Skip to main content

Table 1 Overview of the classification methods in CMA.

From: CMA – a comprehensive Bioconductor package for supervised classification with high dimensional data

Method name

CMA function name

Package

Reference

Componentwise boosting

compBoostCMA

CMA

[39]

Diagonal discriminant analysis

dldaCMA

CMA

[56]

Elastic net

ElasticNetCMA

'glmpath'

[29]

Fisher's discriminant analysis

fdaCMA

CMA

[24]

Flexible discriminant analysis

flexdaCMA

'mgcv'

[24]

Tree-based boosting

gbmCMA

'gbm'

[33]

k-nearest neighbors

knnCMA

'class'

[24]

Linear discriminant analysis *

ldaCMA

'MASS'

[56]

Lasso

LassoCMA

'glmpath'

[57]

Feed-forward neural networks

nnetCMA

'nnet'

[24]

Probalistic nearest neighbors

pknnCMA

CMA

-

Penalized logistic regression

plrCMA

CMA

[58]

Partial Least Squares + *

pls_ldaCMA

'plsgenomics'

[5]

+ logistic regression

pls_lrCMA

'plsgenomics'

[5]

+ random forest

pls_rfCMA

'plsgenomics'

[5]

Probabilistic neural networks

pnnCMA

CMA

[59]

Quadratic discriminant analysis

qdaCMA

'MASS'

[56]

Random forest

rfCMA

'randomForest'

[4]

PAM

scdaCMA

CMA

[44]

Shrinkage discriminant analysis

shrinkldaCMA

CMA

-

Support vector machines

svmCMA

'e1071'

[60]

  1. The first column gives the method name, whereas the name of the classifier in the CMA package is given in the second column. For each classifier, CMA uses either own code or code borrowed from another package, as specified in the third column.