r - 使用 R 更改具有 0 和 1 信息的矩阵中的数据帧

Question

我有一个数据框，例如:

Cluster sequence_name
1       species1
1       species1
1       species2
1       species3
1       species3
1       gene1
1       gene2
2       species4
2       species5
2       spciess5
2       species3
2       gene3
2       gene4

我想用它得到一个矩阵，例如:

           gene1  gene2 gene3 gene4
species5   0      0     1     1
species4   0      0     1     1
species1   1      1     0     0
species2   1      1     0     0
species3   1      1     1     1

1 表示对于 speciesX 基因存在，0 表示不存在。Present 意味着 speciesX 与 geneX 存在于同一簇 中。例如，gene1 作为 species1、2 和 3 存在于 cluster1 中。相反，species5 和 4 不存在于 cluster1 中。

如你所见；有几个重复(在同一个集群中，一个物种可以代表多次)。感谢您的帮助。

真实的数据是这样的:

cluster_names seq_names  
1             AP_000401.1  
1             NP_039001.1  
1             Canis_lupus  
1             Canis_familiaris
2             YP_0090909.1
2             Mustela_putorius
2             Mustela_furo
2             YP_0909200.1

....

...

AP和NP等XX字母是基因和 Genus_specie 物种

回应丹尼斯:

下面是一个头部的真实数据:

cluster_names  seq_names
1   scf7180005155889:2745-3053(-):Drosophia_melanogaster
1   IDBA_scaffold_72878:85-225:292707-293006(+):Orussu_sp
1   scaffold_3615:40850-41320(-):Canis_lupus
1   scaffold_8697:754-1209(-):homo_sapiens
1   scf7180005155889:72-1908(-):homo_sapiens
1   YP_003969716.1
1   NP_003986717.1
2   scaffold_17536:2745-3053(-):Drosophia_melanogaster
2   scf7180005155889:2000-8900(-):Drosophia_melanogaster
2   scaffold_8697:754-1209(-):homo_sapiens
2   YP_003956764.1
2   YP_004894416.1
2   YP_008958968.1

我应该得到的输出是:

回应丹尼斯:

> df <- read.table(text = "Cluster sequence_name
+ 1       :Drosophia_melanogaster
+                  1       scf7180005155889:2745-3053(-):Drosophila_melanogaster
+                  1       scf7180005155889:2745-3053(-):Orussu_sp
+                  1       scf7180005155889:2745-3053(-):Canis_lupus
+                  1       scf7180005155889:72-1908(-):Homo_sapiens
+                  1       scf7180005155889:2745-3053(-):Homo_sapiens
+                  1       YP_003970075.1
+                  1       YP_005070075.1
+                  2       scf7180005155889:72-1908(-):Drosophila_melanogaster
+                  2       scf7180005155889:72-1908(-):Drosophila_melanogaster
+                  2       scf7180005155889:72-1908(-):Homo_sapiens
+                  2       YP_039970075.1
+                  2       NP_003900075.1",header = T)
> df <- setDT(df)
> species <- df[grep("[0-9]+\\([+-]\\):[A-z ]+",sequence_name)]
> species[,sequence_name := str_extract(sequence_name,"(?<=[0-9]\\([+-]\\):)[A-z ]+")]
> genes <- df[grep("[0-9]+\\.1",sequence_name)]
> genes[,sequence_name :=sequence_name]
> plouf <- merge(genes,species,by = "Cluster",allow.cartesian=TRUE)
> result <- dcast(plouf,sequence_name.y~sequence_name.x,fun.aggregate = length)
Using 'sequence_name.y' as value column. Use 'value.var' to override
> row.names(result)<-result$sequence_name.y
> result$sequence_name.y<- NULL
> result
   NP_003900075.1 YP_003970075.1 YP_005070075.1 YP_039970075.1
1:              0              1              1              0
2:              2              1              1              2
3:              1              2              2              1
4:              0              1              1              0

Answer 1

library(data.table)
library(stringr)
df <- setDT(df)

