def writeGff3(data, handle, parentGff3):
for record in GFF.parse(parentGff3):
cdss = list(
feature_lambda(record.features,
feature_test_id, {"id": data.keys()},
subfeatures=False))
record.features = []
for cds in cdss:
if "note" not in cds.qualifiers:
cds.qualifiers["note"] = []
id = get_id(cds)
if data[id]["cleavage"]:
cds.qualifiers["note"].append("Cleavage between %s and %s" %
data[id]["cleavageSite"])
record.features.append(fetchParent(cds))
GFF.write([record], handle)
def shinefind(
genbank_file,
gff3_output=None,
table_output=None,
lookahead_min=5,
lookahead_max=15,
top_only=False,
add=False,
):
table_output.write("\t".join([
"ID",
"Name",
"Terminus",
"Terminus",
"Strand",
"Upstream Sequence",
"SD",
"Spacing",
]) + "\n")
sd_finder = NaiveSDCaller()
# Parse GFF3 records
for record in list(SeqIO.parse(genbank_file, "genbank")):
# Sometimes you have a case where TWO CDS features have the same start. Only handle ONE.
seen = {}
# Shinefind's "gff3_output".
gff3_output_record = SeqRecord(record.seq, record.id)
# Loop over all CDS features
for feature in record.features:
if feature.type != "CDS":
continue
seen_loc = (feature.location.start
if feature.strand > 0 else feature.location.end)
if seen_loc in seen:
continue
else:
seen[seen_loc] = True
sds, start, end, seq = sd_finder.testFeatureUpstream(
feature, record, sd_min=lookahead_min, sd_max=lookahead_max)
feature_id = get_id(feature)
sd_features = sd_finder.to_features(sds,
feature.location.strand,
start,
end,
feature_id=feature.id)
human_strand = "+" if feature.location.strand == 1 else "-"
# http://book.pythontips.com/en/latest/for_-_else.html
log.debug("Found %s SDs", len(sds))
for (sd, sd_feature) in zip(sds, sd_features):
# If we only want the top feature, after the bulk of the
# forloop executes once, we append the top feature, and fake a
# break, because an actual break triggers the else: block
table_output.write("\t".join(
map(
str,
[
feature.id,
feature_id,
feature.location.start,
feature.location.end,
human_strand,
sd_finder.highlight_sd(seq, sd["start"],
sd["end"]),
sd["hit"],
int(sd["spacing"]) + lookahead_min,
],
)) + "\n")
if add:
# Append the top RBS to the gene feature
record.features.append(sd_feature)
# Also register the feature with the separate GFF3 output
gff3_output_record.features.append(sd_feature)
if top_only:
break
else:
if len(sds) != 0:
log.debug("Should not reach here if %s", len(sds) != 0)
# Somehow this is triggerring, and I don't feel like figuring out why. Someone else's problem.
continue
table_output.write("\t".join(
map(
str,
[
feature.id,
feature_id,
feature.location.start,
feature.location.end,
human_strand,
seq,
None,
-1,
],
)) + "\n")
record.features = sorted(record.features,
key=lambda x: x.location.start)
SeqIO.write([record], sys.stdout, "genbank")
gff3_output_record.features = sorted(gff3_output_record.features,
key=lambda x: x.location.start)
gff3_output_record.annotations = {}
GFF.write([gff3_output_record], gff3_output)
top_hits[qseq][fn] = (evalue, sseq, dice)
sys.stdout.write("# Query Feature\tLocation\t")
sys.stdout.write("\t".join(["%s\tevalue\tdice" % x for x in blast_names]))
sys.stdout.write("\n")
for rec in GFF.parse(args.gff3):
for feat in fsort(
feature_lambda(rec.features,
feature_test_type, {"types": "CDS"},
subfeatures=False)):
sys.stdout.write(feat._parent._parent.qualifiers["Name"][0])
sys.stdout.write("\t")
sys.stdout.write(str(feat.location))
for db in blast_names:
fid = get_id(feat)
if fid in top_hits:
if fn in top_hits[fid]:
sys.stdout.write("\t")
sys.stdout.write(";".join([
"%s %s" % (x, y) for (x, y) in top_hits[fid][fn][1]
]))
sys.stdout.write("\t")
sys.stdout.write(str(top_hits[fid][fn][0]))
sys.stdout.write("\t")
sys.stdout.write(str(top_hits[fid][fn][2]))
else:
sys.stdout.write("\tNone")
sys.stdout.write("\tNone")
sys.stdout.write("\tNone")
else:
def find_lipoprotein(gff3_file,
fasta_genome,
lipobox_mindist=10,
lipobox_maxdist=60):
seq_dict = SeqIO.to_dict(SeqIO.parse(fasta_genome, "fasta"))
CASES = [
re.compile('^.{%s,%s}[ACGSILMFTV][^REKD][GASNL]C' %
(lipobox_mindist, lipobox_maxdist)),
# re.compile('^.{%s,%s}AWAC' % (lipobox_mindist, lipobox_maxdist)),
# Make sure to not have multiple cases that share matches, will introduce duplicate features into gff3 file
]
for record in GFF.parse(gff3_file, base_dict=seq_dict):
good_features = []
genes = list(
feature_lambda(record.features,
feature_test_type, {'type': 'gene'},
subfeatures=True))
for gene in genes:
cdss = list(
feature_lambda(gene.sub_features,
feature_test_type, {'type': 'CDS'},
subfeatures=False))
if len(cdss) == 0:
