def __init__(self):
self.rma = RmaApi()
# TODO: only load this, if the file does not exist!
self.PlaneOfSections = self.rma.json_msg_query(
url=
"http://api.brain-map.org/api/v2/data/query.json?criteria=model::PlaneOfSection,rma::options[num_rows$eqall]"
)
def __init__(self, archive_dir=None):
self.bp = BiophysicalApi('http://api.brain-map.org')
self.bp.cache_stimulus = True # change to False to not download the large stimulus NWB file
self.cta = CellTypesApi()
self.rma = RmaApi()
self.neuronal_model_download_endpoint = 'http://celltypes.brain-map.org/neuronal_model/download/'
self.template_names = {}
self.nwb_list = []
if archive_dir == None:
archive_dir = '.'
self.archive_dir = archive_dir
class BiophysicalArchiver(object):
def __init__(self, archive_dir=None):
self.bp = BiophysicalApi('http://api.brain-map.org')
self.bp.cache_stimulus = True # change to False to not download the large stimulus NWB file
self.cta = CellTypesApi()
self.rma = RmaApi()
self.neuronal_model_download_endpoint = 'http://celltypes.brain-map.org/neuronal_model/download/'
self.template_names = {}
self.nwb_list = []
if archive_dir == None:
archive_dir = '.'
self.archive_dir = archive_dir
def get_template_names(self):
template_response = self.rma.model_query('NeuronalModelTemplate')
self.template_names = { t['id']: str(t['name']).replace(' ', '_') for t in template_response}
def get_cells(self):
return self.cta.list_cells(True, True)
def get_neuronal_models(self, specimen_ids):
return self.rma.model_query('NeuronalModel',
criteria='specimen[id$in%s]' % ','.join(str(i) for i in specimen_ids),
include='specimen',
num_rows='all')
def get_stimulus_file(self, neuronal_model_id):
result = self.rma.model_query('NeuronalModel',
criteria='[id$eq%d]' % (neuronal_model_id),
include="specimen(ephys_result(well_known_files(well_known_file_type[name$il'NWB*'])))",
tabular=['path'])
stimulus_filename = result[0]['path']
return stimulus_filename
stimulus_filename = os.path.basename(result[0]['path'])
return stimulus_filename
def archive_cell(self, ephys_result_id, specimen_id, template, neuronal_model_id):
url = self.neuronal_model_download_endpoint + "/%d" % (neuronal_model_id)
file_name = os.path.join(self.archive_dir, 'ephys_result_%d_specimen_%d_%s_neuronal_model_%d.zip' % (ephys_result_id,
specimen_id,
template,
neuronal_model_id))
self.rma.retrieve_file_over_http(url, file_name)
nwb_file = self.get_stimulus_file(neuronal_model_id)
shutil.copy(nwb_file, self.archive_dir)
self.nwb_list.append("%s\t%s" % (os.path.basename(nwb_file),
file_name))
def getAsync(
self, from_cache, aggregations
): # load data once with use_cache = True, then change it to False to read it from disk instead of fetching it from the api
#print('HumanMicroarrayData.get() start')
if not from_cache:
# we use the RmaApi to query specific information, such as the section data sets of a specific gene
# for docs, see: https://alleninstitute.github.io/AllenSDK/allensdk.api.queries.rma_api.html
rma = RmaApi()
# ok, so we don't need to do multiple requests to forward data from a model to a service, but simply use the pipe-concept:
# http://help.brain-map.org/display/api/Service+Pipelines
# e.g. this finds all probes for gabra4 and then queries the microarray-expression data for these probes. note that variables generated by a pipe are referenced by $variableName
