# The names of the sigma factors and the corresponding genes
genes = OrderedDict({
r"$\sigma^{70}$": "rpoD",
r"$\sigma^{24}$": "rpoE",
r"$\sigma^{28}$": "rpoF",
r"$\sigma^{32}$": "rpoH",
r"$\sigma^{38}$": "rpoS",
})
# Find SwissProt entries for these genes in NCBI Entrez protein database
uids = []
for name, gene in genes.items():
query = entrez.SimpleQuery(gene, "Gene Name") \
& entrez.SimpleQuery("srcdb_swiss-prot", "Properties") \
& entrez.SimpleQuery("Escherichia coli K-12", "Organism")
ids = entrez.search(query, "protein")
# Only one entry per gene in E. coli K-12 is expected
assert len(ids) == 1
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
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.gridspec import GridSpec
import biotite
import biotite.sequence as seq
import biotite.sequence.io.fasta as fasta
import biotite.sequence.align as align
import biotite.sequence.graphics as graphics
import biotite.database.entrez as entrez
# Generate example alignment
# (the same as in the bacterial luciferase example)
query = entrez.SimpleQuery("luxA", "Gene Name") \
& entrez.SimpleQuery("srcdb_swiss-prot", "Properties")
uids = entrez.search(query, db_name="protein")
file_name = entrez.fetch_single_file(uids,
biotite.temp_file("fasta"),
db_name="protein",
ret_type="fasta")
fasta_file = fasta.FastaFile.read(file_name)
sequences = [seq.ProteinSequence(seq_str) for seq_str in fasta_file.values()]
matrix = align.SubstitutionMatrix.std_protein_matrix()
alignment, order, _, _ = align.align_multiple(sequences, matrix)
# Order alignment according to the guide tree
alignment = alignment[:, order]
alignment = alignment[220:300]
# Get color scheme names
alphabet = seq.ProteinSequence.alphabet
schemes = [
import numpy as np
import matplotlib.pyplot as plt
import biotite
import biotite.sequence as seq
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())
ret_type="fasta")
print(file_path)
temp_file.close()
########################################################################
# Similar to the *RCSB PDB*, you can also search every
# `field <https://www.ncbi.nlm.nih.gov/books/NBK49540/>`_
# of the *NCBI Entrez* database.
# Search in all fields
print(entrez.SimpleQuery("BL21 genome"))
# Search in the 'Organism' field
print(entrez.SimpleQuery("Escherichia coli", field="Organism"))
########################################################################
# You can also combine multiple :class:`Query` objects in any way you
# like using the binary operators ``|``, ``&`` and ``^``,
# that represent ``OR``, ``AND`` and ``NOT`` linkage, respectively.
composite_query = (entrez.SimpleQuery("50:100", field="Sequence Length") &
(entrez.SimpleQuery("Escherichia coli", field="Organism") |
entrez.SimpleQuery("Bacillus subtilis", field="Organism")))
print(composite_query)
########################################################################
# Finally, the query is given to the :func:`search()` function to obtain
# the GIs, that can be used as input for :func:`fetch()`.
# Return a maximum number of 10 entries
gis = entrez.search(composite_query, "protein", number=10)
print(gis)
import matplotlib.pyplot as plt
from matplotlib.colors import LinearSegmentedColormap
import biotite.sequence as seq
import biotite.sequence.align as align
import biotite.sequence.io.genbank as gb
import biotite.sequence.align as align
import biotite.sequence.graphics as graphics
import biotite.database.entrez as entrez
import biotite.application.clustalo as clustalo
# Search for DNA sequences that belong to the cited article
query = entrez.SimpleQuery("Forensic Sci. Int.", "Journal") \
& entrez.SimpleQuery("159", "Volume") \
& entrez.SimpleQuery("132-140", "Page Number")
uids = entrez.search(query, db_name="nuccore")
# Download and read file containing the Genbank records for the THCA
# synthase genes
multi_file = gb.MultiFile.read(entrez.fetch_single_file(
uids, file_name=None, db_name="nuccore", ret_type="gb"
))
# This dictionary maps the strain ID to the protein sequence
sequences = {}
for gb_file in multi_file:
annotation = gb.get_annotation(gb_file)
# Find ID of strain in 'source' feature
