popv.algorithms.KNN_HARMONY

popv.algorithms.KNN_HARMONY#

class popv.algorithms.KNN_HARMONY(batch_key='_batch_annotation', labels_key='_labels_annotation', result_key='popv_knn_harmony_prediction', embedding_key='X_pca_harmony_popv', umap_key='X_umap_harmony_popv', method_kwargs=None, classifier_dict=None, embedding_kwargs=None)[source]#

Class to compute KNN classifier after Harmony integration.

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”.

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

  • embedding_key (str | None (default: 'X_pca_harmony_popv')) – Key in obsm in which UMAP embedding of integrated data is stored. Default is “X_pca_harmony_popv”.

  • umap_key (str | None (default: 'X_umap_harmony_popv')) – Key in obsm in which UMAP embedding of integrated data is stored. Default is “X_umap_harmony_popv”.

  • method_kwargs (dict | None (default: None)) – Additional parameters for HARMONY. Options at harmony.integrate_scanpy

  • classifier_dict (dict | None (default: None)) – Dictionary to supply non-default values for KNN classifier. n_neighbors and weights supported.

  • embedding_kwargs (dict | None (default: None)) – Dictionary to supply non-default values for UMAP embedding. Options at sc.tl.umap

Methods table#

compute_integration(adata)

Compute integration of adata inplace.

compute_umap(adata)

Compute UMAP embedding of integrated data.

predict(adata)

Predict celltypes using KNN on Harmony.

Methods#

KNN_HARMONY.compute_integration(adata)[source]#

Compute integration of adata inplace.

KNN_HARMONY.compute_umap(adata)[source]#

Compute UMAP embedding of integrated data.

Parameters:

adata – Anndata object. Results are stored in adata.obsm[self.umap_key].

KNN_HARMONY.predict(adata)[source]#

Predict celltypes using KNN on Harmony.

Parameters:

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

Contents