def find_all_orfs(record: Record,
cluster: Optional[Cluster] = None) -> List[CDSFeature]:
""" Find all ORFs of at least 60 bases that don't overlap with existing
CDS features.
Can (and should) be limited to just within a cluster.
Arguments:
record: the record to search
cluster: the specific Cluster to search within, or None
Returns:
a list of CDSFeatures, one for each ORF
"""
# Get sequence for the range
offset = 0
seq = record.seq
existing = record.get_cds_features()
if cluster:
seq = record.seq[cluster.location.start:cluster.location.end]
offset = cluster.location.start
existing = tuple(cluster.cds_children)
# Find orfs throughout the range
forward_matches = scan_orfs(seq, 1, offset)
reverse_matches = scan_orfs(seq.reverse_complement(), -1, offset)
locations = forward_matches + reverse_matches
orfnr = 1
new_features = []
for location in locations:
if cluster:
if isinstance(location.start, (BeforePosition, AfterPosition)):
continue
if isinstance(location.end, (BeforePosition, AfterPosition)):
continue
dummy_feature = Feature(location, feature_type="dummy")
# skip if overlaps with existing CDSs
if any(dummy_feature.overlaps_with(cds) for cds in existing):
continue
feature = create_feature_from_location(record, location, orfnr)
# skip if not wholly contained in the cluster
if cluster and not feature.is_contained_by(cluster):
continue
new_features.append(feature)
orfnr += 1
return new_features
def find_all_orfs(record: Record, area: Optional[CDSCollection] = None) -> List[CDSFeature]:
""" Find all ORFs of at least 60 bases that don't overlap with existing
CDS features.
Can (and should) be limited to just within a specific section of the record.
Arguments:
record: the record to search
area: the specific CDSCollection to search within, or None
Returns:
a list of CDSFeatures, one for each ORF
"""
# Get sequence for the range
offset = 0
seq = record.seq
existing: Iterable[CDSFeature] = record.get_cds_features()
if area:
seq = area.extract(seq)
offset = area.location.start
existing = record.get_cds_features_within_location(area.location,
with_overlapping=True)
# Find orfs throughout the range
forward_matches = scan_orfs(seq, 1, offset)
reverse_matches = scan_orfs(seq.reverse_complement(), -1, offset)
locations = forward_matches + reverse_matches
new_features = []
for location in locations:
if area:
if isinstance(location.start, (BeforePosition, AfterPosition)):
continue
if isinstance(location.end, (BeforePosition, AfterPosition)):
continue
dummy_feature = Feature(location, feature_type="dummy")
# skip if overlaps with existing CDSs
if any(dummy_feature.overlaps_with(cds) for cds in existing):
continue
feature = create_feature_from_location(record, location)
# skip if not wholly contained in the area
if area and not feature.is_contained_by(area):
continue
new_features.append(feature)
return new_features
def store_promoters(promoters: Iterable[Promoter], record: Record) -> None:
"""Store information about promoter sequences to a SeqRecord"""
for promoter in promoters:
# remember to account for 0-indexed start location
new_feature = SeqFeature(FeatureLocation(max(0, promoter.start - 1),
promoter.end),
type="promoter")
new_feature.qualifiers = {
"locus_tag": promoter.get_gene_names(
), # already a list with one or two elements
"seq": [str(promoter.seq)],
}
if isinstance(promoter, CombinedPromoter):
new_feature.qualifiers["note"] = ["bidirectional promoter"]
secmet_version = Feature.from_biopython(new_feature)
secmet_version.created_by_antismash = True
record.add_feature(secmet_version)
def create_feature_from_location(record, location, counter=1, label=None) -> CDSFeature:
""" Creates a CDS feature covering the provided location.
Arguments:
record: The Record the CDSFeature will belong to, used to generate
the feature translation
location: The FeatureLocation specifying the location of the CDSFeature
counter: An integer to use to format a default label 'allorf' with,
used only if label not provided
label: The locus tag, protein id, and gene name to use for the new
CDSFeature
Returns:
The CDSFeature created.
"""
if label is None:
label = 'allorf%03d' % counter
dummy = Feature(location, feature_type="temp")
feature = CDSFeature(location, str(record.get_aa_translation_of_feature(dummy)),
locus_tag=label, protein_id=label, gene=label)
feature.created_by_antismash = True
return feature