# check out this playground: http://api.brain-map.org/examples/rma_builder/index.html
# we only use the product 'Human Microarray', which has the id 2 (id$eq2).
query = (
"http://api.brain-map.org/api/v2/data/query.json?criteria="
f"model::Probe,rma::criteria,gene[acronym$il{self.geneAcronym}],products[id$eq2],rma::options[num_rows$eqall],"
"pipe::list[probes$eq'id'],"
"service::human_microarray_expression[probes$eq$probes]")
data = rma.json_msg_query(url=query)
data = self.transformExpressionData(data)
structure_map = StructureMap.StructureMap(
reference_space_key='annotation/ccf_2017',
resolution=25).get(structure_graph_id=10) # , annotation, meta
# https://stackoverflow.com/questions/19125091/pandas-merge-how-to-avoid-duplicating-columns
# to avoid automatic renaming the duplicate columns by removing any duplicate-column
# note that our merge-condition is index vs structure_id. because structure_id is the index of structure_map,
# it is not identified as a duplicate column.
data = data[data.columns.difference(structure_map.columns)]
ret = Utils.merge_with_structure(data, structure_map,
HumanMicroarrayData.VALUE_COLUMNS,
aggregations)
Utils.save(ret, self.cache_path, 'cache.pkl')
return {'human': ret}
else:
if not glob.glob(self.cache_path):
Utils.log.warning(
f"No cached dataframe found. Check whether you have access to file '{self.cache_path}' and whether it exists. Obtaining data without caching now..."
)
return self.get(False, aggregations)
#print('HumanMicroarrayData.get() done')
return {'human': Utils.load(self.cache_path + 'cache.pkl')}
def __init__(self, master):
rma = RmaApi()
self.structgraph = pd.DataFrame(
rma.model_query('Structure',
criteria='[graph_id$eq1]',
num_rows='all'))
volume = 'App_File/annotation_25.nrrd'
self.readdata, header = nrrd.read(volume)
Frame.__init__(self, master)
self.master = master
self.init_window()
def QueryAPI(model,
criteriaString,
includeString="",
optionsString="",
writeOut=[]):
# Initiate RMA API for Allen data retrieval
api = RmaApi()
# Settings for retrieval
rows = []
blockSize = 2000
done = False
startRow = 0
# for i in range(0, total_rows, blockSize):
while not done:
print "Row %d, attempting to retrieve %d rows..." % (startRow,
blockSize)
tot_rows = len(rows)
if len(includeString) == 0:
rows += api.model_query(model=model,
criteria=criteriaString,
options=optionsString,
start_row=startRow,
num_rows=blockSize)
else:
rows += api.model_query(model=model,
criteria=criteriaString,
include=includeString,
options=optionsString,
start_row=startRow,
num_rows=blockSize)
numRows = len(
rows) - tot_rows # additional rows retrieved on running the query
startRow += numRows
print "%d rows retrieved." % numRows
# Check if we're at the end of the road
if numRows == 0 or numRows < blockSize:
done = True
# Write out the results as they come in, if requested
if isinstance(writeOut, basestring):
json_utilities.write(json_file_name, rows)
print "Wrote to %s" % json_file_name
return rows
def QueryAPI(model,
criteriaString,
includeString=None,
optionsString=None,
writeOut=False):
# Send a query to the Allen API, and assemble results
# Initiate RMA API for Allen data retrieval
api = RmaApi()
# Settings for retrieval
rows = []
blockSize = 2000
done = False
startRow = 0
# for i in range(0, total_rows, blockSize):
while not done:
print("Row %d, attempting to retrieve %d rows..." %
(startRow, blockSize))
tot_rows = len(rows)
# apiQueryPartial = partial(api.model_query,model=model,criteria=criteriaString,
# startRow=startRow,num_rows=blockSize)
rows += api.model_query(model=model,
criteria=criteriaString,
include=includeString,
options=optionsString,
start_row=startRow,
num_rows=blockSize)
numRows = len(
rows) - tot_rows # additional rows retrieved on running the query
startRow += numRows
print("%d rows retrieved." % numRows)
# Check if we're at the end of the road
if numRows == 0 or numRows < blockSize:
done = True
# Write out the results as they come in, if requested
if writeOut:
json_utilities.write(json_file_name, rows)
print("Wrote to %s" % json_file_name)
return rows
def rma():
ju.read_url_get = \
MagicMock(name='read_url_get',
return_value={'msg': _msg})
json.dumps = \
MagicMock(name='dumps')
ju.read = \
MagicMock(name='read',
return_value=_msg)
pj.read_json = \
MagicMock(name='read_json',
return_value=_pd_msg)
pd.DataFrame.to_csv = \
MagicMock(name='to_csv')
pd.DataFrame.from_csv = \
MagicMock(name='from_csv',
return_value=_csv_msg)
os.makedirs = MagicMock(name='makedirs')
return { 'ju_read_url_get': ju.read_url_get,
'ju_write': ju.write,
'ju_read': ju.read,
'pj_read_json': pj.read_json,
'to_csv': pd.DataFrame.to_csv,
'from_csv': pd.DataFrame.from_csv,
'os_makedirs': os.makedirs,
'rma_api': RmaApi() }
def build_url(self, service_name, kwargs):
'''Create a single stage RMA url from a service name and parameters.
