def test_run(self):
tempdir = tempfile.TemporaryDirectory(dir=f"{PROJECT_ROOT}/server")
tempdirname = tempdir.name
c = AppConfig()
# test that eb works
c.update_server_config(
multi_dataset__dataroot=f"{PROJECT_ROOT}/server/test/test_datasets",
app__flask_secret_key="open sesame")
c.complete_config()
c.write_config(f"{tempdirname}/config.yaml")
subprocess.check_call(f"git ls-files . | cpio -pdm {tempdirname}",
cwd=f"{PROJECT_ROOT}/server/eb",
shell=True)
subprocess.check_call(["make", "build"], cwd=tempdirname)
with run_eb_app(tempdirname) as server:
session = requests.Session()
r = session.get(f"{server}/d/pbmc3k.cxg/api/v0.2/config")
data_config = r.json()
assert data_config["config"]["displayNames"]["dataset"] == "pbmc3k"
def data_with_tmp_tiledb_annotations(ext: MatrixDataType):
tmp_dir = tempfile.mkdtemp()
fname = {
MatrixDataType.H5AD: f"{PROJECT_ROOT}/example-dataset/pbmc3k.h5ad",
MatrixDataType.CXG: "test/fixtures/pbmc3k.cxg",
}[ext]
data_locator = DataLocator(fname)
config = AppConfig()
config.update_server_config(
multi_dataset__dataroot=data_locator.path,
authentication__type="test",
)
config.update_default_dataset_config(
embeddings__names=["umap"],
presentation__max_categories=100,
diffexp__lfc_cutoff=0.01,
user_annotations__type="hosted_tiledb_array",
user_annotations__hosted_tiledb_array__db_uri=
"postgresql://*****:*****@localhost:5432",
user_annotations__hosted_tiledb_array__hosted_file_directory=tmp_dir)
config.complete_config()
data = MatrixDataLoader(data_locator.abspath()).open(config)
annotations = AnnotationsHostedTileDB(
tmp_dir,
DbUtils("postgresql://*****:*****@localhost:5432"),
)
return data, tmp_dir, annotations
def test_auth_test(self):
c = AppConfig()
c.update_server_config(authentication__type="test")
c.update_server_config(
multi_dataset__dataroot=dict(
a1=dict(dataroot=self.dataset_dataroot, base_url="auth"),
a2=dict(dataroot=self.dataset_dataroot, base_url="no-auth"),
)
)
# specialize the configs
c.add_dataroot_config("a1", app__authentication_enable=True, user_annotations__enable=True)
c.add_dataroot_config("a2", app__authentication_enable=False, user_annotations__enable=False)
c.complete_config()
with test_server(app_config=c) as server:
session = requests.Session()
# auth datasets
config = session.get(f"{server}/auth/pbmc3k.cxg/api/v0.2/config").json()
userinfo = session.get(f"{server}/auth/pbmc3k.cxg/api/v0.2/userinfo").json()
self.assertFalse(userinfo["userinfo"]["is_authenticated"])
self.assertIsNone(userinfo["userinfo"]["username"])
self.assertTrue(config["config"]["authentication"]["requires_client_login"])
self.assertTrue(config["config"]["parameters"]["annotations"])
login_uri = config["config"]["authentication"]["login"]
logout_uri = config["config"]["authentication"]["logout"]
self.assertEqual(login_uri, "/login?dataset=auth/pbmc3k.cxg")
self.assertEqual(logout_uri, "/logout?dataset=auth/pbmc3k.cxg")
r = session.get(f"{server}/{login_uri}")
# check that the login redirect worked
self.assertEqual(r.history[0].status_code, 302)
self.assertEqual(r.url, f"{server}/auth/pbmc3k.cxg/")
config = session.get(f"{server}/auth/pbmc3k.cxg/api/v0.2/config").json()
userinfo = session.get(f"{server}/auth/pbmc3k.cxg/api/v0.2/userinfo").json()
self.assertTrue(userinfo["userinfo"]["is_authenticated"])
self.assertEqual(userinfo["userinfo"]["username"], "test_account")
self.assertTrue(config["config"]["parameters"]["annotations"])
r = session.get(f"{server}/{logout_uri}")
# check that the logout redirect worked
self.assertEqual(r.history[0].status_code, 302)
self.assertEqual(r.url, f"{server}/auth/pbmc3k.cxg/")
config = session.get(f"{server}/auth/pbmc3k.cxg/api/v0.2/config").json()
userinfo = session.get(f"{server}/auth/pbmc3k.cxg/api/v0.2/userinfo").json()
self.assertFalse(userinfo["userinfo"]["is_authenticated"])
self.assertIsNone(userinfo["userinfo"]["username"])
self.assertTrue(config["config"]["parameters"]["annotations"])
