scvi.external.SOLO#
- class scvi.external.SOLO(adata, **classifier_kwargs)[source]#
Doublet detection in scRNA-seq [Bernstein19].
Most users will initialize the model using the class method
from_scvi_model()
, which takes as input a pre-trainedSCVI
object.- Parameters:
- adata :
AnnData
AnnData object that has been registered via
setup_anndata()
. Object should contain latent representation of real cells and doublets as adata.X. Object should also be registered, using .X and labels_key=”_solo_doub_sim”.- **classifier_kwargs
Keyword args for
Classifier
- adata :
Examples
In the case of scVI trained with multiple batches:
>>> adata = anndata.read_h5ad(path_to_anndata) >>> scvi.model.SCVI.setup_anndata(adata, batch_key="batch") >>> vae = scvi.model.SCVI(adata) >>> vae.train() >>> solo_batch_1 = scvi.external.SOLO.from_scvi_model(vae, restrict_to_batch="batch 1") >>> solo_batch_1.train() >>> solo_batch_1.predict()
Otherwise:
>>> adata = anndata.read_h5ad(path_to_anndata) >>> scvi.model.SCVI.setup_anndata(adata) >>> vae = scvi.model.SCVI(adata) >>> vae.train() >>> solo = scvi.external.SOLO.from_scvi_model(vae) >>> solo.train() >>> solo.predict()
Notes
Solo should be trained on one lane of data at a time. An
SCVI
instance that was trained with multiple batches can be used as input, but Solo should be created and run multiple times, each with a new restrict_to_batch infrom_scvi_model()
.
Attributes table#
Data attached to model instance. |
|
Manager instance associated with self.adata. |
|
The current device that the module's params are on. |
|
Returns computed metrics during training. |
|
Whether the model has been trained. |
|
Observations that are in test set. |
|
Observations that are in train set. |
|
Observations that are in validation set. |
Methods table#
|
Converts a legacy saved model (<v0.15.0) to the updated save format. |
|
Simulate doublets. |
|
Instantiate a SOLO model from an scvi model. |
|
Retrieves the |
|
Returns the object in AnnData associated with the key in the data registry. |
|
Instantiate a model from the saved output. |
|
Return doublet predictions. |
|
Registers an |
|
Save the state of the model. |
|
Sets up the |
|
Move model to device. |
|
Trains the model. |
|
Print summary of the setup for the initial AnnData or a given AnnData object. |
|
Print args used to setup a saved model. |
Attributes#
adata#
adata_manager#
- SOLO.adata_manager#
Manager instance associated with self.adata.
- Return type:
device#
history#
- SOLO.history#
Returns computed metrics during training.
is_trained#
test_indices#
train_indices#
validation_indices#
Methods#
convert_legacy_save#
- classmethod SOLO.convert_legacy_save(dir_path, output_dir_path, overwrite=False, prefix=None)#
Converts a legacy saved model (<v0.15.0) to the updated save format.
- Parameters:
- dir_path :
str
Path to directory where legacy model is saved.
- output_dir_path :
str
Path to save converted save files.
- overwrite :
bool
(default:False
) Overwrite existing data or not. If
False
and directory already exists atoutput_dir_path
, error will be raised.- prefix :
str
|None
Optional
[str
] (default:None
) Prefix of saved file names.
- dir_path :
- Return type:
create_doublets#
- classmethod SOLO.create_doublets(adata_manager, doublet_ratio, indices=None, seed=1)[source]#
Simulate doublets.
- Parameters:
- adata
AnnData object setup with setup_anndata.
- doublet_ratio :
int
Ratio of generated doublets to produce relative to number of cells in adata or length of indices, if not None.
- indices :
Sequence
[int
] |None
Optional
[Sequence
[int
]] (default:None
) Indices of cells in adata to use. If None, all cells are used.
- seed :
int
(default:1
) Seed for reproducibility
- Return type:
from_scvi_model#
- classmethod SOLO.from_scvi_model(scvi_model, adata=None, restrict_to_batch=None, doublet_ratio=2, **classifier_kwargs)[source]#
Instantiate a SOLO model from an scvi model.
- Parameters:
- scvi_model :
SCVI
Pre-trained model of
SCVI
. The adata object used to initialize this model should have only been setup with count data, and optionally a batch_key; i.e., no extra covariates or labels, etc.- adata :
AnnData
|None
Optional
[AnnData
] (default:None
) Optional anndata to use that is compatible with scvi_model.
- restrict_to_batch :
str
|None
Optional
[str
] (default:None
) Batch category in batch_key used to setup adata for scvi_model to restrict Solo model to. This allows to train a Solo model on one batch of a scvi_model that was trained on multiple batches.
- doublet_ratio :
int
(default:2
) Ratio of generated doublets to produce relative to number of cells in adata or length of indices, if not None.
- **classifier_kwargs
Keyword args for
Classifier
- scvi_model :
- Returns:
SOLO model
get_anndata_manager#
- SOLO.get_anndata_manager(adata, required=False)#
Retrieves the
AnnDataManager
for a given AnnData object specific to this model instance.Requires
self.id
has been set. Checks for anAnnDataManager
specific to this model instance.- Parameters:
- Return type:
get_from_registry#
- SOLO.get_from_registry(adata, registry_key)#
Returns the object in AnnData associated with the key in the data registry.
