R 使用unite和map整理评估，以便取消嵌套列表数据集的测试

我正在尝试卸载我用pivot_生成的数据集， 其中有多个列需要取消列表。 在完整数据集上，unnest函数不起作用（我得到一个错误：>错误：不兼容的长度：3,2。） 所以我尝试了一个解决办法 数据集的一部分：

 my_data <-  structure(list(RNAcentral_id = c("URS000000C731", "URS000000C731", 
"URS000000C731", "URS000000C731", "URS000001F3AA", "URS000001F3AA", 
"URS000001F3AA", "URS000001F3AA", "URS000001F3AA", "URS000001F3AA", 
"URS000001F3AA", "URS000001F3AA", "URS000001F3AA", "URS000001F3AA", 
"URS0000023ED8", "URS0000023ED8", "URS0000023ED8", "URS0000023ED8", 
"URS0000023ED8", "URS0000023ED8", "URS0000023ED8", "URS0000023ED8", 
"URS0000023ED8", "URS0000023ED8", "URS0000023ED8", "URS0000023ED8", 
"URS0000050C72", "URS0000050C72", "URS0000050C72", "URS0000050C72", 
"URS0000050C72", "URS0000050C72", "URS0000050C72", "URS0000050C72", 
"URS0000050C72", "URS0000050C72", "URS0000050C72", "URS0000050C72", 
"URS0000050C72", "URS0000050C72", "URS0000050C72", "URS0000050C72", 
"URS00000527A6", "URS00000527A6", "URS00000527A6", "URS00000527A6", 
"URS00000527A6", "URS00000527A6", "URS00000527A6", "URS00000527A6", 
"URS00000527A6", "URS000007CAC8", "URS000007CAC8", "URS000007CAC8", 
"URS000007CAC8", "URS000007CAC8", "URS000007DA54", "URS000007DA54", 
"URS000007DA54", "URS000007DA54", "URS000007DA54", "URS000007DA54", 
"URS000007DA54", "URS000007DA54", "URS000007F1D7", "URS000007F1D7", 
"URS000007F1D7", "URS000007F1D7", "URS000007F1D7", "URS000007F1D7", 
"URS000007F1D7", "URS000007F1D7", "URS000007F1D7", "URS000007F1D7", 
"URS0000088F47", "URS0000088F47", "URS0000088F47", "URS0000088F47", 
"URS0000088F47", "URS0000088F47", "URS0000088F47", "URS00000B589B", 
"URS00000B589B", "URS00000B589B", "URS00000B589B", "URS00000B589B", 
"URS00000B589B", "URS00000B589B"), Database = c("ENSEMBL", "ENSEMBL", 
"ENSEMBL", "GENCODE", "ENSEMBL", "ENSEMBL", "ENSEMBL", "ENSEMBL", 
"ENSEMBL", "ENSEMBL", "ENSEMBL", "ENSEMBL", "GENCODE", "LNCIPEDIA", 
"ENSEMBL", "ENSEMBL", "ENSEMBL", "ENSEMBL", "GENECARDS", "LNCBOOK", 
"LNCIPEDIA", "NONCODE", "NONCODE", "NONCODE", "NONCODE", "NONCODE", 
"ENSEMBL", "ENSEMBL", "ENSEMBL", "ENSEMBL", "ENSEMBL", "ENSEMBL", 
"ENSEMBL", "GENCODE", "LNCBOOK", "NONCODE", "NONCODE", "NONCODE", 
"NONCODE", "NONCODE", "NONCODE", "NONCODE", "ENSEMBL", "ENSEMBL", 
"ENSEMBL", "GENCODE", "GENECARDS", "GENECARDS", "LNCBOOK", "LNCIPEDIA", 
"NONCODE", "ENSEMBL", "ENSEMBL", "ENSEMBL", "GENCODE", "NONCODE", 
"ENSEMBL", "ENSEMBL", "ENSEMBL", "ENSEMBL", "ENSEMBL", "GENCODE", 
"LNCBOOK", "NONCODE", "ENSEMBL", "ENSEMBL", "ENSEMBL", "ENSEMBL", 
"GENCODE", "LNCBOOK", "NONCODE", "NONCODE", "NONCODE", "NONCODE", 
"ENSEMBL", "ENSEMBL", "ENSEMBL", "ENSEMBL", "GENCODE", "GENECARDS", 
"LNCIPEDIA", "ENA", "ENSEMBL", "ENSEMBL", "ENSEMBL", "ENSEMBL", 
"ENSEMBL", "GENCODE"), RNA_type = c("lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", "lncRNA", 
"lncRNA", "snoRNA", "snoRNA", "snoRNA", "snoRNA", "snoRNA", "snoRNA", 
"snoRNA"), gene_name = c("ENSG00000250666.1", "ENSG00000281830.1", 
"ENSG00000281377.1", "LINC01596", "ENSG00000242086.8", "ENSG00000280512.2", 
"ENSG00000281603.2", "ENSG00000281060.2", "ENSG00000281794.2", 
"ENSG00000281915.2", "ENSG00000280993.2", "ENSG00000282953.1", 
"MUC20-OT1", "lnc-MUC20-67", "ENSG00000235273.1", "ENSG00000233950.1", 
"ENSG00000230089.1", "ENSG00000225188.1", "LOC101929006", "HSALNG0049045", 
"lnc-OR14J1-2", "NONHSAG043350.2", "NONHSAG045640.2", "NONHSAG045830.2", 
"NONHSAG046018.2", "NONHSAG046538.2", "ENSG00000231860.1", "ENSG00000224328.1", 
"ENSG00000236766.1", "ENSG00000224508.1", "ENSG00000236522.1", 
"ENSG00000229681.1", "ENSG00000233883.1", "MDC1-AS1", "HSALNG0049184", 
"NONHSAG043427.2", "NONHSAG045580.2", "NONHSAG045701.2", "NONHSAG045891.2", 
"NONHSAG046074.2", "NONHSAG046228.2", "NONHSAG046589.2", "ENSG00000249981.1", 
"ENSG00000276297.1", "ENSG00000280619.1", "AC145141.1", "LOC107987420", 
"LOC107987434", "HSALNG0042531", "lnc-BDP1-1", "NONHSAG040656.2", 
"ENSG00000242086.8", "ENSG00000280512.2", "ENSG00000281794.2", 
"MUC20-OT1", "NONHSAG037073.2", "ENSG00000242086.8", "ENSG00000280512.2", 
"ENSG00000281794.2", "ENSG00000281060.2", "ENSG00000282953.1", 
"MUC20-OT1", "HSALNG0031832", "NONHSAG037073.2", "ENSG00000224835.1", 
"ENSG00000227198.1", "ENSG00000233169.1", "ENSG00000225390.1", 
"C6orf47-AS1", "HSALNG0049305", "NONHSAG043504.2", "NONHSAG046125.2", 
"NONHSAG046270.2", "NONHSAG046461.2", "ENSG00000272566.1", "ENSG00000280590.1", 
"ENSG00000280853.1", "ENSG00000281916.1", "AF250324.1", "ENSG00000272566", 
"lnc-FRG2-13", "ACA38 snoRNA", "ENSG00000200816.1", "ENSG00000266847.1", 
"ENSG00000263994.1", "ENSG00000264153.1", "ENSG00000263879.1", 
"SNORA38")), row.names = c(NA, -88L), class = c("tbl_df", "tbl", 
"data.frame"), spec = structure(list(cols = list(RNAcentral_id = structure(list(), class = c("collector_character", 
"collector")), Database = structure(list(), class = c("collector_character", 
"collector")), external_id = structure(list(), class = c("collector_character", 
"collector")), NCBI_taxon_id = structure(list(), class = c("collector_double", 
"collector")), RNA_type = structure(list(), class = c("collector_character", 
"collector")), gene_name = structure(list(), class = c("collector_character", 
"collector"))), default = structure(list(), class = c("collector_guess", 
"collector")), delim = "\t"), class = "col_spec"))

