def get_gene_experiments(self, gene):
"""
Given a gene_symbol it returns the list of ISH
experiments for this gene
:param gene_symbol: str
"""
url = self.gene_experiments_url.replace("-GENE_SYMBOL-", gene)
data = request(url).json()["msg"]
if not len(data):
print(f"No experiment found for gene {gene}")
return None
else:
return [d["id"] for d in data]
def download_and_cache(url, cachedir):
"""
Given a url to download a gene's ISH experiment data,
this function download and unzips the data
:param url: str, utl to download data
:param cachedir: str, path to folder where data will be downloaded
"""
# Get data
req = request(url)
# Create cache dir
if not os.path.isdir(cachedir):
os.mkdir(cachedir)
# Unzip to cache dir
z = zipfile.ZipFile(io.BytesIO(req.content))
z.extractall(cachedir)
def get_streamlines_data(eids, force_download=False):
"""
Given a list of expeirmental IDs, it downloads the streamline data
from the https://neuroinformatics.nl cache and saves them as
json files.
:param eids: list of integers with experiments IDs
"""
data = []
for eid in track(eids, total=len(eids), description="downloading"):
url = "https://neuroinformatics.nl/HBP/allen-connectivity-viewer/json/streamlines_{}.json.gz".format(
eid
)
jsonpath = streamlines_folder / f"{eid}.json"
if not jsonpath.exists() or force_download:
response = request(url)
# Write the response content as a temporary compressed file
temp_path = streamlines_folder / "temp.gz"
with open(str(temp_path), "wb") as temp:
temp.write(response.content)
# Open in pandas and delete temp
url_data = pd.read_json(
str(temp_path), lines=True, compression="gzip"
)
temp_path.unlink()
# save json
url_data.to_json(str(jsonpath))
# append to lists and return
data.append(url_data)
else:
data.append(pd.read_json(str(jsonpath)))
return data
def get_all_genes(self):
"""
Download metadata about all the genes available in the Allen gene expression dataset
"""
res = request(self.all_genes_url)
return pd.DataFrame(res.json()["msg"])
