R: Retrieve top-ranked features from analysis results

topLabels-methods {Cardinal}

R Documentation

Retrieve top-ranked features from analysis results

Description

The generic function is a convenience method for retrieving top-ranked features from the results of imaging experiment analyses. For mass spectrometry-based imaging experiments, this can be used for identifying important masses from an analysis.

Usage

## S4 method for signature 'ResultSet'
topLabels(object, n = 6,
    model = pData(modelData(object)),
    type = c('+', '-', 'b'),
    sort.by = fvarLabels(object),
    filter = list(),
    ...)

## S4 method for signature 'PCA'
topLabels(object, n = 6,
    sort.by = "loadings",
    ...)

## S4 method for signature 'PLS'
topLabels(object, n = 6,
    sort.by = c("coefficients", "loadings", "weights"),
    ...)

## S4 method for signature 'OPLS'
topLabels(object, n = 6,
    sort.by = c("coefficients",
            "loadings", "Oloadings",
            "weights", "Oweights"),
    ...)

## S4 method for signature 'SpatialKMeans'
topLabels(object, n = 6,
    sort.by = c("betweenss", "withinss"),
    ...)

## S4 method for signature 'SpatialShrunkenCentroids'
topLabels(object, n = 6,
    sort.by = c("tstatistics", "p.values"),
    ...)

## S4 method for signature 'CrossValidated'
topLabels(object, ...)

Arguments

`object`	A `ResultSet` derived object.
`n`	The number of top-ranked records to return.
`model`	If more than one model was fitted, results from which should be shown? Defaults to all models in the `ResultSet`. This can name the models explicitly or specify a list of parameter values.
`type`	How should the records be ranked? '+' shows greatest values first (decreasing order), '-' shows least values first (increasing order), and 'b' uses decreasing order based on absolute values.
`sort.by`	What variable should be used for sorting?
`filter`	A list of named variables with values to use to filter the results. For example, for testing or classification, this can be used to only show rankings for a particular condition.
`...`	Passed to the 'head' function when sorting the final list of results.

Value

A data.frame with the top-ranked labels from the analysis.

Author(s)

Kylie A. Bemis

Examples

set.seed(1)
data <- matrix(c(NA, NA, 1, 1, NA, NA, NA, NA, NA, NA, 1, 1, NA, NA, 
    NA, NA, NA, NA, NA, 0, 1, 1, NA, NA, NA, NA, NA, 1, 0, 0, 1, 
    1, NA, NA, NA, NA, NA, 0, 1, 1, 1, 1, NA, NA, NA, NA, 0, 1, 1, 
    1, 1, 1, NA, NA, NA, NA, 1, 1, 1, 1, 1, 1, 1, NA, NA, NA, 1, 
    1, NA, NA, NA, NA, NA, NA, 1, 1, NA, NA, NA, NA, NA), nrow=9, ncol=9)

msset <- generateImage(data, range=c(200, 300), step=1, as="MSImageSet")

clust1 <- spatialShrunkenCentroids(msset, r=c(1,2), k=c(2,3), s=c(0,1), method="gaussian")

topLabels(clust1)

topLabels(clust1, filter=list(classes=1))

topLabels(clust1, filter=list(r=1, k=2, s=1))

[Package Cardinal version 2.0.4 Index]