SpaRCL.run_RCL#
- SpaRCL.run_RCL(adata, beta=0.01, tol_err=1e-05, n_iters=1000, use_highly_variable=None, random_state=0, device=None, key_added=None, copy=False)[source]#
Relational Contrastive Learning for spatial transcriptomics.
- Parameters:
- adata :
AnnData Annotated data matrix.
- beta :
float(default:0.01) Parameter to balance the main equation and the constraints.
- tol_err :
float(default:1e-05) Relative error tolerance (convergence criteria).
- n_iters :
int(default:1000) Number of iterations for the optimization.
- use_highly_variable :
bool|NoneOptional[bool] (default:None) Whether to use highly variable genes only, stored in adata.var[‘highly_variable’]. By default uses them if they have been determined beforehand.
- random_state :
int(default:0) Change to use different initial states for the optimization.
- device :
str|NoneOptional[str] (default:None) The desired device for PyTorch computation. By default uses cuda if cuda is avaliable cpu otherwise.
- key_added :
str|NoneOptional[str] (default:None) If not specified, the relational contrastive learning data is stored in adata.uns[‘relation’] and the relation matrix is stored in adata.obsp[‘relation’]. If specified, the relational contrastive learning data is added to adata.uns[key_added] and the relation matrix is stored in adata.obsp[key_added+’_relation’].
- copy :
bool(default:False) Return a copy instead of writing to
adata.
- adata :
- Return type:
- Returns:
Depending on
copy, returns or updatesadatawith the following fields.See
key_addedparameter description for the storage path of the relation matrix.- .obsp[‘relation’]
csr_matrix The sample-by-sample relation matrix.
- .uns[‘relation’][‘gene_relation’]
csr_matrix The gene-by-gene relation matrix.
- .uns[‘relation’][‘gene_names’]
ndarray The gene names of gene relation matrix.
- .obsp[‘relation’]