3  SingleCellExperiment

该数据结构实际上是从 SummarizedExperiment 继承而来。

SingleCellExperiment 如 Figure 3.1 所示。

Figure 3.1: `SingleCellExperiment `的结构概述：assays的每一行对应于 rowData（粉色阴影）的一行，而assays的每一列对应于 colData 和 reducedDims（黄色阴影）的一行

3.1 表达矩阵（raw/transformed counts）

要构造一个SingleCellExperiment对象，我们只需要导入assays ( Figure 3.1 ,蓝色框 )，其中行对应于特征（基因），列对应于样本（细胞）。下载：counts_Calero_20160113.tsv。

3.1.1 assays

Code 
library(data.table)
library(dtplyr)
library(stringr)
df <- fread("data/SingleCellExperiment/counts_Calero_20160113.tsv")

df |> 
  dplyr::pull(GeneID) |>  
  str_sub(start = 1,end = 7) |>   
  table()
#> 
#> CBFB-MY ENSMUSG ERCC-00   SIRV1   SIRV2   SIRV3   SIRV4   SIRV5   SIRV6   SIRV7 
#>       1   46603      92       1       1       1       1       1       1       1

外源RNA对照联盟 （External RNA Controls Consortium，ERCC） 定量质控

  1. ERCC RNA Spike-In Mix（Mix1）：适用于绝对定量实验，评估表达水平准确性

  2. ERCC ExFold（Mix1+Mix2）：专为差异表达分析设计，评估倍数变化准确性（Mix1 和 Mix2 形成已知的倍数关系）

erccdashboard (R 包)https://bioconductor.org/packages//release/bioc/html/erccdashboard.html

Lexogen 公司：SIRVs (Spike-in RNA Variant Control Mixes) 可变剪切质控

Code 
# 分离出spike-in RNA
df_spikein <- df[str_detect(df$GeneID,pattern = "^ERCC-"),]

# 只考虑内源性基因
df_endogenous<- df[str_detect(df$GeneID,pattern = "^ENSMUSG"),]

# 分离基因长度
gene_length <- df_endogenous$Length


# geneID -->行标识符
df_endogenous <- df_endogenous |> tibble::column_to_rownames(var = "GeneID") 


# 计数矩阵
counts<- df_endogenous |> dplyr::select(-Length) |>  as.matrix()
dim(counts)
#> [1] 46603    96


# 
# fwrite(df_endogenous, file = "data/SingleCellExperiment/df_endogenous.csv", 
#        row.names = T)

3.1.2 添加assays

使用函数 SingleCellExperiment() 以命名列表的形式提供数据，其中列表的每个对象都是一个矩阵。

Code 
library(SingleCellExperiment)
sce <- SingleCellExperiment(assays = list(counts = counts))
sce
#> class: SingleCellExperiment 
#> dim: 46603 96 
#> metadata(0):
#> assays(1): counts
#> rownames(46603): ENSMUSG00000102693 ENSMUSG00000064842 ...
#>   ENSMUSG00000096730 ENSMUSG00000095742
#> rowData names(0):
#> colnames(96): SLX-9555.N701_S502.C89V9ANXX.s_1.r_1
#>   SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 ...
#>   SLX-9555.N712_S508.C89V9ANXX.s_1.r_1
#>   SLX-9555.N712_S517.C89V9ANXX.s_1.r_1
#> colData names(0):
#> reducedDimNames(0):
#> mainExpName: NULL
#> altExpNames(0):

3.1.2.1 标准化变换

Code 
sce <- scuttle::logNormCounts(sce) #对数变换标准化表达矩阵
sce    #  assays 多了一个  "logcounts"
#> class: SingleCellExperiment 
#> dim: 46603 96 
#> metadata(0):
#> assays(2): counts logcounts
#> rownames(46603): ENSMUSG00000102693 ENSMUSG00000064842 ...
#>   ENSMUSG00000096730 ENSMUSG00000095742
#> rowData names(0):
#> colnames(96): SLX-9555.N701_S502.C89V9ANXX.s_1.r_1
#>   SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 ...
#>   SLX-9555.N712_S508.C89V9ANXX.s_1.r_1
#>   SLX-9555.N712_S517.C89V9ANXX.s_1.r_1
#> colData names(1): sizeFactor
#> reducedDimNames(0):
#> mainExpName: NULL
#> altExpNames(0):
dim(logcounts(sce))
#> [1] 46603    96

3.1.2.2 线性变换

Code 
counts_100 <- counts(sce) + 100
assay(sce, "counts_100") <- counts_100 
assays(sce) 
#> List of length 3
#> names(3): counts logcounts counts_100

3.1.2.3 访问和切片

Code 
#访问计数矩阵
assayNames(sce)
#> [1] "counts"     "logcounts"  "counts_100"
mat2 <- assay(sce, "counts")  #通用
mat3 <- counts(sce)           #特殊名称 counts  
log_mat <- logcounts(sce)

names(assays(sce))
#> [1] "counts"     "logcounts"  "counts_100"
# 切片
assays(sce) <- assays(sce)[1]
assayNames(sce)
#> [1] "counts"

3.2 列数据（colData）

为了进一步构造对象SingleCellExperiment，需要添加列数据colData注释细胞或样本，该对象DataFrame中的行对应于细胞，列对应于样本数据字段，例如原产地批次batch of origin、处理条件treatment condition等（ Figure 3.1 ,橙色框）。下载：E-MTAB-5522.sdrf.txt（第2页）

3.2.1 colData

Code 
sdrf <- fread("data/SingleCellExperiment//E-MTAB-5522.sdrf.txt")

# 仅保留在计数矩阵的细胞  第44列=="counts_Calero_20160113.tsv"
coldata <- sdrf[sdrf$`Derived Array Data File` == "counts_Calero_20160113.tsv", ]

