DESnowball (version 1.0)

select.features: Compute ranking statistics, RD, and p value for gene selection

Description

Gene selection based on the statistical significances according to the Snowball approach (see references for more details).

Usage

select.features(x, cutoff.p = 0.05, p.adjust.method = "BH")

Arguments

x

an output from the main function snowball

cutoff.p

cutoff for top gene list. This is applied on the multiple testing adjusted p values

p.adjust.method

specifies a multiple testing adjustment method, see p.adjust for more details

Value

a list with two elements - fullList and selectedList.fullLIst is a data.frame that contains rd, pval and positive, corresponding respectively to the RD, p value and an indicator variable of weather the RD value is above or below the median value. selectedList is a data.frame that contains the same variables as those in fullList with only the top genes that satisfy the significance cutoff specified by cutoff.p.

References

Xu, Y., Guo, X., Sun, J. and Zhao. Z. Snowball: resampling combined with distance-based regression to discover transcriptional consequences of driver mutation, manuscript.