bio-single-cell-cell-annotation

CellTypist (Python)

Goal: Automatically annotate cell types using a pre-trained or custom CellTypist model.

Approach: Load a reference model, predict cell types with majority voting for cluster-level consensus, and add predictions to AnnData.

"Automatically label my cell types" → Apply a trained classifier to assign cell type identities based on transcriptomic similarity to a reference atlas.

import celltypist
import scanpy as sc

adata = sc.read_h5ad('adata_processed.h5ad')

## Load model

model = celltypist.models.Model.load(model='Immune_All_Low.pkl')

## Predict cell types

predictions = celltypist.annotate(adata, model=model, majority_voting=True)