Classification using for the k-nearest neighbours algorithm.

knnClassification(
  object,
  assessRes,
  scores = c("prediction", "all", "none"),
  k,
  fcol = "markers",
  ...
)

Arguments

object

An instance of class "MSnSet".

assessRes

An instance of class "GenRegRes", as generated by knnOptimisation.

scores

One of "prediction", "all" or "none" to report the score for the predicted class only, for all classes or none.

k

If assessRes is missing, a k must be provided.

fcol

The feature meta-data containing marker definitions. Default is markers.

...

Additional parameters passed to knn from package class.

Value

An instance of class "MSnSet" with

knn and knn.scores feature variables storing the classification results and scores respectively.

Author

Laurent Gatto

Examples

library(pRolocdata)
data(dunkley2006)
## reducing parameter search space and iterations 
params <- knnOptimisation(dunkley2006, k = c(3, 10), times = 3)
#> 
  |                                                                            
  |                                                                      |   0%
  |                                                                            
  |=====                                                                 |   7%
  |                                                                            
  |=========                                                             |  13%
  |                                                                            
  |==============                                                        |  20%
  |                                                                            
  |===================                                                   |  27%
  |                                                                            
  |=======================                                               |  33%
  |                                                                            
  |============================                                          |  40%
  |                                                                            
  |=================================                                     |  47%
  |                                                                            
  |=====================================                                 |  53%
  |                                                                            
  |==========================================                            |  60%
  |                                                                            
  |===============================================                       |  67%
  |                                                                            
  |===================================================                   |  73%
  |                                                                            
  |========================================================              |  80%
  |                                                                            
  |=============================================================         |  87%
  |                                                                            
  |=================================================================     |  93%
  |                                                                            
  |======================================================================| 100%
params
#> Object of class "GenRegRes"
#> Algorithm: knn 
#> Hyper-parameters:
#>  k: 3 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. 
#>  0.9603  0.9690  0.9776  0.9747  0.9819  0.9862 
#>  best k: 3   
plot(params)

f1Count(params)
#> 
#> 3 
#> 1 
levelPlot(params)

getParams(params)
#> k 
#> 3 
res <- knnClassification(dunkley2006, params)
#> [1] "markers"
getPredictions(res, fcol = "knn")
#> ans
#>      ER lumen   ER membrane         Golgi Mitochondrion            PM 
#>            21           180            94           106           138 
#>       Plastid      Ribosome           TGN       vacuole 
#>            49            50            21            30 
#> 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 ... knn.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 knn prediction (k=3) Tue Mar 12 07:13:32 2024 
#> Added knn predictions according to global threshold = 0 Tue Mar 12 07:13:32 2024 
#>  MSnbase version: 1.17.12 
getPredictions(res, fcol = "knn", t = 0.75)
#> ans
#>      ER lumen   ER membrane         Golgi Mitochondrion            PM 
#>            15           173            83           103           120 
#>       Plastid      Ribosome           TGN       unknown       vacuole 
#>            49            44            16            56            30 
#> 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 ... knn.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 knn prediction (k=3) Tue Mar 12 07:13:32 2024 
#> Added knn predictions according to global threshold = 0.75 Tue Mar 12 07:13:32 2024 
#>  MSnbase version: 1.17.12 
plot2D(res, fcol = "knn")