随着单细胞技术的成熟，测序成本的降低，单细胞的数据量和样本量也日益增长。我们知道单细胞转录组的一个主要应用就是解释细胞的异质性，那么，不同器官，不同测序平台，不同物种之间的单细胞数据何如整合分析呢？特别是在单细胞的数据维度这么高的前提下，显然传统的基于回归的方法已经不适用了。于是出现了一批单细胞整合分析的工具，它们大多数是在R生态条件下的。如：
在我们理解单细胞数据的时候一张cell X gene 的大表不能离开我们的脑海。
adata.to_df()
Out[24]:
RP11-34P13.3 FAM138A ... AC213203.1 FAM231B
AAACCCAAGCGTATGG-1 0.0 0.0 ... 0.0 0.0
AAACCCAGTCCTACAA-1 0.0 0.0 ... 0.0 0.0
AAACCCATCACCTCAC-1 0.0 0.0 ... 0.0 0.0
AAACGCTAGGGCATGT-1 0.0 0.0 ... 0.0 0.0
AAACGCTGTAGGTACG-1 0.0 0.0 ... 0.0 0.0
... ... ... ... ...
TTTGTTGCAGGTACGA-1 0.0 0.0 ... 0.0 0.0
TTTGTTGCAGTCTCTC-1 0.0 0.0 ... 0.0 0.0
TTTGTTGGTAATTAGG-1 0.0 0.0 ... 0.0 0.0
TTTGTTGTCCTTGGAA-1 0.0 0.0 ... 0.0 0.0
TTTGTTGTCGCACGAC-1 0.0 0.0 ... 0.0 0.0
当我们有多个样本的时候就是有多张这样的表，那让我们自己手动来整合这两张表的话，我们会怎么做呢？
肯定是行列分别对齐把它们拼在一起啊，就像拼积木一样的，但是这样的结果就是：
两个样本在图谱上完全的分开来了。我们不同平台的样本，相同的细胞类型应该是在一起的啊。于是我们开始思考如何完成这样的整合。
seurat提供了一套解决方案，就是在数据集中构建锚点，将不同数据集中相似的细胞锚在一起。
那么如何锚，选择哪些特征来锚定，又开发出不同的算法。不管算法如何，首先我们看看这种锚定可以为我们带来什么？相同的细胞类型mapping在一起，一个自然的作用就是用来mapping细胞类型未知的数据。
所以在scanpy中也如seurat一样在多样本分析中，分别给出reference的方法和整合的方法。目前在scanpy中分别是ingest和BBKNN（Batch balanced kNN），当然整合也是可以用来做reference的。scanpy.external.pp.mnn_correct应该也是可以用的。
先来看ingest，通过投射到参考数据上的PCA(或备用模型)上，将一个adata的嵌入和注释与一个参考数据集adata_ref集成在一起。该函数使用knn分类器来映射标签，使用UMAP来映射嵌入。
再来看看bbknn是一个快速和直观的批处理效果去除工具，可以直接在scanpy工作流中使用。它是scanpy.api.pp.neighbors()的替代方法，这两个函数都创建了一个邻居图，以便后续在集群、伪时间和UMAP可视化中使用。标准方法首先确定整个数据结构中每个单元的k个最近邻，然后将候选单元转换为指数相关的连接，然后作为进一步分析的基础。
那么我们就来看一下在scanpy的实现吧。
import scanpy as sc
import pandas as pd
import seaborn as sns
import sklearn
import sys
import scipy
import bbknn
sc.settings.verbosity = 1 # verbosity: errors (0), warnings (1), info (2), hints (3)
sc.logging.print_versions()
sc.settings.set_figure_params(dpi=80, frameon=False, figsize=(3, 3))
scanpy==1.4.5.1 anndata==0.7.1 umap==0.3.10 numpy==1.16.5 scipy==1.3.1 pandas==0.25.1 scikit-learn==0.21.3 statsmodels==0.10.1 python-igraph==0.8.0
ingest 注释
adata_ref = sc.datasets.pbmc3k_processed() # this is an earlier version of the dataset from the pbmc3k tutorial
adata_ref
AnnData object with n_obs × n_vars = 2638 × 1838
obs: 'n_genes', 'percent_mito', 'n_counts', 'louvain'
var: 'n_cells'
uns: 'draw_graph', 'louvain', 'louvain_colors', 'neighbors', 'pca', 'rank_genes_groups'
obsm: 'X_pca', 'X_tsne', 'X_umap', 'X_draw_graph_fr'
varm: 'PCs'
我们一次看看以下参考数据集都有哪些内容：
adata_ref.obs
Out[9]:
n_genes percent_mito n_counts louvain
index
AAACATACAACCAC-1 781 0.030178 2419.0 CD4 T cells
AAACATTGAGCTAC-1 1352 0.037936 4903.0 B cells
AAACATTGATCAGC-1 1131 0.008897 3147.0 CD4 T cells
AAACCGTGCTTCCG-1 960 0.017431 2639.0 CD14+ Monocytes
AAACCGTGTATGCG-1 522 0.012245 980.0 NK cells
... ... ... ...
