def test_anndata_loader():
x = np.random.randint(low=0, high=100, size=(15, 4))
batch_ids = np.random.randint(low=0, high=2, size=(15, ))
n_batches = 2
adata = AnnData(X=x, obs=dict(batch=batch_ids))
_ = AnnDatasetFromAnnData(adata, batch_label="batch")
dataset = AnnDatasetFromAnnData(adata, batch_label="batch")
assert (dataset.n_batches == n_batches
), "AnnDatasetFromAnnData should not modify the anndata object"
def test_sparse_data(self):
data = np.random.poisson(0.2, size=(25, 10))
sparse_mat = sp_sparse.csr_matrix(data)
ad = anndata.AnnData(sparse_mat)
AnnDatasetFromAnnData(ad)
sparse_mat = sp_sparse.csc_matrix(data)
ad = anndata.AnnData(sparse_mat)
AnnDatasetFromAnnData(ad)
def train(self,
adata,
condition_key,
cell_type_key,
n_epochs=300,
patience=30,
lr_reducer=20):
le = LabelEncoder()
adata.obs['labels'] = le.fit_transform(adata.obs[cell_type_key].values)
adata.obs['batch_indices'] = le.fit_transform(
adata.obs[condition_key].values)
net_adata = AnnDatasetFromAnnData(adata)
early_stopping_kwargs = {
"early_stopping_metric": "elbo",
"save_best_state_metric": "elbo",
"patience": patience,
"threshold": 0,
"reduce_lr_on_plateau": True,
"lr_patience": lr_reducer,
"lr_factor": 0.1,
}
self.trainer = UnsupervisedTrainer(
self.model,
net_adata,
train_size=0.8,
use_cuda=True,
frequency=1,
early_stopping_kwargs=early_stopping_kwargs,
)
self.trainer.train(n_epochs=n_epochs, lr=0.001)
def run(self):
n_epochs = 100
n_latent = 10
n_hidden = 128
n_layers = 2
net_data = self.data.copy()
net_data.X = self.data.layers['counts']
del net_data.layers['counts']
net_data.raw = None # Ensure that the raw counts are not accidentally used
# Define batch indices
le = LabelEncoder()
net_data.obs['batch_indices'] = le.fit_transform(
net_data.obs[self.batch].values)
net_data = AnnDatasetFromAnnData(net_data)
vae = VAE(net_data.nb_genes,
reconstruction_loss='nb',
n_batch=net_data.n_batches,
n_layers=n_layers,
n_latent=n_latent,
n_hidden=n_hidden)
trainer = UnsupervisedTrainer(vae,
net_data,
train_size=1,
use_cuda=False)
trainer.train(n_epochs=n_epochs, lr=1e-3)
full = trainer.create_posterior(trainer.model,
net_data,
indices=np.arange(len(net_data)))
latent, _, _ = full.sequential().get_latent()
self.data.obsm['X_emb'] = latent
self.dump_to_h5ad("scvi")
def predict(self,
adata,
cell_type_to_predict,
condition_key,
cell_type_key,
target_condition,
source_condition,
n_generated_samples=50):
cell_type_adata = adata.copy()[adata.obs[cell_type_key] ==
cell_type_to_predict]
real_adata = cell_type_adata[cell_type_adata.obs[condition_key] ==
target_condition]
ctrl_adata = cell_type_adata[cell_type_adata.obs[condition_key] ==
source_condition]
le = LabelEncoder()
le.fit([source_condition, target_condition])
real_adata.obs['batch_indices'] = le.transform(
real_adata.obs[condition_key].values)
ctrl_adata.obs['batch_indices'] = le.transform([target_condition] *
ctrl_adata.shape[0])
ctrl_adata = AnnDatasetFromAnnData(ctrl_adata)
posterior = self.trainer.create_posterior(self.trainer.model,
ctrl_adata,
indices=np.arange(
len(ctrl_adata)))
generated_samples, _ = posterior.sequential().generate(
n_generated_samples)
reconstructed = generated_samples.mean(axis=2)
reconstructed_adata = sc.AnnData(X=reconstructed)
reconstructed_adata.obs = ctrl_adata.obs.copy(deep=True)
reconstructed_adata.obs[condition_key].replace(
source_condition,
f'{cell_type_to_predict}_pred_{target_condition}',
inplace=True)
reconstructed_adata.var_names = cell_type_adata.var_names
pred_adata = reconstructed_adata[
reconstructed_adata.obs[condition_key] ==
f'{cell_type_to_predict}_pred_{target_condition}']
sc.pp.normalize_per_cell(pred_adata)
sc.pp.log1p(pred_adata)
return pred_adata
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())
def to_mmd_layer(self, adata, condition_key, cell_type_key):
le = LabelEncoder()
adata.obs['labels'] = le.fit_transform(adata.obs[cell_type_key].values)
adata.obs['batch_indices'] = le.fit_transform(
adata.obs[condition_key].values)
net_adata = AnnDatasetFromAnnData(adata)
posterior = self.trainer.create_posterior(self.trainer.model,
net_adata,
indices=np.arange(
len(net_adata)))
latent, _, __ = posterior.sequential().get_latent()
latent_adata = sc.AnnData(X=latent)
latent_adata.obs = adata.obs.copy(deep=True)
return latent_adata
def correct_scvi(Xs, genes):
import torch
torch.manual_seed(0)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
from scvi.dataset import AnnDatasetFromAnnData
from scvi.dataset.dataset import GeneExpressionDataset
from scvi.inference import UnsupervisedTrainer
from scvi.models import VAE
all_ann = [AnnDatasetFromAnnData(AnnData(X, var=genes)) for X in Xs]
all_dataset = GeneExpressionDataset()