AnnData object should be registered with the model prior to calling this function via the
self._validate_anndata
method.
load#
- classmethod SOLO.load(dir_path, adata=None, use_gpu=None, prefix=None, backup_url=None)#
Instantiate a model from the saved output.
- Parameters:
- dir_path :
str
Path to saved outputs.
- adata :
AnnData
|None
Optional
[AnnData
] (default:None
) AnnData organized in the same way as data used to train model. It is not necessary to run setup_anndata, as AnnData is validated against the saved scvi setup dictionary. If None, will check for and load anndata saved with the model.
- use_gpu :
str
|int
|bool
|None
Union
[str
,int
,bool
,None
] (default:None
) Load model on default GPU if available (if None or True), or index of GPU to use (if int), or name of GPU (if str), or use CPU (if False).
- prefix :
str
|None
Optional
[str
] (default:None
) Prefix of saved file names.
- backup_url :
str
|None
Optional
[str
] (default:None
) URL to retrieve saved outputs from if not present on disk.
- dir_path :
- Returns:
Model with loaded state dictionaries.
Examples
>>> model = ModelClass.load(save_path, adata) # use the name of the model class used to save >>> model.get_....
predict#
register_manager#
- classmethod SOLO.register_manager(adata_manager)#
Registers an
AnnDataManager
instance with this model class.Stores the
AnnDataManager
reference in a class-specific manager store. Intended for use in thesetup_anndata()
class method followed up by retrieval of theAnnDataManager
via the_get_most_recent_anndata_manager()
method in the model init method.Notes
Subsequent calls to this method with an
AnnDataManager
instance referring to the same underlying AnnData object will overwrite the reference to previousAnnDataManager
.
save#
- SOLO.save(dir_path, prefix=None, overwrite=False, save_anndata=False, **anndata_write_kwargs)#
Save the state of the model.
Neither the trainer optimizer state nor the trainer history are saved. Model files are not expected to be reproducibly saved and loaded across versions until we reach version 1.0.
- Parameters:
- dir_path :
str
Path to a directory.
- prefix :
str
|None
Optional
[str
] (default:None
) Prefix to prepend to saved file names.
- overwrite :
bool
(default:False
) Overwrite existing data or not. If False and directory already exists at dir_path, error will be raised.
- save_anndata :
bool
(default:False
) If True, also saves the anndata
- anndata_write_kwargs
Kwargs for
write()
- dir_path :
setup_anndata#
- classmethod SOLO.setup_anndata(adata, labels_key=None, layer=None, **kwargs)[source]#
- Sets up the
AnnData
object for this model. A mapping will be created between data fields used by this model to their respective locations in adata.
None of the data in adata are modified. Only adds fields to adata.
- Parameters:
- labels_key :
str
|None
Optional
[str
] (default:None
) key in adata.obs for label information. Categories will automatically be converted into integer categories and saved to adata.obs[‘_scvi_labels’]. If None, assigns the same label to all the data.
- layer :
str
|None
Optional
[str
] (default:None
) if not None, uses this as the key in adata.layers for raw count data.
- labels_key :
- Sets up the
to_device#
- SOLO.to_device(device)#
Move model to device.
- Parameters:
Examples
>>> adata = scvi.data.synthetic_iid() >>> model = scvi.model.SCVI(adata) >>> model.to_device('cpu') # moves model to CPU >>> model.to_device('cuda:0') # moves model to GPU 0 >>> model.to_device(0) # also moves model to GPU 0
train#
- SOLO.train(max_epochs=400, lr=0.001, use_gpu=None, train_size=0.9, validation_size=None, batch_size=128, plan_kwargs=None, early_stopping=True, early_stopping_patience=30, early_stopping_min_delta=0.0, **kwargs)[source]#
Trains the model.
- Parameters:
- max_epochs :
int
(default:400
) Number of epochs to train for
- lr :
float
(default:0.001
) Learning rate for optimization.
- use_gpu :
str
|int
|bool
|None
Union
[str
,int
,bool
,None
] (default:None
) Use default GPU if available (if None or True), or index of GPU to use (if int), or name of GPU (if str, e.g., ‘cuda:0’), or use CPU (if False).
- train_size :
float
(default:0.9
) Size of training set in the range [0.0, 1.0].
- validation_size :
float
|None
Optional
[float
] (default:None
) Size of the test set. If None, defaults to 1 - train_size. If train_size + validation_size < 1, the remaining cells belong to a test set.
- batch_size :
int
(default:128
) Minibatch size to use during training.
- plan_kwargs :
dict
|None
Optional
[dict
] (default:None
) Keyword args for
ClassifierTrainingPlan
. Keyword arguments passed to- early_stopping :
bool
(default:True
) Adds callback for early stopping on validation_loss
- early_stopping_patience :
int
(default:30
) Number of times early stopping metric can not improve over early_stopping_min_delta
- early_stopping_min_delta :
float
(default:0.0
) Threshold for counting an epoch torwards patience train() will overwrite values present in plan_kwargs, when appropriate.
- **kwargs
Other keyword args for
Trainer
.
- max_epochs :
view_anndata_setup#
- SOLO.view_anndata_setup(adata=None, hide_state_registries=False)#
Print summary of the setup for the initial AnnData or a given AnnData object.