Automated cell type annotation using reference-based methods including CellTypist, scPred, SingleR, and Azimuth for consistent, reproducible cell labeling.
Sign in to like and favorite skills
import celltypist import scanpy as sc adata = sc.read_h5ad('adata_processed.h5ad') # List available models celltypist.models.models_description() # Download model celltypist.models.download_models(model='Immune_All_Low.pkl') # Load model model = celltypist.models.Model.load(model='Immune_All_Low.pkl') # Predict cell types predictions = celltypist.annotate(adata, model=model, majority_voting=True) # Add predictions to adata adata = predictions.to_adata() # Access predictions adata.obs['cell_type_celltypist'] = adata.obs['majority_voting'] adata.obs['cell_type_confidence'] = adata.obs['conf_score'] # Visualize sc.pl.umap(adata, color=['cell_type_celltypist', 'conf_score'])
# Train custom model new_model = celltypist.train(adata_reference, labels='cell_type', n_jobs=10, feature_selection=True, use_SGD=True) # Save model new_model.write('custom_model.pkl') # Use custom model predictions = celltypist.annotate(adata_query, model='custom_model.pkl')
library(SingleR) library(celldex) library(Seurat) library(SingleCellExperiment) seurat_obj <- readRDS('seurat_processed.rds') sce <- as.SingleCellExperiment(seurat_obj) # Load reference (multiple available) ref <- celldex::HumanPrimaryCellAtlasData() # Other options: # ref <- celldex::BlueprintEncodeData() # ref <- celldex::MonacoImmuneData() # ref <- celldex::ImmGenData() # mouse # Run SingleR pred <- SingleR(test = sce, ref = ref, labels = ref$label.main, de.method = 'wilcox') # Add to Seurat seurat_obj$SingleR_labels <- pred$labels seurat_obj$SingleR_pruned <- pred$pruned.labels # Check annotation quality plotScoreHeatmap(pred) plotDeltaDistribution(pred)
# Use fine-grained labels pred_fine <- SingleR(test = sce, ref = ref, labels = ref$label.fine) # Combine multiple references ref1 <- celldex::BlueprintEncodeData() ref2 <- celldex::MonacoImmuneData() pred_combined <- SingleR(test = sce, ref = list(BP = ref1, Monaco = ref2), labels = list(ref1$label.main, ref2$label.main))
library(Seurat) library(Azimuth) seurat_obj <- readRDS('seurat_processed.rds') # Run Azimuth with PBMC reference seurat_obj <- RunAzimuth(seurat_obj, reference = 'pbmcref') # Available references: pbmcref, bonemarrowref, lungref, etc. # Access predictions seurat_obj$azimuth_labels <- seurat_obj$predicted.celltype.l2 seurat_obj$azimuth_score <- seurat_obj$predicted.celltype.l2.score # Visualize DimPlot(seurat_obj, group.by = 'azimuth_labels', label = TRUE) + NoLegend() FeaturePlot(seurat_obj, features = 'predicted.celltype.l2.score')
library(scPred) library(Seurat) # Train on reference reference <- readRDS('reference_seurat.rds') reference <- getFeatureSpace(reference, 'cell_type') reference <- trainModel(reference) # Get training probabilities get_probabilities(reference) get_scpred(reference) # Plot model performance plot_probabilities(reference) # Predict on query query <- readRDS('query_seurat.rds') query <- scPredict(query, reference) # Results query$scpred_prediction query$scpred_max
# CellTypist: filter low confidence high_conf = adata[adata.obs['conf_score'] > 0.5].copy() # Flag uncertain cells adata.obs['annotation_uncertain'] = adata.obs['conf_score'] < 0.3
# SingleR: use pruned labels (low-quality removed) seurat_obj$final_labels <- ifelse(is.na(pred$pruned.labels), 'Unknown', pred$labels) # Azimuth: filter by score seurat_obj$high_conf_labels <- ifelse(seurat_obj$predicted.celltype.l2.score > 0.7, seurat_obj$predicted.celltype.l2, 'Low_confidence')
# Combine multiple methods annotations <- data.frame( SingleR = seurat_obj$SingleR_labels, Azimuth = seurat_obj$azimuth_labels, CellTypist = seurat_obj$celltypist_labels ) # Majority vote get_consensus <- function(x) { tbl <- table(x) if (max(tbl) >= 2) names(which.max(tbl)) else 'Ambiguous' } seurat_obj$consensus_label <- apply(annotations, 1, get_consensus)
import pandas as pd from sklearn.metrics import adjusted_rand_score, normalized_mutual_info_score # Compare two annotations ari = adjusted_rand_score(adata.obs['manual_annotation'], adata.obs['celltypist']) nmi = normalized_mutual_info_score(adata.obs['manual_annotation'], adata.obs['celltypist']) # Confusion matrix pd.crosstab(adata.obs['manual_annotation'], adata.obs['celltypist'])
# Validate predictions with known markers canonical_markers <- list( T_cell = c('CD3D', 'CD3E', 'CD4', 'CD8A'), B_cell = c('CD19', 'MS4A1', 'CD79A'), Monocyte = c('CD14', 'LYZ', 'S100A8'), NK = c('NKG7', 'GNLY', 'NCAM1') ) # Check marker expression per predicted type DotPlot(seurat_obj, features = unlist(canonical_markers), group.by = 'predicted_labels') + RotatedAxis()