# 仅保留部分列和设置行标识符
coldata <- DataFrame(
  genotype=coldata$`Characteristics[genotype]`,
  phenotype=coldata$`Characteristics[phenotype]`,
  spike_in=coldata$`Factor Value[spike-in addition]`,
  row.names = coldata$`Source Name`
)
coldata
#> DataFrame with 96 rows and 3 columns
#>                                                    genotype
#>                                                 <character>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> ...                                                     ...
#> SLX-9555.N712_S505.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S506.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S507.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S508.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S517.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#>                                                   phenotype    spike_in
#>                                                 <character> <character>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..   ERCC+SIRV
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..   ERCC+SIRV
#> ...                                                     ...         ...
#> SLX-9555.N712_S505.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S506.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S507.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S508.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S517.C89V9ANXX.s_1.r_1    wild type phenotype    Premixed

添加之前确保colData的行名与计数矩阵的列名相同

Code 
identical(rownames(coldata), colnames(counts))
#> [1] TRUE

3.2.2 添加colData

3.2.2.1 从头开始

Code 
sce0 <- SingleCellExperiment(assays = list(counts=counts), 
                             colData= coldata)
sce0
colData(sce0)

3.2.2.2 向现有对象添加

Code 
sce
#> class: SingleCellExperiment 
#> dim: 46603 96 
#> metadata(0):
#> assays(1): counts
#> rownames(46603): ENSMUSG00000102693 ENSMUSG00000064842 ...
#>   ENSMUSG00000096730 ENSMUSG00000095742
#> rowData names(0):
#> colnames(96): SLX-9555.N701_S502.C89V9ANXX.s_1.r_1
#>   SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 ...
#>   SLX-9555.N712_S508.C89V9ANXX.s_1.r_1
#>   SLX-9555.N712_S517.C89V9ANXX.s_1.r_1
#> colData names(1): sizeFactor
#> reducedDimNames(0):
#> mainExpName: NULL
#> altExpNames(0):
colData(sce) <- coldata
sce
#> class: SingleCellExperiment 
#> dim: 46603 96 
#> metadata(0):
#> assays(1): counts
#> rownames(46603): ENSMUSG00000102693 ENSMUSG00000064842 ...
#>   ENSMUSG00000096730 ENSMUSG00000095742
#> rowData names(0):
#> colnames(96): SLX-9555.N701_S502.C89V9ANXX.s_1.r_1
#>   SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 ...
#>   SLX-9555.N712_S508.C89V9ANXX.s_1.r_1
#>   SLX-9555.N712_S517.C89V9ANXX.s_1.r_1
#> colData names(3): genotype phenotype spike_in
#> reducedDimNames(0):
#> mainExpName: NULL
#> altExpNames(0):

或者 分块添加

Code 
sce1 <- SingleCellExperiment(list(counts=counts))
sce1$phenotype <- coldata$phenotype
colData(sce1)
#> DataFrame with 96 rows and 1 column
#>                                                   phenotype
#>                                                 <character>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1    wild type phenotype
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1    wild type phenotype
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1    wild type phenotype
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..
#> ...                                                     ...
#> SLX-9555.N712_S505.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..
#> SLX-9555.N712_S506.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..
#> SLX-9555.N712_S507.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..
#> SLX-9555.N712_S508.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..
#> SLX-9555.N712_S517.C89V9ANXX.s_1.r_1    wild type phenotype

3.2.3 函数自动添加

某些函数在colData中返回额外样本元数据字段，自动添加列元数据。

Code 
sce <- scuttle::addPerCellQC(sce)  #quality control metrics质量控制指标
colData(sce)
#> DataFrame with 96 rows and 6 columns
#>                                                    genotype
#>                                                 <character>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> ...                                                     ...
#> SLX-9555.N712_S505.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S506.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S507.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S508.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S517.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#>                                                   phenotype    spike_in
#>                                                 <character> <character>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..   ERCC+SIRV
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..   ERCC+SIRV
#> ...                                                     ...         ...
#> SLX-9555.N712_S505.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S506.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S507.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S508.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S517.C89V9ANXX.s_1.r_1    wild type phenotype    Premixed
#>                                            sum  detected     total
#>                                      <numeric> <numeric> <numeric>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1    854171      7617    854171
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1   1044243      7520   1044243
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1   1152450      8305   1152450
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1   1193876      8142   1193876
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1   1521472      7153   1521472
#> ...                                        ...       ...       ...
#> SLX-9555.N712_S505.C89V9ANXX.s_1.r_1    203221      5608    203221
#> SLX-9555.N712_S506.C89V9ANXX.s_1.r_1   1059853      6948   1059853
#> SLX-9555.N712_S507.C89V9ANXX.s_1.r_1   1672343      6879   1672343
#> SLX-9555.N712_S508.C89V9ANXX.s_1.r_1   1939537      7213   1939537
#> SLX-9555.N712_S517.C89V9ANXX.s_1.r_1   1436899      8469   1436899
sce
#> class: SingleCellExperiment 
#> dim: 46603 96 
#> metadata(0):
#> assays(1): counts
#> rownames(46603): ENSMUSG00000102693 ENSMUSG00000064842 ...
#>   ENSMUSG00000096730 ENSMUSG00000095742
#> rowData names(0):
#> colnames(96): SLX-9555.N701_S502.C89V9ANXX.s_1.r_1
#>   SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 ...
#>   SLX-9555.N712_S508.C89V9ANXX.s_1.r_1
#>   SLX-9555.N712_S517.C89V9ANXX.s_1.r_1
#> colData names(6): genotype phenotype ... detected total
#> reducedDimNames(0):
#> mainExpName: NULL
#> altExpNames(0):

3.3 行数据 ( rowData)

