name: bio-single-cell-clustering description: scRNA-seq clustering analysis keywords:

• clustering
• single-cell
• seurat
• scanpy
• umap measurable_outcome: Identifies stable cell clusters with silhouette score > 0.5. tool_type: mixed primary_tool: Seurat allowed-tools:
• read_file
• run_shell_command

Single-Cell Clustering

Dimensionality reduction, neighbor graph construction, and clustering.

Scanpy (Python)

Required Imports

import scanpy as sc
import matplotlib.pyplot as plt

PCA

# Run PCA
sc.tl.pca(adata, n_comps=50, svd_solver='arpack')

# Visualize variance explained
sc.pl.pca_variance_ratio(adata, n_pcs=50)

# Visualize PCA
sc.pl.pca(adata, color='n_genes_by_counts')

Determine Number of PCs

# Elbow plot to choose number of PCs
sc.pl.pca_variance_ratio(adata, n_pcs=50, log=True)

# Typically use 10-50 PCs based on elbow
n_pcs = 30

Compute Neighbors

# Build k-nearest neighbor graph
sc.pp.neighbors(adata, n_neighbors=15, n_pcs=30)

Clustering (Leiden - Recommended)

# Leiden clustering (preferred over Louvain)
sc.tl.leiden(adata, resolution=0.5)

# Higher resolution = more clusters
sc.tl.leiden(adata, resolution=1.0, key_added='leiden_r1')

# View cluster sizes
adata.obs['leiden'].value_counts()

Clustering (Louvain)

# Louvain clustering (alternative)
sc.tl.louvain(adata, resolution=0.5)

UMAP

# Compute UMAP embedding
sc.tl.umap(adata, min_dist=0.3, spread=1.0)

# Visualize clusters on UMAP
sc.pl.umap(adata, color='leiden')

# Color by gene expression
sc.pl.umap(adata, color=['leiden', 'CD3D', 'MS4A1', 'CD14'])

tSNE

# Compute tSNE (slower than UMAP)
sc.tl.tsne(adata, n_pcs=30, perplexity=30)

# Visualize
sc.pl.tsne(adata, color='leiden')

Complete Clustering Pipeline

import scanpy as sc

# Assumes preprocessed data
adata = sc.read_h5ad('preprocessed.h5ad')

# PCA
sc.tl.pca(adata, n_comps=50)

# Neighbors
sc.pp.neighbors(adata, n_neighbors=15, n_pcs=30)

# Cluster
sc.tl.leiden(adata, resolution=0.5)

# UMAP
sc.tl.umap(adata)

# Visualize
sc.pl.umap(adata, color='leiden')

Exploring Different Resolutions

# Try multiple resolutions
for res in [0.2, 0.5, 0.8, 1.0, 1.5]:
    sc.tl.leiden(adata, resolution=res, key_added=f'leiden_r{res}')
    n_clusters = adata.obs[f'leiden_r{res}'].nunique()
    print(f'Resolution {res}: {n_clusters} clusters')

# Compare on UMAP
sc.pl.umap(adata, color=['leiden_r0.2', 'leiden_r0.5', 'leiden_r1.0'], ncols=3)

PAGA (Trajectory Inference)

# Partition-based graph abstraction
sc.tl.paga(adata, groups='leiden')
sc.pl.paga(adata, color='leiden')

# Use PAGA for UMAP initialization
sc.tl.umap(adata, init_pos='paga')

Seurat (R)

Required Libraries

library(Seurat)
library(ggplot2)

PCA

# Run PCA
seurat_obj <- RunPCA(seurat_obj, features = VariableFeatures(seurat_obj), npcs = 50)

# Visualize PCA
DimPlot(seurat_obj, reduction = 'pca')
VizDimLoadings(seurat_obj, dims = 1:2, reduction = 'pca')

# Heatmaps of PC genes
DimHeatmap(seurat_obj, dims = 1:6, cells = 500, balanced = TRUE)

Determine Number of PCs

# Elbow plot
ElbowPlot(seurat_obj, ndims = 50)

# JackStraw (more rigorous but slow)
seurat_obj <- JackStraw(seurat_obj, num.replicate = 100)
seurat_obj <- ScoreJackStraw(seurat_obj, dims = 1:20)
JackStrawPlot(seurat_obj, dims = 1:20)

Find Neighbors

# Build KNN graph
seurat_obj <- FindNeighbors(seurat_obj, dims = 1:30)

Find Clusters

# Louvain clustering (default)
seurat_obj <- FindClusters(seurat_obj, resolution = 0.5)

# View cluster assignments
head(Idents(seurat_obj))
table(Idents(seurat_obj))

Exploring Different Resolutions

# Try multiple resolutions
seurat_obj <- FindClusters(seurat_obj, resolution = c(0.2, 0.5, 0.8, 1.0, 1.5))

# Results stored in metadata
head(seurat_obj@meta.data)

# Compare resolutions
library(clustree)
clustree(seurat_obj, prefix = 'RNA_snn_res.')

UMAP

# Run UMAP
seurat_obj <- RunUMAP(seurat_obj, dims = 1:30)

# Visualize
DimPlot(seurat_obj, reduction = 'umap', label = TRUE)

# Split by sample
DimPlot(seurat_obj, reduction = 'umap', split.by = 'sample')

tSNE

# Run tSNE
seurat_obj <- RunTSNE(seurat_obj, dims = 1:30)

# Visualize
DimPlot(seurat_obj, reduction = 'tsne')

Complete Clustering Pipeline

library(Seurat)

# Assumes preprocessed data
seurat_obj <- readRDS('preprocessed.rds')

# PCA
seurat_obj <- RunPCA(seurat_obj, npcs = 50, verbose = FALSE)

# Neighbors
seurat_obj <- FindNeighbors(seurat_obj, dims = 1:30)

# Cluster
seurat_obj <- FindClusters(seurat_obj, resolution = 0.5)

# UMAP
seurat_obj <- RunUMAP(seurat_obj, dims = 1:30)

# Visualize
DimPlot(seurat_obj, reduction = 'umap', label = TRUE)

Access Embeddings

# Get PCA coordinates
pca_coords <- Embeddings(seurat_obj, reduction = 'pca')

# Get UMAP coordinates
umap_coords <- Embeddings(seurat_obj, reduction = 'umap')

# Add to metadata for custom plotting
seurat_obj$UMAP_1 <- umap_coords[, 1]
seurat_obj$UMAP_2 <- umap_coords[, 2]

Parameter Reference

Method Comparison

sc.tl.pca()

RunPCA()

sc.pp.neighbors()

FindNeighbors()

sc.tl.leiden()

FindClusters()

sc.tl.umap()

RunUMAP()

sc.tl.tsne()

RunTSNE()

Related Skills

• preprocessing - Data must be preprocessed before clustering
• markers-annotation - Find markers for each cluster
• data-io - Save clustered results