scanpy分析单细胞数据

scanpy和seurat是最常用的分析的单细胞的工具，seurat基于R，而scanpy基于python。
linux下用pip安装scanpy

pip install scanpy

下载测试数据

mkdir data
wget http://cf.10xgenomics.com/samples/cell-exp/1.1.0/pbmc3k/pbmc3k_filtered_gene_bc_matrices.tar.gz -O data/pbmc3k_filtered_gene_bc_matrices.tar.gz
cd data
tar -xzf pbmc3k_filtered_gene_bc_matrices.tar.gz
mkdir write

jupyter下面运行：

import numpy as np
import pandas as pd
import scanpy as sc

sc.settings.verbosity = 3             # verbosity: errors (0), warnings (1), info (2), hints (3)
sc.logging.print_header()
sc.settings.set_figure_params(dpi=80, facecolor='white')

results_file = 'write/pbmc3k.h5ad'  # the file that will store the analysis results

adata=sc.read_10x_mtx('data/filtered_gene_bc_matrices/hg19', var_names='gene_symbols', cache=True)    #读取单细胞测序文件

质控：过滤基因和细胞

sc.pp.filter_cells(adata, min_genes=200)
sc.pp.filter_genes(adata, min_cells=3)

adata.var['mt'] = adata.var_names.str.startswith('MT-')  # annotate the group of mitochondrial genes as 'mt'
sc.pp.calculate_qc_metrics(adata, qc_vars=['mt'], percent_top=None, log1p=False, inplace=True)

sc.pl.violin(adata, ['n_genes_by_counts', 'total_counts', 'pct_counts_mt'],
             jitter=0.4, multi_panel=True)

sc.pl.scatter(adata, x='total_counts', y='pct_counts_mt')
sc.pl.scatter(adata, x='total_counts', y='n_genes_by_counts')

adata = adata[adata.obs.n_genes_by_counts < 2500, :]
adata = adata[adata.obs.pct_counts_mt < 5, :]

sc.pp.normalize_total(adata, target_sum=1e4)

sc.pp.log1p(adata)

计算高度变化的基因

sc.pp.highly_variable_genes(adata, min_mean=0.0125, max_mean=3, min_disp=0.5)

sc.pl.highly_variable_genes(adata)

adata.raw = adata
adata = adata[:, adata.var.highly_variable]
sc.pp.regress_out(adata, ['total_counts', 'pct_counts_mt'])
sc.pp.scale(adata, max_value=10)

PCA主成分分析

sc.tl.pca(adata, svd_solver='arpack')

sc.pl.pca(adata, color='CST3')

选择合适的前几个主成分

sc.pl.pca_variance_ratio(adata, log=True)

adata.write(results_file)

计算邻近图

sc.pp.neighbors(adata, n_neighbors=10, n_pcs=40)

sc.tl.umap(adata)

sc.pl.umap(adata, color=['CST3', 'NKG7', 'PPBP'])

使用标准化的数据进行可视化

sc.pl.umap(adata, color=['CST3', 'NKG7', 'PPBP'], use_raw=False)

使用 Leiden graph-clustering method进行聚类
linux安装 leiden algorithm

conda install -c conda-forge leidenalg
#或
pip3 install leidenalg

sc.tl.leiden(adata)

sc.pl.umap(adata, color=['leiden', 'CST3', 'NKG7'])