我将在这里使用data.table。所以我们的想法是创建两个数据框，一个是基因，一个是物种

species <- df[grep("species",sequence_name)]
species[,sequence_name := str_extract(sequence_name,"(?<=:)[a-z0-9]+$")]
genes <- df[grep("gene",sequence_name)]

> species
   Cluster sequence_name
1:       1      species1
2:       1      species2
3:       1      species3
4:       2      species4
5:       2      species5
6:       2      species3
> genes
   Cluster sequence_name
1:       1         gene1
2:       1         gene2
3:       2         gene3
4:       2         gene4

您希望使用 allow.cartesian=TRUE 将它们按集群合并在一起，因为您的合并向量不是任何数据帧的单一标识符:

plouf <- merge(genes,species,by = "Cluster",allow.cartesian=TRUE)

    Cluster sequence_name.x sequence_name.y
 1:       1           gene1        species1
 2:       1           gene1        species2
 3:       1           gene1        species3
 4:       1           gene2        species1
 5:       1           gene2        species2
 6:       1           gene2        species3
 7:       2           gene3        species4
 8:       2           gene3        species5
 9:       2           gene3        species3
10:       2           gene4        species4
11:       2           gene4        species5
12:       2           gene4        species3

然后，在计算出现次数的同时获取宽格式的结果，您可以在此处使用 dcast 执行此操作:

result <- dcast(plouf,sequence_name.y~sequence_name.x,fun.aggregate = length)


   sequence_name.y gene1 gene2 gene3 gene4
1:        species1     1     1     0     0
2:        species2     1     1     0     0
3:        species3     1     1     1     1
4:        species4     0     0     1     1
5:        species5     0     0     1     1

等等。我让 dplyr 有经验的用户提出与 dplyr 等效/改进的解决方案。

数据:

df <- read.table(text = "Cluster sequence_name
1       Scaffold_1:species1
                 1       Scaffold_2:species2
                 1       Scaffold_3:species3
                 1       gene1
                 1       gene2
                 2       Scaffold_4:species4
                 2       Scaffold_5:species5
                 2       Scaffold_6:species3
                 2       gene3
                 2       gene4",header = T)

---

用你展示的真实数据:

df <- read.table(text ="cluster_names  seq_names
                 1   scf7180005155889:2745-3053(-):Drosophia_melanogaster
                 1   scaffold_2484:292707-293006(+):Orussu_sp
                 1   scaffold_3615:40850-41320(-):Canis_lupus
                 1   scaffold_8697:754-1209(-):homo_sapiens
                 1   scf7180005155889:72-1908(-):homo_sapiens
                 1   YP_003969716.1
                 1   NP_003986717.1
                 2   scaffold_17536:2745-3053(-):Drosophia_melanogaster
                 2   scf7180005155889:2000-8900(-):Drosophia_melanogaster
                 2   scaffold_8697:754-1209(-):homo_sapiens
                 2   YP_003956764.1
                 2   YP_004894416.1
                 2   YP_008958968.1",header = T)

您应该将创建两个数据表的步骤更改为:

species <- df[grep("[0-9]+\\([+-]\\):[A-z ]+",seq_names)]
species[,sequence_name := str_extract(seq_names,"(?<=[0-9]\\([+-]\\):)[A-z ]+")]
genes <- df[grep("[0-9]+\\.1",seq_names)]
genes[,sequence_name :=seq_names]

此处 [0-9]+\\.1" 假设所有基因都以 1 结尾，并且在物种描述中没有意义。要提取物种信息，我想它总是在数字后包含 (+): 或 (-)+ 。

但这是一个正则表达式问题，如果您有问题，应该是另一个问题。您在这里的问题是找到调整数据以获得结果的方法。我通过为您提供处理示例数据的步骤来回答:使用正则表达式创建两个基因和物种数据框，合并它们并重新塑造它们。

其余工作:

plouf <- merge(genes,species,by = "cluster_names",allow.cartesian=TRUE)
result <- dcast(plouf,sequence_name.y~sequence_name.x,fun.aggregate = length)