def get_fasta(self, id_):
"""Returns FASTA string given a valid identifier
.. seealso:: :mod:`bioservices.apps.fasta` for dedicated tools to
manipulate FASTA
"""
from bioservices.apps.fasta import FASTA
f = FASTA()
f.load_fasta(id_)
return f.fasta
def get_fasta_sequence(self, id_):
"""Returns FASTA sequence (Not FASTA)
:param str id_: Should be the entry name
:return: returns fasta sequence (string)
.. warning:: this is the sequence found in a fasta file, not the fasta
content itself. The difference is that the header is removed and the
formatting of end of lines every 60 characters is removed.
"""
from bioservices.apps.fasta import FASTA
f = FASTA()
f.load_fasta(id_)
return f.sequence
def test_fasta():
fasta = FASTA()
fasta.load_fasta(None)
fasta.load_fasta("P43403")
fasta.load_fasta("P43403") # already there
fasta.header
fasta.gene_name
fasta.sequence
fasta.fasta
fasta.identifier
fh = tempfile.NamedTemporaryFile(delete=False)
fasta.save_fasta(fh.name)
fasta.read_fasta(fh.name)
fh.delete = True
fh.close()
def setup_class(klass):
klass.s = FASTA(verbose=False)
from bioservices import UniProt
from bioservices import PDB
from bioservices.apps.fasta import FASTA
from bioservices import ChEMBL
import os
# Leos from uniprot id to the protein name
f = FASTA()
u = UniProt(cache=True, verbose=False)
s = PDB()
c = ChEMBL(verbose=False)
"""
pdb chain to uniprot id: ftp.ebi.ac.uk/pub/databases/msd/sifts/csv/pdb_chain_uniprot.csv
import requests
from xml.etree.ElementTree import fromstring
pdb_id = '4hhb.A'
pdb_mapping_url = 'http://www.rcsb.org/pdb/rest/das/pdb_uniprot_mapping/alignment'
uniprot_url = 'http://www.uniprot.org/uniprot/{}.xml'
def get_uniprot_accession_id(response_xml):
root = fromstring(response_xml)
return next(
el for el in root.getchildren()[0].getchildren()
if el.attrib['dbSource'] == 'UniProt'
).attrib['dbAccessionId']
def get_uniprot_protein_name(uniport_id):
uinprot_response = requests.get(
uniprot_url.format(uniport_id)
).text