Vfrdtyky

I am fairly new to R. My data looks something like this (only with 9000 columns and 66 rows)

Time <- c(0, 6.4, 8.6, 15.2, 19.4, 28.1, 42.6, 73, 73, 85, 88, 88, 88, 88, 88)

ID1 <- c(55030, 54539, 54937, 48897, 58160, 54686, 55393, 47191, 39805, 37601, 51328, 28882, 45587, 60061, 31892, 28670)

ID2 <- c(20485, 11907, 10571, 20974, 10462, 11149, 20970, NA, NA, 9295, NA, 8714, 24446, 10748, 9037, 11859)

ID3 <- c(93914, 44482, 43705, 51144, 49485, 43908, 44324, 37342, 18872, 39660,61673, 43837, 36528, 44738, 41648, 11100)

DF <- data.frame (Time, ID1, ID2, ID3)

I want to get a data frame that looks like this :

ID1, rho, p-value

ID2, rho, p-value

...

The rho and the p-value would be the results from a cor.test (spearman) with Time and each ID

Among other things I've tried this:

results <- data.frame(ID="", Estimate="", P.value="")

estimates = numeric(16)

pvalues = numeric(16)

for (i in 2:4){

  test <- cor.test(DF[,1], DF[,i])

  estimates[i] = test$estimate

  pvalues[i] = test$p.value

}

And R gives me the following error:

Error: object 'test' not found

I've also tried:

result <- do.call(rbind,lapply(2:4, function(x) {

  cor.result<-cor.test(DF[,1],DF[,x])

  pvalue <- cor.result$p.value

  estimate <- cor.result$estimate

  return(data.frame(pvalue = pvalue, estimate = estimate))

})

)

And R gives me a similar error

Error: object 'cor.result' not found

I'm sure it's an easy fix but I can't seem to figure it out. Any help is more than welcome.

This is what I got after running

dput(head(SmallDataset[,1:5]))



structure(list(Species = c("Human.hsapiens", "Chimpanzee.ptroglodytes", 

"Gorilla.ggorilla", "Orangutan.pabelii", "Gibbon.nleucogenys", 

"Macaque.mmulatta"), Time = c(0, 6.4, 8.61, 15.2, 19.43, 28.1

), ID1 = c(55030, 54539, 54937, 48897, 58160, 54686), ID2 = c(20485, 

11907, 10571, 20974, 10462, 11149), ID3 = c(93914, 44482, 43705, 

51144, 49485, 43908)), row.names = c(NA, -6L), class = c("tbl_df", 

"tbl", "data.frame"))

My solution involves defining a function within a lapply call

##

library(dplyr)



###Create dataframe

Time <- c(0, 6.4, 8.6, 15.2, 19.4, 28.1, 42.6, 73, 73, 85, 88, 88, 88, 88, 88, 89)

ID1 <- c(55030, 54539, 54937, 48897, 58160, 54686, 55393, 47191, 39805, 37601, 51328, 28882, 45587, 60061, 31892, 28670)

ID2 <- c(20485, 11907, 10571, 20974, 10462, 11149, 20970, NA, NA, 9295, NA, 8714, 24446, 10748, 9037, 11859)

ID3 <- c(93914, 44482, 43705, 51144, 49485, 43908, 44324, 37342, 18872, 39660,61673, 43837, 36528, 44738, 41648, 11100)

DF <- data.frame (Time, ID1, ID2, ID3)



##Run the correlations

l2 <- lapply(2:4, function(i)cor.test(DF$Time, DF[,i]))



##Define function to extract p_value and coefficients

l3 <- lapply(l2, function(i){

  return(tibble(estimate = i$estimate,

         p_value = i$p.value))

})



##Create a dataframe with information

l4 <- bind_rows(l3) %>% mutate(ID = paste0("ID", 1:3)) ##Data frame with info



l4

Consider building a list of data frames witih lapply (an iteration function similar to for but builds a list of objects of equal length as input). Afterwards, row bind all data frame elements together:

results <- lapply(2:4, function(i){      

  test <- cor.test(DF[,1], DF[,i])



  data.frame(ID = names(DF)[i],

             estimate =  unname(test$estimate),

             pvalues = unname(test$p.value))      

})



final_df <- do.call(rbind, results)

final_df



#    ID   estimate     pvalues

# 1 ID1 -0.6238591 0.009805341

# 2 ID2 -0.2270515 0.455676037

# 3 ID3 -0.4964092 0.050481533

NOTE: Your posted data for Time is missing an observation and cannot immediately be cast into data.frame() with other vectors. To resolve, I supplemented a 6th 88 at end:

Time <- c(0, 6.4, 8.6, 15.2, 19.4, 28.1, 42.6, 73, 73, 85, 88, 88, 88, 88, 88, 88)

Using posted SmallDataset:

SmallDataset <- structure(...)



results <- lapply(3:5, function(i){      

  test <- cor.test(SmallDataset$Time, SmallDataset[,i])



  data.frame(ID = names(SmallDataset)[i],

             estimate =  unname(test$estimate),

             pvalues = unname(test$p.value))      

})



final_df <- do.call(rbind, results)

final_df



#    ID    estimate   pvalues

# 1 ID1  0.03251407 0.9512461

# 2 ID2 -0.41733336 0.4103428

# 3 ID3 -0.60732484 0.2010166