all_dataset.populate_from_datasets(all_ann)
vae = VAE(all_dataset.nb_genes,
n_batch=all_dataset.n_batches,
n_labels=all_dataset.n_labels,
n_hidden=128,
n_latent=30,
n_layers=2,
dispersion='gene')
trainer = UnsupervisedTrainer(
vae,
all_dataset,
train_size=1.,
use_cuda=True,
)
n_epochs = 100
#trainer.train(n_epochs=n_epochs)
#torch.save(trainer.model.state_dict(),
# 'data/harmonization.vae.pkl')
trainer.model.load_state_dict(torch.load('data/harmonization.vae.pkl'))
trainer.model.eval()
full = trainer.create_posterior(trainer.model,
all_dataset,
indices=np.arange(len(all_dataset)))
latent, batch_indices, labels = full.sequential().get_latent()
return latent
def test_use_raw_flag(self):
raw_data = np.random.randint(1, 5, size=(4, 7))
ad = anndata.AnnData(raw_data)
ad.raw = ad.copy()
dataset = AnnDatasetFromAnnData(ad, use_raw=True)
np.testing.assert_array_equal(dataset.X, raw_data)
def test_train_one(self):
data = np.random.randint(1, 5, size=(4, 7))
ad = anndata.AnnData(data)
dataset = AnnDatasetFromAnnData(ad)
unsupervised_training_one_epoch(dataset)
def test_init(self):
data = np.random.randint(1, 5, size=(3, 7))
ad = anndata.AnnData(data)
dataset = AnnDatasetFromAnnData(ad)
self.assertEqual(3, dataset.nb_cells)
self.assertEqual(7, dataset.nb_genes)
adatas = []
for b in np.unique(anndataset_111.obs["batch_indices"]):
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 = {
def main():
usage = 'solo'
parser = ArgumentParser(usage,
formatter_class=ArgumentDefaultsHelpFormatter)
parser.add_argument(dest='model_json_file',
help='json file to pass VAE parameters')
parser.add_argument(
dest='data_path',
help=
'path to h5ad, loom or 10x directory containing cell by genes counts')
parser.add_argument('-d',
dest='doublet_depth',
default=2.,
type=float,
help='Depth multiplier for a doublet relative to the \
average of its constituents')
parser.add_argument('-g',
dest='gpu',
default=True,
action='store_true',
help='Run on GPU')
parser.add_argument('-a',
dest='anndata_output',
default=False,
action='store_true',
help='output modified anndata object with solo scores \
Only works for anndata')
parser.add_argument('-o', dest='out_dir', default='solo_out')
parser.add_argument('-r',
dest='doublet_ratio',
default=2.,
type=float,
help='Ratio of doublets to true \
cells')
parser.add_argument('-s',
dest='seed',
default=None,
help='Path to previous solo output \
directory. Seed VAE models with previously \
trained solo model. Directory structure is assumed to \
be the same as solo output directory structure. \
should at least have a vae.pt a pickled object of \
vae weights and a latent.npy an np.ndarray of the \
latents of your cells.')
parser.add_argument('-k',
dest='known_doublets',
help='Experimentally defined doublets tsv file. \
Should be a single column of True/False. True \
indicates the cell is a doublet. No header.',
type=str)
parser.add_argument('-t',
dest='doublet_type',
help='Please enter \
multinomial, average, or sum',
default='multinomial',
choices=['multinomial', 'average', 'sum'])
parser.add_argument('-e',
dest='expected_number_of_doublets',
help='Experimentally expected number of doublets',
type=int,
default=None)
parser.add_argument('-p',
dest='plot',
default=False,
action='store_true',
help='Plot outputs for solo')
parser.add_argument('-l',
dest='normal_logging',
default=False,
action='store_true',
help='Logging level set to normal (aka not debug)')
parser.add_argument('--random_size',
dest='randomize_doublet_size',
default=False,
action='store_true',
help='Sample depth multipliers from Unif(1, \
DoubletDepth) \
to provide a diversity of possible doublet depths.')
args = parser.parse_args()
if not args.normal_logging:
scvi._settings.set_verbosity(10)
model_json_file = args.model_json_file
data_path = args.data_path
if args.gpu and not torch.cuda.is_available():
args.gpu = torch.cuda.is_available()
print('Cuda is not available, switching to cpu running!')
if not os.path.isdir(args.out_dir):
os.mkdir(args.out_dir)
##################################################
# data
# read loom/anndata
data_ext = os.path.splitext(data_path)[-1]
if data_ext == '.loom':
scvi_data = LoomDataset(data_path)
elif data_ext == '.h5ad':
adata = anndata.read(data_path)
if issparse(adata.X):
adata.X = adata.X.todense()
scvi_data = AnnDatasetFromAnnData(adata)
elif os.path.isdir(data_path):
scvi_data = Dataset10X(save_path=data_path,
measurement_names_column=1,
dense=True)
cell_umi_depth = scvi_data.X.sum(axis=1)
fifth, ninetyfifth = np.percentile(cell_umi_depth, [5, 95])
min_cell_umi_depth = np.min(cell_umi_depth)
max_cell_umi_depth = np.max(cell_umi_depth)
if fifth * 10 < ninetyfifth:
print("""WARNING YOUR DATA HAS A WIDE RANGE OF CELL DEPTHS.
