FastMINE2: Plus version of MINE correlation

In huangwb8/lucky: Launch Usual Clinical tool for Kind Yield

Description

Plus version of MINE correlation.We recommnand FastMINE2 intead of old function FastMINE.

Usage

FastMINE2(data, transposition = F, control.markers = NULL,
  target.markers = NULL, alpha = 0.6, nperm = 1000, seed = 1234,
  p.adjust.method = "BH", n.cores = 1)

Arguments

data	a data frame or a matrix
control.markers	control markers
target.markers	target markers
alpha	In the original article, the authors state that the default value α=0.6 (which is the exponent of the search-grid size B(n)=n^α) has been empirically chosen. It is worthwhile noting that alpha and C are defined to obtain an heuristic approximation in a reasonable amount of time. In case of small sample size (etc. n<=63) it is preferable to increase alpha to 1 to obtain a solution closer to the theoretical one. Note: if you set α=1 in a big sample size data set, it would be time-consuming.
nperm	integer, number of permutation to perform
seed	seed for random number generation reproducibility
p.adjust.method	method for pvalue adjustment, see p.adjust for available methods.
n.cores	the core of parallel calculation
transpositon	if you have a data frame like sample on cols and markers on rows(etc. a conventional gene expression matrix), you should set transpositon=T

Details

It seems that even if you set control.markers=NULL and target.markers=NULL at the same time to calculate all pairs, it would not take much time than hours, which is recommanded to do deeper exploration for your data.

Author(s)

Weibin Huang<[e-mail]>

See Also

mine.

Examples

library(minerva)
data("Spellman")
data <- Spellman[1:100] # dim(Spellman)
colnames(data)

dat.cor <- FastMINE2(data)

dat.cor1 <- FastMINE2(data,control.markers = c("time"))

dat.cor2 <- FastMINE2(data,control.markers = c("time","YAL001C"))

huangwb8/lucky documentation built on Oct. 16, 2019, 9:01 a.m.