def populate(self):
counts_filename = "sourcedata/{}_counts.csv".format(self.file_prefix)
coordinates_filename = "sourcedata/{}_cellcentroids.csv".format(
self.file_prefix
)
data_path = os.path.join(self.save_path, "seqfishplus")
if not os.path.exists(data_path):
os.makedirs(data_path)
with zipfile.ZipFile(os.path.join(self.save_path, self.filenames[0])) as f:
f.extract(counts_filename, path=data_path)
f.extract(coordinates_filename, path=data_path)
df_counts = pd.read_csv(os.path.join(data_path, counts_filename))
df_coordinates = pd.read_csv(os.path.join(data_path, coordinates_filename))
coordinates = CellMeasurement(
name="coords",
data=df_coordinates[["X", "Y"]],
columns_attr_name="axis",
columns=["x", "y"],
)
cell_attributes_name_mapping = {
"Cell ID": "cell_id",
"Field of View": "field_of_view",
}
if self.tissue_region == "subventricular cortex":
cell_attributes_name_mapping.update({"Region": "region"})
cell_attributes_dict = {}
for column_name, attribute_name in cell_attributes_name_mapping.items():
cell_attributes_dict[attribute_name] = df_coordinates[column_name]
self.populate_from_data(
X=df_counts.values,
gene_names=df_counts.columns,
Ys=[coordinates],
cell_attributes_dict=cell_attributes_dict,
)
def test_special_dataset_size(self):
gene_dataset = GeneExpressionDataset()
x = np.random.randint(1, 100, (17 * 2, 10))
y = np.random.randint(1, 100, (17 * 2, 10))
gene_dataset.populate_from_data(x)
protein_data = CellMeasurement(
name="protein_expression",
data=y,
columns_attr_name="protein_names",
columns=np.arange(10),
)
gene_dataset.initialize_cell_measurement(protein_data)
# Test UnsupervisedTrainer
vae = VAE(
gene_dataset.nb_genes,
n_batch=gene_dataset.n_batches,
n_labels=gene_dataset.n_labels,
)
trainer = UnsupervisedTrainer(
vae,
gene_dataset,
train_size=0.5,
use_cuda=False,
data_loader_kwargs={"batch_size": 8},
)
trainer.train(n_epochs=1)
# Test JVATrainer
jvae = JVAE(
[gene_dataset.nb_genes, gene_dataset.nb_genes],
gene_dataset.nb_genes,
[slice(None)] * 2,
["zinb", "zinb"],
[True, True],
n_batch=1,
)
cls = Classifier(gene_dataset.nb_genes, n_labels=2, logits=True)
trainer = JVAETrainer(
jvae,
cls,
[gene_dataset, gene_dataset],
train_size=0.5,
use_cuda=False,
data_loader_kwargs={"batch_size": 8},
)
trainer.train(n_epochs=1)
totalvae = TOTALVI(gene_dataset.nb_genes,
len(gene_dataset.protein_names))
trainer = TotalTrainer(
totalvae,
gene_dataset,
train_size=0.5,
use_cuda=False,
data_loader_kwargs={"batch_size": 8},
early_stopping_kwargs=None,
)
trainer.train(n_epochs=1)
def test_data_loader(self):
data = np.ones((25, 10)) * 100
paired = np.ones((25, 4)) * np.arange(0, 4)
pair_names = ["gabou", "achille", "pedro", "oclivio"]
y = CellMeasurement(name="dev",
data=paired,
columns_attr_name="dev_names",
columns=pair_names)
dataset = GeneExpressionDataset()
dataset.populate_from_data(data, Ys=[y])
ad = dataset.to_anndata()
dataset_ad = AnnDatasetFromAnnData(
ad, cell_measurements_col_mappings={"dev": "dev_names"})
self.assertTrue((paired == dataset_ad.dev).all())
self.assertTrue((dataset.X == dataset_ad.X).all())
self.assertTrue((dataset.cell_types == dataset_ad.cell_types).all())
adatas.append(anndataset_111[anndataset_111.obs["batch_indices"] == b, :].copy())
adatas[-1].obs["batch_indices"] *= 0
for b in np.unique(anndataset_206.obs["batch_indices"]):
adatas.append(anndataset_206[anndataset_206.obs["batch_indices"] == b, :].copy())
adatas[-1].obs["batch_indices"] *= 0
names = ["111_d1", "111_d2", "206_d1", "206_d2"]
# Iterate over datasets
for n, adata in zip(names, adatas):
hvg = adata.var["hvg_encode"]
dataset = AnnDatasetFromAnnData(ad=adata[:, hvg])
protein_data = CellMeasurement(
name="protein_expression",
data=adata.obsm["protein_expression"].astype(np.float32),
columns_attr_name="protein_names",
columns=adata.uns["protein_names"],
)
dataset.initialize_cell_measurement(protein_data)
dataset.gene_names = adata[:, hvg].var_names.values
set_seed(0)
model = TOTALVI(dataset.nb_genes, dataset.protein_expression.shape[1], n_latent=20,)
use_cuda = True
lr = 4e-3
early_stopping_kwargs = {
"early_stopping_metric": "elbo",
"save_best_state_metric": "elbo",
"patience": 45,
"threshold": 0,