TTTCGAACTCTCAT-1 1155 0.021104 3459.0 CD14+ Monocytes
TTTCTACTGAGGCA-1 1227 0.009294 3443.0 B cells
TTTCTACTTCCTCG-1 622 0.021971 1684.0 B cells
TTTGCATGAGAGGC-1 454 0.020548 1022.0 B cells
TTTGCATGCCTCAC-1 724 0.008065 1984.0 CD4 T cells
[2638 rows x 4 columns]
adata_ref.var
Out[10]:
n_cells
index
TNFRSF4 155
CPSF3L 202
ATAD3C 9
C1orf86 501
RER1 608
...
ICOSLG 34
SUMO3 570
SLC19A1 31
S100B 94
PRMT2 588
[1838 rows x 1 columns]
adata_ref.uns['louvain_colors']
Out[14]:
array(['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b',
'#e377c2', '#bcbd22'], dtype='<U7')
adata_ref.obsm
Out[16]: AxisArrays with keys: X_pca, X_tsne, X_umap, X_draw_graph_fr
adata_ref.obsm['X_umap']
Out[17]:
array([[ 1.35285574, 2.26612719],
[-0.47802448, 7.87730423],
[ 2.16588875, -0.24481226],
...,
[ 0.34670979, 8.34967798],
[ 0.19864146, 9.56698797],
[ 2.62803322, 0.36722543]])
有没有再次理解AnnData 这个对象的数据结构呢？
可以看到在这个数据集中降维聚类都是做过的，我们可以画个图看看：
sc.pl.umap(adata_ref, color='louvain')
接下来我们看看要预测的数据集是怎样的。
adata = sc.datasets.pbmc68k_reduced()
adata
AnnData object with n_obs × n_vars = 700 × 765
obs: 'bulk_labels', 'n_genes', 'percent_mito', 'n_counts', 'S_score', 'G2M_score', 'phase', 'louvain'
var: 'n_counts', 'means', 'dispersions', 'dispersions_norm', 'highly_variable'
uns: 'bulk_labels_colors', 'louvain', 'louvain_colors', 'neighbors', 'pca', 'rank_genes_groups'
obsm: 'X_pca', 'X_umap'
varm: 'PCs'
可见它也是降维聚类过的了。
sc.pl.umap(adata, color='louvain')
这个数据集并没有得到细胞类型的定义。
构建注释数据结构：
var_names = adata_ref.var_names.intersection(adata.var_names) # 取交集
adata_ref = adata_ref[:, var_names]
adata = adata[:, var_names]
sc.pp.pca(adata_ref)
sc.pp.neighbors(adata_ref)
sc.tl.umap(adata_ref)
sc.tl.leiden(adata_ref)# 新的聚类方法
sc.pl.umap(adata_ref, color=['louvain','leiden'])
adata_ref
AnnData object with n_obs × n_vars = 2638 × 208
obs: 'n_genes', 'percent_mito', 'n_counts', 'louvain', 'leiden'
var: 'n_cells'
uns: 'draw_graph', 'louvain', 'louvain_colors', 'neighbors', 'pca', 'rank_genes_groups', 'umap', 'leiden', 'leiden_colors'
obsm: 'X_pca', 'X_tsne', 'X_umap', 'X_draw_graph_fr'
varm: 'PCs'
sc.pp.pca(adata)
sc.pp.neighbors(adata)
sc.tl.umap(adata)
sc.tl.leiden(adata)
sc.pl.umap(adata, color=['louvain','leiden'])
adata
AnnData object with n_obs × n_vars = 700 × 208
obs: 'bulk_labels', 'n_genes', 'percent_mito', 'n_counts', 'S_score', 'G2M_score', 'phase', 'louvain', 'leiden'
var: 'n_counts', 'means', 'dispersions', 'dispersions_norm', 'highly_variable'