PLEASE MANUALLY REVIEW YOUR DATA""")
print(
f"Min cell depth: {min_cell_umi_depth}, Max cell depth: {max_cell_umi_depth}"
)
else:
msg = f'{data_path} is not a recognized format.\n'
msg += 'must be one of {h5ad, loom, 10x directory}'
raise TypeError(msg)
num_cells, num_genes = scvi_data.X.shape
if args.known_doublets is not None:
print('Removing known doublets for in silico doublet generation')
print('Make sure known doublets are in the same order as your data')
known_doublets = np.loadtxt(args.known_doublets, dtype=str) == 'True'
assert len(known_doublets) == scvi_data.X.shape[0]
known_doublet_data = make_gene_expression_dataset(
scvi_data.X[known_doublets], scvi_data.gene_names)
known_doublet_data.labels = np.ones(known_doublet_data.X.shape[0])
singlet_scvi_data = make_gene_expression_dataset(
scvi_data.X[~known_doublets], scvi_data.gene_names)
singlet_num_cells, _ = singlet_scvi_data.X.shape
else:
known_doublet_data = None
singlet_num_cells = num_cells
known_doublets = np.zeros(num_cells, dtype=bool)
singlet_scvi_data = scvi_data
singlet_scvi_data.labels = np.zeros(singlet_scvi_data.X.shape[0])
scvi_data.labels = known_doublets.astype(int)
##################################################
# parameters
# check for parameters
if not os.path.exists(model_json_file):
raise FileNotFoundError(f'{model_json_file} does not exist.')
# read parameters
with open(model_json_file, 'r') as model_json_open:
params = json.load(model_json_open)
# set VAE params
vae_params = {}
for par in [
'n_hidden', 'n_latent', 'n_layers', 'dropout_rate', 'ignore_batch'
]:
if par in params:
vae_params[par] = params[par]
vae_params['n_batch'] = 0 if params.get('ignore_batch',
False) else scvi_data.n_batches
# training parameters
batch_size = params.get('batch_size', 128)
valid_pct = params.get('valid_pct', 0.1)
learning_rate = params.get('learning_rate', 1e-3)
stopping_params = {'patience': params.get('patience', 10), 'threshold': 0}
# protect against single example batch
while num_cells % batch_size == 1:
batch_size = int(np.round(1.25 * batch_size))
print('Increasing batch_size to %d to avoid single example batch.' %
batch_size)
##################################################
# VAE
vae = VAE(n_input=singlet_scvi_data.nb_genes,
n_labels=2,
reconstruction_loss='nb',
log_variational=True,
**vae_params)
if args.seed:
if args.gpu:
device = torch.device('cuda')
vae.load_state_dict(torch.load(os.path.join(args.seed, 'vae.pt')))
vae.to(device)
else:
map_loc = 'cpu'
vae.load_state_dict(
torch.load(os.path.join(args.seed, 'vae.pt'),
map_location=map_loc))
# save latent representation
utrainer = \
UnsupervisedTrainer(vae, singlet_scvi_data,
train_size=(1. - valid_pct),
frequency=2,
metrics_to_monitor=['reconstruction_error'],
use_cuda=args.gpu,
early_stopping_kwargs=stopping_params,
batch_size=batch_size)
full_posterior = utrainer.create_posterior(utrainer.model,
singlet_scvi_data,
indices=np.arange(
len(singlet_scvi_data)))
latent, _, _ = full_posterior.sequential(batch_size).get_latent()
np.save(os.path.join(args.out_dir, 'latent.npy'),
latent.astype('float32'))
else:
stopping_params['early_stopping_metric'] = 'reconstruction_error'
stopping_params['save_best_state_metric'] = 'reconstruction_error'
# initialize unsupervised trainer
utrainer = \
UnsupervisedTrainer(vae, singlet_scvi_data,
train_size=(1. - valid_pct),
frequency=2,
metrics_to_monitor=['reconstruction_error'],
use_cuda=args.gpu,
early_stopping_kwargs=stopping_params,
batch_size=batch_size)
utrainer.history['reconstruction_error_test_set'].append(0)
# initial epoch
utrainer.train(n_epochs=2000, lr=learning_rate)
# drop learning rate and continue
utrainer.early_stopping.wait = 0
utrainer.train(n_epochs=500, lr=0.5 * learning_rate)
# save VAE
torch.save(vae.state_dict(), os.path.join(args.out_dir, 'vae.pt'))
# save latent representation
full_posterior = utrainer.create_posterior(utrainer.model,
singlet_scvi_data,
indices=np.arange(
len(singlet_scvi_data)))
latent, _, _ = full_posterior.sequential(batch_size).get_latent()
np.save(os.path.join(args.out_dir, 'latent.npy'),
latent.astype('float32'))
##################################################
# simulate doublets
non_zero_indexes = np.where(singlet_scvi_data.X > 0)
cells = non_zero_indexes[0]
genes = non_zero_indexes[1]
cells_ids = defaultdict(list)
for cell_id, gene in zip(cells, genes):
cells_ids[cell_id].append(gene)