continue
# Someday this will bite me in the arse.
cds = cdss[0]
try:
tmpseq = str(
cds.extract(record.seq).translate(table=11,
cds=True)).replace(
"*", "")
except:
continue
for case in CASES:
m = case.search(tmpseq)
if m:
if cds.location.strand > 0:
start = cds.location.start + (3 * (m.end() - 4))
end = cds.location.start + (3 * m.end())
else:
start = cds.location.end - (3 * (m.end() - 4))
end = cds.location.end - (3 * m.end())
tmp = SeqFeature(FeatureLocation(
min(start, end),
max(start, end),
strand=cds.location.strand),
type='Lipobox',
qualifiers={
'source': 'CPT_LipoRy',
'ID': '%s.lipobox' % get_id(gene),
})
tmp.qualifiers['sequence'] = str(
tmp.extract(record).seq.translate())
gene.sub_features.append(tmp)
good_features.append(gene)
record.features = good_features
yield [record]
def main(fasta, gff3, feature_filter=None, nodesc=False):
if feature_filter == "nice_cds":
from gff2gb import gff3_to_genbank as cpt_Gff2Gbk
for rec in cpt_Gff2Gbk(gff3, fasta, 11):
seenList = {}
if rec.seq[0] == "?":
print("No Fasta ID matches GFF")
exit(1)
for feat in sorted(rec.features, key=lambda x: x.location.start):
if feat.type != "CDS":
continue
ind = 0
if (str(
feat.qualifiers.get("locus_tag",
get_id(feat)).replace(" ", "-"))
in seenList.keys()):
seenList[str(
feat.qualifiers.get("locus_tag",
get_id(feat)).replace(" ",
"-"))] += 1
ind = seenList[str(
feat.qualifiers.get("locus_tag",
get_id(feat)).replace(" ", "-"))]
else:
seenList[str(
feat.qualifiers.get("locus_tag",
get_id(feat)).replace(" ",
"-"))] = 1
append = ""
if ind != 0:
append = "_" + str(ind)
if nodesc:
description = ""
else:
feat.qualifiers["ID"] = [feat._ID]
product = feat.qualifiers.get("product", "")
description = "{1} [Location={0.location};ID={0.qualifiers[ID][0]}]".format(
feat, product)
# print(feat.qualifiers.get('locus_tag', get_id(feat)).replace(' ', '-'))
yield [
SeqRecord(
feat.extract(rec).seq,
id=str(
feat.qualifiers.get(
"locus_tag", get_id(feat)).replace(" ", "-")) +
append,
description=description,
)
]
elif feature_filter == "unique_cds":
seq_dict = SeqIO.to_dict(SeqIO.parse(fasta, "fasta"))
seen_ids = {}
for rec in GFF.parse(gff3, base_dict=seq_dict):
noMatch = True
if "Alias" in rec.features[0].qualifiers.keys():
lColumn = rec.features[0].qualifiers["Alias"][0]
else:
lColumn = ""
for x in seq_dict:
if x == rec.id or x == lColumn:
noMatch = False
if noMatch:
print("No Fasta ID matches GFF")
exit(1)
newfeats = []
for feat in sorted(
feature_lambda(rec.features,
feature_test_type, {"type": "CDS"},
subfeatures=False),
key=lambda f: f.location.start,
):
nid = rec.id + "____" + feat.id
if nid in seen_ids:
nid = nid + "__" + uuid.uuid4().hex
feat.qualifiers["ID"] = nid
newfeats.append(feat)
seen_ids[nid] = True
if nodesc:
description = ""
else:
important_data = {"Location": feat.location}
if "Name" in feat.qualifiers:
important_data["Name"] = feat.qualifiers.get(
"Name", [""])[0]
description = "[{}]".format(";".join([
"{key}={value}".format(key=k, value=v)
for (k, v) in important_data.items()
]))
yield [
SeqRecord(
feat.extract(rec).seq,
id=nid.replace(" ", "-"),
description=description,
)
]
rec.features = newfeats
rec.annotations = {}
GFF.write([rec], sys.stderr)
else:
seq_dict = SeqIO.to_dict(SeqIO.parse(fasta, "fasta"))
for rec in GFF.parse(gff3, base_dict=seq_dict):
noMatch = True
if "Alias" in rec.features[0].qualifiers.keys():
lColumn = rec.features[0].qualifiers["Alias"][0]