uns: 'bulk_labels_colors', 'louvain', 'louvain_colors', 'neighbors', 'pca', 'rank_genes_groups', 'umap', 'leiden', 'leiden_colors'
obsm: 'X_pca', 'X_umap'
varm: 'PCs'
用ingest来做细胞注释吧。
sc.tl.ingest(adata, adata_ref, obs='louvain')
adata.uns['louvain_colors'] = adata_ref.uns['louvain_colors'] # fix colors
我们来看看sc.tl.ingest的帮助文档：
Help on function ingest in module scanpy.tools._ingest:
ingest(adata: anndata._core.anndata.AnnData, adata_ref: anndata._core.anndata.AnnData, obs: Union[str, Iterable[str], NoneType] = None, embedding_method: Union[str, Iterable[str]] = ('umap', 'pca'), labeling_method: str = 'knn', inplace: bool = True, **kwargs)
Map labels and embeddings from reference data to new data.
:tutorial:`integrating-data-using-ingest`
Integrates embeddings and annotations of an `adata` with a reference dataset
`adata_ref` through projecting on a PCA (or alternate
model) that has been fitted on the reference data. The function uses a knn
classifier for mapping labels and the UMAP package [McInnes18]_ for mapping
the embeddings.
.. note::
We refer to this *asymmetric* dataset integration as *ingesting*
annotations from reference data to new data. This is different from
learning a joint representation that integrates both datasets in an
unbiased way, as CCA (e.g. in Seurat) or a conditional VAE (e.g. in
scVI) would do.
You need to run :func:`~scanpy.pp.neighbors` on `adata_ref` before
passing it.
Parameters
----------
adata
The annotated data matrix of shape `n_obs` × `n_vars`. Rows correspond
to cells and columns to genes. This is the dataset without labels and
embeddings.
adata_ref
The annotated data matrix of shape `n_obs` × `n_vars`. Rows correspond
to cells and columns to genes.
Variables (`n_vars` and `var_names`) of `adata_ref` should be the same
as in `adata`.
This is the dataset with labels and embeddings
which need to be mapped to `adata`.
obs
Labels' keys in `adata_ref.obs` which need to be mapped to `adata.obs`
(inferred for observation of `adata`).
embedding_method
Embeddings in `adata_ref` which need to be mapped to `adata`.
The only supported values are 'umap' and 'pca'.
labeling_method
The method to map labels in `adata_ref.obs` to `adata.obs`.
The only supported value is 'knn'.
inplace
Only works if `return_joint=False`.
Add labels and embeddings to the passed `adata` (if `True`)
or return a copy of `adata` with mapped embeddings and labels.