# choose doublets function type
if args.doublet_type == 'average':
doublet_function = create_average_doublet
elif args.doublet_type == 'sum':
doublet_function = create_summed_doublet
else:
doublet_function = create_multinomial_doublet
cell_depths = singlet_scvi_data.X.sum(axis=1)
num_doublets = int(args.doublet_ratio * singlet_num_cells)
if known_doublet_data is not None:
num_doublets -= known_doublet_data.X.shape[0]
# make sure we are making a non negative amount of doublets
assert num_doublets >= 0
in_silico_doublets = np.zeros((num_doublets, num_genes), dtype='float32')
# for desired # doublets
for di in range(num_doublets):
# sample two cells
i, j = np.random.choice(singlet_num_cells, size=2)
# generate doublets
in_silico_doublets[di, :] = \
doublet_function(singlet_scvi_data.X, i, j,
doublet_depth=args.doublet_depth,
cell_depths=cell_depths, cells_ids=cells_ids,
randomize_doublet_size=args.randomize_doublet_size)
# merge datasets
# we can maybe up sample the known doublets
# concatentate
classifier_data = GeneExpressionDataset()
classifier_data.populate_from_data(
X=np.vstack([scvi_data.X, in_silico_doublets]),
labels=np.hstack(
[np.ravel(scvi_data.labels),
np.ones(in_silico_doublets.shape[0])]),
remap_attributes=False)
assert (len(np.unique(classifier_data.labels.flatten())) == 2)
##################################################
# classifier
# model
classifier = Classifier(n_input=(vae.n_latent + 1),
n_hidden=params['cl_hidden'],
n_layers=params['cl_layers'],
n_labels=2,
dropout_rate=params['dropout_rate'])
# trainer
stopping_params['early_stopping_metric'] = 'accuracy'
stopping_params['save_best_state_metric'] = 'accuracy'
strainer = ClassifierTrainer(classifier,
classifier_data,
train_size=(1. - valid_pct),
frequency=2,
metrics_to_monitor=['accuracy'],
use_cuda=args.gpu,
sampling_model=vae,
sampling_zl=True,
early_stopping_kwargs=stopping_params,
batch_size=batch_size)
# initial
strainer.train(n_epochs=1000, lr=learning_rate)
# drop learning rate and continue
strainer.early_stopping.wait = 0
strainer.train(n_epochs=300, lr=0.1 * learning_rate)
torch.save(classifier.state_dict(),
os.path.join(args.out_dir, 'classifier.pt'))
##################################################
# post-processing
# use logits for predictions for better results
logits_classifier = Classifier(n_input=(vae.n_latent + 1),
n_hidden=params['cl_hidden'],
n_layers=params['cl_layers'],
n_labels=2,
dropout_rate=params['dropout_rate'],
logits=True)
logits_classifier.load_state_dict(classifier.state_dict())
# using logits leads to better performance in for ranking
logits_strainer = ClassifierTrainer(logits_classifier,
classifier_data,
train_size=(1. - valid_pct),
frequency=2,
metrics_to_monitor=['accuracy'],
use_cuda=args.gpu,
sampling_model=vae,
sampling_zl=True,
early_stopping_kwargs=stopping_params,
batch_size=batch_size)
# models evaluation mode
vae.eval()
classifier.eval()
logits_classifier.eval()
print('Train accuracy: %.4f' % strainer.train_set.accuracy())
print('Test accuracy: %.4f' % strainer.test_set.accuracy())
# compute predictions manually
# output logits
train_y, train_score = strainer.train_set.compute_predictions(soft=True)
test_y, test_score = strainer.test_set.compute_predictions(soft=True)
# train_y == true label
# train_score[:, 0] == singlet score; train_score[:, 1] == doublet score
train_score = train_score[:, 1]
train_y = train_y.astype('bool')
test_score = test_score[:, 1]
test_y = test_y.astype('bool')
train_auroc = roc_auc_score(train_y, train_score)
test_auroc = roc_auc_score(test_y, test_score)
print('Train AUROC: %.4f' % train_auroc)
print('Test AUROC: %.4f' % test_auroc)
train_fpr, train_tpr, train_t = roc_curve(train_y, train_score)
test_fpr, test_tpr, test_t = roc_curve(test_y, test_score)
train_t = np.minimum(train_t, 1 + 1e-9)
test_t = np.minimum(test_t, 1 + 1e-9)
train_acc = np.zeros(len(train_t))
for i in range(len(train_t)):
train_acc[i] = np.mean(train_y == (train_score > train_t[i]))
test_acc = np.zeros(len(test_t))
for i in range(len(test_t)):
test_acc[i] = np.mean(test_y == (test_score > test_t[i]))
# write predictions
# softmax predictions
order_y, order_score = strainer.compute_predictions(soft=True)
_, order_pred = strainer.compute_predictions()
doublet_score = order_score[:, 1]
np.save(os.path.join(args.out_dir, 'no_updates_softmax_scores.npy'),
doublet_score[:num_cells])