'''
rma = RmaApi()
fmt = kwargs.get('fmt', 'json')
schema_entry = ConnectedServices._schema[service_name]
params = []
for parameter in schema_entry['parameters']:
value = kwargs.get(parameter['name'], None)
if value is not None:
params.append((parameter['name'], value))
service_stage = rma.service_stage(service_name, params)
url = rma.build_query_url([service_stage], fmt)
return url
def build_url(self, service_name, kwargs):
'''Create a single stage RMA url from a service name and parameters.
'''
rma = RmaApi()
fmt = kwargs.get('fmt', 'json')
schema_entry = ConnectedServices._schema[service_name]
params = []
for parameter in schema_entry['parameters']:
value = kwargs.get(parameter['name'], None)
if value != None:
params.append((parameter['name'], value))
service_stage = rma.service_stage(service_name,
params)
url = rma.build_query_url([service_stage], fmt)
return url
def generateQueryRows(model, criteria, options='[only$eq''genes.entrez_id,data_sets.id'']',
include='structure,section_data_set(genes)', startRow=0, blockSize=2000, verbose=True):
"""
GENERATOR: obtain object for iteratively obtaining rows from an AllenSDK Rma query.
ARGUMENTS:
model: the type of query (str)
criteria: criteria for the query (str). Where a function to automatically obtain this string does not exist,
please write one.
options: options string for query
include: include string for query
startRow: at which row of the query result would you like to start retriving data? (int)
blockSize: how many rows would you like to retrive with each iteration? (int)
verbose: additional print out, as per usual (bool)
DEPENDENCIES: Packages/modules/etc: RmaApi (allensdk.api.queries.rma_api)
(1) RmaApi().model_query() ;
1) allensdk front end for data access (class method)
YEILDS: rows of data ([{}, {}...]; json.dump() compatable)
"""
# [only$eq''genes.entrez_id,data_sets.id'']
if verbose:
print('Obtaining generator object for {} query'.format(model))
print('Criteria: {}'.format(criteria))
print('Options: {}'.format(options))
print('Include: {}'.format(include))
done = False
api = RmaApi()
while not done:
if verbose:
print('Querying rows {} - {}'.format(startRow, startRow + blockSize))
queryResult = api.model_query(model=model, criteria=criteria, options=options,
include=include, start_row=startRow, num_rows=blockSize)
if type(queryResult) == str:
raise ValueError('Query returned an error message. RMA query likely contains a syntactic error')
retrieved = len(queryResult)
if verbose:
print('{} rows were found'.format(retrieved))
startRow += retrieved
print('new start row: {}'.format(startRow))
done = retrieved == 0
yield queryResult
class AllenSdkHelper:
def __init__(self):
self.rma = RmaApi()
