Classification using the support vector machine algorithm.
Usage
svmClassification(
object,
assessRes,
scores = c("prediction", "all", "none"),
cost,
sigma,
fcol = "markers",
...
)Arguments
- object
An instance of class
"MSnSet".- assessRes
An instance of class
"GenRegRes", as generated bysvmOptimisation.- scores
One of
"prediction","all"or"none"to report the score for the predicted class only, for all classes or none.- cost
If
assessResis missing, acostmust be provided.- sigma
If
assessResis missing, asigmamust be provided.- fcol
The feature meta-data containing marker definitions. Default is
markers.- ...
Additional parameters passed to
svmfrom packagee1071.
Value
An instance of class "MSnSet" with
svm and svm.scores feature variables storing the
classification results and scores respectively.
Examples
library(pRolocdata)
data(dunkley2006)
## reducing parameter search space and iterations
params <- svmOptimisation(dunkley2006, cost = 2^seq(-2,2,2), sigma = 10^seq(-1, 1, 1), times = 3)
#>
|
| | 0%
|
|===== | 7%
|
|========= | 13%
|
|============== | 20%
|
|=================== | 27%
|
|======================= | 33%
|
|============================ | 40%
|
|================================= | 47%
|
|===================================== | 53%
|
|========================================== | 60%
|
|=============================================== | 67%
|
|=================================================== | 73%
|
|======================================================== | 80%
|
|============================================================= | 87%
|
|================================================================= | 93%
|
|======================================================================| 100%
params
#> Object of class "GenRegRes"
#> Algorithm: svm
#> Hyper-parameters:
#> cost: 0.25 1 4
#> sigma: 0.1 1 10
#> Design:
#> Replication: 3 x 5-fold X-validation
#> Partitioning: 0.2/0.8 (test/train)
#> Results
#> macro F1:
#> Min. 1st Qu. Median Mean 3rd Qu. Max.
#> 0.9740 0.9762 0.9783 0.9841 0.9891 1.0000
#> best sigma: 0.1
#> best cost: 4 1
plot(params)
f1Count(params)
#> 1 4
#> 0.1 1 0
levelPlot(params)
getParams(params)
#> sigma cost
#> 0.1 1.0
res <- svmClassification(dunkley2006, params)
#> [1] "markers"
getPredictions(res, fcol = "svm")
#> ans
#> ER lumen ER membrane Golgi Mitochondrion PM
#> 16 177 99 102 136
#> Plastid Ribosome TGN vacuole
#> 52 54 18 35
#> MSnSet (storageMode: lockedEnvironment)
#> assayData: 689 features, 16 samples
#> element names: exprs
#> protocolData: none
#> phenoData
#> sampleNames: M1F1A M1F4A ... M2F11B (16 total)
#> varLabels: membrane.prep fraction replicate
#> varMetadata: labelDescription
#> featureData
#> featureNames: AT1G09210 AT1G21750 ... AT4G39080 (689 total)
#> fvarLabels: assigned evidence ... svm.pred (11 total)
#> fvarMetadata: labelDescription
#> experimentData: use 'experimentData(object)'
#> pubMedIds: 16618929
#> Annotation:
#> - - - Processing information - - -
#> Loaded on Thu Jul 16 22:53:08 2015.
#> Normalised to sum of intensities.
#> Added markers from 'mrk' marker vector. Thu Jul 16 22:53:08 2015
#> Performed svm prediction (sigma=0.1 cost=1) Sat Nov 23 16:04:53 2024
#> Added svm predictions according to global threshold = 0 Sat Nov 23 16:04:53 2024
#> MSnbase version: 1.17.12
getPredictions(res, fcol = "svm", t = 0.75)
#> ans
#> ER lumen ER membrane Golgi Mitochondrion PM
#> 14 147 70 93 109
#> Plastid Ribosome TGN unknown vacuole
#> 44 27 13 144 28
#> MSnSet (storageMode: lockedEnvironment)
#> assayData: 689 features, 16 samples
#> element names: exprs
#> protocolData: none
#> phenoData
#> sampleNames: M1F1A M1F4A ... M2F11B (16 total)
#> varLabels: membrane.prep fraction replicate
#> varMetadata: labelDescription
#> featureData
#> featureNames: AT1G09210 AT1G21750 ... AT4G39080 (689 total)
#> fvarLabels: assigned evidence ... svm.pred (11 total)
#> fvarMetadata: labelDescription
#> experimentData: use 'experimentData(object)'
#> pubMedIds: 16618929
#> Annotation:
#> - - - Processing information - - -
#> Loaded on Thu Jul 16 22:53:08 2015.
#> Normalised to sum of intensities.
#> Added markers from 'mrk' marker vector. Thu Jul 16 22:53:08 2015
#> Performed svm prediction (sigma=0.1 cost=1) Sat Nov 23 16:04:53 2024
#> Added svm predictions according to global threshold = 0.75 Sat Nov 23 16:04:53 2024
#> MSnbase version: 1.17.12
plot2D(res, fcol = "svm")
