R 如何基于输出列中的值提取列名并获取计数
我对R中的数据帧操作有一个疑问，即根据输出列中以逗号分隔的值提取列名并获得计数 我有一个输入文件，在A列中包含基因，在其他列中包含文献ID。输入文件的示例如下所示。我想要的是收集输出列中值为1的所有文献ID，并在计数列中计算ID的数量。输出文件的示例如下所示。在此之后，我将使用这个输出文件合并数据帧，并使用merge函数合并感兴趣的基因列表。请帮我做这个R 如何基于输出列中的值提取列名并获取计数,r,dataframe,merge,dplyr,tidyr,R,Dataframe,Merge,Dplyr,Tidyr,我对R中的数据帧操作有一个疑问，即根据输出列中以逗号分隔的值提取列名并获得计数 我有一个输入文件，在A列中包含基因，在其他列中包含文献ID。输入文件的示例如下所示。我想要的是收集输出列中值为1的所有文献ID，并在计数列中计算ID的数量。输出文件的示例如下所示。在此之后，我将使用这个输出文件合并数据帧，并使用merge函数合并感兴趣的基因列表。请帮我做这个 Input_data <- read.csv(file = "./Input.csv", stringsAsFact
Input_data <- read.csv(file = "./Input.csv", stringsAsFactors = FALSE, check.names = FALSE)
Output_data <- read.csv(file = "./Output.csv", stringsAsFactors = FALSE, check.names = FALSE)
Genes <- read.csv(file = "./Genes.csv", stringsAsFactors = FALSE, check.names = FALSE)
Merge_data <- merge(Output_data, Genes, by = "Genes")
Input_data
dput(Input_data)
structure(list(Genes = c("Gene_A", "Gene_B", "Gene_C", "Gene_D",
"Gene_E", "Gene_F", "Gene_G", "Gene_H", "Gene_I", "Gene_J", "Gene_K",
"Gene_L", "Gene_M"), `20706538` = c(0L, 1L, 1L, 1L, 0L, 1L, 1L,
1L, 0L, 0L, 0L, 0L, 0L), `14557386` = c(0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L), `22999554` = c(0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), `21906313` = c(1L, 1L, 1L, 1L,
0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 1L), `25229268` = c(1L, 1L, 1L,
0L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L), `22633082` = c(0L, 1L,
1L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L), `19228761` = c(1L,
1L, 1L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L), `19543402` = c(0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), `26955776` = c(1L,
1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L), `21126355` = c(1L,
1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 1L)), class = "data.frame", row.names = c(NA,
-13L))
Output_data
dput(Output_data)
structure(list(Genes = c("Gene_A", "Gene_B", "Gene_C", "Gene_D",
"Gene_E", "Gene_F", "Gene_G", "Gene_H", "Gene_I", "Gene_J", "Gene_K",
"Gene_L", "Gene_M"), Output = c("21906313, 25229268, 19228761, 26955776, 21126355",
"20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355",
"20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355",
"20706538, 21906313, 22633082, 19228761, 26955776, 21126355",
"", "20706538, 21906313, 25229268, 22633082, 26955776, 21126355",
"20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355",
"20706538, 21906313, 25229268, 22633082, 26955776, 21126355",
"", "", "", "", "21906313, 21126355"), Counts = c(5L, 7L, 7L,
6L, 0L, 6L, 7L, 6L, 0L, 0L, 0L, 0L, 2L)), class = "data.frame", row.names = c(NA,
-13L))
Genes
dput(Genes)
structure(list(Genes = c("Gene_A", "Gene_B", "Gene_C", "Gene_D",
"Gene_E", "Gene_F", "Gene_G", "Gene_H", "Gene_I", "Gene_J", "Gene_K",
"Gene_L", "Gene_M", "Gene_N", "Gene_O", "Gene_P", "Gene_Q", "Gene_R",
"Gene_S", "Gene_T", "Gene_U", "Gene_V", "Gene_W")), class = "data.frame", row.names = c(NA,
-23L))
这是使用tidyr和dplyr包的可能解决方案 基本上，我们首先确保您的数据是可用的，也就是说，您可以使用pivot_longer函数以更简单的方式处理数据，然后我们应用非常标准的dplyr语句来创建所需的输出。如果您不熟悉它们，我建议您一次运行管道的一个步骤，并了解每个通道的功能
library(tidyr)
library(dplyr)
Input_data %>%
pivot_longer(-Genes, names_to = "num", values_to = "value") %>%
group_by(Genes) %>%
mutate(
Output = paste(num[value == 1], collapse = ", "),
Counts = sum(value == 1)
) %>%
select(-c(num, value)) %>%
distinct() %>%
right_join(Genes, by = "Genes")