# TODO: only load this, if the file does not exist!
self.PlaneOfSections = self.rma.json_msg_query(
url=
"http://api.brain-map.org/api/v2/data/query.json?criteria=model::PlaneOfSection,rma::options[num_rows$eqall]"
)
# path=Utils.makedir(f'cache\\models') + '\\PlaneOfSection.json',
def getPlaneOfSections(self):
return self.PlaneOfSections
def rma5():
ju.read_url_get = \
MagicMock(name='read_url_get',
side_effect = [{'msg': _msg},
{'msg': _msg},
{'msg': _msg},
{'msg': _msg},
{'msg': _msg}])
ju.read = \
MagicMock(name='read',
return_value=[{'whatever': True},
{'whatever': True},
{'whatever': True},
{'whatever': True},
{'whatever': True}])
pj.read_json = \
MagicMock(name='read_json',
return_value=pd.DataFrame([{'whatever': True},
{'whatever': True},
{'whatever': True},
{'whatever': True},
{'whatever': True}]))
pd.DataFrame.to_csv = \
MagicMock(name='to_csv')
pd.DataFrame.from_csv = \
MagicMock(name='from_csv',
return_value=_csv_msg)
os.makedirs = MagicMock(name='makedirs')
return { 'ju_read_url_get': ju.read_url_get,
#'ju_write': json.dumps,
'ju_read': ju.read,
'pj_read_json': pj.read_json,
'to_csv': pd.DataFrame.to_csv,
'from_csv': pd.DataFrame.from_csv,
'os_makedirs': os.makedirs,
'rma_api': RmaApi() }
from allensdk.api.queries.rma_api import RmaApi
rma = RmaApi()
data = rma.model_query('Atlas', criteria="[name$il'*Mouse*']")
def rma():
return RmaApi()
def get_hemispheres():
return RmaApi().model_query(model='Hemisphere')
def get_hemispheres_excpt():
return RmaApi().model_query(model='Hemisphere',
excpt=['symbol'])
def generate_layer_ontology(output):
all_structs = []
root = RmaApi().model_query("Structure",
criteria="[graph_id$eq1],[acronym$eqgrey]")[0]
all_structs.append(root)
layers = [{
'id': 900000000,
'acronym': 'Isocortex1',
'name': 'Isocortex layer 1',
'color_hex_triplet': '7fc97f'
}, {
'id': 900000001,
'acronym': 'Isocortex2/3',
'name': 'Isocortex layer 2/3',
'color_hex_triplet': 'beaed4'
}, {
'id': 900000002,
'acronym': 'Isocortex4',
'name': 'Isocortex layer 4',
'color_hex_triplet': 'fdc086'
}, {
'id': 900000003,
'acronym': 'Isocortex5',
'name': 'Isocortex layer 5',
'color_hex_triplet': 'ffff99'
}, {
'id': 900000004,
'acronym': 'Isocortex6a',
'name': 'Isocortex layer 6a',
'color_hex_triplet': '386cb0'
}, {
'id': 900000005,
'acronym': 'Isocortex6b',
'name': 'Isocortex layer 6b',
'color_hex_triplet': 'f0027f'
}]
all_structs += layers
for layer in layers:
layer['structure_id_path'] = '/%d/%d/' % (root['id'], layer['id'])
layer['parent_structure_id'] = root['id']
structs = RmaApi().model_query("Structure",
criteria="structure_sets[name$eq'%s']" %
layer['name'])
for struct in structs:
struct['structure_id_path'] = '/%d/%d/%d/' % (
root['id'], layer['id'], struct['id'])
struct['color_hex_triplet'] = layer['color_hex_triplet']
struct['parent_structure_id'] = layer['id']
all_structs += structs
# Generate structure similar to the one returned by the http://api.brain-map.org/api/v2/data/Structure/query.json
content = {
"msg": all_structs,
"num_rows": len(all_structs),
"start_row": 0,
"success": True,
"total_rows": len(all_structs)
}
ju.write(output, content)
#===============================================================================
