def test_conversion_highlevel(path):
"""
Test whether the high-level GenBank interface can properly read
the locus, annotation and sequence from GenBank file and write
these properties to a file, without data changing.
"""
suffix = path[-2:]
gb_file = gb.GenBankFile.read(path)
ref_locus = gb.get_locus(gb_file)
ref_annot_seq = gb.get_annotated_sequence(gb_file, format=suffix)
gb_file = gb.GenBankFile()
gb.set_locus(gb_file, *ref_locus)
gb.set_annotated_sequence(gb_file, ref_annot_seq)
temp = TemporaryFile("w+")
gb_file.write(temp)
temp.seek(0)
gb_file = gb.GenBankFile.read(temp)
temp.close()
test_locus = gb.get_locus(gb_file)
test_annot_seq = gb.get_annotated_sequence(gb_file, format=suffix)
assert test_locus == ref_locus
assert test_annot_seq.sequence == ref_annot_seq.sequence
assert test_annot_seq.annotation == ref_annot_seq.annotation
assert test_annot_seq.sequence_start == ref_annot_seq.sequence_start
def test_genbank_utility_gp():
"""
Check whether the high-level utility functions return the expected
content of a known GenPept file.
"""
gp_file = gb.GenBankFile.read(join(data_dir("sequence"), "bt_lysozyme.gp"))
#[print(e) for e in gp_file._field_pos]
assert gb.get_locus(gp_file) \
== ("AAC37312", 147, "", False, "MAM", "27-APR-1993")
assert gb.get_definition(gp_file) == "lysozyme [Bos taurus]."
assert gb.get_version(gp_file) == "AAC37312.1"
assert gb.get_gi(gp_file) == 163334
annotation = gb.get_annotation(gp_file)
feature = seq.Feature(
"Site",
[seq.Location(start, stop) for start, stop in zip(
[52,55,62,76,78,81,117,120,125],
[53,55,62,76,78,81,117,120,126]
)],
{"note": "lysozyme catalytic cleft [active]", "site_type": "active"}
)
in_annotation = False
for f in annotation:
if f.key == feature.key and f.locs == feature.locs and \
all([(key, val in f.qual.items())
for key, val in feature.qual.items()]):
in_annotation = True
assert in_annotation
assert len(gb.get_sequence(gp_file, format="gp")) == 147
def test_genbank_utility_gb():
"""
Check whether the high-level utility functions return the expected
content of a known GenBank file.
"""
gb_file = gb.GenBankFile.read(join(data_dir("sequence"), "ec_bl21.gb"))
assert gb.get_locus(gb_file) \
== ("CP001509", 4558953, "DNA", True, "BCT", "16-FEB-2017")
assert gb.get_definition(gb_file) \
== ("Escherichia coli BL21(DE3), complete genome.")
assert gb.get_version(gb_file) == "CP001509.3"
assert gb.get_gi(gb_file) == 296142109
assert gb.get_db_link(gb_file) \
== {"BioProject" : "PRJNA20713", "BioSample" : "SAMN02603478"}
annotation = gb.get_annotation(gb_file, include_only=["CDS"])
feature = seq.Feature(
"CDS",
[seq.Location(5681, 6457, seq.Location.Strand.REVERSE)],
{"gene": "yaaA", "transl_table": "11"}
)
in_annotation = False
for f in annotation:
if f.key == feature.key and f.locs == feature.locs and \
all([(key, val in f.qual.items())
for key, val in feature.qual.items()]):
in_annotation = True
assert in_annotation
assert len(gb.get_sequence(gb_file, format="gb")) == 4558953
"protein",
ret_type="gb")
# Array that will hold for each of the genes and each of the 4 domains
# the first and last position
# The array is initally filled with -1, as the value -1 will indicate
# that the domain does not exist in the sigma factor
domain_pos = np.full((len(genes), 4, 2), -1, dtype=int)
# Array that will hold the total sequence length of each sigma factor
seq_lengths = np.zeros(len(genes), dtype=int)
# Read the merged file containing multiple GenBank entries
multi_file = gb.MultiFile()
multi_file.read(file_name)
# Iterate over each GenBank entry
for i, gb_file in enumerate(multi_file):
_, length, _, _, _, _ = gb.get_locus(gb_file)
seq_lengths[i] = length
annotation = gb.get_annotation(gb_file)
# Find features, that represent a sigma factor domain
for feature in annotation:
if feature.key == "Region" and "note" in feature.qual \
and "Sigma-70 factor domain" in feature.qual["note"]:
# Extract the domain number
# and decrement for 0-based indexing
#
# e.g. 'Sigma-70 factor domain-2.' => 1
# ^
domain_index = int(
re.findall("(?<=Sigma-70 factor domain-)\d+",
feature.qual["note"])[0]) - 1
# Expect a single contiguous location of the domain
import biotite.sequence.graphics as graphics
import biotite.database.entrez as entrez
PLASMID_URL = "https://media.addgene.org/snapgene-media/" \
"v1.6.2-0-g4b4ed87/sequences/67/17/246717/" \
"addgene-plasmid-26094-sequence-246717.gbk"
response = requests.get(PLASMID_URL)
gb_file = gb.GenBankFile.read(io.StringIO(response.text))
annotation = gb.get_annotation(gb_file,
include_only=[
"promoter", "terminator", "protein_bind",
"RBS", "CDS", "rep_origin", "primer_bind"
])
_, seq_length, _, _, _, _ = gb.get_locus(gb_file)
# AddGene stores the plasmid name in the 'KEYWORDS' field
# [0][0][0] ->
# The first (and only) 'KEYWORDS' field
# The first entry in the tuple
# The first (and only) line in the field
plasmid_name = gb_file.get_fields("KEYWORDS")[0][0][0]
def custom_feature_formatter(feature):
# AddGene stores the feature label in the '\label' qualifier
label = feature.qual.get("label")
if feature.key == "promoter":
return True, biotite.colors["dimgreen"], "black", label
elif feature.key == "terminator":
return True, "firebrick", "black", label
