Quickstart (Python)

# Import Scanpy for preprocessing and CyteType for annotation.
import scanpy as sc

from cytetype import CyteType, marker_dotplot

# Use a consistent figure resolution for the plots below.
sc.set_figure_params(dpi=100, frameon=False)

# Download the 10x Genomics PBMC 3k dataset with raw counts.
adata = sc.datasets.pbmc3k()
adata

# Remove cells with few detected genes and genes detected in very few cells.
sc.pp.filter_cells(adata, min_genes=200)
sc.pp.filter_genes(adata, min_cells=3)

# Drop cells with a high fraction of mitochondrial reads.
adata.var["mt"] = adata.var_names.str.startswith("MT-")
sc.pp.calculate_qc_metrics(adata, qc_vars=["mt"], percent_top=None, log1p=False, inplace=True)
adata = adata[adata.obs["pct_counts_mt"] < 5].copy()

# Keep the raw counts in a layer; CyteType uploads them with the normalized data.
adata.layers["counts"] = adata.X.copy()

# Normalize and log-transform; CyteType expects log-normalized values in adata.X.
sc.pp.normalize_total(adata, target_sum=1e4)
sc.pp.log1p(adata)

# Find highly variable genes, reduce dimensions and build the neighbor graph.
sc.pp.highly_variable_genes(adata, n_top_genes=2000)
sc.tl.pca(adata, mask_var="highly_variable")
sc.pp.neighbors(adata, n_neighbors=10, n_pcs=40)

# Cluster with Leiden and compute a UMAP for plotting and for the report.
sc.tl.leiden(adata, resolution=0.8, flavor="igraph", n_iterations=2, key_added="leiden")
sc.tl.umap(adata)

# Rank marker genes for each cluster; CyteType reads them from adata.uns.
sc.tl.rank_genes_groups(adata, groupby="leiden", method="wilcoxon", key_added="rank_genes_leiden")

# Check the inputs and build the files that are uploaded with the job.
annotator = CyteType(adata, group_key="leiden", rank_key="rank_genes_leiden")

# Describe the study, submit the job and wait for it to finish.
adata = annotator.run(
    study_context=(
        "Peripheral blood mononuclear cells (PBMCs) from a healthy human donor, "
        "profiled with 10x Genomics 3' single-cell RNA-seq."
    ),
    metadata={"title": "PBMC 3k quickstart"},
)

# Show one row per cluster with its label, Cell Ontology term ID and reviewer confidence.
columns = [
    "leiden",
    "cytetype_annotation_leiden",
    "cytetype_cellOntologyTermID_leiden",
    "cytetype_reviewerConfidence_leiden",
]
adata.obs[columns].drop_duplicates().sort_values("leiden").reset_index(drop=True)

# Plot the CyteType labels on the UMAP.
sc.pl.umap(adata, color="cytetype_annotation_leiden", title="CyteType annotation")

# Show the marker genes that support each label, grouped by cell type.
marker_dotplot(adata, group_key="leiden")

# Look at the evidence recorded for the first cluster.
results = annotator.get_results()
first = results["annotations"][0]
{key: first[key] for key in ("clusterId", "annotation", "cellState", "reviewerConfidence", "supportingMarkers")}

# Get the link to the interactive report.
adata.uns["cytetype_jobDetails"]["report_url"]

# Remove the upload files and the temporary helper column.
annotator.cleanup()

# Save the annotated data; the CyteType results are saved with it.
adata.write_h5ad("pbmc3k_cytetype.h5ad")