Returns
-------
* if `inplace=False` returns a copy of `adata`
with mapped embeddings and labels in `obsm` and `obs` correspondingly
* if `inplace=True` returns `None` and updates `adata.obsm` and `adata.obs`
with mapped embeddings and labels
Example
-------
Call sequence:
import scanpy as sc
sc.pp.neighbors(adata_ref)
sc.tl.umap(adata_ref)
sc.tl.ingest(adata, adata_ref, obs='cell_type')
.. _ingest PBMC tutorial: https://scanpy-tutorials.readthedocs.io/en/latest/integrating-pbmcs-using-ingest.html
.. _ingest Pancreas tutorial: https://scanpy-tutorials.readthedocs.io/en/latest/integrating-pancreas-using-ingest.html
通过比较‘bulk_label’注释和‘louvain’注释，我们发现数据被合理地映射，只有树突细胞的注释似乎是含糊不清的，在adata中可能已经是模糊的了。我们来对adata做进一步的处理。
adata_concat = adata_ref.concatenate(adata, batch_categories=['ref', 'new'])
adata_concat.obs.louvain = adata_concat.obs.louvain.astype('category')
adata_concat.obs.louvain.cat.reorder_categories(adata_ref.obs.louvain.cat.categories, inplace=True) # fix category ordering
adata_concat.uns['louvain_colors'] = adata_ref.uns['louvain_colors'] # fix category colors
adata_concat
sc.pl.umap(adata_concat, color=['batch', 'louvain'])
AnnData object with n_obs × n_vars = 3338 × 208
obs: 'G2M_score', 'S_score', 'batch', 'bulk_labels', 'leiden', 'louvain', 'n_counts', 'n_genes', 'percent_mito', 'phase'
var: 'n_cells-ref', 'n_counts-new', 'means-new', 'dispersions-new', 'dispersions_norm-new', 'highly_variable-new'
obsm: 'X_pca', 'X_umap'
虽然在单核细胞和树突状细胞簇中似乎存在一些批处理效应，但在其他方面，新数据被绘制得相对均匀。
巨核细胞只存在于adata_ref中，没有来自adata映射的单元格。如果交换参考数据和查询数据，巨核细胞不再作为单独的集群出现。这是一个极端的情况，因为参考数据非常小;但是，人们应该始终质疑参考数据是否包含足够的生物变异，以便有意义地容纳查询数据。
使用BBKNN整合
sc.tl.pca(adata_concat)
sc.external.pp.bbknn(adata_concat, batch_key='batch') # running bbknn 1.3.6
sc.tl.umap(adata_concat)
sc.pl.umap(adata_concat, color=['batch', 'louvain'])
adata_concat
Out[45]:
AnnData object with n_obs × n_vars = 3338 × 208
obs: 'G2M_score', 'S_score', 'batch', 'bulk_labels', 'leiden', 'louvain', 'n_counts', 'n_genes', 'percent_mito', 'phase'
var: 'n_cells-ref', 'n_counts-new', 'means-new', 'dispersions-new', 'dispersions_norm-new', 'highly_variable-new'
uns: 'batch_colors', 'louvain_colors', 'pca', 'neighbors', 'umap'
obsm: 'X_pca', 'X_umap'
varm: 'PCs'
BBKNN并不维持巨核细胞簇。然而，它似乎更均匀地混合细胞。
一个例子使用BBKNN整合数据的例子
以下数据已在scGen论文[Lotfollahi19]中使用。点击pancreas下载数据。
它包含了来自4个不同研究(Segerstolpe16, Baron16, Wang16, Muraro16)的人类胰腺数据，这些数据在单细胞数据集集成的开创性论文(Butler18, Haghverdi18)中被使用过，并在此后多次被使用。
h5ad = 'E:\\learnscanpy\\data\\objects-pancreas\\pancreas.h5ad'
adata_all = sc.read_h5ad(h5ad)
adata_all
AnnData object with n_obs × n_vars = 14693 × 2448
obs: 'celltype', 'sample', 'n_genes', 'batch', 'n_counts', 'louvain'
var: 'n_cells-0', 'n_cells-1', 'n_cells-2', 'n_cells-3'
uns: 'celltype_colors', 'louvain', 'neighbors', 'pca', 'sample_colors'
obsm: 'X_pca', 'X_umap'
varm: 'PCs'
counts = adata_all.obs.celltype.value_counts()
counts
Out[173]:
alpha 4214
beta 3354
ductal 1804
acinar 1368
not applicable 1154
delta 917
gamma 571
endothelial 289
activated_stellate 284
dropped 178
quiescent_stellate 173
mesenchymal 80
macrophage 55
PSC 54
unclassified endocrine 41
co-expression 39
mast 32
epsilon 28
mesenchyme 27
schwann 13
t_cell 7
MHC class II 5
unclear 4
unclassified 2
Name: celltype, dtype: int64
adata_all.obs
Out[171]:
celltype sample ... n_counts louvain
index ...