添加行数据rawData注释基因，DataFrame中每行对应一个基因，每列对应一个基因数据字段，例如转录本长度、基因符号等注释。（ Figure 3.1 ,绿色框）

3.3.0.1 rowData

Code 
rowData(sce)
#> DataFrame with 46603 rows and 0 columns
rowData(sce)$Length <- gene_length
rowData(sce)
#> DataFrame with 46603 rows and 1 column
#>                       Length
#>                    <integer>
#> ENSMUSG00000102693      1070
#> ENSMUSG00000064842       110
#> ENSMUSG00000051951      6094
#> ENSMUSG00000102851       480
#> ENSMUSG00000103377      2819
#> ...                      ...
#> ENSMUSG00000094431       100
#> ENSMUSG00000094621       121
#> ENSMUSG00000098647        99
#> ENSMUSG00000096730      3077
#> ENSMUSG00000095742       243

某些函数在rowData中返回额外基因元数据字段，自动添加行元数据。

Code 
sce <- scuttle::addPerFeatureQC(sce)
rowData(sce)
#> DataFrame with 46603 rows and 3 columns
#>                       Length      mean  detected
#>                    <integer> <numeric> <numeric>
#> ENSMUSG00000102693      1070 0.0000000   0.00000
#> ENSMUSG00000064842       110 0.0000000   0.00000
#> ENSMUSG00000051951      6094 0.0000000   0.00000
#> ENSMUSG00000102851       480 0.0000000   0.00000
#> ENSMUSG00000103377      2819 0.0208333   1.04167
#> ...                      ...       ...       ...
#> ENSMUSG00000094431       100         0         0
#> ENSMUSG00000094621       121         0         0
#> ENSMUSG00000098647        99         0         0
#> ENSMUSG00000096730      3077         0         0
#> ENSMUSG00000095742       243         0         0

3.3.0.2 rowRanges

rowRanges：以GRangesList或 GRanges的形式保存基因组坐标，描述了特征（基因、基因组区域）的染色体、起始坐标和结束坐标。

Code 
SummarizedExperiment::rowRanges(sce)  #empty
#> GRangesList object of length 46603:
#> $ENSMUSG00000102693
#> GRanges object with 0 ranges and 0 metadata columns:
#>    seqnames    ranges strand
#>       <Rle> <IRanges>  <Rle>
#>   -------
#>   seqinfo: no sequences
#> 
#> $ENSMUSG00000064842
#> GRanges object with 0 ranges and 0 metadata columns:
#>    seqnames    ranges strand
#>       <Rle> <IRanges>  <Rle>
#>   -------
#>   seqinfo: no sequences
#> 
#> $ENSMUSG00000051951
#> GRanges object with 0 ranges and 0 metadata columns:
#>    seqnames    ranges strand
#>       <Rle> <IRanges>  <Rle>
#>   -------
#>   seqinfo: no sequences
#> 
#> ...
#> <46600 more elements>

填充 rowRanges的方式取决于在比对和定量过程中使用的生物体种类和注释文件。 常用的是Ensembl 标识符，因此我们可以使用rtracklayer从包含 Ensembl 注释的 GTF 文件中载入GRanges。下载：Mus_musculus.GRCm38.82.gtf.gz

Note

GTF（General Transfer Format）通用转录组注释格式

  1. seqid 字符串 参考序列 ID（如染色体编号、 scaffold 编号），示例：chr1、NC_000001

  2. source 字符串 注释来源（数据库或预测工具），示例：Ensembl、Gencode、augustus

  3. type 字符串 注释特征类型（严格限定关键词），常见：gene、transcript、exon、CDS

  4. start 整数 特征在参考序列上的起始坐标（1-based 索引，闭区间），示例：1001

  5. end 整数 特征在参考序列上的终止坐标，示例：2000

  6. score 浮点数 /. 置信度得分（预测工具输出），. 表示无数据，示例：95.3、.

  7. strand 字符 链方向，+（正链）、-（负链）、.（未知）、?（不确定）

  8. phase 整数 /. 仅 CDS 特征有效，0/1/2 表示密码子阅读框偏移，非 CDS 特征用.，示例：0、.

  9. attributes 字符串 键值对属性（核心扩展字段），格式：key1 “value1”; key2 “value2”;

Code 
gene_data <- rtracklayer::import("data/SingleCellExperiment/Mus_musculus.GRCm38.82.gtf.gz")
gene_data[1:6,1:9]
#> GRanges object with 6 ranges and 9 metadata columns:
#>       seqnames          ranges strand |   source       type     score     phase
#>          <Rle>       <IRanges>  <Rle> | <factor>   <factor> <numeric> <integer>
#>   [1]        1 3073253-3074322      + |  havana  gene              NA      <NA>
#>   [2]        1 3073253-3074322      + |  havana  transcript        NA      <NA>
#>   [3]        1 3073253-3074322      + |  havana  exon              NA      <NA>
#>   [4]        1 3102016-3102125      + |  ensembl gene              NA      <NA>
#>   [5]        1 3102016-3102125      + |  ensembl transcript        NA      <NA>
#>   [6]        1 3102016-3102125      + |  ensembl exon              NA      <NA>
#>                  gene_id gene_version     gene_name gene_source gene_biotype
#>              <character>  <character>   <character> <character>  <character>
#>   [1] ENSMUSG00000102693            1 4933401J01Rik      havana          TEC
#>   [2] ENSMUSG00000102693            1 4933401J01Rik      havana          TEC
#>   [3] ENSMUSG00000102693            1 4933401J01Rik      havana          TEC
#>   [4] ENSMUSG00000064842            1       Gm26206     ensembl        snRNA
#>   [5] ENSMUSG00000064842            1       Gm26206     ensembl        snRNA
#>   [6] ENSMUSG00000064842            1       Gm26206     ensembl        snRNA
#>   -------
#>   seqinfo: 45 sequences from an unspecified genome; no seqlengths