# no-auth datasets
config = session.get(f"{server}/no-auth/pbmc3k.cxg/api/v0.2/config").json()
userinfo = session.get(f"{server}/no-auth/pbmc3k.cxg/api/v0.2/userinfo").json()
self.assertIsNone(userinfo)
self.assertFalse(config["config"]["parameters"]["annotations"])
def test_update(self):
c = AppConfig()
c.update_server_config(app__verbose=True,
multi_dataset__dataroot="datadir")
v = c.server_config.changes_from_default()
self.assertCountEqual(v,
[("app__verbose", True, False),
("multi_dataset__dataroot", "datadir", None)])
c = AppConfig()
c.update_default_dataset_config(app__scripts=(),
app__inline_scripts=())
v = c.server_config.changes_from_default()
self.assertCountEqual(v, [])
c = AppConfig()
c.update_default_dataset_config(app__scripts=[],
app__inline_scripts=[])
v = c.default_dataset_config.changes_from_default()
self.assertCountEqual(v, [])
c = AppConfig()
c.update_default_dataset_config(app__scripts=("a", "b"),
app__inline_scripts=["c", "d"])
v = c.default_dataset_config.changes_from_default()
self.assertCountEqual(v, [("app__scripts", ["a", "b"], []),
("app__inline_scripts", ["c", "d"], [])])
def data_with_tmp_annotations(ext: MatrixDataType, annotations_fixture=False):
tmp_dir = tempfile.mkdtemp()
annotations_file = path.join(tmp_dir, "test_annotations.csv")
if annotations_fixture:
shutil.copyfile(
f"{PROJECT_ROOT}/server/test/fixtures/pbmc3k-annotations.csv",
annotations_file)
fname = {
MatrixDataType.H5AD: f"{PROJECT_ROOT}/example-dataset/pbmc3k.h5ad",
MatrixDataType.CXG: "test/fixtures/pbmc3k.cxg",
}[ext]
data_locator = DataLocator(fname)
config = AppConfig()
config.update_server_config(single_dataset__obs_names=None,
single_dataset__var_names=None,
single_dataset__datapath=data_locator.path)
config.update_default_dataset_config(
embeddings__names=["umap"],
presentation__max_categories=100,
diffexp__lfc_cutoff=0.01,
)
config.complete_config()
data = MatrixDataLoader(data_locator.abspath()).open(config)
annotations = AnnotationsLocalFile(None, annotations_file)
return data, tmp_dir, annotations
def setUp(self):
self.data_file = DataLocator(
f"{PROJECT_ROOT}/example-dataset/pbmc3k.h5ad")
config = AppConfig()
config.update_server_config(
single_dataset__datapath=self.data_file.path)
config.complete_config()
self.data = AnndataAdaptor(self.data_file, config)
def get_basic_config(self):
config = AppConfig()
config.update_server_config(
single_dataset__obs_names=None, single_dataset__var_names=None,
)
config.update_default_dataset_config(
embeddings__names=["umap"], presentation__max_categories=100, diffexp__lfc_cutoff=0.01,
)
return config
def test_auth_none(self):
c = AppConfig()
c.update_server_config(
authentication__type=None, multi_dataset__dataroot=self.dataset_dataroot
)
c.update_default_dataset_config(user_annotations__enable=False)
c.complete_config()
with test_server(app_config=c) as server:
session = requests.Session()
config = session.get(f"{server}/d/pbmc3k.cxg/api/v0.2/config").json()
userinfo = session.get(f"{server}/d/pbmc3k.cxg/api/v0.2/userinfo").json()
self.assertNotIn("authentication", config["config"])
self.assertIsNone(userinfo)
def test_auth_session(self):
c = AppConfig()
c.update_server_config(
authentication__type="session", multi_dataset__dataroot=self.dataset_dataroot
)
c.update_default_dataset_config(user_annotations__enable=True)
c.complete_config()
with test_server(app_config=c) as server:
session = requests.Session()
config = session.get(f"{server}/d/pbmc3k.cxg/api/v0.2/config").json()
userinfo = session.get(f"{server}/d/pbmc3k.cxg/api/v0.2/userinfo").json()
self.assertFalse(config["config"]["authentication"]["requires_client_login"])
self.assertTrue(userinfo["userinfo"]["is_authenticated"])
self.assertEqual(userinfo["userinfo"]["username"], "anonymous")
def test_auth_oauth_session(self):
# test with session cookies
app_config = AppConfig()
app_config.update_server_config(
authentication__type="oauth",
authentication__params_oauth__api_base_url=
