popv.algorithms.Support_Vector

popv.algorithms.Support_Vector#

class popv.algorithms.Support_Vector(batch_key='_batch_annotation', labels_key='_labels_annotation', layer_key=None, result_key='popv_svm_prediction', classifier_dict={})[source]#

Class to compute LinearSVC.

Parameters:

  • batch_key (str | None (default: '_batch_annotation')) – Key in obs field of adata for batch information. Default is “_batch_annotation”.

  • labels_key (str | None (default: '_labels_annotation')) – Key in obs field of adata for cell-type information. Default is “_labels_annotation”.

  • layer_key (str | None (default: None)) – Key in layers field of adata used for classification. By default uses ‘X’ (log1p10K).

  • result_key (str | None (default: 'popv_svm_prediction')) – Key in obs in which celltype annotation results are stored. Default is “popv_svm_prediction”.

  • classifier_dict (str | None (default: {})) – Dictionary to supply non-default values for SVM classifier. Options at sklearn.svm.LinearSVC. Default is {‘C’: 1, ‘max_iter’: 5000, ‘class_weight’: ‘balanced’}.

Methods table#

compute_integration(adata)

Compute integration of adata inplace.

compute_umap(adata)

Compute UMAP embedding of adata inplace.

predict(adata)

Predict celltypes using LinearSVC.

Methods#

abstractmethod Support_Vector.compute_integration(adata)[source]#

Compute integration of adata inplace.

abstractmethod Support_Vector.compute_umap(adata)[source]#

Compute UMAP embedding of adata inplace.

Support_Vector.predict(adata)[source]#

Predict celltypes using LinearSVC.

Parameters:

adata – Anndata object. Results are stored in adata.obs[self.result_key].

Contents