# 整理数据
gene_data <- gene_data[gene_data$type=="gene",]
names(gene_data) <- gene_data$gene_id

# 保留gene_开头的列   metadata columns
library(GenomicRanges)
is.gene.related <- str_detect(colnames(mcols(gene_data)),"^gene_") 
table(is.gene.related)
#> is.gene.related
#> FALSE  TRUE 
#>    21     5

mcols(gene_data) <- mcols(gene_data)[,is.gene.related]
mcols(gene_data)  # 46603 ×  5
#> DataFrame with 46603 rows and 5 columns
#>                               gene_id gene_version      gene_name
#>                           <character>  <character>    <character>
#> ENSMUSG00000102693 ENSMUSG00000102693            1  4933401J01Rik
#> ENSMUSG00000064842 ENSMUSG00000064842            1        Gm26206
#> ENSMUSG00000051951 ENSMUSG00000051951            5           Xkr4
#> ENSMUSG00000102851 ENSMUSG00000102851            1        Gm18956
#> ENSMUSG00000103377 ENSMUSG00000103377            1        Gm37180
#> ...                               ...          ...            ...
#> ENSMUSG00000094431 ENSMUSG00000094431            1 CAAA01205117.1
#> ENSMUSG00000094621 ENSMUSG00000094621            1 CAAA01098150.1
#> ENSMUSG00000098647 ENSMUSG00000098647            1 CAAA01064564.1
#> ENSMUSG00000096730 ENSMUSG00000096730            6       Vmn2r122
#> ENSMUSG00000095742 ENSMUSG00000095742            1 CAAA01147332.1
#>                       gene_source         gene_biotype
#>                       <character>          <character>
#> ENSMUSG00000102693         havana                  TEC
#> ENSMUSG00000064842        ensembl                snRNA
#> ENSMUSG00000051951 ensembl_havana       protein_coding
#> ENSMUSG00000102851         havana processed_pseudogene
#> ENSMUSG00000103377         havana                  TEC
#> ...                           ...                  ...
#> ENSMUSG00000094431        ensembl                miRNA
#> ENSMUSG00000094621        ensembl                miRNA
#> ENSMUSG00000098647        ensembl                miRNA
#> ENSMUSG00000096730        ensembl       protein_coding
#> ENSMUSG00000095742        ensembl       protein_coding
#rownames(sce) 46603行 观测基因
SummarizedExperiment::rowRanges(sce) <- gene_data[rownames(sce)]
SummarizedExperiment::rowRanges(sce)[1:6,]
#> GRanges object with 6 ranges and 5 metadata columns:
#>                      seqnames          ranges strand |            gene_id
#>                         <Rle>       <IRanges>  <Rle> |        <character>
#>   ENSMUSG00000102693        1 3073253-3074322      + | ENSMUSG00000102693
#>   ENSMUSG00000064842        1 3102016-3102125      + | ENSMUSG00000064842
#>   ENSMUSG00000051951        1 3205901-3671498      - | ENSMUSG00000051951
#>   ENSMUSG00000102851        1 3252757-3253236      + | ENSMUSG00000102851
#>   ENSMUSG00000103377        1 3365731-3368549      - | ENSMUSG00000103377
#>   ENSMUSG00000104017        1 3375556-3377788      - | ENSMUSG00000104017
#>                      gene_version     gene_name    gene_source
#>                       <character>   <character>    <character>
#>   ENSMUSG00000102693            1 4933401J01Rik         havana
#>   ENSMUSG00000064842            1       Gm26206        ensembl
#>   ENSMUSG00000051951            5          Xkr4 ensembl_havana
#>   ENSMUSG00000102851            1       Gm18956         havana
#>   ENSMUSG00000103377            1       Gm37180         havana
#>   ENSMUSG00000104017            1       Gm37363         havana
#>                              gene_biotype
#>                               <character>
#>   ENSMUSG00000102693                  TEC
#>   ENSMUSG00000064842                snRNA
#>   ENSMUSG00000051951       protein_coding
#>   ENSMUSG00000102851 processed_pseudogene
#>   ENSMUSG00000103377                  TEC
#>   ENSMUSG00000104017                  TEC
#>   -------
#>   seqinfo: 45 sequences from an unspecified genome; no seqlengths

sce
#> class: SingleCellExperiment 
#> dim: 46603 96 
#> metadata(0):
#> assays(1): counts
#> rownames(46603): ENSMUSG00000102693 ENSMUSG00000064842 ...
#>   ENSMUSG00000096730 ENSMUSG00000095742
#> rowData names(5): gene_id gene_version gene_name gene_source
#>   gene_biotype
#> colnames(96): SLX-9555.N701_S502.C89V9ANXX.s_1.r_1
#>   SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 ...
#>   SLX-9555.N712_S508.C89V9ANXX.s_1.r_1
#>   SLX-9555.N712_S517.C89V9ANXX.s_1.r_1
#> colData names(6): genotype phenotype ... detected total
#> reducedDimNames(0):
#> mainExpName: NULL
#> altExpNames(0):

3.3.1 其他元数据

其他注释以命名列表存储在metadata 中。 例如，实验元数据，高度可变基因（highly variable genes）。。。，缺点是与表达矩阵的行或列的操作不同步。

