1

I'm trying to subset my current data frame with a new data frame that lists genes I'm investigating in one column and p-values in another (for each gene).

I have a data frame called m3 that looks like below:

Sample #          BRCA       TP53        MYC       Status       Overall Survival
1                   0          1          1          0             5.8
2                   1          0          0          1             8.4
3                   0          0          1          1             2.2
4                   0          0          0          0             16.2

The dimensions of my actual data frame are 72 x 258. I'm trying to loop through each column and calculate the p-value for the survival analysis I am running. I'm trying to determine if having a specific mutation will result in a statistically significant survival difference. I denote a patient has a mutation by 1 for each gene.

I have written a survival function for just one column, but I want to loop through each one and then ultimately subset it to create a new data frame. I am unsure if it would be wise to use the apply function (I have read that is common) or to use a for loop.

survfit(Surv(m3$Overall.Survival, m3$Status) ~m3$BRCA2, data = m3

I tried this initially, but it did not work...

for (col in 2:ncol(m3) ){surv.mod.list[col] <- survfit(S ~ m3[ , col], data = m3)}

Can you please help me with my loop?

4

1 回答 1

0

像这样的东西呢，使用lapply()？

library(survey)
m3.lst <- lapply(2:(ncol(m3)), function(x) {
  survfit(Surv(m3$Overall.Survival, m3$Status) ~ m3[, x], data = m3)
  })
m3.lst
于 2018-02-21T02:34:58.190 回答