import anndata
import scanpy as sc
from cytetype import CyteType

# ------ Example Scanpy Pipeline ------
#  Skip this step if you already have clusters and marker genes in an AnnData object. 
adata = anndata.read_h5ad("path/to/your/data.h5ad")
sc.pp.normalize_total(adata, target_sum=1e4)
sc.pp.log1p(adata)
sc.pp.highly_variable_genes(adata, n_top_genes=1000)
sc.pp.pca(adata)
sc.pp.neighbors(adata)
sc.tl.leiden(adata, key_added="clusters")
sc.tl.rank_genes_groups(adata, groupby="clusters", method="t-test")
# ------ Example Scanpy Pipeline ------

# ------ CyteType ------
annotator = CyteType(adata, group_key="clusters")
adata = annotator.run(
    study_context="Brief study description (e.g., Human brain tissue ...)",
)

# View results
print(adata.obs.cytetype_annotation_clusters)
print(adata.obs.cytetype_cellOntologyTerm_clusters)