Code 
DEG_up <- c("gene_x", "gene_y")
metadata(sce) <- list(HVGs = DEG_up)
metadata(sce)
#> $HVGs
#> [1] "gene_x" "gene_y"
DEG_down <- c("gene_a", "gene_b")
metadata(sce)$DEG_down <- DEG_down
metadata(sce)
#> $HVGs
#> [1] "gene_x" "gene_y"
#> 
#> $DEG_down
#> [1] "gene_a" "gene_b"
sce
#> class: SingleCellExperiment 
#> dim: 46603 96 
#> metadata(2): HVGs DEG_down
#> assays(1): counts
#> rownames(46603): ENSMUSG00000102693 ENSMUSG00000064842 ...
#>   ENSMUSG00000096730 ENSMUSG00000095742
#> rowData names(5): gene_id gene_version gene_name gene_source
#>   gene_biotype
#> colnames(96): SLX-9555.N701_S502.C89V9ANXX.s_1.r_1
#>   SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 ...
#>   SLX-9555.N712_S508.C89V9ANXX.s_1.r_1
#>   SLX-9555.N712_S517.C89V9ANXX.s_1.r_1
#> colData names(6): genotype phenotype ... detected total
#> reducedDimNames(0):
#> mainExpName: NULL
#> altExpNames(0):

3.4 子集和组合

3.4.1 子集

Code 
first.10 <- sce[,1:10]
ncol(counts(first.10)) #  计数矩阵仅有 10 列
#> [1] 10
colData(first.10) # only 10 rows.
#> DataFrame with 10 rows and 6 columns
#>                                                    genotype
#>                                                 <character>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S508.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S517.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N702_S502.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N702_S503.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#>                                                   phenotype    spike_in
#>                                                 <character> <character>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..   ERCC+SIRV
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..   ERCC+SIRV
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..   ERCC+SIRV
#> SLX-9555.N701_S508.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..   ERCC+SIRV
#> SLX-9555.N701_S517.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N702_S502.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N702_S503.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#>                                            sum  detected     total
#>                                      <numeric> <numeric> <numeric>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1    854171      7617    854171
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1   1044243      7520   1044243
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1   1152450      8305   1152450
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1   1193876      8142   1193876
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1   1521472      7153   1521472
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1    866705      6828    866705
#> SLX-9555.N701_S508.C89V9ANXX.s_1.r_1    608581      6966    608581
#> SLX-9555.N701_S517.C89V9ANXX.s_1.r_1   1113526      8634   1113526
#> SLX-9555.N702_S502.C89V9ANXX.s_1.r_1   1308250      8364   1308250
#> SLX-9555.N702_S503.C89V9ANXX.s_1.r_1    778605      8665    778605

只想要野生型细胞

Code 
wt.only <- sce[, sce$phenotype == "wild type phenotype"]
ncol(counts(wt.only))
#> [1] 48
colData(wt.only)
#> DataFrame with 48 rows and 6 columns
#>                                                    genotype           phenotype
#>                                                 <character>         <character>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1 Doxycycline-inducibl.. wild type phenotype
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 Doxycycline-inducibl.. wild type phenotype
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1 Doxycycline-inducibl.. wild type phenotype
#> SLX-9555.N701_S517.C89V9ANXX.s_1.r_1 Doxycycline-inducibl.. wild type phenotype
#> SLX-9555.N702_S502.C89V9ANXX.s_1.r_1 Doxycycline-inducibl.. wild type phenotype
#> ...                                                     ...                 ...
#> SLX-9555.N711_S517.C89V9ANXX.s_1.r_1 Doxycycline-inducibl.. wild type phenotype
#> SLX-9555.N712_S502.C89V9ANXX.s_1.r_1 Doxycycline-inducibl.. wild type phenotype
#> SLX-9555.N712_S503.C89V9ANXX.s_1.r_1 Doxycycline-inducibl.. wild type phenotype
#> SLX-9555.N712_S504.C89V9ANXX.s_1.r_1 Doxycycline-inducibl.. wild type phenotype
#> SLX-9555.N712_S517.C89V9ANXX.s_1.r_1 Doxycycline-inducibl.. wild type phenotype
#>                                         spike_in       sum  detected     total
#>                                      <character> <numeric> <numeric> <numeric>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1   ERCC+SIRV    854171      7617    854171
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1   ERCC+SIRV   1044243      7520   1044243
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1   ERCC+SIRV   1152450      8305   1152450
#> SLX-9555.N701_S517.C89V9ANXX.s_1.r_1   ERCC+SIRV   1113526      8634   1113526
#> SLX-9555.N702_S502.C89V9ANXX.s_1.r_1   ERCC+SIRV   1308250      8364   1308250
#> ...                                          ...       ...       ...       ...
#> SLX-9555.N711_S517.C89V9ANXX.s_1.r_1    Premixed   1317671      8581   1317671
#> SLX-9555.N712_S502.C89V9ANXX.s_1.r_1    Premixed   1736189      9687   1736189
#> SLX-9555.N712_S503.C89V9ANXX.s_1.r_1    Premixed   1521132      8983   1521132
#> SLX-9555.N712_S504.C89V9ANXX.s_1.r_1    Premixed   1759166      8480   1759166
#> SLX-9555.N712_S517.C89V9ANXX.s_1.r_1    Premixed   1436899      8469   1436899