else:
lColumn = ""
for x in seq_dict:
if x == rec.id or x == lColumn:
noMatch = False
if noMatch:
print("No Fasta ID matches GFF")
exit(1)
for feat in sorted(
feature_lambda(
rec.features,
feature_test_type,
{"type": feature_filter},
subfeatures=False,
),
key=lambda f: f.location.start,
):
id = feat.id
if len(id) == 0:
id = get_id(feat)
if nodesc:
description = ""
else:
important_data = {"Location": feat.location}
if "Name" in feat.qualifiers:
important_data["Name"] = feat.qualifiers.get(
"Name", [""])[0]
description = "[{}]".format(";".join([
"{key}={value}".format(key=k, value=v)
for (k, v) in important_data.items()
]))
yield [
SeqRecord(
feat.extract(rec).seq,
id=id.replace(" ", "-"),
description=description,
)
]
def main(fasta, gff3, feature_filter=None, nodesc=False):
if feature_filter == 'nice_cds':
from gff2gb import gff3_to_genbank
for rec in gff3_to_genbank(gff3, fasta):
for feat in sorted(rec.features, key=lambda x: x.location.start):
if feat.type != 'CDS':
continue
if nodesc:
description = ''
else:
feat.qualifiers['ID'] = [feat._ID]
product = feat.qualifiers.get('product', '')
description = '{1} [Location={0.location};ID={0.qualifiers[ID][0]}]'.format(
feat, product)
yield [
SeqRecord(feat.extract(rec).seq,
id=feat.qualifiers.get('locus_tag',
get_id(feat)).replace(
' ', '-'),
description=description)
]
elif feature_filter == 'unique_cds':
seq_dict = SeqIO.to_dict(SeqIO.parse(fasta, "fasta"))
seen_ids = {}
for rec in GFF.parse(gff3, base_dict=seq_dict):
newfeats = []
for feat in sorted(feature_lambda(rec.features,
feature_test_type,
{'type': 'CDS'},
subfeatures=False),
key=lambda f: f.location.start):
nid = rec.id + '____' + feat.id
if nid in seen_ids:
nid = nid + '__' + uuid.uuid4().hex
feat.qualifiers['ID'] = nid
newfeats.append(feat)
seen_ids[nid] = True
if nodesc:
description = ''
else:
important_data = {
'Location': feat.location,
}
if 'Name' in feat.qualifiers:
important_data['Name'] = feat.qualifiers.get(
'Name', [''])[0]
description = '[{}]'.format(';'.join([
'{key}={value}'.format(key=k, value=v)
for (k, v) in important_data.items()
]))
yield [
SeqRecord(feat.extract(rec).seq,
id=nid.replace(' ', '-'),
description=description)
]
rec.features = newfeats
rec.annotations = {}
GFF.write([rec], sys.stderr)
else:
seq_dict = SeqIO.to_dict(SeqIO.parse(fasta, "fasta"))
for rec in GFF.parse(gff3, base_dict=seq_dict):
for feat in sorted(feature_lambda(rec.features,
feature_test_type,
{'type': feature_filter},
subfeatures=False),
key=lambda f: f.location.start):
id = feat.id
if len(id) == 0:
id = get_id(feat)
if nodesc:
description = ''
else:
important_data = {
'Location': feat.location,
}
if 'Name' in feat.qualifiers:
important_data['Name'] = feat.qualifiers.get(
'Name', [''])[0]
description = '[{}]'.format(';'.join([
'{key}={value}'.format(key=k, value=v)
for (k, v) in important_data.items()
]))
yield [
SeqRecord(feat.extract(rec).seq,
id=id.replace(' ', '-'),
description=description)
]
def shinefind(fasta,
gff3,
gff3_output=None,
table_output=None,
lookahead_min=5,
lookahead_max=15,
top_only=False,
add=False):
table_output.write('\t'.join([
'ID', 'Name', 'Terminus', 'Terminus', 'Strand', 'Upstream Sequence',
'SD', 'Spacing'
]) + "\n")
sd_finder = NaiveSDCaller()
# Load up sequence(s) for GFF3 data
seq_dict = SeqIO.to_dict(SeqIO.parse(fasta, "fasta"))
# Parse GFF3 records
for record in GFF.parse(gff3, base_dict=seq_dict):