np.save(os.path.join(args.out_dir, 'no_updates_softmax_scores_sim.npy'),
doublet_score[num_cells:])
# logit predictions
logit_y, logit_score = logits_strainer.compute_predictions(soft=True)
logit_doublet_score = logit_score[:, 1]
np.save(os.path.join(args.out_dir, 'logit_scores.npy'),
logit_doublet_score[:num_cells])
np.save(os.path.join(args.out_dir, 'logit_scores_sim.npy'),
logit_doublet_score[num_cells:])
# update threshold as a function of Solo's estimate of the number of
# doublets
# essentially a log odds update
# TODO put in a function
diff = np.inf
counter_update = 0
solo_scores = doublet_score[:num_cells]
logit_scores = logit_doublet_score[:num_cells]
d_s = (args.doublet_ratio / (args.doublet_ratio + 1))
while (diff > .01) | (counter_update < 5):
# calculate log odss calibration for logits
d_o = np.mean(solo_scores)
c = np.log(d_o / (1 - d_o)) - np.log(d_s / (1 - d_s))
# update soloe scores
solo_scores = 1 / (1 + np.exp(-(logit_scores + c)))
# update while conditions
diff = np.abs(d_o - np.mean(solo_scores))
counter_update += 1
np.save(os.path.join(args.out_dir, 'softmax_scores.npy'), solo_scores)
if args.expected_number_of_doublets is not None:
k = len(solo_scores) - args.expected_number_of_doublets
if args.expected_number_of_doublets / len(solo_scores) > .5:
print('''Make sure you actually expect more than half your cells
to be doublets. If not change your
-e parameter value''')
assert k > 0
idx = np.argpartition(solo_scores, k)
threshold = np.max(solo_scores[idx[:k]])
is_solo_doublet = solo_scores > threshold
else:
is_solo_doublet = solo_scores > .5
is_doublet = known_doublets
new_doublets_idx = np.where(~(is_doublet) & is_solo_doublet[:num_cells])[0]
is_doublet[new_doublets_idx] = True
np.save(os.path.join(args.out_dir, 'is_doublet.npy'),
is_doublet[:num_cells])
np.save(os.path.join(args.out_dir, 'is_doublet_sim.npy'),
is_doublet[num_cells:])
np.save(os.path.join(args.out_dir, 'preds.npy'), order_pred[:num_cells])
np.save(os.path.join(args.out_dir, 'preds_sim.npy'),
order_pred[num_cells:])
smoothed_preds = knn_smooth_pred_class(X=latent,
pred_class=is_doublet[:num_cells])
np.save(os.path.join(args.out_dir, 'smoothed_preds.npy'), smoothed_preds)
if args.anndata_output and data_ext == '.h5ad':
adata.obs['is_doublet'] = is_doublet[:num_cells]
adata.obs['logit_scores'] = logit_doublet_score[:num_cells]
adata.obs['softmax_scores'] = doublet_score[:num_cells]
adata.write(os.path.join(args.out_dir, "soloed.h5ad"))
if args.plot:
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
import seaborn as sns
# plot ROC
plt.figure()
plt.plot(train_fpr, train_tpr, label='Train')
plt.plot(test_fpr, test_tpr, label='Test')
plt.gca().set_xlabel('False positive rate')
plt.gca().set_ylabel('True positive rate')
plt.legend()
plt.savefig(os.path.join(args.out_dir, 'roc.pdf'))
plt.close()
# plot accuracy
plt.figure()
plt.plot(train_t, train_acc, label='Train')
plt.plot(test_t, test_acc, label='Test')
plt.axvline(0.5, color='black', linestyle='--')
plt.gca().set_xlabel('Threshold')
plt.gca().set_ylabel('Accuracy')
plt.legend()
plt.savefig(os.path.join(args.out_dir, 'accuracy.pdf'))
plt.close()
# plot distributions
plt.figure()
sns.distplot(test_score[test_y], label='Simulated')
sns.distplot(test_score[~test_y], label='Observed')
plt.legend()
plt.savefig(os.path.join(args.out_dir, 'train_v_test_dist.pdf'))
plt.close()
plt.figure()
sns.distplot(doublet_score[:num_cells], label='Observed')
plt.legend()
plt.savefig(os.path.join(args.out_dir, 'real_cells_dist.pdf'))
plt.close()
scvi_umap = umap.UMAP(n_neighbors=16).fit_transform(latent)
fig, ax = plt.subplots(1, 1, figsize=(10, 10))
ax.scatter(scvi_umap[:, 0],
scvi_umap[:, 1],
c=doublet_score[:num_cells],
s=8,
cmap="GnBu")
ax.set_xlabel("UMAP 1")
ax.set_ylabel("UMAP 2")
ax.set_xticks([], [])
ax.set_yticks([], [])
fig.savefig(os.path.join(args.out_dir, 'umap_solo_scores.pdf'))
def load_posterior(dir_path: str,
model: nn.Module,
use_cuda: Optional[Union[bool, str]] = "auto",
**posterior_kwargs):
"""Function to use in order to retrieve a posterior that was saved using the ``save_posterior`` method
Because of pytorch model loading usage, this function needs a scVI model object initialized with exact same parameters
that during training.
Because saved posteriors correspond to already trained models, data is loaded sequentially using a ``SequentialSampler``.