只想保留蛋白质编码基因

Code 
coding.only <- sce[rowData(sce)$gene_biotype == "protein_coding",]
nrow(counts(coding.only))
#> [1] 22013
rowData(coding.only)
#> DataFrame with 22013 rows and 5 columns
#>                               gene_id gene_version      gene_name
#>                           <character>  <character>    <character>
#> ENSMUSG00000051951 ENSMUSG00000051951            5           Xkr4
#> ENSMUSG00000025900 ENSMUSG00000025900            9            Rp1
#> ENSMUSG00000025902 ENSMUSG00000025902           12          Sox17
#> ENSMUSG00000033845 ENSMUSG00000033845           12         Mrpl15
#> ENSMUSG00000025903 ENSMUSG00000025903           13         Lypla1
#> ...                               ...          ...            ...
#> ENSMUSG00000079808 ENSMUSG00000079808            3     AC168977.1
#> ENSMUSG00000095041 ENSMUSG00000095041            6           PISD
#> ENSMUSG00000063897 ENSMUSG00000063897            3          DHRSX
#> ENSMUSG00000096730 ENSMUSG00000096730            6       Vmn2r122
#> ENSMUSG00000095742 ENSMUSG00000095742            1 CAAA01147332.1
#>                       gene_source   gene_biotype
#>                       <character>    <character>
#> ENSMUSG00000051951 ensembl_havana protein_coding
#> ENSMUSG00000025900 ensembl_havana protein_coding
#> ENSMUSG00000025902 ensembl_havana protein_coding
#> ENSMUSG00000033845 ensembl_havana protein_coding
#> ENSMUSG00000025903 ensembl_havana protein_coding
#> ...                           ...            ...
#> ENSMUSG00000079808        ensembl protein_coding
#> ENSMUSG00000095041        ensembl protein_coding
#> ENSMUSG00000063897        ensembl protein_coding
#> ENSMUSG00000096730        ensembl protein_coding
#> ENSMUSG00000095742        ensembl protein_coding

3.4.2 组合

按列组合，假设所有涉及的对象都具有相同的行注释值和兼容的列注释字段

Code 
sce2 <- cbind(sce, sce)
ncol(counts(sce2)) # twice as many columns
#> [1] 192
colData(sce2) # twice as many rows
#> DataFrame with 192 rows and 6 columns
#>                                                    genotype
#>                                                 <character>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> ...                                                     ...
#> SLX-9555.N712_S505.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S506.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S507.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S508.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#> SLX-9555.N712_S517.C89V9ANXX.s_1.r_1 Doxycycline-inducibl..
#>                                                   phenotype    spike_in
#>                                                 <character> <character>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1    wild type phenotype   ERCC+SIRV
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..   ERCC+SIRV
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..   ERCC+SIRV
#> ...                                                     ...         ...
#> SLX-9555.N712_S505.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S506.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S507.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S508.C89V9ANXX.s_1.r_1 induced CBFB-MYH11 o..    Premixed
#> SLX-9555.N712_S517.C89V9ANXX.s_1.r_1    wild type phenotype    Premixed
#>                                            sum  detected     total
#>                                      <numeric> <numeric> <numeric>
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1    854171      7617    854171
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1   1044243      7520   1044243
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1   1152450      8305   1152450
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1   1193876      8142   1193876
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1   1521472      7153   1521472
#> ...                                        ...       ...       ...
#> SLX-9555.N712_S505.C89V9ANXX.s_1.r_1    203221      5608    203221
#> SLX-9555.N712_S506.C89V9ANXX.s_1.r_1   1059853      6948   1059853
#> SLX-9555.N712_S507.C89V9ANXX.s_1.r_1   1672343      6879   1672343
#> SLX-9555.N712_S508.C89V9ANXX.s_1.r_1   1939537      7213   1939537
#> SLX-9555.N712_S517.C89V9ANXX.s_1.r_1   1436899      8469   1436899

按行组合，假设所有对象都具有相同的列注释值和兼容的行注释字段。

Code 
sce2 <- rbind(sce, sce)
nrow(counts(sce2)) # twice as many rows
#> [1] 93206
rowData(sce2) # twice as many rows
#> DataFrame with 93206 rows and 5 columns
#>                               gene_id gene_version      gene_name
#>                           <character>  <character>    <character>
#> ENSMUSG00000102693 ENSMUSG00000102693            1  4933401J01Rik
#> ENSMUSG00000064842 ENSMUSG00000064842            1        Gm26206
#> ENSMUSG00000051951 ENSMUSG00000051951            5           Xkr4
#> ENSMUSG00000102851 ENSMUSG00000102851            1        Gm18956
#> ENSMUSG00000103377 ENSMUSG00000103377            1        Gm37180
#> ...                               ...          ...            ...
#> ENSMUSG00000094431 ENSMUSG00000094431            1 CAAA01205117.1
#> ENSMUSG00000094621 ENSMUSG00000094621            1 CAAA01098150.1
#> ENSMUSG00000098647 ENSMUSG00000098647            1 CAAA01064564.1
#> ENSMUSG00000096730 ENSMUSG00000096730            6       Vmn2r122
#> ENSMUSG00000095742 ENSMUSG00000095742            1 CAAA01147332.1
#>                       gene_source         gene_biotype
#>                       <character>          <character>
#> ENSMUSG00000102693         havana                  TEC
#> ENSMUSG00000064842        ensembl                snRNA
#> ENSMUSG00000051951 ensembl_havana       protein_coding
#> ENSMUSG00000102851         havana processed_pseudogene
#> ENSMUSG00000103377         havana                  TEC
#> ...                           ...                  ...
#> ENSMUSG00000094431        ensembl                miRNA
#> ENSMUSG00000094621        ensembl                miRNA
#> ENSMUSG00000098647        ensembl                miRNA
#> ENSMUSG00000096730        ensembl       protein_coding
#> ENSMUSG00000095742        ensembl       protein_coding

