scanpy API 参考（查阅材料）

import scanpy as sc
adata = sc.datasets.pbmc3k_processed()
sc.tl.paga(adata, groups='louvain')
sc.pl.paga(adata)

sc.pl.paga(adata, node_size_scale=10, edge_width_scale=2)

import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
sc.tl.paga(adata, groups="bulk_labels")
sc.pl.paga_compare(adata, basis="umap")

def my_vmin(values): returnnp.mean(values)

import scanpy as sc
adata = sc.datasets.pbmc3k_processed()
sc.pl.pca(adata)

sc.pl.pca(adata, color="louvain")

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

pp.pca

import scanpy as sc
adata = sc.datasets.pbmc3k_processed()

sc.pl.pca_loadings(adata, components = '1,2,3')

def my_vmin(values): returnnp.mean(values)

import scanpy as sc
adata = sc.datasets.pbmc3k_processed()
sc.pl.pca_overview(adata, color="louvain")

pp.pca

import scanpy as sc
adata = sc.datasets.pbmc3k_processed()
sc.pl.pca_variance_ratio(adata)

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

import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
sc.pl.rank_genes_groups(adata)

sc.pl.rank_genes_groups(adata, n_genes=10)

tl.rank_genes_groups

import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
sc.tl.rank_genes_groups(adata, 'bulk_labels', n_genes=adata.raw.shape[1])

sc.pl.rank_genes_groups_dotplot(adata,n_genes=2)

sc.pl.rank_genes_groups_dotplot(adata, n_genes=2, standard_scale='var')

sc.pl.rank_genes_groups_dotplot(
    adata,
    n_genes=4,
    values_to_plot="logfoldchanges", cmap='bwr',
    vmin=-4,
    vmax=4,
    min_logfoldchange=3,
    colorbar_title='log fold change'
)

sc.pl.rank_genes_groups_dotplot(
    adata,
    n_genes=-4,
    values_to_plot="logfoldchanges",
    cmap='bwr',
    vmin=-4,
    vmax=4,
    min_logfoldchange=3,
    colorbar_title='log fold change',
)

var_names = {'T-cell': ['CD3D', 'CD3E', 'IL32'],
              'B-cell': ['CD79A', 'CD79B', 'MS4A1'],
              'myeloid': ['CST3', 'LYZ'] }
sc.pl.rank_genes_groups_dotplot(
    adata,
    var_names=var_names,
    values_to_plot="logfoldchanges",
    cmap='bwr',
    vmin=-4,
    vmax=4,
    min_logfoldchange=3,
    colorbar_title='log fold change',
)

tl.rank_genes_groups

import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
sc.tl.rank_genes_groups(adata, 'bulk_labels')
sc.pl.rank_genes_groups_heatmap(adata)

sc.pl.rank_genes_groups_heatmap(adata, show_gene_labels=True)

sc.pl.rank_genes_groups_heatmap(adata, n_genes=5, show_gene_labels=True)

import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
sc.tl.rank_genes_groups(adata, 'bulk_labels', n_genes=adata.raw.shape[1])

sc.pl.rank_genes_groups_matrixplot(
    adata,
    n_genes=4,
    values_to_plot="logfoldchanges",
    cmap='bwr',
    vmin=-4,
    vmax=4,
    min_logfoldchange=3,
    colorbar_title='log fold change',
)

sc.pl.rank_genes_groups_matrixplot(
    adata,
    n_genes=-4,
    values_to_plot="logfoldchanges",
    cmap='bwr',
    vmin=-4,
    vmax=4,
    min_logfoldchange=3,
    colorbar_title='log fold change',
)

var_names = {"T-cell": ['CD3D', 'CD3E', 'IL32'],
              'B-cell': ['CD79A', 'CD79B', 'MS4A1'],
              'myeloid': ['CST3', 'LYZ'] }
sc.pl.rank_genes_groups_matrixplot(
    adata,
    var_names=var_names,
    values_to_plot="logfoldchanges",
    cmap='bwr',
    vmin=-4,
    vmax=4,
    min_logfoldchange=3,
    colorbar_title='log fold change',
)

import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
sc.tl.rank_genes_groups(adata, "bulk_labels")
sc.pl.rank_genes_groups_stacked_violin(adata, n_genes=4, min_logfoldchange=4, figsize=(8, 6))

import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
sc.tl.rank_genes_groups(adata, 'bulk_labels')
sc.pl.rank_genes_groups_tracksplot(adata)

import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
sc.tl.rank_genes_groups(adata, "bulk_labels")
sc.pl.rank_genes_groups_violin(adata, groups=["CD34+"], n_genes=5)

scrublet()

scrublet_simulate_doublets()

