def test_classification_with_colon(self):
# since SMCOG id and description are stored in a string separated by :,
# ensure that descriptions containing : are properly handled
cds = CDSFeature(FeatureLocation(0, 100),
locus_tag="test",
translation="AAA")
record = helpers.DummyRecord(features=[cds], seq="A" * 100)
record.add_cluster(helpers.DummyCluster(0, 100))
results = SMCOGResults(record.id)
results.best_hits[cds.get_name()] = HMMResult(
"SMCOG1212:sodium:dicarboxylate_symporter", 0, 100, 2.3e-126, 416)
results.add_to_record(record)
gene_functions = cds.gene_functions.get_by_tool("smcogs")
assert len(gene_functions) == 1
assert str(gene_functions[0]).startswith(
"transport (smcogs) SMCOG1212:sodium:dicarboxylate_symporter"
" (Score: 416; E-value: 2.3e-126)")
def generate_motif_features(record: Record, feature: CDSFeature,
motifs: List[HMMResult]) -> List[CDSMotif]:
""" Convert a list of HMMResult to a list of CDSMotif features """
# use a locus tag if one exists
locus_tag = feature.get_name()
if feature.locus_tag:
locus_tag = feature.locus_tag
# grab the translation table if it's there
if feature.transl_table:
transl_table = feature.transl_table
else:
transl_table = 1
motif_features = []
for i, motif in enumerate(motifs):
i += 1 # user facing, so 1-indexed
loc = feature.get_sub_location_from_protein_coordinates(
motif.query_start, motif.query_end)
new_motif = CDSMotif(loc)
new_motif.label = motif.hit_id
new_motif.motif = motif.hit_id # TODO: why both label AND motif?
new_motif.domain_id = 'nrpspksmotif_{}_{:04d}'.format(locus_tag, i)
new_motif.evalue = motif.evalue
new_motif.score = motif.bitscore
new_motif.tool = "pksnrpsmotif"
new_motif.detection = "hmmscan"
new_motif.database = "abmotifs"
new_motif.locus_tag = locus_tag
new_motif.translation = str(
new_motif.extract(record.seq).translate(table=transl_table))
new_motif.notes.append(
"NRPS/PKS Motif: %s (e-value: %s, bit-score: %s)" %
(motif.hit_id, motif.evalue,
motif.bitscore)) # TODO move to CDSMotif
motif_features.append(new_motif)
return motif_features
def generate_domain_features(
record: Record, gene: CDSFeature,
domains: List[HMMResult]) -> Dict[HMMResult, AntismashDomain]:
""" Generates AntismashDomain features for each provided HMMResult
Arguments:
record: the record the new features will belong to
gene: the CDSFeature the domains were found in
domains: a list of HMMResults found in the CDSFeature
Returns:
a dictionary mapping the HMMResult used to the matching AntismashDomain
"""
new_features = {}
nrat = 0
nra = 0
nrcal = 0
nrkr = 0
nrXdom = 0
for domain in domains:
loc = gene.get_sub_location_from_protein_coordinates(
domain.query_start, domain.query_end)
# set up new feature
new_feature = AntismashDomain(loc)
new_feature.domain = domain.hit_id
new_feature.locus_tag = gene.locus_tag
new_feature.detection = "hmmscan"
new_feature.database = "nrpspksdomains.hmm"
new_feature.evalue = domain.evalue
new_feature.score = domain.bitscore
transl_table = gene.transl_table or 1
new_feature.translation = str(
new_feature.extract(record.seq).translate(table=transl_table))
if domain.hit_id == "AMP-binding":
nra += 1
domainname = "{}_A{}".format(gene.get_name(), nra)
new_feature.label = domainname
new_feature.domain_id = "nrpspksdomains_" + domainname
elif domain.hit_id == "PKS_AT":
nrat += 1
domainname = "{}_AT{}".format(gene.get_name(), nrat)
new_feature.label = domainname
new_feature.domain_id = "nrpspksdomains_" + domainname
elif domain.hit_id == "CAL_domain":
nrcal += 1
domainname = gene.get_name() + "_CAL" + str(nrcal)
new_feature.label = domainname
new_feature.domain_id = "nrpspksdomains_" + domainname
elif domain.hit_id == "PKS_KR":
nrkr += 1
domainname = gene.get_name() + "_KR" + str(nrkr)
new_feature.label = domainname
new_feature.domain_id = "nrpspksdomains_" + domainname
else:
nrXdom += 1
new_feature.domain_id = "nrpspksdomains_" + gene.get_name(
).partition(".")[0] + "_Xdom" + '{:02d}'.format(nrXdom)
assert new_feature.get_name() not in new_features
new_features[domain] = new_feature
return new_features