# A tibble: 23 x 3
# Groups: Genes [23]
# Genes Output Counts
# <chr> <chr> <int>
# 1 Gene_A "21906313, 25229268, 19228761, 26955776, 21126355" 5
# 2 Gene_B "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
# 3 Gene_C "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
# 4 Gene_D "20706538, 21906313, 22633082, 19228761, 26955776, 21126355" 6
# 5 Gene_E "" 0
# 6 Gene_F "20706538, 21906313, 25229268, 22633082, 26955776, 21126355" 6
# 7 Gene_G "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
# 8 Gene_H "20706538, 21906313, 25229268, 22633082, 26955776, 21126355" 6
# 9 Gene_I "" 0
# 10 Gene_J "" 0
# ... with 13 more rows
这是使用tidyr和dplyr包的可能解决方案 基本上，我们首先确保您的数据是可用的，也就是说，您可以使用pivot_longer函数以更简单的方式处理数据，然后我们应用非常标准的dplyr语句来创建所需的输出。如果您不熟悉它们，我建议您一次运行管道的一个步骤，并了解每个通道的功能
library(tidyr)
library(dplyr)
Input_data %>%
pivot_longer(-Genes, names_to = "num", values_to = "value") %>%
group_by(Genes) %>%
mutate(
Output = paste(num[value == 1], collapse = ", "),
Counts = sum(value == 1)
) %>%
select(-c(num, value)) %>%
distinct() %>%
right_join(Genes, by = "Genes")
# A tibble: 23 x 3
# Groups: Genes [23]
# Genes Output Counts
# <chr> <chr> <int>
# 1 Gene_A "21906313, 25229268, 19228761, 26955776, 21126355" 5
# 2 Gene_B "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
# 3 Gene_C "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
# 4 Gene_D "20706538, 21906313, 22633082, 19228761, 26955776, 21126355" 6
# 5 Gene_E "" 0
# 6 Gene_F "20706538, 21906313, 25229268, 22633082, 26955776, 21126355" 6
# 7 Gene_G "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
# 8 Gene_H "20706538, 21906313, 25229268, 22633082, 26955776, 21126355" 6
# 9 Gene_I "" 0
# 10 Gene_J "" 0
# ... with 13 more rows
您的数据是宽格式的，这意味着一行/观测值具有多个值。当您的数据是长格式时更容易，这意味着每行只有一个值。看一看 我的解决方案与@Ric S非常相似，我使用Summary，而不是mutate，它适用于这样的情况，即您希望分组变量的每个级别都只有一个条目：
Input_data <- structure(list(Genes = c("Gene_A", "Gene_B", "Gene_C", "Gene_D",
"Gene_E", "Gene_F", "Gene_G", "Gene_H", "Gene_I", "Gene_J", "Gene_K",
"Gene_L", "Gene_M"), `20706538` = c(0L, 1L, 1L, 1L, 0L, 1L, 1L,
1L, 0L, 0L, 0L, 0L, 0L), `14557386` = c(0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L), `22999554` = c(0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), `21906313` = c(1L, 1L, 1L, 1L,
0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 1L), `25229268` = c(1L, 1L, 1L,
0L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L), `22633082` = c(0L, 1L,
1L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L), `19228761` = c(1L,
1L, 1L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L), `19543402` = c(0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), `26955776` = c(1L,
1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L), `21126355` = c(1L,
1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 1L)), class = "data.frame", row.names = c(NA,
-13L))
Genes <- structure(list(Genes = c("Gene_A", "Gene_B", "Gene_C", "Gene_D",
"Gene_E", "Gene_F", "Gene_G", "Gene_H", "Gene_I", "Gene_J", "Gene_K",
"Gene_L", "Gene_M", "Gene_N", "Gene_O", "Gene_P", "Gene_Q", "Gene_R",
"Gene_S", "Gene_T", "Gene_U", "Gene_V", "Gene_W")), class = "data.frame", row.names = c(NA,
-23L))
library(dplyr)
library(tidyr)
summary_data <- Input_data %>%
pivot_longer(-Genes, values_to = "is_contained", names_to = "literature_id") %>%
group_by(Genes) %>%
filter(is_contained == 1) %>%
summarise(Output = paste0(literature_id, collapse = ", "),
Counts = n()) %>%
right_join(Genes) %>%
mutate(Output = if_else(is.na(Output),
"",
Output),
Counts = if_else(is.na(Counts),