3.5 单细胞特定字段

3.5.1 降维 reducedDims

降维结果保存在一个列表中，列表的每一个对象是一个代表计数矩阵的低维的数值矩阵，其中行表示计数矩阵的列（如细胞），列表示维度。

PCA 
sce
#> class: SingleCellExperiment 
#> dim: 46603 96 
#> metadata(2): HVGs DEG_down
#> assays(1): counts
#> rownames(46603): ENSMUSG00000102693 ENSMUSG00000064842 ...
#>   ENSMUSG00000096730 ENSMUSG00000095742
#> rowData names(5): gene_id gene_version gene_name gene_source
#>   gene_biotype
#> colnames(96): SLX-9555.N701_S502.C89V9ANXX.s_1.r_1
#>   SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 ...
#>   SLX-9555.N712_S508.C89V9ANXX.s_1.r_1
#>   SLX-9555.N712_S517.C89V9ANXX.s_1.r_1
#> colData names(6): genotype phenotype ... detected total
#> reducedDimNames(0):
#> mainExpName: NULL
#> altExpNames(0):
sce <- scater::logNormCounts(sce)
sce <- scater::runPCA(sce)
head(reducedDim(sce, "PCA"))
#>                                              PC1        PC2        PC3
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1  25.3211829 -29.255059  19.924611
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1   8.5853041 -24.268878 -18.126000
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  47.1785847 -10.430627  19.918057
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1  -0.7246197  42.677052 -18.786200
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 -44.8772729   7.165398  -2.557318
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -38.3072406   7.030712  -6.703706
#>                                            PC4         PC5       PC6       PC7
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1  2.353028   0.7134296 -4.657165 -4.529785
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1  9.457525   6.6261762 -7.374656  9.479859
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  9.043069   0.5371746  5.369461 -4.579162
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 10.052217 -11.2629834  5.066610 -3.989710
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1  2.063798  23.2470805  9.972536 -2.224446
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 35.617030  11.8510185 -5.534609 -1.628105
#>                                             PC8        PC9        PC10
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1  12.739486  5.3528313 -17.4712747
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1   9.933231 -3.0253703  -7.7697509
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  -5.394808 -0.2653627   1.9569984
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1   1.609922 -5.9842292   4.2662705
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1   0.922675 -3.3105931 -10.4905096
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -10.031722  1.3764729  -0.6400844
#>                                           PC11       PC12      PC13
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1  6.272022   1.309453  2.142689
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 -8.628675 -23.782808 13.086537
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1 -1.742621   5.794494  1.081155
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1  7.924183   4.118848 -1.318160
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 -3.991925   2.945433  7.997875
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -2.048618  16.074028 -1.601696
#>                                              PC14      PC15        PC16
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1  -3.21487530 -3.586042  -0.8868563
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1  -0.07695582 -1.622621  16.5055262
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1   5.37813494 -4.204543  -2.4987753
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1  -3.08602026 -1.632896  14.2865809
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1  -2.60771987 19.278739 -10.3415881
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -14.46500274 -9.901801  14.8844890
#>                                            PC17      PC18       PC19       PC20
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1  8.3092835 -8.254021  3.2032199   8.400580
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 -7.0968297  7.479420  2.3893440  11.335409
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  6.1373345  6.841587  2.0491731 -12.153631
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 10.6386401 -6.811841  4.3494316  11.066570
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 -2.3761618  7.564805 -0.5513294  -2.781294
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -0.5659762 -2.644617  3.7978583   1.368715
#>                                            PC21       PC22       PC23
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1   6.046180  0.3084271 15.4402055
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1  -2.781302 10.9606893  0.9337166
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  -7.230595  4.2540263 -3.7111678
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1  -4.998028 -3.7927570 -5.8715888
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 -14.916002 -0.6490183 -5.7146241
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -16.096460 -1.5767236  1.6884199
#>                                            PC24       PC25        PC26
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1   4.681700 -6.8980048  -6.9414484
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 -12.282928 -7.7927146 -15.5028217
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  -2.971526 -1.0340304   3.0595966
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1  -7.261821  0.1469728  -0.3389878
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1  -6.742021  9.0437395  13.3845540
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1  15.742625  2.8595182   1.0181258
#>                                           PC27       PC28         PC29
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1  2.542829   9.985183  -3.49240985
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1  4.475004  -8.571937   1.37038588
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1 -7.788931  -3.190580  -0.07106325
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 -4.334259  13.180193 -12.61790029
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 -4.173710   5.856713   2.51899198
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1  3.088050 -17.295198  -3.71292452
#>                                              PC30       PC31      PC32
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1 -15.80727198 -0.5220196  7.013530
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1  11.10310511 -6.5958587 13.719887
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  -0.01329056  7.0592846  3.650680
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1  -1.88963759 18.5238767  2.819896
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 -12.55439568  1.9920756  8.699811
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -11.41168626  4.4201476  5.879863
#>                                           PC33       PC34      PC35       PC36
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1 -6.114895 -8.0054624 -8.761877 -8.7666596
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 11.659703  5.4103879 -5.109168  2.3577599
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  4.115808  2.7495522  2.431918  3.9233042
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 -9.079732 -0.6305226  6.234937 -4.1432864
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1  8.695278 -6.0949988 -4.720441  6.2858893
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -1.344748 -3.3667688 -5.063130  0.7113685
#>                                           PC37       PC38      PC39        PC40
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1 -4.146180  -4.632087 -7.384395   5.3545001
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 -8.559027  -1.528232 -6.537447  -0.6943536
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  2.049022   2.601003 -5.790073   0.4880258
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1  8.396337  -5.866749 -4.707630   5.3081910
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 -2.584457 -11.548363 -6.699724 -17.0674135
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 10.266019   4.807745  6.021079   1.2115131
#>                                           PC41       PC42       PC43
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1 -3.939611  13.753571  -2.933861
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 -8.165024  -8.682295  -5.419327
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1 -3.556190 -11.034037   1.609018
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1  1.450141  -3.135220   3.758943
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1  7.091337  -9.855553   7.788290
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -1.975210  -1.080137 -14.012539
#>                                             PC44      PC45       PC46
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1  7.10867875  2.744699  0.3557068
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1  0.09050595  3.099078 -3.0561133
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  0.63401271 -7.388260 -4.8308179
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1 -4.57483871  6.691166 -4.6248279
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1  9.95694101 -3.096031  4.8812097
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1  1.94998482  0.468822 -6.8053076
#>                                              PC47       PC48        PC49
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1  -2.91052787 -12.911035   0.9586156
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1   0.99067457   3.865605  -9.6252109
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1   0.05644908   7.466290 -14.3186667
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1   1.52787940   0.740261  -0.2277275
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1   4.97965548  -6.475406   7.2102380
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -11.00798917  -2.598978   3.5586230
#>                                           PC50
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1 -1.468232
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 -4.673149
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1 -4.002830
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1  1.546890
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1  2.537450
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -7.319533
tSNE 
sce <- scater::runTSNE(sce, perplexity = 0.1)
#> Perplexity should be lower than K!
head(reducedDim(sce, "TSNE"))
#>                                           TSNE1      TSNE2
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1   762.5866  -549.3040
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1   336.7162   591.4587
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1 -1167.2996  -411.6957
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1   172.7646  -188.8121
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1   575.0761 -1154.9966
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1   139.4120 -1428.1949
UMAP 
sce <- scater::runUMAP(sce)
head(reducedDim(sce,"UMAP"))
#>                                          UMAP1       UMAP2
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1  6.476384  0.92232811
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1  5.694130  0.40770971
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  6.899131  1.31853854
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1  8.024528 -0.69645191
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 -8.901412  0.26416027
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -9.432525  0.08151817
手动添加UMAP 
u <- uwot::umap(t(logcounts(sce)), n_neighbors = 2)
reducedDim(sce, "UMAP_uwot") <- u
reducedDims(sce) # Now stored in the object.
#> List of length 4
#> names(4): PCA TSNE UMAP UMAP_uwot
head(reducedDim(sce, "UMAP_uwot"))
#>                                           [,1]      [,2]
#> SLX-9555.N701_S502.C89V9ANXX.s_1.r_1  4.899905 2.3621000
#> SLX-9555.N701_S503.C89V9ANXX.s_1.r_1  5.569812 0.4105074
#> SLX-9555.N701_S504.C89V9ANXX.s_1.r_1  4.316229 2.7554661
#> SLX-9555.N701_S505.C89V9ANXX.s_1.r_1  4.784112 4.8707987
#> SLX-9555.N701_S506.C89V9ANXX.s_1.r_1 -3.444970 0.4209308
#> SLX-9555.N701_S507.C89V9ANXX.s_1.r_1 -1.768182 1.6421386
Code 
reducedDims(sce) 
#> List of length 4
#> names(4): PCA TSNE UMAP UMAP_uwot

