This function generates a heatmap plot of feature statistics across alpha, which includes statistical significance annotations for individual features. By default, features are selected (and ordered top-down) by statistical significance based on a given value of alpha; options are provided to customize feature selection and display.
plotFeatureHeatmap(x, alpha.index=NULL, stat=c("freq","coef"), feature.all=FALSE,
feature.pval.thres=NULL, feature.set=NULL, feature.top.n=25, signif.code=TRUE,
xlab=NULL, ylab=NULL, main=NULL, col.main="black", cex.main=0.95, line=1,
col=NULL, breaks=NULL, scale="none", Rowv=FALSE, Colv=FALSE, na.color=NULL,
cexRow=NULL, srtRow=0, cexCol=0.75, srtCol=45, margins=c(5, 5), key=TRUE,
key.title=NA, dendogram="none", trace="none", notecol.freq="black",
notecol.coef="white", notecex=1, subtitle1=NULL, col.subtitle1="black",
line.subtitle1=-1, cex.subtitle1=0.65, subtitle2=NULL, col.subtitle2="darkgray",
line.subtitle2=-2, cex.subtitle2=0.55, …)eNetXplorer object.
Integer indices to select alpha values. Default is 1:length(alpha)
Feature statistic: "freq" for nonzero frequency, "coef" for mean nonzero coefficient.
(Feature selection argument 1) Logical to show all features. Default is FALSE.
(Feature selection argument 2) P-value threshold to select features. Default is NULL.
(Feature selection argument 3) Character vector of feature names to display. Default is NULL.
(Feature selection argument 4) Number of top features (ordered by p-value) to display. Default is 25.
Logical to display statistical significance annotations. Default is TRUE.
Label for x axis.
Label for y axis.
Custom title.
Title color.
Title size.
Title location.
Heatmap color vector. Length must be one less than number of breaks.
Color breaks vector. Default number of breaks is 10.
Logical to scale the data for heatmap in either the row or column direction. Default is "none".
Logical to reorder rows by hierarchical clustering. Default is FALSE.
Logical to reorder columns by hierarchical clustering. Default is FALSE.
Color to use for missing values.
Size of row labels.
Angle of row labels, in degrees from horizontal.
Size of column labels.
Angle of column labels, in degrees from horizontal.
Numeric vector of length 2 containing the margins for column and row names, respectively.
Logical to display key. Default is TRUE.
Main title of the color key.
To draw dendograms. Default is "none".
To display trace lines. Default is "none".
Color of statistical significance annotations for feature frequency heatmaps.
Color of statistical significance annotations for feature coefficient heatmaps.
Size of significance annotations.
Custom subtitle 1.
Color of subtitle 1.
Position of subtitle 1.
Size of subtitle 1.
Custom subtitle 2.
Color of subtitle 2.
Position of subtitle 2.
Size of subtitle 2.
Additional plotting parameters.
Feature selection criteria are hierarchical based on arguments 1 through 4 (see argument description above), with argument 1 at the top of the hierarchy. E.g. if feature.all is explicitly set to TRUE, it will take precedence over any other feature selection argument. By default, the top 25 features are displayed, ordered top-down by significance based on the given value of alpha.
# NOT RUN {
data(QuickStartEx)
fit = eNetXplorer(x=QuickStartEx$predictor,y=QuickStartEx$response,
family="gaussian",n_run=20,n_perm_null=10,seed=111)
plot(x=fit,plot.type="featureHeatmap",stat="freq")
plotFeatureHeatmap(x=fit,alpha.index=3,stat="freq",main="custom title")
# }
Run the code above in your browser using DataLab