generateExprVal.method.farms {farms} | R Documentation |
Generate an expression from the probe
generateExprVal.method.farms(probes, weight, mu, cyc, tol, weighted.mean, robust, ...)
probes |
a matrix of probe intesities with rows representing
probes and columns representing
samples. Usually pm(probeset) where probeset is a
of class ProbeSet |
weight |
Hyperparameter value in the range of [0,1] which determines the influence of the prior. The default value is 0.5 |
mu |
Hyperparameter value which allows to quantify different aspects of potential prior knowledge. A value near zero assumes that most genes do not contain a signal, and introduces a bias for loading matrix elements near zero. Default value is 0 |
cyc |
Value which determinates the maximum numbers of EM-Steps. Default value is set to number of arrays/2 |
tol |
Value which determinates the termination tolerance. Convergence threshold is set to 1E-05. |
weighted.mean |
Boolean flag, that indicates wether a weighted mean or a least square fit is used to summarize the loading matrix. The default value is set to TRUE . |
robust |
Boolean flag, that ensures non-constant results. Default value is TRUE. |
... |
extra arguments to pass to the respective function |
A list containing entries:
exprs |
The expression values. |
se.exprs |
Estimate of the hidden variable. |
generateExprSet-methods
,generateExprVal.method.playerout
,li.wong
, medianpolish
data(SpikeIn) ##SpikeIn is a ProbeSets probes <- pm(SpikeIn) exprs.farms <- generateExprVal.method.farms(probes)