Parameters
----------
dir_path
directory containing the posterior properties to be retrieved.
model
scVI initialized model.
use_cuda
Specifies if the computations should be perfomed with a GPU.
Default: ``True``
If ``auto``, then cuda availability is inferred, with a preference to load on GPU.
If ``False``, the model will be loaded on the CPU, even if it was trained using a GPU.
**posterior_kwargs
additional parameters to feed to the posterior constructor.
Returns
-------
>>> model = VAE(nb_genes, n_batches, n_hidden=128, n_latent=10)
>>> trainer = UnsupervisedTrainer(vae, dataset, train_size=0.5, use_cuda=use_cuda)
>>> trainer.train(n_epochs=200)
>>> trainer.train_set.save_posterior("./my_run_train_posterior")
>>> model = VAE(nb_genes, n_batches, n_hidden=128, n_latent=10)
>>> post = load_posterior("./my_run_train_posterior", model=model)
"""
# Avoid circular imports
from scvi.inference.total_inference import TotalPosterior
from scvi.inference.jvae_trainer import JPosterior
from scvi.inference.posterior import Posterior
from scvi.inference.annotation import AnnotationPosterior
post_type_path = os.path.join(dir_path, "posterior_type.txt")
dataset_path = os.path.join(dir_path, "anndata_dataset.h5ad")
model_path = os.path.join(dir_path, "model_params.pt")
indices_path = os.path.join(dir_path, "indices.npy")
data_loader_kwargs_path = os.path.join(dir_path, "data_loader_kwargs.h5")
# Infering posterior type
with open(post_type_path, "r") as post_file:
post_class_str = post_file.readline()
str_to_classes = dict(
TotalPosterior=TotalPosterior,
JPosterior=JPosterior,
Posterior=Posterior,
AnnotationPosterior=AnnotationPosterior,
)
if post_class_str not in str_to_classes:
raise ValueError("Posterior type {} not eligible for loading".format(
post_class_str))
post_class = str_to_classes[post_class_str]
# Loading dataset and associated measurements
ad = anndata.read_h5ad(filename=dataset_path)
key = "cell_measurements_col_mappings"
if key in ad.uns:
cell_measurements_col_mappings = ad.uns[key]
else:
cell_measurements_col_mappings = dict()
dataset = AnnDatasetFromAnnData(
ad=ad, cell_measurements_col_mappings=cell_measurements_col_mappings)
# Loading scVI model
if use_cuda == "auto":
use_cuda = torch.cuda.is_available()
use_cuda = use_cuda and torch.cuda.is_available()
if use_cuda:
model.load_state_dict(torch.load(model_path))
model.cuda()
else:
device = torch.device("cpu")
model.load_state_dict(torch.load(model_path, map_location=device))
model.eval()
# Loading data loader options and posterior
indices = np.load(file=indices_path)
data_loader_kwargs = pd.read_hdf(data_loader_kwargs_path,
key="data_loader").to_dict()
my_post = post_class(model=model,
gene_dataset=dataset,
shuffle=False,
indices=indices,
use_cuda=use_cuda,
data_loader_kwargs=data_loader_kwargs,
**posterior_kwargs)
return my_post
def test_protected_X(self):
data = np.random.poisson(0.2, size=(25, 10))
ad = anndata.AnnData(data)
ad.obs["_X"] = np.zeros(25)
AnnDatasetFromAnnData(ad)
def runScanvi(adata, batch, labels):
# Use non-normalized (count) data for scanvi!
# Check for counts data layer
if 'counts' not in adata.layers:
raise TypeError(
'Adata does not contain a `counts` layer in `adata.layers[`counts`]`'
)
from scvi.models import VAE, SCANVI
from scvi.inference import UnsupervisedTrainer, SemiSupervisedTrainer
from sklearn.preprocessing import LabelEncoder
from scvi.dataset import AnnDatasetFromAnnData
import numpy as np
# STEP 1: prepare the data
net_adata = adata.copy()
net_adata.X = adata.layers['counts']
del net_adata.layers['counts']
# Ensure that the raw counts are not accidentally used
del net_adata.raw # Note that this only works from anndata 0.7
# Define batch indices
le = LabelEncoder()
net_adata.obs['batch_indices'] = le.fit_transform(
net_adata.obs[batch].values)
net_adata.obs['labels'] = le.fit_transform(net_adata.obs[labels].values)
net_adata = AnnDatasetFromAnnData(net_adata)
print("scANVI dataset object with {} batches and {} cell types".format(
net_adata.n_batches, net_adata.n_labels))
#if hvg is True:
# # this also corrects for different batches by default
# net_adata.subsample_genes(2000, mode="seurat_v3")
# # Defaults from SCVI github tutorials scanpy_pbmc3k and harmonization
n_epochs_scVI = np.min([round((20000 / adata.n_obs) * 400), 400]) #400
n_epochs_scANVI = int(np.min([10, np.max([2, round(n_epochs_scVI / 3.)])]))
