MarkerTest: ROC-based marker discovery

In tangchao7498/ICAS:

Description

Identifies 'markers' of SJ expression using ROC analysis. For each SJ, evaluates (using AUC) a classifier built on that SJ alone, to classify between two groups of cells.

Usage

MarkerTest(object, cells.1, cells.2, genes.use = NULL,
  print.bar = TRUE)

Arguments

object	ICASDataSet object
cells.1	Group 1 cells
cells.2	Group 2 cells
genes.use	SJs to test. Default is to use all SJs
print.bar	Print a progress bar once expression testing begins (uses pbapply to do this)

Details

An AUC value of 1 means that expression values for this SJ alone can perfectly classify the two groupings (i.e. Each of the cells in cells.1 exhibit a higher level than each of the cells in cells.2). An AUC value of 0 also means there is perfect classification, but in the other direction. A value of 0.5 implies that the SJ has no predictive power to classify the two groups.

Value

Returns a 'predictive power' (abs(AUC-0.5)) ranked matrix of putative differentially expressed SJs.

tangchao7498/ICAS documentation built on Jan. 28, 2021, 3:56 p.m.