0L,
Counts))
summary_data
# A tibble: 23 x 3
Genes Output Counts
<chr> <chr> <int>
1 Gene_A "21906313, 25229268, 19228761, 26955776, 21126355" 5
2 Gene_B "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
3 Gene_C "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
4 Gene_D "20706538, 21906313, 22633082, 19228761, 26955776, 21126355" 6
5 Gene_E "" 0
6 Gene_F "20706538, 21906313, 25229268, 22633082, 26955776, 21126355" 6
7 Gene_G "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
8 Gene_H "20706538, 21906313, 25229268, 22633082, 26955776, 21126355" 6
9 Gene_I "" 0
10 Gene_J "" 0
# ... with 13 more rows
您的数据是宽格式的，这意味着一行/观测值具有多个值。当您的数据是长格式时更容易，这意味着每行只有一个值。看一看 我的解决方案与@Ric S非常相似，我使用Summary，而不是mutate，它适用于这样的情况，即您希望分组变量的每个级别都只有一个条目：
Input_data <- structure(list(Genes = c("Gene_A", "Gene_B", "Gene_C", "Gene_D",
"Gene_E", "Gene_F", "Gene_G", "Gene_H", "Gene_I", "Gene_J", "Gene_K",
"Gene_L", "Gene_M"), `20706538` = c(0L, 1L, 1L, 1L, 0L, 1L, 1L,
1L, 0L, 0L, 0L, 0L, 0L), `14557386` = c(0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L), `22999554` = c(0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), `21906313` = c(1L, 1L, 1L, 1L,
0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 1L), `25229268` = c(1L, 1L, 1L,
0L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L), `22633082` = c(0L, 1L,
1L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L), `19228761` = c(1L,
1L, 1L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L), `19543402` = c(0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L), `26955776` = c(1L,
1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 0L), `21126355` = c(1L,
1L, 1L, 1L, 0L, 1L, 1L, 1L, 0L, 0L, 0L, 0L, 1L)), class = "data.frame", row.names = c(NA,
-13L))
Genes <- structure(list(Genes = c("Gene_A", "Gene_B", "Gene_C", "Gene_D",
"Gene_E", "Gene_F", "Gene_G", "Gene_H", "Gene_I", "Gene_J", "Gene_K",
"Gene_L", "Gene_M", "Gene_N", "Gene_O", "Gene_P", "Gene_Q", "Gene_R",
"Gene_S", "Gene_T", "Gene_U", "Gene_V", "Gene_W")), class = "data.frame", row.names = c(NA,
-23L))
library(dplyr)
library(tidyr)
summary_data <- Input_data %>%
pivot_longer(-Genes, values_to = "is_contained", names_to = "literature_id") %>%
group_by(Genes) %>%
filter(is_contained == 1) %>%
summarise(Output = paste0(literature_id, collapse = ", "),
Counts = n()) %>%
right_join(Genes) %>%
mutate(Output = if_else(is.na(Output),
"",
Output),
Counts = if_else(is.na(Counts),
0L,
Counts))
summary_data
# A tibble: 23 x 3
Genes Output Counts
<chr> <chr> <int>
1 Gene_A "21906313, 25229268, 19228761, 26955776, 21126355" 5
2 Gene_B "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
3 Gene_C "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
4 Gene_D "20706538, 21906313, 22633082, 19228761, 26955776, 21126355" 6
5 Gene_E "" 0
6 Gene_F "20706538, 21906313, 25229268, 22633082, 26955776, 21126355" 6
7 Gene_G "20706538, 21906313, 25229268, 22633082, 19228761, 26955776, 21126355" 7
8 Gene_H "20706538, 21906313, 25229268, 22633082, 26955776, 21126355" 6
9 Gene_I "" 0
10 Gene_J "" 0
# ... with 13 more rows
有了你的解决方案，我更好地理解了在这种情况下使用摘要而不是变异的优点，谢谢@starja+1@starja，谢谢你的解决方案，这非常有帮助。@starja，这对我的大规模数据很有帮助。我发现有数百个重复的基因具有相同的信息。我如何只提取我专栏中的独特基因而不是重复基因。谢谢你，Toufitry summary\u data%>%distinctGenes、.keep\u all=true使用你的解决方案，我更好地理解在这种情况下使用summary而不是变异的优点，谢谢@starja+1@starja，谢谢你的解决方案，这非常有帮助。@starja，这对我的大规模数据很有帮助。我发现有数百个重复的基因具有相同的信息。我如何只提取我专栏中的独特基因而不是重复基因。谢谢，Toufitry summary\u data%>%distinctGenes，.keep\u all=TRUE