n_latent = 30
n_hidden = 128
n_layers = 2
# STEP 2: RUN scVI to initialize scANVI
vae = VAE(
net_adata.nb_genes,
reconstruction_loss='nb',
n_batch=net_adata.n_batches,
n_latent=n_latent,
n_hidden=n_hidden,
n_layers=n_layers,
)
trainer = UnsupervisedTrainer(
vae,
net_adata,
train_size=1.0,
use_cuda=False,
)
trainer.train(n_epochs=n_epochs_scVI, lr=1e-3)
# STEP 3: RUN scANVI
scanvi = SCANVI(net_adata.nb_genes,
net_adata.n_batches,
net_adata.n_labels,
n_hidden=n_hidden,
n_latent=n_latent,
n_layers=n_layers,
dispersion='gene',
reconstruction_loss='nb')
scanvi.load_state_dict(trainer.model.state_dict(), strict=False)
# use default parameter from semi-supervised trainer class
trainer_scanvi = SemiSupervisedTrainer(scanvi, net_adata)
# use all cells as labelled set
trainer_scanvi.labelled_set = trainer_scanvi.create_posterior(
trainer_scanvi.model, net_adata, indices=np.arange(len(net_adata)))
# put one cell in the unlabelled set
trainer_scanvi.unlabelled_set = trainer_scanvi.create_posterior(
indices=[0])
trainer_scanvi.train(n_epochs=n_epochs_scANVI)
# extract info from posterior
scanvi_full = trainer_scanvi.create_posterior(trainer_scanvi.model,
net_adata,
indices=np.arange(
len(net_adata)))
latent, _, _ = scanvi_full.sequential().get_latent()
adata.obsm['X_emb'] = latent
return adata
def scvi(
adata: AnnData,
n_hidden: int = 128,
n_latent: int = 10,
n_layers: int = 1,
dispersion: str = "gene",
n_epochs: int = 400,
lr: int = 1e-3,
train_size: int = 1.0,
batch_key: Optional[str] = None,
use_highly_variable_genes: bool = True,
subset_genes: Optional[Sequence[Union[int, str]]] = None,
linear_decoder: bool = False,
copy: bool = False,
use_cuda: bool = True,
return_posterior: bool = True,
trainer_kwargs: dict = {},
model_kwargs: dict = {},
) -> Optional[AnnData]:
"""\
SCVI [Lopez18]_.
Fits scVI model onto raw count data given an anndata object
scVI uses stochastic optimization and deep neural networks to aggregate information
across similar cells and genes and to approximate the distributions that underlie
observed expression values, while accounting for batch effects and limited sensitivity.
To use a linear-decoded Variational AutoEncoder model (implementation of [Svensson20]_.),
set linear_decoded = True. Compared to standard VAE, this model is less powerful, but can
be used to inspect which genes contribute to variation in the dataset. It may also be used
for all scVI tasks, like differential expression, batch correction, imputation, etc.
However, batch correction may be less powerful as it assumes a linear model.
.. note::
More information and bug reports `here <https://github.com/YosefLab/scVI>`__.
Parameters
----------
adata
An anndata file with `X` attribute of unnormalized count data
n_hidden
Number of nodes per hidden layer
n_latent
Dimensionality of the latent space
n_layers
Number of hidden layers used for encoder and decoder NNs
dispersion
One of the following
* `'gene'` - dispersion parameter of NB is constant per gene across cells
* `'gene-batch'` - dispersion can differ between different batches
* `'gene-label'` - dispersion can differ between different labels
* `'gene-cell'` - dispersion can differ for every gene in every cell
n_epochs
Number of epochs to train
lr
Learning rate
train_size
The train size, either a float between 0 and 1 or an integer for the number of training samples to use
batch_key
Column name in anndata.obs for batches.
If None, no batch correction is performed
If not None, batch correction is performed per batch category
use_highly_variable_genes
If true, uses only the genes in anndata.var["highly_variable"]
subset_genes
Optional list of indices or gene names to subset anndata.
If not None, use_highly_variable_genes is ignored
linear_decoder
If true, uses LDVAE model, which is an implementation of [Svensson20]_.
copy
If true, a copy of anndata is returned
return_posterior
If true, posterior object is returned
use_cuda
If true, uses cuda
trainer_kwargs
Extra arguments for UnsupervisedTrainer
model_kwargs
Extra arguments for VAE or LDVAE model
Returns
-------
If `copy` is true, anndata is returned.
If `return_posterior` is true, the posterior object is returned
If both `copy` and `return_posterior` are true,
a tuple of anndata and the posterior are returned in that order.
`adata.obsm['X_scvi']` stores the latent representations
`adata.obsm['X_scvi_denoised']` stores the normalized mean of the negative binomial
`adata.obsm['X_scvi_sample_rate']` stores the mean of the negative binomial
If linear_decoder is true:
`adata.uns['ldvae_loadings']` stores the per-gene weights in the linear decoder as a
genes by n_latent matrix.
"""
warnings.warn(
"scvi via scanpy external API is no longer supported. " +
"Please use the new scvi-tools package from `scvi-tools.org`",
FutureWarning,
)
try:
from scvi.models import VAE, LDVAE
from scvi.inference import UnsupervisedTrainer
from scvi.dataset import AnnDatasetFromAnnData
except ImportError:
raise ImportError(
"Please install scvi package from https://github.com/YosefLab/scVI"
)
# check if observations are unnormalized using first 10
# code from: https://github.com/theislab/dca/blob/89eee4ed01dd969b3d46e0c815382806fbfc2526/dca/io.py#L63-L69
if len(adata) > 10:
X_subset = adata.X[:10]
else:
X_subset = adata.X
norm_error = (
'Make sure that the dataset (adata.X) contains unnormalized count data.'
