R: An Interface for glmnet Package's glmnet Function

elasticNetGLMinterface {ClassifyR}

R Documentation

An Interface for glmnet Package's glmnet Function

Description

An elastic net GLM classifier uses a penalty which is a combination of a lasso penalty and a ridge penalty, scaled by a lambda value, to fit a sparse linear model to the data.

Usage

  ## S4 method for signature 'matrix'
elasticNetGLMtrainInterface(measurements, classes, ...)
  ## S4 method for signature 'DataFrame'
elasticNetGLMtrainInterface(measurements, classes, lambda = NULL,
                             ..., verbose = 3)
  ## S4 method for signature 'MultiAssayExperiment'
elasticNetGLMtrainInterface(measurements, targets = names(measurements), ...)
  ## S4 method for signature 'multnet,matrix'
elasticNetGLMpredictInterface(model, test, ...)
  ## S4 method for signature 'multnet,DataFrame'
elasticNetGLMpredictInterface(model, test, classes = NULL, lambda, ..., verbose = 3)
  ## S4 method for signature 'multnet,MultiAssayExperiment'
elasticNetGLMpredictInterface(model, test, targets = names(test), ...)

Arguments

`measurements`	Either a `matrix`, `DataFrame` or `MultiAssayExperiment` containing the training data. For a `matrix`, the rows are features, and the columns are samples. If of type `DataFrame`, the data set is subset to only those features of type `integer`.
`classes`	Either a vector of class labels of class `factor` of the same length as the number of samples in `measurements` or if the measurements are of class `DataFrame` a character vector of length 1 containing the column name in `measurement` is also permitted. Not used if `measurements` is a `MultiAssayExperiment` object.
`lambda`	The lambda value passed directly to `glmnet` if the training function is used or passed as `s` to `predict.glmnet` if the prediction function is used.
`test`	An object of the same class as `measurements` with no samples in common with `measurements` and the same number of features as it.
`targets`	If `measurements` is a `MultiAssayExperiment`, the names of the data tables to be used. `"clinical"` is also a valid value and specifies that integer variables from the clinical data table will be used.
`...`	Variables not used by the `matrix` nor the `MultiAssayExperiment` method which are passed into and used by the `DataFrame` method (e.g. `verbose`) or, for the training function, options that are used by the `glmnet` function. For the testing function, this variable simply contains any parameters passed from the classification framework to it which aren't used by glmnet's `predict` fuction.
`model`	A trained elastic net GLM, as created by the `glmnet` function.
`verbose`	Default: 3. A number between 0 and 3 for the amount of progress messages to give. This function only prints progress messages if the value is 3.

Details

If measurements is an object of class MultiAssayExperiment, the factor of sample classes must be stored in the DataFrame accessible by the colData function with column name "class".

The value of the "family" parameter is fixed to "multinomial" so that classification with more than 2 classes is possible. During classifier training, if more than one lambda value is considered by specifying a vector of them as input, then the chosen value is determined based on classifier resubstitution performance. Leaving the default value of NULL, however, causes the glmnet function to determine a set of values to evaluate and then a single lambda value is chosen based on the fraction of (null) deviance explained by the fitted model.

Value

For elasticNetGLMtrainInterface, an object of type glmnet. For elasticNetGLMpredictInterface, a factor vector of class predictions.

Author(s)

Dario Strbenac

Examples

  if(require(glmnet))
  {
    # Genes 76 to 100 have differential expression.
    genesMatrix <- sapply(1:25, function(sample) c(rnorm(100, 9, 2)))
    genesMatrix <- cbind(genesMatrix, sapply(1:25, function(sample)
                                      c(rnorm(75, 9, 2), rnorm(25, 14, 2))))
    classes <- factor(rep(c("Poor", "Good"), each = 25))
    colnames(genesMatrix) <- paste("Sample", 1:ncol(genesMatrix))
    rownames(genesMatrix) <- paste("Gene", 1:nrow(genesMatrix))
    
    resubstituteParams <- ResubstituteParams(nFeatures = seq(10, 100, 10),
                                             performanceType = "balanced error",
                                             better = "lower")
                                             
    # alpha is a user-specified tuning parameter.
    # lambda is automatically tuned, based on glmnet defaults, if not user-specified.                 
    trainParams <- TrainParams(elasticNetGLMtrainInterface,
                               tuneParams = list(alpha = c(0, 0.5, 1)),
                               resubstituteParams = resubstituteParams)
    predictParams <- PredictParams(elasticNetGLMpredictInterface,
                                   getClasses = function(result) result)                           
    classified <- runTests(genesMatrix, classes, "Example", "Differential Expression",
                           permutations = 5,
                           params = list(trainParams, predictParams))
                           
    classified <- calcCVperformance(classified, "balanced error")
    head(tunedParameters(classified))
    performance(classified)
  }

[Package ClassifyR version 2.0.10 Index]