# Shinefind's "gff3_output".
gff3_output_record = SeqRecord(record.seq, record.id)
# Filter out just coding sequences
ignored_features = []
for x in record.features:
# If feature X does NOT contain a CDS, add to ignored_features
# list. This means if we have a top level gene feature with or
# without a CDS subfeature, we're catch it appropriately here.
if len(
list(
feature_lambda([x],
feature_test_type, {'type': 'CDS'},
subfeatures=True))) == 0:
ignored_features.append(x)
# Loop over all gene features
for gene in feature_lambda(record.features,
feature_test_type, {'type': 'gene'},
subfeatures=True):
# Get the CDS from this gene.
feature = list(
feature_lambda(gene.sub_features,
feature_test_type, {'type': 'CDS'},
subfeatures=True))
# If no CDSs are in this gene feature, then quit
if len(feature) == 0:
# We've already caught these above in our ignored_features
# list, so we skip out on the rest of this for loop
continue
else:
# Otherwise pull the first (bad?) We don't expect >1 CDS/gene
feature = feature[0]
# Three different ways RBSs can be stored that we expect.
rbs_rbs = list(
feature_lambda(gene.sub_features,
feature_test_type, {'type': 'RBS'},
subfeatures=False))
rbs_sds = list(
feature_lambda(gene.sub_features,
feature_test_type,
{'type': 'Shine_Dalgarno_sequence'},
subfeatures=False))
regulatory_elements = list(
feature_lambda(gene.sub_features,
feature_test_type, {'type': 'regulatory'},
subfeatures=False))
rbs_regulatory = list(
feature_lambda(regulatory_elements,
feature_test_quals,
{'regulatory_class': ['ribosome_binding_site']},
subfeatures=False))
rbss = rbs_rbs + rbs_sds + rbs_regulatory
# If someone has already annotated an RBS, we quit
if len(rbss) > 0:
log.debug("Has %s RBSs", len(rbss))
ignored_features.append(gene)
continue
sds, start, end, seq = sd_finder.testFeatureUpstream(
feature, record, sd_min=lookahead_min, sd_max=lookahead_max)
feature_id = get_id(feature)
sd_features = sd_finder.to_features(sds,
feature.location.strand,
start,
end,
feature_id=feature.id)
human_strand = '+' if feature.location.strand == 1 else '-'
# http://book.pythontips.com/en/latest/for_-_else.html
log.debug('Found %s SDs', len(sds))
for (sd, sd_feature) in zip(sds, sd_features):
# If we only want the top feature, after the bulk of the
# forloop executes once, we append the top feature, and fake a
# break, because an actual break triggers the else: block
table_output.write('\t'.join(
map(str, [
feature.id,
feature_id,
feature.location.start,
feature.location.end,
human_strand,
sd_finder.highlight_sd(seq, sd['start'], sd['end']),
sd['hit'],
int(sd['spacing']) + lookahead_min,
])) + "\n")
if add:
# Append the top RBS to the gene feature
gene.sub_features.append(sd_feature)
# Pick out start/end locations for all sub_features
locations = [x.location.start for x in gene.sub_features] + \
[x.location.end for x in gene.sub_features]
# Update gene's start/end to be inclusive
gene.location._start = min(locations)
gene.location._end = max(locations)
# Also register the feature with the separate GFF3 output
sd_feature = fix_gene_boundaries(sd_feature)
gff3_output_record.features.append(sd_feature)
if top_only:
break
else:
if len(sds) != 0:
log.debug('Should not reach here if %s', len(sds) != 0)
# Somehow this is triggerring, and I don't feel like figuring out why. Someone else's problem.
continue
table_output.write('\t'.join(
map(str, [
feature.id,
feature_id,
feature.location.start,
feature.location.end,
human_strand,
seq,
None,
-1,
])) + "\n")
record.annotations = {}
GFF.write([record], sys.stdout)
gff3_output_record.features = sorted(gff3_output_record.features,
key=lambda x: x.location.start)
gff3_output_record.annotations = {}
GFF.write([gff3_output_record], gff3_output)
def feature_test_id(feature, **kwargs):
return get_id(feature) in kwargs["id"]