# example 1
#===============================================================================
from allensdk.api.queries.rma_api import RmaApi
rma = RmaApi()
data = rma.model_query('Atlas', criteria="[name$il'*Mouse*']")
#===============================================================================
# example 2
#===============================================================================
associations = ''.join(
['[id$eq1]', 'structure_graph(ontology),', 'graphic_group_labels'])
atlas_data = rma.model_query(
'Atlas',
include=associations,
criteria=associations,
only=[
'atlases.id', 'atlases.name', 'atlases.image_type', 'ontologies.id',
'ontologies.name', 'structure_graphs.id', 'structure_graphs.name',
'graphic_group_labels.id', 'graphic_group_labels.name'
])
#===============================================================================
# example 3
#===============================================================================
#===============================================================================
# example 1
#===============================================================================
from allensdk.api.queries.rma_api import RmaApi
rma = RmaApi()
data = rma.model_query('Atlas',
criteria="[name$il'*Mouse*']")
#===============================================================================
# example 2
#===============================================================================
associations = ''.join(['[id$eq1]',
'structure_graph(ontology),',
'graphic_group_labels'])
atlas_data = rma.model_query('Atlas',
include=associations,
criteria=associations,
only=['atlases.id',
'atlases.name',
'atlases.image_type',
'ontologies.id',
'ontologies.name',
'structure_graphs.id',
'structure_graphs.name',
'graphic_group_labels.id',
'graphic_group_labels.name'])
def getAsync(self, from_cache, aggregations):
# load data once with from_cache = False, then change it to True to read it from disk instead of fetching it from the api
if not from_cache:
# we use the RmaApi to query specific information, such as the section data sets of a specific gene
# for docs, see: https://alleninstitute.github.io/AllenSDK/allensdk.api.queries.rma_api.html
rma = RmaApi()
# there might be a way to retrieve data in higher resolution, as stated here (default is 25, 10 is also available - but resolution is ignored for download_gene_expression_grid_data)
# https://alleninstitute.github.io/AllenSDK/_modules/allensdk/api/queries/grid_data_api.html
# See `Downloading 3-D Projection Grid Data <http://help.brain-map.org/display/api/Downloading+3-D+Expression+Grid+Data#name="Downloading3-DExpressionGridData-DOWNLOADING3DPROJECTIONGRIDDATA">`_
gdApi = GridDataApi()
# http://api.brain-map.org/examples/rma_builder/index.html
# http://api.brain-map.org/examples/rma_builder/rma_builder.html
# https://allensdk.readthedocs.io/en/latest/data_api_client.html
sectionDataSets = pd.DataFrame(
rma.model_query(
model='SectionDataSet',
#! criteria="plane_of_section[name$eqcoronal]", note that saggital only spans the left hemisphere, so this is tough to compare with human data.
filters={'failed': 'false'},
include=
f"genes[acronym$il{self.geneAcronym}],products[id$eq1]", # $il = case-insensitive like | yes, weird notation... id = 1 = mouse brain atlas (not developing!)