f"http://localhost:{PORT}",
authentication__params_oauth__client_id="mock_client_id",
authentication__params_oauth__client_secret="mock_client_secret",
authentication__params_oauth__session_cookie=True,
)
app_config.update_server_config(
multi_dataset__dataroot=self.dataset_dataroot)
app_config.complete_config()
self.auth_flow(app_config)
def test_auth_test_single(self):
c = AppConfig()
c.update_server_config(
authentication__type="test",
single_dataset__datapath=f"{self.dataset_dataroot}/pbmc3k.cxg")
c.complete_config()
with test_server(app_config=c) as server:
session = requests.Session()
config = session.get(f"{server}/api/v0.2/config").json()
userinfo = session.get(f"{server}/api/v0.2/userinfo").json()
self.assertFalse(userinfo["userinfo"]["is_authenticated"])
self.assertIsNone(userinfo["userinfo"]["username"])
self.assertTrue(config["config"]["authentication"]["requires_client_login"])
self.assertTrue(config["config"]["parameters"]["annotations"])
login_uri = config["config"]["authentication"]["login"]
logout_uri = config["config"]["authentication"]["logout"]
self.assertEqual(login_uri, "/login")
self.assertEqual(logout_uri, "/logout")
r = session.get(f"{server}/{login_uri}")
# check that the login redirect worked
self.assertEqual(r.history[0].status_code, 302)
self.assertEqual(r.url, f"{server}/")
config = session.get(f"{server}/api/v0.2/config").json()
userinfo = session.get(f"{server}/api/v0.2/userinfo").json()
self.assertTrue(userinfo["userinfo"]["is_authenticated"])
self.assertEqual(userinfo["userinfo"]["username"], "test_account")
self.assertTrue(config["config"]["parameters"]["annotations"])
r = session.get(f"{server}/{logout_uri}")
# check that the logout redirect worked
self.assertEqual(r.history[0].status_code, 302)
self.assertEqual(r.url, f"{server}/")
config = session.get(f"{server}/api/v0.2/config").json()
userinfo = session.get(f"{server}/api/v0.2/userinfo").json()
self.assertFalse(userinfo["userinfo"]["is_authenticated"])
self.assertIsNone(userinfo["userinfo"]["username"])
self.assertTrue(config["config"]["parameters"]["annotations"])
def test_auth_oauth_cookie(self):
# test with specified cookie
app_config = AppConfig()
app_config.update_server_config(
authentication__type="oauth",
authentication__params_oauth__api_base_url=
f"http://localhost:{PORT}",
authentication__params_oauth__client_id="mock_client_id",
authentication__params_oauth__client_secret="mock_client_secret",
authentication__params_oauth__session_cookie=False,
authentication__params_oauth__cookie=dict(key="test_cxguser",
httponly=True,
max_age=60),
)
app_config.update_server_config(
multi_dataset__dataroot=self.dataset_dataroot)
app_config.complete_config()
self.auth_flow(app_config, "test_cxguser")
def app_config(data_locator,
backed=False,
extra_server_config={},
extra_dataset_config={}):
config = AppConfig()
config.update_server_config(
single_dataset__obs_names=None,
single_dataset__var_names=None,
adaptor__anndata_adaptor__backed=backed,
single_dataset__datapath=data_locator,
limits__diffexp_cellcount_max=None,
limits__column_request_max=None,
)
config.update_default_dataset_config(
embeddings__names=["umap", "tsne", "pca"],
presentation__max_categories=100,
diffexp__lfc_cutoff=0.01)
config.update_server_config(**extra_server_config)
config.update_default_dataset_config(**extra_dataset_config)
config.complete_config()
return config
with config_location.local_handle() as lh:
logging.info(f"Configuration from {config_file}")
app_config.update_from_config_file(lh)
has_config = True
else:
logging.critical(f"Configuration file not found {config_file}")
sys.exit(1)
if not has_config:
logging.critical("No config file found")
sys.exit(1)
dataroot = os.getenv("CXG_DATAROOT")
if dataroot:
logging.info("Configuration from CXG_DATAROOT")
app_config.update_server_config(multi_dataset__dataroot=dataroot)
secret_name = os.getenv("CXG_AWS_SECRET_NAME")
if secret_name:
