import biotite.sequence.io.fasta as fasta
import biotite.sequence.io.genbank as gb
import biotite.sequence.graphics as graphics
import biotite.application.clustalo as clustalo
import biotite.database.entrez as entrez
# Search for protein products of LexA gene in UniProtKB/Swiss-Prot database
query = entrez.SimpleQuery("lexA", "Gene Name") \
& entrez.SimpleQuery("srcdb_swiss-prot", "Properties")
# Search for the first 200 hits
# More than 200 UIDs are not recommended for the EFetch service
uids = entrez.search(query, db_name="protein", number=200)
file_name = entrez.fetch_single_file(uids, biotite.temp_file("lexa.gb"),
db_name="protein", ret_type="gb")
# The file contains multiple concatenated GenPept files
# -> Usage of MultiFile
multi_file = gb.MultiFile("gp")
multi_file.read(file_name)
# Separate MultiFile into single GenPeptFile instances
files = [f for f in multi_file]
print("Definitions:")
for file in files[:10]:
print(file.get_definition())
print()
print("Sources:")
for file in files[:10]:
print(file.get_source())
########################################################################
# The names of the sources are too long to be properly displayed later
# on. Therefore, we write a function that creates a proper abbreviation
# for a species name.
uids += ids
# Download corresponding GenBank files as single, merged file
file_name = entrez.fetch_single_file(uids,
biotite.temp_file("gb"),
"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
# ^
def test_multi_file():
multi_file = gb.MultiFile(file_type="gp")
multi_file.read(join(data_dir, "multifile.gp"))
accessions = [f.get_accession() for f in multi_file]
assert accessions == ["1L2Y_A", "3O5R_A", "5UGO_A"]