提问者:小点点

group_by总结和崩溃


我有以下数据框。

     df <- structure(list(Genecoverage = c(19.8511111111111, 10.1516966067864, 
14.5631205673759, 7.25225225225225, 10.774011299435, 11.4794520547945, 
17.7967032967033, 12.6770616770617, 14.1375, 13.2422422422422, 
14.0379403794038, 11.4844006568145, 21.296875, 18.90625, 24.3293253173013
), Gene = c("k141_32902_11", "k141_32902_16", "k141_32902_22", 
"k141_32902_23", "k141_32902_27", "k141_32902_28", "k141_32902_29", 
"k141_32902_3", "k141_32902_30", "k141_32902_37", "k141_32902_38", 
"k141_32902_5", "k141_3238_18", "k141_3238_3", "k141_3238_6"), 
    sample.x = c("10", "10", "10", "10", "10", "10", "10", "10", 
    "10", "10", "10", "10", "10", "10", "10"), Phylum = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "Firmicutes", class = "factor"), 
    Class = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
    2L, 2L, 1L, 1L, 1L), .Label = c("Bacilli", "Tissierellia"
    ), class = "factor"), Order = structure(c(2L, 2L, 2L, 2L, 
    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L), .Label = c("Bacillales", 
    "Tissierellales"), class = "factor"), Family = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("Peptoniphilaceae", 
    "Staphylococcaceae"), class = "factor"), Genus = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L), .Label = c("Peptoniphilus", 
    "Staphylococcus"), class = "factor"), Species = structure(c(1L, 
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "unknown", class = "factor"), 
    newgene = c("k141_32902", "k141_32902", "k141_32902", "k141_32902", 
    "k141_32902", "k141_32902", "k141_32902", "k141_32902", "k141_32902", 
    "k141_32902", "k141_32902", "k141_32902", "k141_3238", "k141_3238", 
    "k141_3238")), .Names = c("Genecoverage", "Gene", "sample.x", 
"Phylum", "Class", "Order", "Family", "Genus", "Species", "newgene"
), row.names = c("42481", "42486", "42493", "42494", "42498", 
"42499", "42500", "42501", "42502", "42509", "42510", "42512", 
"41540", "41546", "41552"), class = "data.frame")

这将返回以下数据帧

      Genecoverage          Gene sample.x     Phylum        Class          Order            Family          Genus Species    newgene
42481    19.851111 k141_32902_11       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
42486    10.151697 k141_32902_16       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
42493    14.563121 k141_32902_22       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
42494     7.252252 k141_32902_23       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
42498    10.774011 k141_32902_27       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
42499    11.479452 k141_32902_28       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
42500    17.796703 k141_32902_29       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
42501    12.677062  k141_32902_3       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
42502    14.137500 k141_32902_30       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
42509    13.242242 k141_32902_37       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
42510    14.037940 k141_32902_38       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
42512    11.484401  k141_32902_5       10 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
41540    21.296875  k141_3238_18       10 Firmicutes      Bacilli     Bacillales Staphylococcaceae Staphylococcus unknown  k141_3238
41546    18.906250   k141_3238_3       10 Firmicutes      Bacilli     Bacillales Staphylococcaceae Staphylococcus unknown  k141_3238
41552    24.329325   k141_3238_6       10 Firmicutes      Bacilli     Bacillales Staphylococcaceae Staphylococcus unknown  k141_3238

我想通过Gene计算中位数,并创建一个新的列,其中包含在聚合期间合并的新基因。

newdata <- data.frame(df%>%

 group_by(Phylum,Class,Order,Family,Genus,Species,newgene )%>%
        summarise_if(is.numeric, median))

这将返回以下内容

      Phylum        Class          Order            Family          Genus Species    newgene Genecoverage
1 Firmicutes      Bacilli     Bacillales Staphylococcaceae Staphylococcus unknown  k141_3238     21.29688
2 Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902     12.95965

我在这里的问题是我丢失了基因列的信息。因此,例如,理想情况下,我想创建一个新列,折叠所有基因列名。例如,在新基因上面的输出数据框中k141_3238对应于合并的基因k141_32902_11、k141_32902_16、k141_32902_22…

这就是最终数据帧的外观:

 Phylum        Class          Order            Family          Genus Species    newgene
Firmicutes      Bacilli     Bacillales Staphylococcaceae Staphylococcus unknown  k141_3238 
Firmicutes Tissierellia Tissierellales  Peptoniphilaceae  Peptoniphilus unknown k141_32902
  Genecoverage Concatenated_genes
        21.3 k141_3238_18,k141_3238_3,k141_3238_6
        13.0 k141_32902_11,k141_32902_16,k141_32902_22

共1个答案

匿名用户

我们可以将summarise_all与用户定义的函数一起使用。如果列是数字,此函数将计算中位数,否则使用toString连接所有字符串信息。

library(dplyr)

newdata <- df %>% 
  group_by(Phylum, Class, Order, Family, Genus, Species, newgene) %>%
  select(-sample.x) %>%
  summarise_all(funs(ifelse(is.numeric(.), median(.), toString(.)))) %>%
  rename(Concatenated_genes = Gene)