# need to find the secret manager region.
# 1. from CXG_AWS_SECRET_REGION_NAME
# 2. discover from dataroot location (if on s3)
# 3. discover from config file location (if on s3)
secret_region_name = os.getenv("CXG_AWS_SECRET_REGION_NAME")
if secret_region_name is None:
secret_region_name = discover_s3_region_name(
app_config.multi_dataset__dataroot)
if not secret_region_name:
secret_region_name = discover_s3_region_name(config_file)
if not secret_region_name:
logging.error("Could not determine the AWS Secret Manager region")
def test_multi_dataset(self):
c = AppConfig()
# test for illegal url_dataroots
for illegal in ("../b", "!$*", "\\n", "", "(bad)"):
c.update_server_config(
multi_dataset__dataroot={"tag": {"base_url": illegal, "dataroot": "{PROJECT_ROOT}/example-dataset"}}
)
with self.assertRaises(ConfigurationError):
c.complete_config()
# test for legal url_dataroots
for legal in ("d", "this.is-okay_", "a/b"):
c.update_server_config(
multi_dataset__dataroot={"tag": {"base_url": legal, "dataroot": "{PROJECT_ROOT}/example-dataset"}}
)
c.complete_config()
# test that multi dataroots work end to end
c.update_server_config(
multi_dataset__dataroot=dict(
s1=dict(dataroot=f"{PROJECT_ROOT}/example-dataset", base_url="set1/1/2"),
s2=dict(dataroot=f"{PROJECT_ROOT}/server/test/test_datasets", base_url="set2"),
s3=dict(dataroot=f"{PROJECT_ROOT}/server/test/test_datasets", base_url="set3"),
)
)
# Change this default to test if the dataroot overrides below work.
c.update_default_dataset_config(app__about_legal_tos="tos_default.html")
# specialize the configs for set1
c.add_dataroot_config(
"s1", user_annotations__enable=False, diffexp__enable=True, app__about_legal_tos="tos_set1.html"
)
# specialize the configs for set2
c.add_dataroot_config(
"s2", user_annotations__enable=True, diffexp__enable=False, app__about_legal_tos="tos_set2.html"
)
# no specializations for set3 (they get the default dataset config)
c.complete_config()
with test_server(app_config=c) as server:
session = requests.Session()
r = session.get(f"{server}/set1/1/2/pbmc3k.h5ad/api/v0.2/config")
data_config = r.json()
assert data_config["config"]["displayNames"]["dataset"] == "pbmc3k"
assert data_config["config"]["parameters"]["annotations"] is False
assert data_config["config"]["parameters"]["disable-diffexp"] is False
assert data_config["config"]["parameters"]["about_legal_tos"] == "tos_set1.html"
r = session.get(f"{server}/set2/pbmc3k.cxg/api/v0.2/config")
data_config = r.json()
assert data_config["config"]["displayNames"]["dataset"] == "pbmc3k"
assert data_config["config"]["parameters"]["annotations"] is True
assert data_config["config"]["parameters"]["about_legal_tos"] == "tos_set2.html"
r = session.get(f"{server}/set3/pbmc3k.cxg/api/v0.2/config")
data_config = r.json()
assert data_config["config"]["displayNames"]["dataset"] == "pbmc3k"
assert data_config["config"]["parameters"]["annotations"] is True
assert data_config["config"]["parameters"]["disable-diffexp"] is False
assert data_config["config"]["parameters"]["about_legal_tos"] == "tos_default.html"
r = session.get(f"{server}/health")
assert r.json()["status"] == "pass"
def main():
parser = argparse.ArgumentParser("A command to test diffexp")
parser.add_argument("dataset", help="name of a dataset to load")
parser.add_argument("-na",
"--numA",
type=int,
help="number of rows in group A")
parser.add_argument("-nb",
"--numB",
type=int,
