def _de_core(adata, model_fn, groupby, group1, group2, idx1, idx2, all_stats,
all_stats_fn, col_names, mode, batchid1, batchid2, delta,
batch_correction, fdr, silent, **kwargs):
"""Internal function for DE interface."""
if group1 is None and idx1 is None:
group1 = adata.obs[groupby].astype("category").cat.categories.tolist()
if len(group1) == 1:
raise ValueError(
"Only a single group in the data. Can't run DE on a single group."
)
if not isinstance(group1, IterableClass) or isinstance(group1, str):
group1 = [group1]
# make a temp obs key using indices
temp_key = None
if idx1 is not None:
obs_col, group1, group2 = _prepare_obs(idx1, idx2, adata)
temp_key = "_scvi_temp_de"
adata.obs[temp_key] = obs_col
groupby = temp_key
df_results = []
dc = DifferentialComputation(model_fn, adata)
for g1 in track(
group1,
description="DE...",
disable=silent,
):
cell_idx1 = (adata.obs[groupby] == g1).to_numpy().ravel()
if group2 is None:
cell_idx2 = ~cell_idx1
else:
cell_idx2 = (adata.obs[groupby] == group2).to_numpy().ravel()
all_info = dc.get_bayes_factors(
cell_idx1,
cell_idx2,
mode=mode,
delta=delta,
batchid1=batchid1,
batchid2=batchid2,
use_observed_batches=not batch_correction,
**kwargs,
)
if all_stats is True:
genes_properties_dict = all_stats_fn(adata, cell_idx1, cell_idx2)
all_info = {**all_info, **genes_properties_dict}
res = pd.DataFrame(all_info, index=col_names)
sort_key = "proba_de" if mode == "change" else "bayes_factor"
res = res.sort_values(by=sort_key, ascending=False)
if mode == "change":
res["is_de_fdr_{}".format(fdr)] = _fdr_de_prediction(
res["proba_de"], fdr=fdr)
if idx1 is None:
g2 = "Rest" if group2 is None else group2
res["comparison"] = "{} vs {}".format(g1, g2)
df_results.append(res)
if temp_key is not None:
del adata.obs[temp_key]
result = pd.concat(df_results, axis=0)
return result
def test_differential_computation(save_path):
n_latent = 5
adata = synthetic_iid()
model = SCVI(adata, n_latent=n_latent)
model.train(1)
model_fn = partial(model.get_normalized_expression, return_numpy=True)
dc = DifferentialComputation(model_fn, adata)
cell_idx1 = np.asarray(adata.obs.labels == "label_1")
cell_idx2 = ~cell_idx1
dc.get_bayes_factors(cell_idx1,
cell_idx2,
mode="vanilla",
use_permutation=True)
dc.get_bayes_factors(cell_idx1,
cell_idx2,
mode="change",
use_permutation=False)
dc.get_bayes_factors(cell_idx1,
cell_idx2,
mode="change",
cred_interval_lvls=[0.75])
delta = 0.5
def change_fn_test(x, y):
return x - y
def m1_domain_fn_test(samples):
return np.abs(samples) >= delta
dc.get_bayes_factors(
cell_idx1,
cell_idx2,
mode="change",
m1_domain_fn=m1_domain_fn_test,
change_fn=change_fn_test,
)
# should fail if just one batch
with pytest.raises(ValueError):
model.differential_expression(adata[:20], groupby="batch")
# test view
model.differential_expression(adata[adata.obs["labels"] == "label_1"],
groupby="batch")
# test that ints as group work
a = synthetic_iid()
a.obs["test"] = [0] * 200 + [1] * 200
model = SCVI(a)
model.differential_expression(groupby="test", group1=0)
# test that string but not as categorical work
a = synthetic_iid()
a.obs["test"] = ["0"] * 200 + ["1"] * 200
model = SCVI(a)
model.differential_expression(groupby="test", group1="0")
def test_differential_computation(save_path):
n_latent = 5
adata = synthetic_iid()
model = SCVI(adata, n_latent=n_latent)
model.train(1)
model_fn = partial(model.get_normalized_expression, return_numpy=True)
dc = DifferentialComputation(model_fn, adata)
cell_idx1 = np.asarray(adata.obs.labels == "label_1")
cell_idx2 = ~cell_idx1
dc.get_bayes_factors(cell_idx1, cell_idx2, mode="vanilla", use_permutation=True)
res = dc.get_bayes_factors(
cell_idx1, cell_idx2, mode="change", use_permutation=False
)
assert (res["delta"] == 0.5) and (res["pseudocounts"] == 0.0)
res = dc.get_bayes_factors(
cell_idx1, cell_idx2, mode="change", use_permutation=False, delta=None
)
dc.get_bayes_factors(
cell_idx1,
cell_idx2,
mode="change",
use_permutation=False,
delta=None,
pseudocounts=None,
)
dc.get_bayes_factors(cell_idx1, cell_idx2, mode="change", cred_interval_lvls=[0.75])
delta = 0.5
def change_fn_test(x, y):
return x - y
def m1_domain_fn_test(samples):
return np.abs(samples) >= delta
dc.get_bayes_factors(
cell_idx1,
cell_idx2,
mode="change",
m1_domain_fn=m1_domain_fn_test,
change_fn=change_fn_test,
)
# should fail if just one batch
with pytest.raises(ValueError):
model.differential_expression(adata[:20], groupby="batch")
# test view
model.differential_expression(
adata[adata.obs["labels"] == "label_1"], groupby="batch"
)
# Test query features
obs_col, group1, _, = _prepare_obs(
idx1="(labels == 'label_1') & (batch == 'batch_1')", idx2=None, adata=adata
)
assert (obs_col == group1).sum() == adata.obs.loc[
lambda x: (x.labels == "label_1") & (x.batch == "batch_1")
].shape[0]
model.differential_expression(
idx1="labels == 'label_1'",
)
model.differential_expression(
idx1="labels == 'label_1'", idx2="(labels == 'label_2') & (batch == 'batch_1')"
)
# test that ints as group work
a = synthetic_iid()
a.obs["test"] = [0] * 200 + [1] * 200
model = SCVI(a)
model.differential_expression(groupby="test", group1=0)
# test that string but not as categorical work
a = synthetic_iid()
a.obs["test"] = ["0"] * 200 + ["1"] * 200
model = SCVI(a)
model.differential_expression(groupby="test", group1="0")