scgen.SCGEN.binary_classifier¶
- SCGEN.binary_classifier(adata, delta, ctrl_key, stim_key, path_to_save, save=True, fontsize=14)[source]¶
Latent space classifier.
Builds a linear classifier based on the dot product between the difference vector and the latent representation of each cell and plots the dot product results between delta and latent representation.
- Parameters
- adata : ~anndata.AnnData
AnnData object with equivalent structure to initial AnnData. If None, defaults to the AnnData object used to initialize the model. Must have been setup with batch_key and labels_key, corresponding to batch and cell type metadata, respectively.
- delta : float
Difference between stimulated and control cells in latent space
- ctrl_key : basestring
key for control part of the data found in condition_key.
- stim_key : basestring
key for stimulated part of the data found in condition_key.
- path_to_save : basestring
path to save the plot.
- save : boolean
Specify if the plot should be saved or not.
- fontsize : integer
Set the font size of the plot.
Examples
>>> import anndata >>> import scgen >>> import scanpy as sc >>> train = sc.read("./tests/data/train.h5ad", backup_url="https://goo.gl/33HtVh") >>> scgen.SCGEN.setup_anndata(train) >>> network = scgen.SCGEN(train) >>> network.train() >>> unperturbed_data = train[((train.obs["cell_type"] == "CD4T") & (train.obs["condition"] == "control"))] >>> pred, delta = network.predict( >>> adata=train, >>> adata_to_predict=unperturbed_data, >>> ctrl_key="control", >>> stim_key="stimulated" >>>) >>> network.binary_classifier( >>> network, >>> train, >>> delta, >>> ctrl_key="control", >>> stim_key="stimulated", >>> path_to_save="tests/binary_classifier.pdf" >>> )