None

def my_vmin(values): returnnp.mean(values)

>>> import scanpy as sc
>>> adata = sc.datasets.visium_sge("Targeted_Visium_Human_Glioblastoma_Pan_Cancer")
FutureWarning: The function visium_sge is deprecated and will be removed in the future. Use :func:`squidpy.datasets.visium` instead.
    adata = sc.datasets.visium_sge("Targeted_Visium_Human_Glioblastoma_Pan_Cancer")
>>> sc.pp.calculate_qc_metrics(adata, inplace=True)
>>> sc.pl.spatial(adata, color="log1p_n_genes_by_counts")
FutureWarning: The function spatial is deprecated and will be removed in the future. Use :func:`squidpy.pl.spatial_scatter` instead.
    sc.pl.spatial(adata, color="log1p_n_genes_by_counts")

scanpy.datasets.visium_sge()

def my_vmin(values): returnnp.mean(values)

import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
sc.tl.tsne(adata)
sc.pl.tsne(adata, color='bulk_labels')

def my_vmin(values): returnnp.mean(values)

import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
sc.pl.umap(adata)

sc.pl.umap(adata, color="louvain")

sc.pl.umap(adata, color="HES4")

sc.pl.umap(adata, color=["HES4", "TNFRSF4"])

tl.umap

numpy.ndarray

scipy.sparse.{csr,csc}_{array,matrix}

numpy.ndarray

scipy.sparse.{csr,csc}_{array,matrix}

'pynndescent'

PyNNDescentTransformer

'rapids'

adata.uns['neighbors' | key_added]dict

>>> import scanpy as sc
>>> adata = sc.datasets.pbmc68k_reduced()
>>> # Basic usage
>>> sc.pp.neighbors(adata, 20, metric="cosine")
>>> # Provide your own transformer for more control and flexibility
>>> from sklearn.neighbors import KNeighborsTransformer
>>> transformer = KNeighborsTransformer(
...     n_neighbors=10, metric="manhattan", algorithm="kd_tree"
... )
>>> sc.pp.neighbors(adata, transformer=transformer)
>>> # now you can e.g. access the index: `transformer._tree`

sc.pp.filter_genes(adata, min_counts=1)         # only consider genes with more than 1 count
sc.pp.normalize_per_cell(                       # normalize with total UMI count per cell
     adata, key_n_counts='n_counts_all'
)
filter_result = sc.pp.filter_genes_dispersion(  # select highly-variable genes
    adata.X, flavor='cell_ranger', n_top_genes=n_top_genes, log=False
)
adata = adata[:, filter_result.gene_subset]     # subset the genes
sc.pp.normalize_per_cell(adata)                 # renormalize after filtering
if log: sc.pp.log1p(adata)                      # log transform: adata.X = log(adata.X + 1)
sc.pp.scale(adata)                              # scale to unit variance and shift to zero mean

numpy.ndarray

scipy.sparse.{csr,csc}_{array,matrix}

.obs['doublet_score']

.obs['predicted_doublet']

.uns['scrublet']['doublet_scores_sim']

.uns['scrublet']['doublet_parents']

.uns['scrublet']['parameters']

scrublet_simulate_doublets()

scrublet_score_distribution()

numpy.ndarray

scipy.sparse.{csr,csc}_{array,matrix}

AnnData

.obsm['scrublet']['doublet_parents']

.uns['scrublet']['parameters']

scrublet()

scrublet_score_distribution()

Self

DotPlot

>>> import scanpy as sc
>>> adata = sc.datasets.pbmc68k_reduced()
>>> markers = {"T-cell": "CD3D", "B-cell": "CD79A", "myeloid": "CST3"}
>>> dp = sc.pl.DotPlot(adata, markers, groupby="bulk_labels")
>>> dp.legend(colorbar_title="log(UMI counts + 1)").show()

dotplot()

rank_genes_groups_dotplot()

>>> import scanpy as sc
>>> adata = sc.datasets.pbmc68k_reduced()
>>> markers = ["C1QA", "PSAP", "CD79A", "CD79B", "CST3", "LYZ"]
>>> sc.pl.DotPlot(adata, markers, groupby="bulk_labels").show()

