getK {ruv}

Get K

Description

Finds an often-suitable value of K for use in RUV-4.

Usage

getK(Y, X, ctl, Z = 1, eta = NULL, include.intercept = TRUE,
     fullW0 = NULL, cutoff = NULL, method="select", l=1, inputcheck = TRUE)

Arguments

Y

The data. A m by n matrix, where m is the number of samples and n is the number of features.

X

The factor(s) of interest. A m by p matrix, where m is the number of samples and p is the number of factors of interest. Note that X should be only a single column, i.e. p = 1; if X has more than one column, only column l will be used (see below).

ctl

An index vector to specify the negative controls. Either a logical vector of length n or a vector of integers.

Z

Any additional covariates to include in the model, typically a m by q matrix. Factors and dataframes are also permissible, and converted to a matrix by design.matrix. Alternatively, may simply be 1 (the default) for an intercept term. May also be NULL.

eta

Gene-wise (as opposed to sample-wise) covariates. These covariates are adjusted for by RUV-1 before any further analysis proceeds. Can be either (1) a matrix with n columns, (2) a matrix with n rows, (3) a dataframe with n rows, (4) a vector or factor of length n, or (5) simply 1, for an intercept term.

include.intercept

Applies to both Z and eta. When Z or eta (or both) is specified (not NULL) but does not already include an intercept term, this will automatically include one. If only one of Z or eta should include an intercept, this variable should be set to FALSE, and the intercept term should be included manually where desired.

fullW0

Can be included to speed up execution. Is returned by previous calls of getK, RUV4, RUVinv, or RUVrinv (see below).

cutoff

Specify an alternative cut-off. Default is the (approximate) 90th percentile of the distribution of the first singular value of an m by n gaussian matrix.

method

Can be set to either leave1out, fast, or select. leave1out is the preferred method but may be slow, fast is an approximate method that is faster but may provide poor results if n_c is not much larger than m, and select (the default) tries to choose for you.

l

Which column of X to use in the getK algorithm.

inputcheck

Perform a basic sanity check on the inputs, and issue a warning if there is a problem.

Value

A list containing

k

the estimated value of k

cutoff

The cutoff value used

sizeratios

A measure of the relative sizes of the rows of alpha.

fullW0

Can be used to speed up future calls of RUV4.

Warning

This value of K will not be the best choice in all cases. Moreover, it will often be a poor choice of K for use with RUV2. See Gagnon-Bartsch and Speed (2012) for commentary on estimating k.

Author(s)

Johann Gagnon-Bartsch [e-mail]

References

Using control genes to correct for unwanted variation in microarray data. Gagnon-Bartsch and Speed, 2012. Available at: http://biostatistics.oxfordjournals.org/content/13/3/539.full.

Removing Unwanted Variation from High Dimensional Data with Negative Controls. Gagnon-Bartsch, Jacob, and Speed, 2013. Available at: http://statistics.berkeley.edu/tech-reports/820.

See Also

RUV4

Examples

## Create some simulated data
m = 50
n = 10000
nc = 1000
p = 1
k = 20
ctl = rep(FALSE, n)
ctl[1:nc] = TRUE
X = matrix(c(rep(0,floor(m/2)), rep(1,ceiling(m/2))), m, p)
beta = matrix(rnorm(p*n), p, n)
beta[,ctl] = 0
W = matrix(rnorm(m*k),m,k)
alpha = matrix(rnorm(k*n),k,n)
epsilon = matrix(rnorm(m*n),m,n)
Y = X%*%beta + W%*%alpha + epsilon

## Run getK
temp = getK(Y, X, ctl)
K = temp$k