MLPA (version 1.10.0)

classify: Apply the binary predictor to FSA peaks

Description

Predict to which class the sample is most likely to belong, using a modified LPS model.

Usage

classify(peaks, model, plot = TRUE)

Arguments

peaks

A data.frame, as returned by peaks.fsa.

model

A fsaModel object, as returned by model.

plot

Single logical value, whether to plot a visual representation of the prediction or not.

Value

Returns a list :

score

The raw score used to make the prediction.

p

The probability to belong to each of the two groups.

class

The final prediction, as a group name. May be NA if no probability passes the model threshold.

References

Radmacher MD, McShane LM, Simon R. A paradigm for class prediction using gene expression profiles. J Comput Biol. 2002;9(3):505-11.

Wright G, Tan B, Rosenwald A, Hurt EH, Wiestner A, Staudt LM. A gene expression-based method to diagnose clinically distinct subgroups of diffuse large B cell lymphoma. Proc Natl Acad Sci U S A. 2003 Aug 19;100(17):9991-6.

Bohers E, Mareschal S, Bouzelfen A, Marchand V, Ruminy P, Maingonnat C, Menard AL, Etancelin P, Bertrand P, Dubois S, Alcantara M, Bastard C, Tilly H, Jardin F. Targetable activating mutations are very frequent in GCB and ABC diffuse large B-cell lymphoma. Genes Chromosomes Cancer. 2014 Feb;53(2):144-53.

See Also

read.fsa, peaks.fsa, model, GEP.process

Examples

# NOT RUN {
  # Example FSA file provided
  fsa <- read.fsa(system.file("extdata/fsa/A5918.fsa", package="MLPA"))
  fsa <- align.fsa(fsa)
  
  # Build model from design file
  design <- designFile(system.file("extdata/design.conf", package="MLPA"))
  design$model$disable <- NULL
  model <- do.call("model", design$model)
  
  # Get peak heights
  peaks <- peaks.fsa(fsa, ranges=design$PEAKS$ranges)
  
  # Classify sample
  p <- classify(peaks, model, plot=TRUE)
  print(p)
  
  # Observe sample in model
  plot(model)
  abline(v=p$score)
# }