>>> markers = {"T-cell": "CD3D", "B-cell": "CD79A", "myeloid": "CST3"}
>>> sc.pl.DotPlot(adata, markers, groupby="bulk_labels").show()

DEFAULT_COLORMAP
DEFAULT_COLOR_LEGEND_TITLE
DEFAULT_COLOR_ON
DEFAULT_DOT_EDGECOLOR
DEFAULT_DOT_EDGELW
DEFAULT_DOT_MAX
DEFAULT_DOT_MIN
DEFAULT_LARGEST_DOT
DEFAULT_LEGENDS_WIDTH
DEFAULT_PLOT_X_PADDING
DEFAULT_PLOT_Y_PADDING
DEFAULT_SAVE_PREFIX
DEFAULT_SIZE_EXPONENT
DEFAULT_SIZE_LEGEND_TITLE
DEFAULT_SMALLEST_DOT

Self

DotPlot

>>> import scanpy as sc
>>> adata = sc.datasets.pbmc68k_reduced()
>>> markers = ['C1QA', 'PSAP', 'CD79A', 'CD79B', 'CST3', 'LYZ']

>>> sc.pl.DotPlot(adata, markers, groupby='bulk_labels') \
...     .style(cmap='RdBu_r', color_on='square').show()

>>> sc.pl.DotPlot(adata, markers, groupby='bulk_labels') \
...     .style(dot_edge_color='black', dot_edge_lw=1, grid=True) \
...     .show()

matrixplot()

rank_genes_groups_matrixplot()

import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
markers = ['C1QA', 'PSAP', 'CD79A', 'CD79B', 'CST3', 'LYZ']
sc.pl.MatrixPlot(adata, markers, groupby='bulk_labels').show()

markers = {'T-cell': 'CD3D', 'B-cell': 'CD79A', 'myeloid': 'CST3'}
sc.pl.MatrixPlot(adata, markers, groupby='bulk_labels').show()

DEFAULT_COLORMAP
DEFAULT_COLOR_LEGEND_TITLE
DEFAULT_EDGE_COLOR
DEFAULT_EDGE_LW
DEFAULT_SAVE_PREFIX

Self

MatrixPlot

import scanpy as sc

adata = sc.datasets.pbmc68k_reduced()
markers = ['C1QA', 'PSAP', 'CD79A', 'CD79B', 'CST3', 'LYZ']

(
    sc.pl.MatrixPlot(adata, markers, groupby='bulk_labels')
    .style(cmap='Blues', edge_color='none')
    .show()
)

stacked_violin()

violin()

>>> import scanpy as sc
>>> adata = sc.datasets.pbmc68k_reduced()
>>> markers = ["C1QA", "PSAP", "CD79A", "CD79B", "CST3", "LYZ"]
>>> sc.pl.StackedViolin(
...     adata, markers, groupby="bulk_labels", dendrogram=True
... )
<scanpy.plotting._stacked_violin.StackedViolin object at 0x...>

>>> markers = {"T-cell": "CD3D", "B-cell": "CD79A", "myeloid": "CST3"}
>>> sc.pl.StackedViolin(
...     adata, markers, groupby="bulk_labels", dendrogram=True
... )
<scanpy.plotting._stacked_violin.StackedViolin object at 0x...>

DEFAULT_COLORMAP
DEFAULT_COLOR_LEGEND_TITLE
DEFAULT_CUT
DEFAULT_DENSITY_NORM
DEFAULT_INNER
DEFAULT_JITTER
DEFAULT_JITTER_SIZE
DEFAULT_LINE_WIDTH
DEFAULT_PLOT_X_PADDING
DEFAULT_PLOT_YTICKLABELS
DEFAULT_PLOT_Y_PADDING
DEFAULT_ROW_PALETTE
DEFAULT_SAVE_PREFIX
DEFAULT_STRIPPLOT
DEFAULT_YLIM

Self

StackedViolin

>>> import scanpy as sc
>>> adata = sc.datasets.pbmc68k_reduced()
>>> markers = ['C1QA', 'PSAP', 'CD79A', 'CD79B', 'CST3', 'LYZ']

>>> sc.pl.StackedViolin(adata, markers, groupby='bulk_labels') \
...     .style(row_palette='Blues', linewidth=0).show()