SigCheck (version 1.0.2)

sigCheckKnown: Check classification performance of signature against a panel of known gene signatures

Description

Compare the classification performance of a known panel of gene signatures to the signature being checked. By default, a panel of gene signatures from Venet et. al. is used.

Usage

sigCheckKnown(expressionSet, classes, signature, annotation, validationSamples,  classifierMethod = svmI, classifierScore, knownSignatures="cancer")

Arguments

expressionSet

An ExpressionSet object containing the data to be checked, including an expression matrix, feature labels, and samples.

classes

Specifies which label is to be used to determine the classification categories (must be one of varLabels(expressionSet)). There should be only two unique values in expressionSet$classes.

signature

A vector of feature labels specifying which features comprise the signature to be checked. These feature labels should match values as specified in the annotation parameter (default is row names in the expressionSet). Alternatively, this can be a integer vector of feature indexes.

annotation

Character string specifying which featureData field should be used as the annotation. If missing, the row names of the expressionSet are used as the feature names.

validationSamples

Optional specification, as a vector of sample indices, of what samples in the should used for validation. If present, a classifier will be trained, using the specified signature and classification method, on the non-validation samples, and it's performance evaluated by attempting to classify the validations samples. If missing, a leave-one-out (LOO) validation method will be used, where a separate classifier will be trained to classify each sample using the remaining samples.

classifierMethod

The MLInterfaces learnerSchema object indicating the machine learning method to use for classification. Default is svmI for linear Support Vector Machine classification. See MLearn for available methods.

classifierScore

A performance measure of the baseline classifier. Generally the classifierScore element of the result list returned by sigCheckClassifier. If missing, sigCheckClassifier will be called to establish baseline performance.

knownSignatures

Either a character string specifying which set of signatures to use from the included sets in knownSignatures, or a list of previously identified signatures to compare performance against. Each element in the list should be a vector of feature labels. Default is to use the "cancer" signatures from the included knownSignatures data set, taken from Venet et. al.

Value

A list with six elements:

• $sigPerformance is the percentage of validationSamples correctly classified (or, in the LOO case, the percentage of total samples correctly classified by classifiers trained using the remaining samples.)
• $modePerformance is the percentage of validationSamples correctly classified by a "mode" classifier (or, in the LOO case, the percentage of total samples correctly classified by a "mode" classifier, which is equal the number of samples with the more-frequent category.) The "mode" classifier always predicts the category that appears most often in the training set. If the training set is balanced between categories, one category will always be predicted.
• $known is a character string indicating which gene signature set was checked. Either one of the sets in knownSignatures, or the string "user specified".
• $knownSigs is the number of signatures evaluated (equal to length(knownSignatures), minus any signatures with zero features matching the labels in expressionSet.)
• $rank is the performance rank of the primary signature classifier on the original dataset amongst the performances of the known signatures on the same dataset.
• $performanceKnown is a vector of performance scores (proportion of the validation set correctly predicted) for each known signature on the dataset.

Details

sigCheckClassifier is called for each of the known signatures.

References

Venet, David, Jacques E. Dumont, and Vincent Detours. "Most random gene expression signatures are significantly associated with breast cancer outcome." PLoS Computational Biology 7.10 (2011): e1002240.

See Also

knownSignatures, sigCheck, sigCheckClassifier, sigCheckRandom, sigCheckPermuted, MLearn

Examples

library(breastCancerNKI)
data(nki)
nki <- nki[,!is.na(nki$e.dmfs)]
data(knownSignatures)
results <- sigCheckKnown(nki, classes="e.dmfs", 
                         signature=knownSignatures$cancer$VANTVEER, 
                         annotation="HUGO.gene.symbol", 
                         validationSamples=275:319)