num_rows='all'))
# model's documentation: http://api.brain-map.org/doc/SectionDataSet.html
# https://community.brain-map.org/t/attempting-to-download-substructures-for-coronal-p56-mouse-atlas/174/2
experiments = {}
# http://help.brain-map.org/display/mousebrain/Documentation
annotations = np.fromfile(Utils.getRelativeFilepath(
"annotations\\P56_Mouse_gridAnnotation\\gridAnnotation.raw"),
dtype="uint32")
# https://community.brain-map.org/t/how-to-acquire-the-structure-label-for-the-expression-grid-data/150/4
# for Mouse P56, structure_graph_id = 1 according to http://help.brain-map.org/display/api/Atlas+Drawings+and+Ontologies
structure_map = StructureMap.StructureMap(
reference_space_key='annotation/ccf_2017',
resolution=25).get(structure_graph_id=1) # , annotation, meta
# from http://alleninstitute.github.io/AllenSDK/_static/examples/nb/reference_space.html#Downloading-an-annotation-volume
for index, row in sectionDataSets.iterrows(
): # https://stackoverflow.com/questions/16476924/how-to-iterate-over-rows-in-a-dataframe-in-pandas
exp_id = row['id']
exp_path = f"cache\\mouse_ish-expr\\{exp_id}\\"
try:
# https://community.brain-map.org/t/whole-mouse-brain-gene-expression-data/447/4
# explanation of what "energy" means here:
# expression density = sum of expressing pixels / sum of all pixels in division
# expression intensity = sum of expressing pixel intensity / sum of expressing pixels
# expression energy = expression intensity * expression density
gdApi.download_gene_expression_grid_data(
exp_id, GridDataApi.ENERGY, exp_path)
expression_levels = np.fromfile(exp_path + "energy.raw",
dtype=np.float32)
# According to the doc @ http://help.brain-map.org/display/api/Downloading+3-D+Expression+Grid+Data
# we have "A raw uncompressed float (32-bit) little-endian volume representing average expression energy per voxel.
# A value of "-1" represents no data. This file is returned by default if the volumes parameter is null."
data = pd.DataFrame({
Constants.EXPR_LVL: expression_levels,
"structure_id": annotations
})
# some expression_levels are assigned to a structure of id 0. same is true for Jure's approach.
# according to the Allen institue, this is just due to background-noise:
# https://community.brain-map.org/t/how-to-acquire-the-structure-label-for-the-expression-grid-data/150/4
# values of -1 mean "no value obtained", hence we filter them out:
data = data[(data[Constants.EXPR_LVL] != -1)
& (data.structure_id != 0)]
data[Constants.Z_SCORE] = Utils.z_score(
data[Constants.EXPR_LVL])
# https://stackoverflow.com/questions/31528819/using-merge-on-a-column-and-index-in-pandas
# https://stackoverflow.com/questions/45147100/pandas-drop-columns-with-all-nans
name = f'mouse_{exp_id}_{Constants.PlaneOfSections[row["plane_of_section_id"]]}'
data = Utils.merge_with_structure(
data, structure_map, MouseISHData.VALUE_COLUMNS,
aggregations)
Utils.save(data, self.cache_path, name + '.pkl')
experiments['mouse - ' + Constants.PlaneOfSections[
row["plane_of_section_id"]]] = data
except Exception as e:
print(
f"Error retrieving mouse-ish experiment {exp_id}: {str(e)}"
)
raise e
return experiments
else:
if not glob.glob(self.cache_path):
Utils.log.warning(
f"No cached dataframe found. Check whether you have access to file '{self.cache_path}' and whether it exists. Obtaining data without caching now..."
