Learn R Programming

CMA (version 1.30.0)

Synthesis of microarray-based classification

Description

This package provides a comprehensive collection of various microarray-based classification algorithms both from Machine Learning and Statistics. Variable Selection, Hyperparameter tuning, Evaluation and Comparison can be performed combined or stepwise in a user-friendly environment.

Copy Link

Version

Version

1.30.0

License

GPL (>= 2)

Maintainer

Christoph Bernau

Last Published

February 15th, 2017

Functions in CMA (1.30.0)

Evaluation of classifiers

evaloutput-class

Combine list elements returned by the method classification

shrinkldaCMA-methods

Shrinkage linear discriminant analysis

Synthesis of microarray-based classification

classification-methods

General method for classification with various methods

Classifiability of observations

tuningresult-class

Probability plot

Hyperparameter tuning for classifiers

varseloutput-class

L1 penalized logistic regression

ElasticNetCMA-methods

Classfication and variable selection by the ElasticNet

Show best hyperparameter settings

Quadratic Discriminant Analysis

Fisher's Linear Discriminant Analysis

Planarplot-methods

Visualize Separability of different classes

weighted.mcr-methods

General method for tuning / selection bias correction

Tree-based Gradient Boosting

Nearest Neighbours

Combine list elements returned by the method classification

plot tuningresult

Visualize results of tuning

Classification based on Random Forests

Support Vector Machine

Componentwise Boosting

Nearest Neighbours

Probabilistic Neural Networks

prediction-methods

General method for predicting class lables of new observations

Partial Least Squares combined with Linear Discriminant Analysis

Tuning / Selection bias correction based on matrix of subsampling fold errors

Tree-based Gradient Boosting

Compare different classifiers

Small blue round cell tumor dataset of Khan et al. (2001)

Cross-tabulation of predicted and true class labels

Feed-forward Neural Networks

Linear Discriminant Analysis

General method for predicting classes of new observations

GeneSelection-methods

General method for variable selection with various methods

flexdaCMA-methods

Flexible Discriminant Analysis

LassoCMA-methods

L1 penalized logistic regression

Summarize classifier evaluation

learningsets-class

Shrunken Centroids Discriminant Analysis

L2 penalized logistic regression

Partial Least Squares followed by random forests

scdaCMA-methods

Shrunken Centroids Discriminant Analysis

Flexible Discriminant Analysis

Quadratic Discriminant Analysis

Support Vector Machine

predoutput-class

Classification based on Random Forests

GenerateLearningsets

Repeated Divisions into learn- and tets sets

pknnCMA-methods

Probabilistic nearest neighbours

General method for tuning / selection bias correction based on a matrix of subsampling fold errors.

Shrinkage linear discriminant analysis

clvarseloutput-class

"clvarseloutput"

pls_ldaCMA-methods

Partial Least Squares combined with Linear Discriminant Analysis

Partial Least Squares followed by logistic regression

Filter functions for Gene Selection

compBoostCMA-methods

Componentwise Boosting

L2 penalized logistic regression

Visualize Separability of different classes

General method for classification with various methods

evaluation-methods

Evaluation of classifiers

Fisher's Linear Discriminant Analysis

Receiver Operator Characteristic

pls_rfCMA-methods

Partial Least Squares followed by random forests

nnetCMA-methods

Feed-Forward Neural Networks

Classfication and variable selection by the ElasticNet

Display 'top' variables

ALL/AML dataset of Golub et al. (1999)

Internal functions

dldaCMA-methods

Diagonal Discriminant Analysis

Hyperparameter tuning for classifiers

General method for variable selection with various methods

wmcr.result-class

pls_lrCMA-methods

Partial Least Squares followed by logistic regression

Probabilistic Neural Networks

Barplot of variable importance

Make a boxplot of the classifier evaluation

Probabilistic Nearest Neighbours

Linear Discriminant Analysis

Tuning / Selection bias correction

compare-methods

Compare different classifiers

Diagonal Discriminant Analysis