TGC",
"GAT759813GAA",
"GAT759813GAG",
"GAT759813GGA",
"GAT759813GGT",
"GAT759813GGC",
"GAT759813GGG",
"GAT759813TTT",
"GAT759813TTC",
"GAT759813ATA",
"GAT759813ATT",
"GAT759813ATC",
"GAT759813CAT",
"GAT759813CAC",
"GAT759813AAA",
"GAT759813AAG",
"GAT759813ATG",
"GAT759813TTA",
"GAT759813TTG",
"GAT759813CTA",
"GAT759813CTT",
"GAT759813CTC",
"GAT759813CTG",
"GAT759813AAT",
"GAT759813AAC",
"GAT759813CAA",
"GAT759813CAG",
"GAT759813CCA",
"GAT759813CCT",
"GAT759813CCC",
"GAT759813CCG",
"GAT759813AGT",
"GAT759813AGC",
"GAT759813TCA",
"GAT759813TCT",
"GAT759813TCC",
"GAT759813TCG",
"GAT759813AGA",
"GAT759813AGG",
"GAT759813CGA",
"GAT759813CGT",
"GAT759813CGC",
"GAT759813CGG",
"GAT759813ACA",
"GAT759813ACT",
"GAT759813ACC",
"GAT759813ACG",
"GAT759813TGG",
"GAT759813GTA",
"GAT759813GTT",
"GAT759813GTC",
"GAT759813GTG",
"GAT759813TAT",
"GAT759813TAC",
])
DB.drop_database("mykrobe-test")
def run(parser, args):
DB = connect('mykrobe-%s' % (args.db_name))
if DB is not None:
try:
Variant.objects()
logging.info(
"Connected to mykrobe-%s" % (args.db_name))
except (ServerSelectionTimeoutError):
DB = None
logging.warning(
"Could not connect to database. Continuing without using genetic backgrounds")
mutations = []
reference = os.path.basename(args.reference_filepath).split('.fa')[0]
if args.vcf:
run_make_probes_from_vcf_file(args)
elif args.genbank:
aa2dna = GeneAminoAcidChangeToDNAVariants(
args.reference_filepath,
args.genbank)
if args.text_file:
with open(args.text_file, 'r') as infile:
reader = csv.reader(infile, delimiter="\t")
for row in reader:
gene, mutation_string, alphabet = row
if alphabet == "DNA":
protein_coding_var = False
else:
protein_coding_var = True
for var_name in aa2dna.get_variant_names(
gene, mutation_string, protein_coding_var):
mutation = Mutation(reference=reference,
var_name=var_name,
gene=aa2dna.get_gene(gene),
mut=mutation_string)
mutations.append(mutation)
else:
for variant in args.variants:
gene, mutation = variant.split("_")
for var_name in aa2dna.get_variant_names(gene, mutation):
mutations.append(
Mutation(reference=reference,
var_name=var_name,
gene=gene,
mut=mutation))
else:
if args.text_file:
with open(args.text_file, 'r') as infile:
reader = csv.reader(infile, delimiter="\t")
for row in reader:
gene_name, pos, ref, alt, alphabet = row
if gene_name == "ref":
mutations.append(
Mutation(
reference=reference,
var_name="".join([ref, pos, alt])))
else:
mutations.append(
Mutation(
reference=reference,
var_name=row[0]))
else:
mutations.extend(Mutation(reference=reference, var_name=v)
for v in args.variants)
al = AlleleGenerator(
reference_filepath=args.reference_filepath,
kmer=args.kmer)
for enum, mut in enumerate(mutations):
if enum % 100 == 0:
logger.info(
"%i of %i - %f%%" % (enum, len(mutations), round(100*enum/len(mutations), 2)))
variant_panel = make_variant_probe(
al, mut.variant, args.kmer, DB=DB, no_backgrounds=args.no_backgrounds)
if variant_panel is not None:
for i, ref in enumerate(variant_panel.refs):
try:
gene_name = mut.gene.name
except AttributeError:
gene_name = "NA"
sys.stdout.write(
">ref-%s?var_name=%s&num_alts=%i&ref=%s&enum=%i&gene=%s&mut=%s\n" %
(mut.mut, mut.variant.var_name, len(
variant_panel.alts), mut.reference, i, gene_name, mut.mut))
sys.stdout.write("%s\n" % ref)
for i, a in enumerate(variant_panel.alts):
sys.stdout.write(">alt-%s?var_name=%s&enum=%i&gene=%s&mut=%s\n" %