human1_lib1.final_cell_0001-0 acinar Baron ... 2.241100e+04 2
human1_lib1.final_cell_0002-0 acinar Baron ... 2.794900e+04 2
human1_lib1.final_cell_0003-0 acinar Baron ... 1.689200e+04 2
human1_lib1.final_cell_0004-0 acinar Baron ... 1.929900e+04 2
human1_lib1.final_cell_0005-0 acinar Baron ... 1.506700e+04 2
... ... ... ... ...
reads.29499-3 ductal Wang ... 1.056558e+06 10
reads.29500-3 ductal Wang ... 9.926309e+05 10
reads.29501-3 beta Wang ... 1.751338e+06 10
reads.29502-3 dropped Wang ... 2.163764e+06 10
reads.29503-3 beta Wang ... 2.038979e+06 10
[14693 rows x 6 columns]
可以看出这个数据集已经降维聚类好了，所以我们可以可视化一下：
sc.pl.umap(adata_all,color=['sample', 'celltype','louvain'])
样本之间的批次很严重啊。
去掉细胞数较小的小群，
minority_classes = counts.index[-5:].tolist() # get the minority classes
# ['schwann', 't_cell', 'MHC class II', 'unclear', 'unclassified']
adata_all = adata_all[ # actually subset
~adata_all.obs.celltype.isin(minority_classes)]
adata_all.obs.celltype.cat.reorder_categories( # reorder according to abundance
counts.index[:-5].tolist(), inplace=True)
adata_all.obs.celltype.value_counts()
Out[182]:
alpha 4214
beta 3354
ductal 1804
acinar 1368
not applicable 1154
delta 917
gamma 571
endothelial 289
activated_stellate 284
dropped 178
quiescent_stellate 173
mesenchymal 80
macrophage 55
PSC 54
unclassified endocrine 41
co-expression 39
mast 32
epsilon 28
mesenchyme 27
进行pca降维和umap降维：
sc.pp.pca(adata_all)
sc.pp.neighbors(adata_all)
sc.tl.umap(adata_all)
sc.pl.umap(adata_all, color=['batch', 'celltype'], palette=sc.pl.palettes.vega_20_scanpy)
下面我们使用BBKNN来整合数据：
sc.external.pp.bbknn(adata_all, batch_key='batch')
sc.tl.umap(adata_all)
adata_all
sc.pl.umap(adata_all, color=['sample','batch', 'celltype'])
果然要比原始的数据好多了。但是改变的是什么？
AnnData object with n_obs × n_vars = 14662 × 2448
obs: 'celltype', 'sample', 'n_genes', 'batch', 'n_counts', 'louvain'
var: 'n_cells-0', 'n_cells-1', 'n_cells-2', 'n_cells-3'
uns: 'celltype_colors', 'louvain', 'neighbors', 'pca', 'sample_colors', 'louvain_colors', 'umap', 'batch_colors'
obsm: 'X_pca', 'X_umap'
varm: 'PCs'
如果想对其中某个样本进行单独的注释，可以用上面提到的ingest。选择一个参考批次来训练模型和建立邻域图(这里是一个PCA)，并分离出所有其他批次。
adata_ref = adata_all[adata_all.obs.batch == '0']
adata_ref
Out[191]:
View of AnnData object with n_obs × n_vars = 8549 × 2448
obs: 'celltype', 'sample', 'n_genes', 'batch', 'n_counts', 'louvain'
var: 'n_cells-0', 'n_cells-1', 'n_cells-2', 'n_cells-3'
uns: 'celltype_colors', 'louvain', 'neighbors', 'pca', 'sample_colors', 'louvain_colors', 'umap', 'batch_colors'
obsm: 'X_pca', 'X_umap'
varm: 'PCs'
sc.pp.pca(adata_ref)
sc.pp.neighbors(adata_ref)
sc.tl.umap(adata_ref)
adata_ref
Out[197]:
AnnData object with n_obs × n_vars = 8549 × 2448
obs: 'celltype', 'sample', 'n_genes', 'batch', 'n_counts', 'louvain'
var: 'n_cells-0', 'n_cells-1', 'n_cells-2', 'n_cells-3'
uns: 'celltype_colors', 'louvain', 'neighbors', 'pca', 'sample_colors', 'louvain_colors', 'umap', 'batch_colors'