help="number of rows in group B")
parser.add_argument("-va",
"--varA",
help="obs variable:value to use for group A")
parser.add_argument("-vb",
"--varB",
help="obs variable:value to use for group B")
parser.add_argument("-t",
"--trials",
default=1,
type=int,
help="number of trials")
parser.add_argument("-a",
"--alg",
choices=("default", "generic", "cxg"),
default="default",
help="algorithm to use")
parser.add_argument("-s",
"--show",
default=False,
action="store_true",
help="show the results")
parser.add_argument("-n",
"--new-selection",
default=False,
action="store_true",
help="change the selection between each trial")
parser.add_argument("--seed",
default=1,
type=int,
help="set the random seed")
args = parser.parse_args()
app_config = AppConfig()
app_config.update_server_config(single_dataset__datapath=args.dataset)
app_config.update_server_config(app__verbose=True)
app_config.complete_config()
loader = MatrixDataLoader(args.dataset)
adaptor = loader.open(app_config)
if args.show:
if isinstance(adaptor, CxgAdaptor):
adaptor.open_array("X").schema.dump()
random.seed(args.seed)
np.random.seed(args.seed)
rows = adaptor.get_shape()[0]
if args.numA:
filterA = random.sample(range(rows), args.numA)
elif args.varA:
vname, vval = args.varA.split(":")
filterA = get_filter_from_obs(adaptor, vname, vval)
else:
print("must supply numA or varA")
sys.exit(1)
if args.numB:
filterB = random.sample(range(rows), args.numB)
elif args.varB:
vname, vval = args.varB.split(":")
filterB = get_filter_from_obs(adaptor, vname, vval)
else:
print("must supply numB or varB")
sys.exit(1)
for i in range(args.trials):
if args.new_selection:
if args.numA:
filterA = random.sample(range(rows), args.numA)
if args.numB:
filterB = random.sample(range(rows), args.numB)
maskA = np.zeros(rows, dtype=bool)
maskA[filterA] = True
maskB = np.zeros(rows, dtype=bool)
maskB[filterB] = True
t1 = time.time()
if args.alg == "default":
results = adaptor.compute_diffexp_ttest(maskA, maskB)
elif args.alg == "generic":
results = diffexp_generic.diffexp_ttest(adaptor, maskA, maskB)
elif args.alg == "cxg":
if not isinstance(adaptor, CxgAdaptor):
print("cxg only works with CxgAdaptor")
sys.exit(1)
results = diffexp_cxg.diffexp_ttest(adaptor, maskA, maskB)
t2 = time.time()
print("TIME=", t2 - t1)
if args.show:
for res in results:
print(res)
def launch(
datapath,
dataroot,
verbose,
debug,
open_browser,
port,
host,
embedding,
obs_names,
var_names,
max_category_items,
disable_custom_colors,
diffexp_lfc_cutoff,
title,
scripts,
about,
disable_annotations,
annotations_file,
annotations_dir,
backed,
disable_diffexp,
experimental_annotations_ontology,
experimental_annotations_ontology_obo,
experimental_enable_reembedding,
config_file,
dump_default_config,
):
"""Launch the cellxgene data viewer.
This web app lets you explore single-cell expression data.
Data must be in a format that cellxgene expects.
Read the "getting started" guide to learn more:
https://chanzuckerberg.github.io/cellxgene/getting-started.html
Examples:
> cellxgene launch example-dataset/pbmc3k.h5ad --title pbmc3k
> cellxgene launch <your data file> --title <your title>
> cellxgene launch <url>"""
# TODO Examples to provide when "--dataroot" is unhidden
# > cellxgene launch --dataroot example-dataset/
#
# > cellxgene launch --dataroot <url>
if dump_default_config:
print(default_config)
sys.exit(0)
# Startup message
click.echo("[cellxgene] Starting the CLI...")
