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
"R": -4.5
}
# Look for the Swiss-Prot entry contaning the human HCN1 channel
query = entrez.SimpleQuery("HCN1", "Gene Name") \
& entrez.SimpleQuery("h**o sapiens", "Organism") \
& entrez.SimpleQuery("srcdb_swiss-prot", "Properties")
uids = entrez.search(query, db_name="protein")
file_name = entrez.fetch(uids[0],
biotite.temp_dir(),
"gp",
db_name="protein",
ret_type="gp")
gp_file = gb.GenBankFile.read(file_name)
hcn1 = seq.ProteinSequence(gb.get_sequence(gp_file, format="gp"))
print(hcn1)
########################################################################
# The positional hydropathy is calculated and smoothened using
# a moving average for clearer visualization.
hydropathies = np.array([hydropathy_dict[symbol] for symbol in hcn1])
def moving_average(data_set, window_size):
weights = np.full(window_size, 1 / window_size)
return np.convolve(data_set, weights, mode='valid')
# Apply moving average over 15 amino acids for clearer visualization
import biotite.structure.graphics as strucgraphics
import biotite.application.viennarna as viennarna
# Download Escherichia coli BL21 and Salmonella enterica genome
gb_file = gb.MultiFile.read(
entrez.fetch_single_file(["CP001509", "CP019649"], None, "nuccore", "gb"))
ec_file, se_file = tuple(gb_file)
annot_seq = gb.get_annotated_sequence(ec_file, include_only=["ncRNA"])
# Find M1 gene in E. coli genome via its annotation
for feature in annot_seq.annotation:
if "product" in feature.qual and "RNase P" in feature.qual["product"]:
m1_sequence = annot_seq[feature]
# Get S. enterica genome sequence
se_genome = gb.get_sequence(se_file)
# We want to search in the genome sequence and its reverse complement
genomic_seqs = [se_genome, se_genome.reverse().complement()]
########################################################################
# In an initial fast matching step, we look for matching *k-mers*
# between *M1* and the *S. enterica* genome.
# A matching *k-mer* is a length *k* subsequence, that appears in both
# sequences.
# In *Biotite* this task is carried out by a :class:`KmerTable`.
#
# Later we will perform costly gapped alignments at the match positions.
# To reduce the number of triggered gapped alignments at unspecific
# matches, we add some additional filters:
# One extra condition is that two non-overlapping matches must appear