3.5.2 替代试验 Alternative Experiments

SingleCellExperiment提供了”替代实验”的概念，其是一组不同特征但同一组样本/细胞的数据。经典应用是存储加标转录（spike-in transcripts）的每细胞计数，能够保留这些数据以供下游使用，但要将其与保存的内源性基因计数分离，因为此类替代特征通常需要单独处理。

Code 
df_spikein <- df_spikein |> tibble::column_to_rownames("GeneID")
spike_length <- df_spikein$Length
spike_mat<- as.matrix(df_spikein[,-1]) 
spike_mat[1:2,1:2]
#>            SLX-9555.N701_S502.C89V9ANXX.s_1.r_1
#> ERCC-00002                                12948
#> ERCC-00003                                  220
#>            SLX-9555.N701_S503.C89V9ANXX.s_1.r_1
#> ERCC-00002                                11287
#> ERCC-00003                                  911

首先创建一个单独的对象SummarizedExperiment

Code 
spike_se <- SummarizedExperiment(list(counts=spike_mat))
spike_se
#> class: SummarizedExperiment 
#> dim: 92 96 
#> metadata(0):
#> assays(1): counts
#> rownames(92): ERCC-00002 ERCC-00003 ... ERCC-00170 ERCC-00171
#> rowData names(0):
#> colnames(96): SLX-9555.N701_S502.C89V9ANXX.s_1.r_1
#>   SLX-9555.N701_S503.C89V9ANXX.s_1.r_1 ...
#>   SLX-9555.N712_S508.C89V9ANXX.s_1.r_1
#>   SLX-9555.N712_S517.C89V9ANXX.s_1.r_1
#> colData names(0):
Code 
altExp(sce, "spike") <- spike_se

altExps(sce) 
#> List of length 1
#> names(1): spike

替代实验概念确保单细胞数据集的所有相关方面都可以保存在单个对象中，并且确保我们的加标数据与内源性基因的数据同步。

Code 
sub <- sce[,1:2] # retain only two samples.
altExp(sub, "spike")
#> class: SummarizedExperiment 
#> dim: 92 2 
#> metadata(0):
#> assays(1): counts
#> rownames(92): ERCC-00002 ERCC-00003 ... ERCC-00170 ERCC-00171
#> rowData names(0):
#> colnames(2): SLX-9555.N701_S502.C89V9ANXX.s_1.r_1
#>   SLX-9555.N701_S503.C89V9ANXX.s_1.r_1
#> colData names(0):

任何SummarizedExperiment对象都可以存储为alternative Experiment, 包括另一个 SingleCellExperiment。

3.5.3 缩放因子sizeFactors

Code 
# 反卷积deconvolution-based size factors
sce <- scran::computeSumFactors(sce) 
summary(sizeFactors(sce))
#>    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
#>  0.1513  0.7417  0.9478  1.0000  1.1239  3.5583

3.5.4 文库大小因子

Code 
# library size-derived factors
sizeFactors(sce) <- scater::librarySizeFactors(sce) 
summary(sizeFactors(sce))
#>    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
#>  0.1703  0.7657  0.9513  1.0000  1.1064  3.6050

3.5.5 聚类标签

该函数允许我们获取或设置每个细胞标签的向量或因子，通常对应于由无监督聚类分析的分组 或从分类算法预测细胞类型身份。

Code 
colLabels(sce) <- scran::clusterCells(sce, use.dimred="PCA")
table(colLabels(sce))
#> 
#>  1  2 
#> 47 49