the data set that should be analyzed. Every
row of this data set must correspond to a gene.
cl
a vector containing the class labels of the samples.
In the two class unpaired case, the label of a
sample is either 0 (e.g., control group) or 1
(e.g., case group). For one class data, the label for
each sample should be 1.
num.perm
number of permutations used in the
calculation of the null density. Default is 'num.perm=100'.
logged
if "TRUE", data has bee logged, otherwise set it
to "FALSE"
na.rm
if 'FALSE' (default), the NA value will not
be used in computing rank. If 'TRUE', the missing
values will be replaced by the gene-wise mean of
the non-missing values. Gene with all values missing
will be assigned "NA"
gene.names
if "NULL", no gene name will be assigned
to the estimated percentage of
false positive predictions (pfp).
plot
If "TRUE", plot the estimated pfp verse the
rank of each gene.
rand
if specified, the random number generator will
be put in a reproducible state using the rand value as seed.
huge
If "TRUE", use an alternative method for computation. Using
considerably less memory, this allows the Rank Product to be
calculated for larger input data (see details). However, the result
will not contain the Orirank value.
For input with n rows, m=m1+m2 columns for two classes, and k
permutations, memory requirements are 2n with huge=TRUE instead of
n*k+n*m1*m2.
Value
A result of identifying differentially expressed genes
between two classes. The identification consists of two parts,
the identification of up-regulated and down-regulated genes in
class 2 compared to class 1, respectively.
pfp
estimated percentage of false positive predictions
(pfp) up to the position of each gene under two
identificaiton each
pval
estimated pvalue for each gene being up- and down-regulated
RPs
Original rank-product of each genes for two
dentificaiton each
RPrank
rank of the rank product of each genes
Orirank
original rank in each comparison, which
is used to construct rank product. Not present if huge=TRUE is used.
AveFC
fold change of average expression under class 1 over
that under class 2. log-fold change if data is in log
scaled, original fold change if data is unlogged.
Note
Percentage of false prediction (pfp), in theory, is
equivalent of false
discovery rate (FDR), and it is possible to be large than 1.
The function looks for up- and down- regulated genes in two
seperate steps, thus two pfps and pvalues are computed and used to identify
gene that belong to each group.
This function is suitable to deal with data from a
single origin, e.g. single experiment. If the data has
different origin, e.g. generated at different
laboratories, please refer RP.advance.
Breitling, R., Armengaud, P., Amtmann, A., and Herzyk,
P.(2004) Rank Products:A simple, yet powerful, new method to
detect differentially regulated genes in
replicated microarray experiments, FEBS Letter, 57383-92
See Also
topGeneRPadvanceplotRP
Examples
# Load the data of Golub et al. (1999). data(golub)
# contains a 3051x38 gene expression
# matrix called golub, a vector of length called golub.cl
# that consists of the 38 class labels,
# and a matrix called golub.gnames whose third column
# contains the gene names.
data(golub)
#use a subset of data as example, apply the rank
#product method
subset <- c(1:4,28:30)
#Setting rand=123, to make the results reproducible,
RP.out <- RP(golub[,subset],golub.cl[subset],rand=123)
# class 2: label =1, class 1: label = 0
#pfp for identifying genes that are up-regulated in class 2
#pfp for identifying genes that are down-regulated in class 2
head(RP.out$pfp)
Results
R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> library(RankProd)
> png(filename="/home/ddbj/snapshot/RGM3/R_BC/result/RankProd/RP.Rd_%03d_medium.png", width=480, height=480)
> ### Name: RP
> ### Title: Rank Product Analysis of Microarray
> ### Aliases: RP
> ### Keywords: htest
>
> ### ** Examples
>
> # Load the data of Golub et al. (1999). data(golub)
> # contains a 3051x38 gene expression
> # matrix called golub, a vector of length called golub.cl
> # that consists of the 38 class labels,
> # and a matrix called golub.gnames whose third column
> # contains the gene names.
> data(golub)
>
>
> #use a subset of data as example, apply the rank
> #product method
> subset <- c(1:4,28:30)
> #Setting rand=123, to make the results reproducible,
>
> RP.out <- RP(golub[,subset],golub.cl[subset],rand=123)
Rank Product analysis for two-class case
Starting 100 permutations...
Computing pfp ..
Outputing the results ..
>
> # class 2: label =1, class 1: label = 0
> #pfp for identifying genes that are up-regulated in class 2
> #pfp for identifying genes that are down-regulated in class 2
> head(RP.out$pfp)
class1 < class2 class1 > class 2
1 1.007990 1.111147959
2 1.073962 1.051125828
3 1.071897 0.992755906
4 1.031353 0.010000000
5 1.077310 0.006666667
6 1.030667 0.010000000
>
>
>
>
>
>
>
> dev.off()
null device
1
>