Above-Minimum Frequency Ratio

This function computes the ratio of values above a minimum value for each feature.

See the Details section below for further information.

Usage

rowAboveMinFreqRatio(x, g = NULL, min.expr = 0)

Arguments

x

matrix or data.frame, where rows are features and columns are observations.

g

(optional) vector or factor object giving the group for the corresponding elements of x.

min.expr

numerical value indicating the minimum expression required for min.prop samples.

Value

A vector of length nrow(x) containing the computed ratios. If g is provided, a matrix with ratios for each class as column vectors is returned.

Details

For each feature, the above-minimum frequency ratio (AMFR) is computed as:

$$Above-Minimum Frequency Ratio (AMFR) = \frac{Number of samples where expression is greater than provided minimum}{Total number of observations}$$

If g is provided, the above-minimum frequency ratio (\(AMFR_{ij}\)) is computed for each group \(j\) as:

$$AMFR_{ij} = \frac{Number of samples in j-th class where expression is greater than provided minimum}{Total number of observations in j-th class}$$

Author

Alessandro Barberis

Examples

#Seed
set.seed(1010)

#Define row/col size
nr = 5
nc = 10

#Data
x = matrix(
 data = sample.int(n = 100, size = nr*nc, replace = TRUE),
 nrow = nr,
 ncol = nc,
 dimnames = list(
   paste0("f",seq(nr)),
   paste0("S",seq(nc))
 )
)

#Grouping variable
g = c(rep("a", nc/2), rep("b", nc/2))

#AMFR
rowAboveMinFreqRatio(x)
#> f1 f2 f3 f4 f5 
#>  1  1  1  1  1 

#AMFR by group
rowAboveMinFreqRatio(x = x, g = g)
#>    a b
#> f1 1 1
#> f2 1 1
#> f3 1 1
#> f4 1 1
#> f5 1 1