)
if sp.sparse.issparse(X_subset):
assert (X_subset.astype(int) != X_subset).nnz == 0, norm_error
else:
assert np.all(X_subset.astype(int) == X_subset), norm_error
if subset_genes is not None:
adata_subset = adata[:, subset_genes]
elif use_highly_variable_genes and "highly_variable" in adata.var:
adata_subset = adata[:, adata.var["highly_variable"]]
else:
adata_subset = adata
if batch_key is not None:
codes, uniques = pd.factorize(adata_subset.obs[batch_key])
adata_subset.obs['_tmp_scvi_batch'] = codes
n_batches = len(uniques)
else:
n_batches = 0
dataset = AnnDatasetFromAnnData(adata_subset.copy(),
batch_label='_tmp_scvi_batch')
if linear_decoder:
vae = LDVAE(
n_input=dataset.nb_genes,
n_batch=n_batches,
n_labels=dataset.n_labels,
n_hidden=n_hidden,
n_latent=n_latent,
n_layers_encoder=n_layers,
dispersion=dispersion,
**model_kwargs,
)
else:
vae = VAE(
dataset.nb_genes,
n_batch=n_batches,
n_labels=dataset.n_labels,
n_hidden=n_hidden,
n_latent=n_latent,
n_layers=n_layers,
dispersion=dispersion,
**model_kwargs,
)
trainer = UnsupervisedTrainer(
model=vae,
gene_dataset=dataset,
use_cuda=use_cuda,
train_size=train_size,
**trainer_kwargs,
)
trainer.train(n_epochs=n_epochs, lr=lr)
full = trainer.create_posterior(trainer.model,
dataset,
indices=np.arange(len(dataset)))
latent, batch_indices, labels = full.sequential().get_latent()
if copy:
adata = adata.copy()
adata.obsm['X_scvi'] = latent
adata.obsm['X_scvi_denoised'] = full.sequential().get_sample_scale()
adata.obsm['X_scvi_sample_rate'] = full.sequential().imputation()
if linear_decoder:
loadings = vae.get_loadings()
df = pd.DataFrame(loadings, index=adata_subset.var_names)
adata.uns['ldvae_loadings'] = df
if copy and return_posterior:
return adata, full
elif copy:
return adata
elif return_posterior:
return full
def runScvi(adata, batch, hvg=None):
# Use non-normalized (count) data for scvi!
# Expects data only on HVGs
checkSanity(adata, batch, hvg)
# Check for counts data layer
if 'counts' not in adata.layers:
raise TypeError(
'Adata does not contain a `counts` layer in `adata.layers[`counts`]`'
)
from scvi.models import VAE
from scvi.inference import UnsupervisedTrainer
from sklearn.preprocessing import LabelEncoder
from scvi.dataset import AnnDatasetFromAnnData
# Defaults from SCVI github tutorials scanpy_pbmc3k and harmonization
n_epochs = np.min([round((20000 / adata.n_obs) * 400), 400])
n_latent = 30
n_hidden = 128
n_layers = 2
net_adata = adata.copy()
net_adata.X = adata.layers['counts']
del net_adata.layers['counts']
# Ensure that the raw counts are not accidentally used
del net_adata.raw # Note that this only works from anndata 0.7
# Define batch indices
le = LabelEncoder()
net_adata.obs['batch_indices'] = le.fit_transform(
net_adata.obs[batch].values)
net_adata = AnnDatasetFromAnnData(net_adata)
vae = VAE(
net_adata.nb_genes,
reconstruction_loss='nb',
n_batch=net_adata.n_batches,
n_layers=n_layers,
n_latent=n_latent,
n_hidden=n_hidden,
)
trainer = UnsupervisedTrainer(
vae,
net_adata,
train_size=1.0,
use_cuda=False,
)
trainer.train(n_epochs=n_epochs, lr=1e-3)
full = trainer.create_posterior(trainer.model,
net_adata,
indices=np.arange(len(net_adata)))
latent, _, _ = full.sequential().get_latent()
adata.obsm['X_emb'] = latent
return adata
# SCVI
##############################################################
import time
from scvi.dataset import AnnDatasetFromAnnData
from scvi.dataset.dataset import GeneExpressionDataset
from scvi.inference import UnsupervisedTrainer
from scvi.models import SCANVI, VAE
from umap import UMAP
import scanpy as sc
# TODO: import the datasets into SCVI objects (sigh!)
# scVI wants raw counts, but who knows about those TabulaMurisSenis data
# quick and dirty solution for now
asubr_scvi = asubr.copy()
asubr_scvi.X.data = asubr_scvi.X.data.astype(np.int64)
ds_atlas = AnnDatasetFromAnnData(asubr_scvi)
asub2_scvi = asub2.copy()
asub2_scvi.X.data = asub2_scvi.X.data.astype(np.int64)
ds_new = AnnDatasetFromAnnData(asub2_scvi)
all_dataset = GeneExpressionDataset()
all_dataset.populate_from_datasets([ds_atlas, ds_new])
##############################################################
t0 = time.time()
print('Prepare some data structures')
vae = VAE(
all_dataset.nb_genes,
n_batch=all_dataset.n_batches,
n_labels=all_dataset.n_labels,