(mut.mut, mut.variant.var_name, i, gene_name, mut.mut))
sys.stdout.write("%s\n" % a)
else:
logging.warning(
"All variants failed for %s_%s - %s" %
(mut.gene, mut.mut, mut.variant))
def setup(self):
self.reference_filepath = f"{DATA_DIR}/NC_000962.3.fasta"
self.reference = os.path.basename(
self.reference_filepath).split('.fa')[0]
self.aa2dna = GeneAminoAcidChangeToDNAVariants(
f"{DATA_DIR}/NC_000962.3.fasta", f"{DATA_DIR}/NC_000962.3.gb")
def run(parser, args):
# There's no need to try to connect to database if we're not doing backgrounds
if args.no_backgrounds:
logger.info(
"Not connecting to database, because --no-backgrounds option used")
DB = None
else:
DB = connect("%s-%s" % (DB_PREFIX, args.db_name))
if DB is not None:
try:
Variant.objects()
logger.info("Connected to %s-%s" % (DB_PREFIX, args.db_name))
except (ServerSelectionTimeoutError):
DB = None
logger.warning(
"Could not connect to database. Continuing without using genetic backgrounds"
)
mutations = []
lineages = set()
reference = os.path.basename(args.reference_filepath).split(".fa")[0]
if args.vcf:
run_make_probes_from_vcf_file(args)
elif args.genbank:
aa2dna = GeneAminoAcidChangeToDNAVariants(args.reference_filepath,
args.genbank)
if args.text_file:
with open(args.text_file, "r") as infile:
reader = csv.reader(infile, delimiter="\t")
for row in reader:
gene, mutation_string, alphabet = row
if alphabet == "DNA":
protein_coding_var = False
else:
protein_coding_var = True
for var_name in aa2dna.get_variant_names(
gene, mutation_string, protein_coding_var):
mutation = Mutation(
reference=reference,
var_name=var_name,
gene=aa2dna.get_gene(gene),
mut=mutation_string,
protein_coding_var=protein_coding_var,
)
mutations.append(mutation)
else:
for variant in args.variants:
gene, mutation = variant.split("_")
for var_name in aa2dna.get_variant_names(gene, mutation):
mutations.append(
Mutation(
reference=reference,
var_name=var_name,
gene=gene,
mut=mutation,
))
else:
if args.text_file:
mutations, lineages = load_dna_vars_txt_file(
args.text_file, reference)
if args.lineage:
with open(args.lineage, "w") as f:
json.dump(lineages, f, sort_keys=True, indent=2)
else:
mutations.extend(
Mutation(reference=reference, var_name=v)
for v in args.variants)
al = AlleleGenerator(reference_filepath=args.reference_filepath,
kmer=args.kmer)
for enum, mut in enumerate(mutations):
if enum % 100 == 0:
logger.info(
"%i of %i - %f%%" %
(enum, len(mutations), round(100 * enum / len(mutations), 2)))
variant_panel = make_variant_probe(al,
mut.variant,
args.kmer,
DB=DB,
no_backgrounds=args.no_backgrounds)
if variant_panel is not None:
for i, ref in enumerate(variant_panel.refs):
try:
gene_name = mut.gene.name
except AttributeError:
gene_name = "NA"
sys.stdout.write(
">ref-%s?var_name=%s&num_alts=%i&ref=%s&enum=%i&gene=%s&mut=%s\n"
% (
mut.mutation_output_name,
mut.variant.var_name,
len(variant_panel.alts),
mut.reference,
i,
gene_name,
mut.mutation_output_name,
))
sys.stdout.write("%s\n" % ref)
for i, a in enumerate(variant_panel.alts):
sys.stdout.write(
">alt-%s?var_name=%s&enum=%i&gene=%s&mut=%s\n" % (
mut.mutation_output_name,
mut.variant.var_name,
i,
gene_name,
mut.mutation_output_name,
))
sys.stdout.write("%s\n" % a)
else:
logger.warning("All variants failed for %s_%s - %s" %
(mut.gene, mut.mutation_output_name, mut.variant))