Description Usage Arguments Details Value Examples
makeBinarySig
Convert some sort of significance distribution
to binary signifcance calls.
1 2 | makeBinarySig(x, alpha = 0.05, what = "q.value", na.include = TRUE,
verbose = TRUE)
|
x |
A dataframe or matrix containing the significance (p/q/fdr p) values to convert |
alpha |
The threshold that defines what is and is not significance |
what |
Character vector defining a string to look for in the column names. For example, "q.value" |
na.include |
Logical, should NAs be classified as not significant? If false, all rows with any NAs are dropped. |
verbose |
Logical, should the number of significant values be printed |
Given a matrix with p/q values, this function greps for the string in "what" and classifies each column as either significant (1) or not (0). Esspecially useful for a dataset that has many p-value or q-value columns
a dataframe with all values in the original matrix with column names containing what, where the values have been transformed to binary
1 2 3 4 5 6 7 8 9 | ## Not run:
data(kidney) # from SimSeq
counts<-kidney$counts
counts<-counts[sample(1:nrow(counts),1000),]
info<-data.frame(rep=kidney$replic, treatment=kidney$treatment)
stats<-pipeLIMMA(counts=counts, info=info, formula = " ~ treatment", block=NULL)
sig<-makeBinarySig(x= stats$stats, what="Pvalue")
## End(Not run)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.