-
Fixed various tidyverse warnings.
-
Fixed an error when calculating the mds dimensions for multiple class comparisons with differing numbers of observations.
-
Added the
transformPercent()
method for theAnalysisData
S4 class to scale as a percentage of feature maximum intensity. -
Feature intensities are now displayed as relative percent intensities in heat maps generated by
plotExplanatoryHeatmap()
. -
Reduced the gap between the dendrogram and heat map in outputs of
plotExplanatoryHeatmap()
.
-
Fixed the margin value displayed in plots from
plotSupervisedRF()
-
The
plotExplanatoryHeatmap()
method for theAnalysis
S4 class now returns a warning and skips plotting if an error is encountered whilst trying to plot a heat map.
-
Added the argument
refactor
to the methodtransformTICnorm()
to enable the feature intensities of total ion count (TIC) normalised data to be refactored back to a range consistent with the original data by multiplying the normalised values by the median TIC. -
Removed the permutation cap when the
perm
argument ofrandomForest()
is less than the total number of permutations possible.
-
The class occupancy methods now throw a helpful error message if no features are available on which to compute class occupancy.
-
Fixed a bug where it was not possible to customize the order of class labels in the legend of
plotLDA()
.
-
It is now possible to specify multiple
cls
arguments to the aggregation methods. -
Correlation thresholds are now available for both coefficient and total number using the
minCoef
andmaxCor
arguments in thecorrelations()
method. -
Added the
predictions()
accessor method for theRandomForest
S4 class to enable the retrieval of the out of bag model response predictions. -
The occupancy filtering methods now error if the value supplied to argument
occupancy
is non-numeric. -
Memory usage and performance improvements for the
randomForest()
method. -
Added
type()
andresponse()
methods for theUnivariate
S4 class. -
plotLDA()
now returns a warning and skips plotting if an error is encountered during PC-LDA. -
The value
pre-treated
is now the default for argumenttype
in theAnalysis
S4 class accessor methods. -
Added the
value
argument to theexplanatoryFeatures()
method to allow the specification of on which importance value to apply the specifiedthreshold
. -
The specified
cls
argument is now correctly displayed on the x-axis title of the resulting plots from theplotFeature()
method.
-
Added the method
predict()
for theRandomForest
S4 class to predict model response values. -
Added the method
mtry()
for theAnalysisData
S4 class to return the defaultmtry
random forest parameter for a given response variable. -
Added the method
tune()
for theAnalysisData
S4 class to tune the random forest parametersmtry
andntree
for a given response variable.
-
Suppressed name repair console message encountered during random forest permutation testing.
-
Added the
proximity()
method for extracting sample proximities from theRandomForest
S4 class. -
Added the
mds()
method to perform multidimensional scaling on sample proximities from theRandomForest
S4 class. -
Added the
roc()
method to calculate receiver-operator characteristic curves from theRandomForest
S4 class.
-
An error is now thrown during random forest classification when less than two classes are specified.
-
plotSupervisedRF()
now skips plotting if errors are encountered during random forest training.
- Single replicate classes now automatically removed by
plotLDA()
.
-
plotExplanatoryHeatmap()
method for theAnalysis
class now returns the plot only if the number of plots is equal to 1. -
Removed reference to the
nCores
parameter from the documentation example ofmetabolyse()
.
- Correlation analysis results now include an absolute correlation coefficient column by which the results are also arranged in descending order.
- Console output from
imputeAll()
now suppressed.
-
Temporarily added jasenfinch/missForest as a remote until stekhoven/missForest pull request #25 is resolved.
-
The limit of the number of plotted features in
plotExplanatoryHeatmap
can now be specified using thefeatureLimit
argument. -
plotExplanatoryHeatmap()
now returns NULL and returns a message when no explanatory features are found. -
Fixed the alignment of the dendrogram branches with heat map rows in
plotExplanatoryHeatmap()
. -
Fixed
ggplot2::guides()
warning inplotFeature()
andplotTIC()
. -
Fixed bug in
explanatoryFeatures()
methods forAnalysis
class and lists where the threshold was not applied. -
Corrected the text in the modelling vignette concerning the results of using unsupervised random forest for outlier detection.
-
Package version, creation date and verbose argument added to prototype of
Analysis
class. -
All generics are now defined as standard generics.
-
Added
metrics
method forAnalysis
class. -
metrics
method for lists now ignores list elements that are not of classRandomForest
.
- Changed the
RSDthresh
argument default to 50% instead of 0.5% inQCrsdFilter
generic.
-
Added a
NEWS.md
file to track changes to the package. -
pkgdown
site now available at https://jasenfinch.github.io/metabolyseR/. -
Bug reports and issues URL at https://github.com/jasenfinch/metabolyseR/issues added to package DESCRIPTION.
-
Dedicated vignettes now available for a quick start example analysis, data pre-treatment and data modelling.
-
Function examples added to all documentation pages.
-
Unit test coverage increased to > 95%.
-
Parallel processing is now implemented using the
future
package. -
plan()
from thefuture
package is re-exported. -
RandomForest
andUnivariate
classes now inherit from class theAnalysisData
class. -
Improvements to plot theme aesthetics.
-
type
argument added toplotPCA()
,plotLDA()
,plotUnsupervisedRF()
andplotSupervisedRF()
methods for theAnalysis
class. -
"pre-treated"
for specifying type argument inAnalysis
class methods now used over"preTreated"
-
Added
clsRename()
method for renaming class information columns. -
plotMeasures()
method renamed toplotMetrics()
. -
Added
plotMDS()
,plotImportance()
andplotMetrics()
methods for lists ofRandomForest
class objects. -
Added
plotExplanatoryHeatmap()
method for lists ofRandomForest
orUnivariate
class objects. -
Renamed
keepVariables()
andremoveVariables()
methods tokeepFeatures()
andremoveFeatures()
. -
Added the helper functions
preTreatmentElements()
,preTreatmentMethods()
andpreTreatParameters()
for declaring pre-treatment parameters for theAnalysisParameters
class. -
Added the helper functions
modellingMethods()
andmodellingParameters()
for declaring modelling parameters for theAnalysisParameters
class. -
Added helper function
correlationsParameters()
for declaring correlations parameters for theAnalysisParameters
class. -
Added
binaryComparisons()
method for retrieving all possible binary class comparisons from anAnalysisData
class object. -
changeParameter()
now assigns parameter values through direct assignment. -
Added
analysisResults()
method from extracting analysis elements results from theAnalysis
class. -
Added
exportParameters()
method for exporting analysis parameters to YAML file format. -
Added
dat()
andsinfo()
accessor methods for theAnalysis
class. -
Relative standard deviation (RSD) values are now specified and returned as percentages.