我的解决方法尝试：

mynested_data <- my_data %>% 
         pivot_wider(names_from = Database, values_from = c(gene_name))

c("ENSEMBL", "GENCODE", "NONCODE", "ENA", "GENECARDS", "LNCBOOK", 
  "LNCIPEDIA") %>% 
   set_names(.) %>% 
   map(~ mynested_data %>%  
         unnest_wider(.x, names_sep = "_") %>%
         unite(col = !!.x, vars(starts_with(!!quo(.x))), sep = ";"))

Error: Must subset columns with a valid subscript vector.
x Subscript has the wrong type `quosures`.
\u2139 It must be numeric or character.
Run `rlang::last_error()` to see where the error occurred.

myu嵌套数据%
pivot_更宽（名称来自=数据库，值来自=c（基因名称））
c（“ENSEMBL”、“GENCODE”、“NONCODE”、“ENA”、“GENECARDS”、“LNCBOOK”，
“保密媒体”）%%>%
设置_名称（%）%%>%
映射（~mynested_data%>%
unnest_加宽（.x，名称_sep=“”）%%>%
unite（col=！！.x，vars（以（！！quo（.x））开头），sep=“；”）
错误：必须使用有效的下标向量子集列。
x下标的类型“quosures”错误。
\u2139必须是数字或字符。
运行`rlang:：last_error（）`查看错误发生的位置。

在unite中，我还尝试使用

col=.x

或

col=！！quo（.x）

但我得到了相同的错误

Edit1我期望得到的结果 我这样做是为了得到一个每行（条目）有一个RNAU id的TIBLE，列表“columns”由多个条目组成的字符串用分隔符“；”连接起来。 ENSEMBL一列、GENCODE一列等

---

我们可以在这里直接使用

pivot\u wide

：

tidyr::pivot_wider(my_data, names_from = Database, 
                    values_from = gene_name, values_fn = toString)

或在带有dcast的

数据表中：

library(data.table)
dcast(setDT(my_data), RNA_type + RNAcentral_id~ Database, 
      value.var = 'gene_name', fun.aggregate = toString)

对不起，我没有说结果。我需要每个RNAcentral_id有一行，这就是为什么我需要它更广泛地使用unnest_，以便在合并到生成的列后使用，并重新创建起始列。@KGeles Ohh..我明白了。所以，也许你需要更广泛的（我的数据，名字来自数据库，值来自基因，值来自于字符串）

？天哪，这是什么魔法：P。就是这样。。。。你能把它也包括在你的答案里吗。作为编辑？当然。更新了答案。

library(data.table)
dcast(setDT(my_data), RNA_type + RNAcentral_id~ Database, 
      value.var = 'gene_name', fun.aggregate = toString)