def test_retrieve_data():
"""Test retrieve_data function"""
data = enasearch.retrieve_data(ids="ERA000010-ERA000020",
display="xml",
download=None,
file=None,
offset=None,
length=None,
subseq_range=None,
expanded=None,
header=None)
assert "ROOT" in data
data = enasearch.retrieve_data(ids="A00145",
display="fasta",
download=None,
file=None,
offset=0,
length=100000,
subseq_range="3-63",
expanded=None,
header=None)
pprint([seq.id for seq in data])
assert 'ENA|A00145|A00145.1' in [seq.id for seq in data]
data = enasearch.retrieve_data(ids="AL513382",
display="text",
download=None,
file=None,
offset=0,
length=100000,
subseq_range=None,
expanded="true",
header=None)
pprint(data)
assert "AL513382" in data and len(data.split("\n")) >= 200000
data = enasearch.retrieve_data(ids="AL513382",
display="text",
download=None,
file=None,
offset=0,
length=100000,
subseq_range=None,
expanded=None,
header="true")
pprint(data)
assert "AL513382" in data and len(data.split("\n")) >= 745
data = enasearch.retrieve_data(ids="PRJEB2772",
display="xml",
download=None,
file=None,
offset=0,
length=100000,
subseq_range=None,
expanded=None,
header=None)
pprint(data)
assert "ROOT" in data
def retrieve_data(ids, display, download, file, offset, length, subseq_range,
expanded, header):
"""Retrieve ENA data (other than taxon).
This function retrieves data (other than taxon) from ENA by:
- Building the URL based on the ids to retrieve and some parameters to format the results
- Requesting the URL to extract the data
The output can be redirected to a file and directly display to the standard
output given the display chosen.
"""
download = None if not download else download
file = None if not file else file
offset = None if not offset else offset
length = None if not length else length
subseq_range = None if not subseq_range else subseq_range
expanded = True if expanded else False
header = True if header else False
data = enasearch.retrieve_data(ids=",".join(ids),
display=display,
download=download,
file=file,
offset=offset,
length=length,
subseq_range=subseq_range,
expanded=expanded,
header=header)
if file is None:
print_display(data, display)
def retrieve_data(ids, display, download, file, offset, length, subseq_range,
expanded, header):
""" Retrieve ENA data (other than taxon and project) """
download = None if not download else download
file = None if not file else file
offset = None if not offset else offset
length = None if not length else length
subseq_range = None if not subseq_range else subseq_range
expanded = True if expanded else False
header = True if header else False
data = enasearch.retrieve_data(ids=",".join(ids),
display=display,
download=download,
file=file,
offset=offset,
length=length,
subseq_range=subseq_range,
expanded=expanded,
header=header)
if file is None:
print_display(data, display)
def sample2assembly(sample_id):
response = ena_sample(sample_id, result='assembly')
if response.status_code != 200:
return ''
else:
out = response.text
data = json.loads(out)
return data[0]
data = enasearch.search_data(free_text_search=True,
query="CABMLH010000000",
result='wgs_set',
display='xml')
data = enasearch.retrieve_data(ids="CABMLH010000000", display="html")
def get_returnable_fields(result):
url = f"https://www.ebi.ac.uk/ena/portal/api/returnFields?dataPortal=ena&format=json&result={result}"
response = requests.get(url, )
out = response.text
data = json.loads(out)
return data
returnable_fields = get_returnable_fields('wgs_set')
returnable_fields = [_['columnId'] for _ in returnable_fields]
def file_report(sample_id):
def search_ena_accessions(accessions: List[str]):
ids = ','.join(accessions)
return enasearch.retrieve_data(ids=ids, display="xml")