# app config
app_config = AppConfig()
server_config = app_config.server_config
try:
if config_file:
app_config.update_from_config_file(config_file)
# Determine which config options were give on the command line.
# Those will override the ones provided in the config file (if provided).
cli_config = AppConfig()
cli_config.update_server_config(
app__verbose=verbose,
app__debug=debug,
app__host=host,
app__port=port,
app__open_browser=open_browser,
single_dataset__datapath=datapath,
single_dataset__title=title,
single_dataset__about=about,
single_dataset__obs_names=obs_names,
single_dataset__var_names=var_names,
multi_dataset__dataroot=dataroot,
adaptor__anndata_adaptor__backed=backed,
)
cli_config.update_default_dataset_config(
app__scripts=scripts,
user_annotations__enable=not disable_annotations,
user_annotations__local_file_csv__file=annotations_file,
user_annotations__local_file_csv__directory=annotations_dir,
user_annotations__ontology__enable=experimental_annotations_ontology,
user_annotations__ontology__obo_location=experimental_annotations_ontology_obo,
presentation__max_categories=max_category_items,
presentation__custom_colors=not disable_custom_colors,
embeddings__names=embedding,
embeddings__enable_reembedding=experimental_enable_reembedding,
diffexp__enable=not disable_diffexp,
diffexp__lfc_cutoff=diffexp_lfc_cutoff,
)
diff = cli_config.server_config.changes_from_default()
changes = {key: val for key, val, _ in diff}
app_config.update_server_config(**changes)
diff = cli_config.default_dataset_config.changes_from_default()
changes = {key: val for key, val, _ in diff}
app_config.update_default_dataset_config(**changes)
# process the configuration
# any errors will be thrown as an exception.
# any info messages will be passed to the messagefn function.
def messagefn(message):
click.echo("[cellxgene] " + message)
# Use a default secret if one is not provided
if not server_config.app__flask_secret_key:
app_config.update_server_config(app__flask_secret_key="SparkleAndShine")
app_config.complete_config(messagefn)
except (ConfigurationError, DatasetAccessError) as e:
raise click.ClickException(e)
handle_scripts(scripts)
# create the server
server = CliLaunchServer(app_config)
if not server_config.app__verbose:
log = logging.getLogger("werkzeug")
log.setLevel(logging.ERROR)
cellxgene_url = f"http://{app_config.server_config.app__host}:{app_config.server_config.app__port}"
if server_config.app__open_browser:
click.echo(f"[cellxgene] Launching! Opening your browser to {cellxgene_url} now.")
webbrowser.open(cellxgene_url)
else:
click.echo(f"[cellxgene] Launching! Please go to {cellxgene_url} in your browser.")
click.echo("[cellxgene] Type CTRL-C at any time to exit.")
if not server_config.app__verbose:
f = open(devnull, "w")
sys.stdout = f
try:
server.app.run(
host=server_config.app__host,
debug=server_config.app__debug,
port=server_config.app__port,
threaded=not server_config.app__debug,
use_debugger=False,
use_reloader=False,
)
except OSError as e:
if e.errno == errno.EADDRINUSE:
raise click.ClickException("Port is in use, please specify an open port using the --port flag.") from e
raise
with config_location.local_handle() as lh:
logging.info(f"Configuration from {config_file}")
app_config.update_from_config_file(lh)
has_config = True
else:
logging.critical(f"Configuration file not found {config_file}")
sys.exit(1)
if not has_config:
logging.critical("No config file found")
sys.exit(1)
dataroot = os.getenv("CXG_DATAROOT")
if dataroot:
logging.info("Configuration from CXG_DATAROOT")
app_config.update_server_config(multi_dataset__dataroot=dataroot)
# update from secret manager
try:
handle_config_from_secret(app_config)
except SecretKeyRetrievalError:
sys.exit(1)
# features are unsupported in the current hosted server
app_config.update_default_dataset_config(
embeddings__enable_reembedding=False, )
app_config.update_server_config(
multi_dataset__allowed_matrix_types=["cxg"], )
app_config.complete_config(logging.info)
if not app_config.server_config.app__flask_secret_key: