Description Usage Arguments Value Examples
This is equivalent to the 'modz' procedure used in collapsing replicates in traditional L1000 data processing. The weight for each replicate is computed as its normalized average correlation to the other replicates in the set.
1 | distil(m, dimension = "col", method = "spearman")
|
m |
a numeric matrix where the rows or columns are assumed to be replicates |
dimension |
the dimension to collapse. either 'row' or 'col' |
method |
the correlation method to use |
a list with the following elements
a vector of the collapsed values
a vector of the pairwise correlations
a vector of the computed weights
1 2 |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.