dupcor.series {limma} | R Documentation |
Estimate the correlation between duplicate spots (replicate spots on the same array) from a series of arrays.
duplicateCorrelation(object,design=rep(1,ncol(M)),ndups=2,spacing=1,initial=0.8,trim=0.15,weights=NULL) dupcor.series(M,design=rep(1,ncol(M)),ndups=2,spacing=1,initial=0.7,trim=0.15,weights=NULL)
object |
a numeric matrix of log-ratios or an MAList object from which the log-ratios can be extracted.
If object is an MAList then the arguments design , ndups , spacing and weights will be extracted from it if available and do not have to be specified as arguments. |
M |
a numeric matrix. Usually the log-ratios of expression for a series of cDNA microarrrays with rows corresponding to genes and columns to arrays. |
design |
the design matrix of the microarray experiment, with rows corresponding to arrays and columns to comparisons to be estimated. The number of rows must match the number of columns of M . Defaults to the unit vector meaning that the arrays are treated as replicates. |
ndups |
a positive integer giving the number of times each gene is printed on an array. nrow(M) must be divisible by ndups . |
spacing |
the spacing between the rows of M corresponding to duplicate spots, spacing=1 for consecutive spots |
initial |
a numeric value between -1 and 1 giving an initial estimate for the correlation. |
trim |
the fraction of observations to be trimmed from each end of tanh(cor.genes) when computing the trimmed mean. |
weights |
an optional numeric matrix of the same dimension as M containing weights for each spot. If smaller than M then it will be filled out the same size. |
This function estimates the between-duplicate correlation using REML individually for each gene.
It also returns a robust average of the individual correlations which can be used as input for
functions such as gls.series
.
duplicateCorrelation
is a more object-orientated version of dupcor.series
but produces the same value.
A list with components
cor |
the average estimated inter-duplicate correlation. The average is the 0.1 trimmed mean of the correlations for individual genes on the tanh-transformed scale. |
cor.genes |
a numeric vector of length nrow(M)/ndups giving the individual gene correlations. |
This function may take long time to execute as it makes a call to gls
for each gene.
Execution could be speeded up greatly if it could be assumed that M
contains no NAs.
Gordon Smyth
Smyth, G. K., Michaud, J., and Scott, H. (2003). The use of within-array duplicate spots for assessing differential expression in microarray experiments. http://www.statsci.org/smyth/pubs/dupcor.pdf
These functions use gls
in the nlme package.
An overview of linear model functions in limma is given by 5.LinearModels.
# See gls.series for an example