obsm: 'X_pca', 'X_umap'
varm: 'PCs'
sc.pl.umap(adata_ref, color='celltype')
选取数据集用ingest于adata_ref进行mapping：
adatas = [adata_all[adata_all.obs.batch == i].copy() for i in ['1', '2', '3']]
sc.settings.verbosity = 2 # a bit more logging
for iadata, adata in enumerate(adatas):
print(f'... integrating batch {iadata+1}')
adata.obs['celltype_orig'] = adata.obs.celltype # save the original cell type
sc.tl.ingest(adata, adata_ref, obs='celltype')
integrating batch 1
running ingest
finished (0:00:08)
integrating batch 2
running ingest
finished (0:00:06)
integrating batch 3
running ingest
finished (0:00:03)
adata_concat = adata_ref.concatenate(adatas)
adata_concat
Out[200]:
AnnData object with n_obs × n_vars = 14662 × 2448
obs: 'batch', 'celltype', 'celltype_orig', 'louvain', 'n_counts', 'n_genes', 'sample'
var: 'n_cells-0', 'n_cells-1', 'n_cells-2', 'n_cells-3'
obsm: 'X_pca', 'X_umap'
adata_concat.obs.celltype = adata_concat.obs.celltype.astype('category')
adata_concat.obs.celltype.cat.reorder_categories(adata_ref.obs.celltype.cat.categories, inplace=True) # fix category ordering
adata_concat.uns['celltype_colors'] = adata_ref.uns['celltype_colors'] # fix category coloring
sc.pl.umap(adata_concat, color=['celltype_orig','batch', 'celltype'])
与BBKNN的结果相比，这是以一种更加明显的方式保持分群。如果已经观察到一个想要的连续结构(例如在造血数据集中)，摄取允许容易地维持这个结构。
一致性评估
adata_query = adata_concat[adata_concat.obs.batch.isin(['1', '2', '3'])]
View of AnnData object with n_obs × n_vars = 6113 × 2448
obs: 'batch', 'celltype', 'celltype_orig', 'louvain', 'n_counts', 'n_genes', 'sample'
var: 'n_cells-0', 'n_cells-1', 'n_cells-2', 'n_cells-3'
uns: 'celltype_colors', 'celltype_orig_colors', 'batch_colors'
obsm: 'X_pca', 'X_umap'
sc.pl.umap(
adata_query, color=['batch', 'celltype', 'celltype_orig'], wspace=0.4)
这个结果依然不能很好的反映一致性，让我们首先关注与参考保守的细胞类型，以简化混淆矩阵的reads。
obs_query = adata_query.obs
conserved_categories = obs_query.celltype.cat.categories.intersection(obs_query.celltype_orig.cat.categories) # intersected categories
obs_query_conserved = obs_query.loc[obs_query.celltype.isin(conserved_categories) & obs_query.celltype_orig.isin(conserved_categories)] # intersect categories
obs_query_conserved.celltype.cat.remove_unused_categories(inplace=True) # remove unused categoriyes
obs_query_conserved.celltype_orig.cat.remove_unused_categories(inplace=True) # remove unused categoriyes
obs_query_conserved.celltype_orig.cat.reorder_categories(obs_query_conserved.celltype.cat.categories, inplace=True) # fix category ordering
obs_query_conserved
Out[214]:
batch celltype celltype_orig ... n_counts n_genes sample
D28.1_1-1-1 1 alpha alpha ... 2.322583e+04 5448 Muraro
D28.1_13-1-1 1 ductal ductal ... 2.334263e+04 5911 Muraro
D28.1_15-1-1 1 alpha alpha ... 2.713471e+04 5918 Muraro
D28.1_17-1-1 1 alpha alpha ... 1.581207e+04 4522 Muraro
D28.1_2-1-1 1 endothelial endothelial ... 3.173151e+04 6464 Muraro
... ... ... ... ... ... ...