)
return self.get(False, aggregations)
return {
'mouse - ' + Utils.getFilename(file).split('_')[2]:
Utils.load(file)
for file in glob.glob(f'{self.cache_path}/*.pkl')
}
class ISHFetcher:
''' A downloader object for Section Data Sets
Methods
-------
find_id_ish:
Returns the ids of Section Data Sets (a single gene experiment) sorted by qc time
download_grid_all:
Dowloads all the expression energy 3d density file (200um grid) that satisfy the query
download_grid_recent:
Dowloads the most recently qc-ed expression energy 3d density file (200um grid) that satisfy the query
Attributes
----------
rma:
Rma Api instance
gda
GridData Api instance
res
results of the find_id_ish query
'''
def __init__(self) -> None:
self.rma = RmaApi()
self.gda = GridDataApi()
self.res = None # type: List
def find_id_ish(self,
gene: str,
sag_or_cor: str = "sagittal",
adu_or_dev: str = "adult",
time_point: str = "P56") -> List:
"""Returns the ids of Section Data Sets (a single gene experiment)
Args
----
gene: str
the gene to search for
sag_or_cor: str (accepts * wild cards)
`coronal` or `sagittal` or `*`
adu_or_dev: str (accepts * wild cards)
`adult`, `development`, `both`
time_point: str (it will be autmatically wildcarded)
e.g. "P56", "E", "E13", "P"
Returns
-------
list of ids:
sorted by most_recent to mose ancient
"""
if adu_or_dev == "adult" and "E" in time_point:
raise ValueError("there is not adult with age %s" % time_point)
if adu_or_dev == "adult":
adu_or_dev = "Mouse"
elif adu_or_dev == "development":
adu_or_dev = "DevMouse"
elif adu_or_dev == "both":
adu_or_dev = "*Mouse"
else:
raise ValueError("adu_or_dev='%s' is not valid" % adu_or_dev)
criteria = [
"[failed$eq'false']",
"reference_space[name$li'*%s*']" % time_point,
"products[abbreviation$li'%s']" % adu_or_dev,
"plane_of_section[name$li'%s']" % sag_or_cor,
"genes[acronym$eq'%s']" % gene
]
# include='reference_space',
self.res = self.rma.model_query("SectionDataSet",
criteria=','.join(criteria),
only=["id", "qc_date"],
num_rows='all')
if isinstance(self.res, str):
raise ValueError("Bad query! Server returned :\n%s" % self.res)
if self.res == []:
return []
qc_date = []
for i in self.res:
if i["qc_date"] is None:
qc_date.append('')
else:
qc_date.append(i["qc_date"])
ix = np.argsort(qc_date)
ix = ix[::-1]
results = []
for i in ix:
results.append(int(self.res[i]["id"]))
return results
def download_grid_all(self,
gene: str,
folder: str = '../data',
sag_or_cor: str = "sagittal",
adu_or_dev: str = "adult",
time_point: str = "P56") -> None:
"""Dowloads all the files
Args
----
gene: str
the gene to search for
sag_or_cor: str (accepts * wild cards)
`coronal` or `sagittal` or `*`
adu_or_dev: str (accepts * wild cards)
`adult`, `development`, `both`
time_point: str (it will be autmatically wildcarded)
e.g. "P56", "E", "E13", "P"
"""
ids = self.find_id_ish(gene,
sag_or_cor=sag_or_cor,
adu_or_dev=adu_or_dev,
time_point=time_point)
for idd in ids:
self.gda.download_expression_grid_data(
idd,
path=os.path.join(
folder,
"%s_%s_%s_%s.zip" % (gene, sag_or_cor, time_point, idd)))
def download_grid_recent(self,
gene: str,
folder: str = '../data',
sag_or_cor: str = "sagittal",
adu_or_dev: str = "adult",
time_point: str = "P56") -> Union[str, bool]:
"""Dowloads the most recently qc-ed file among the ones available
Args
----
gene: str
the gene to search for
sag_or_cor: str (accepts * wild cards)
`coronal` or `sagittal` or `*`
adu_or_dev: str (accepts * wild cards)
`adult`, `development`, `both`
time_point: str (it will be autmatically wildcarded)
e.g. "P56", "E", "E13", "P"
Returns
-------
output_path: output_path or bool
if the download was successfull returns the path to the file otherwise False
"""
ids = self.find_id_ish(gene,
sag_or_cor=sag_or_cor,
adu_or_dev=adu_or_dev,
time_point=time_point)
try:
idd = ids[0]
output_path = os.path.join(
folder,
"%s_%s_%s_%s.zip" % (gene, sag_or_cor, time_point, idd))
self.gda.download_expression_grid_data(idd, path=output_path)
return output_path
except IndexError:
logging.warn("Experiment %s was never performed" % gene)
return False
def __init__(self) -> None:
self.rma = RmaApi()
self.gda = GridDataApi()
self.res = None # type: List