从一个数据帧中获取数据，然后在R

Question

我有这样的桌子（下图）。

gene_nameIGHV1-11IGHV1-12IGHV1-15ighv1-18IGHV1-19 sample_50.01747729IGHV1-2 sample_6 sample_70.00103484IGHV1-13Sample_80.01517765IGHV1-160.007588820.00827872中的此表（下）

sample_name	GENE_FRACTION
Sample_1	0.00057491
Sample_2	0.0044843
Sample_3	0.01253306
Sample_4	0.00942854
0.00034495		IGHV1-11
		sample_9
	ighv1-18	Sample_10
		如何将上表转换为r？

sample_name

IGHV1-11

IGHV1-12IGHV1-15ighv1-18IGHV1-19IGHV1-2IGHV1-13IGHV1-160.00448430 sample_2wt00.00448430000000 sample_4mt0000.0094285400000.01747729 sample_6wt000000.00034495000 sample_8wt0000000.0151776500 sample_10mt0000.0082787200000 thanks填充您的附加逻辑MT或WT是硬编码，我们忽略了样本11，因为它不是您的第一个数据帧的一部分，您可以使用@L Tyrone的-apprach或在：

df <- data.frame(
  Gene_name = c("IGHV1-11", "IGHV1-12", "IGHV1-15", "IGHV1-18", "IGHV1-19", 
                "IGHV1-2", "IGHV1-11", "IGHV1-13", "IGHV1-16", "IGHV1-18"),
  Sample_name = c("sample_1", "sample_2", "sample_3", "sample_4", "sample_5", 
                  "sample_6", "sample_7", "sample_8", "sample_9", "sample_10"),
  Gene_fraction = c(0.00057491, 0.0044843, 0.01253306, 0.00942854, 0.01747729, 
                    0.00034495, 0.00103484, 0.01517765, 0.00758882, 0.00827872)
)

# In tidyverse
library(tidyverse)

df1 <- df %>% 
  mutate(Sample_name = ifelse( # your logic of adding suffix MT/WT
    as.numeric(gsub("sample_", "", Sample_name)) %in% c(4, 7, 9, 10, 11),
    paste0(Sample_name, "MT"),
    paste0(Sample_name, "WT")
  )) %>%
  pivot_wider(names_from = Gene_name, # pivoting wider
              values_from = Gene_fraction,
              values_fill = 0)

# or in base R
df2 <- df
# Modify sample names
df2$Sample_name <- ifelse(as.numeric(sub("sample_", "", df2$Sample_name)) %in% c(4, 7, 9, 10, 11),
                         paste0(df$Sample_name, "MT"),
                         paste0(df$Sample_name, "WT"))

# Pivot to wide format
df2 <- reshape(df2, idvar = "Sample_name", timevar = "Gene_name", 
                   direction = "wide", v.names = "Gene_fraction")

colnames(df2) <- gsub("Gene_fraction.", "", colnames(df2))

# Replace NA with 0 
df2[is.na(df2)] <- 0

							sample_1wt	0.00057491
0	0	0	0	0
					sample_3wt	0	0	0.01253306
0	0	0	0
				sample_5wt	0	0	0	0
0	0	0
			sample_7mt	0.00103484	0	0	0	0
0	0
		sample_9mt	0	0	0	0	0	0
0.00758882
	sample_11mt	0	0	0	0	0.04679775	0	0
		我应该在每一行上迭代并将值附加到新的数据框中吗？			tidyverse	base R	中使用它。