reads.29498-3-3 3 ductal ductal ... 1.362606e+06 19950 Wang
reads.29499-3-3 3 ductal ductal ... 1.056558e+06 19950 Wang
reads.29500-3-3 3 ductal ductal ... 9.926309e+05 19950 Wang
reads.29501-3-3 3 beta beta ... 1.751338e+06 19950 Wang
reads.29503-3-3 3 beta beta ... 2.038979e+06 19950 Wang
pd.crosstab(obs_query_conserved.celltype, obs_query_conserved.celltype_orig)
Out[215]:
celltype_orig alpha beta ductal acinar delta gamma endothelial mast
celltype
alpha 1819 3 7 0 1 20 0 5
beta 49 803 3 1 10 26 0 0
ductal 8 5 693 263 0 0 0 0
acinar 1 3 2 145 0 3 0 0
delta 5 4 0 0 305 73 0 0
gamma 1 5 0 0 0 194 0 0
endothelial 2 0 0 0 0 0 36 0
mast 0 0 1 0 0 0 0 2
总的来说，保守的细胞类型也如预期的那样被映射。主要的例外是原始注释中出现的一些腺泡细胞。然而，已经观察到参考数据同时具有腺泡和导管细胞，这就解释了差异，并指出了初始注释中潜在的不一致性。
现在让我们继续看看所有的细胞类型。
pd.crosstab(adata_query.obs.celltype, adata_query.obs.celltype_orig)
Out[216]:
celltype_orig PSC acinar ... not applicable unclassified endocrine
celltype ...
alpha 0 0 ... 304 11
beta 0 1 ... 522 24
ductal 0 263 ... 106 1
acinar 0 145 ... 86 0
delta 0 0 ... 95 5
gamma 0 0 ... 14 0
endothelial 1 0 ... 7 0
activated_stellate 49 1 ... 17 0
quiescent_stellate 4 0 ... 1 0
macrophage 0 0 ... 1 0
mast 0 0 ... 1 0
[11 rows x 16 columns]
我们观察到PSC(胰腺星状细胞)细胞实际上只是不一致地注释并正确地映射到“激活的星状细胞”上。
此外，很高兴看到“间充质”和“间充质”细胞都属于同一类别。但是，这个类别又是“activated_stellate”，而且可能是错误的。这就是我们说的，算法只能接近真相，而不能定义真相。
可视化分布的批次
通常，批量对应的是想要比较的实验。Scanpy提供了方便的可视化可能性，主要有
- a density plot
- a partial visualization of a subset of categories/groups in an emnbedding
sc.tl.embedding_density(adata_concat, groupby='batch')
sc.pl.embedding_density(adata_concat, groupby='batch')
for batch in ['1', '2', '3']:
sc.pl.umap(adata_concat, color='batch', groups=[batch])
BBKNN: fast batch alignment of single cell transcriptomes
integrating-data-using-ingest
