Learn R Programming

netClass (version 1.2.1)

netClass: An R Package for Network-Based Biomarker Discovery

Description

netClass is an R package for network-based feature (gene) selection for biomarkers discovery via integrating biological information. This package adapts the following 5 algorithms for classifying and predicting gene expression data using prior knowledge: 1) average gene expression of pathway (aep); 2) pathway activities classification (PAC); 3) Hub network Classification (hubc); 4) filter via top ranked genes (FrSVM); 5) network smoothed t-statistic (stSVM).

Copy Link

Version

Install

install.packages('netClass')

Monthly Downloads

8

Version

1.2.1

License

GPL (>= 2)

Maintainer

Yupeng Cun

Last Published

December 3rd, 2013

Functions in netClass (1.2.1)

Gs2

An subgraph of hub nodes
cv.hubc

Cross validation for hub nodes classification
cv.pac

Cross validation for Pathway Activities Classification(PAC)
predictFrsvm

Predicting the test data using frsvm trained model
pGeneRANK

GeneRANK
expr

Two expression profile matrixs and their labels
netClass-package

An R package for network-Based microarray Classification
getGraphRank

Random walk kernel matrix smoothing t-statistic
classify.hubc

Training and predicting using hub nodes classification methods
EN2SY

An list for mapping gene entre ids to symbol ids
classify.stsvm

Training and predicting using stSVM classification methods
cv.stsvm

Cross validation for smoothed t-statistic to select significant top ranked differential expressed genes
pOfHubs

Computing p value of hubs using the permutation test
train.pac

Training the data using pac methods
train.hubc

Predicting the data using hub nodes classification model
predictStsvm

Predicting the test data using stsvm trained model
predictPac

Predicting the test data using pac trained model
probeset2pathway

Generae a mean gene expression of genes of each pathway matrix
train.stsvm

Training the data using stsvm methods
train.aep

Training the data using aep methods
getGeneRanking

Get gene ranking based on geneRank algorithm.
classify.frsvm

Training and predicting using FrSVM
classify.pac

Training and predicting using PAC classification methods
cv.frsvm

Cross validation for FrSVM
predictAep

Predicting the test tdata using aep trained model
train.frsvm

Training the data using frsvm method
ad.matrix

An adjacency matrix of a sample graph...
classify.aep

Training and predicting using aepSVM (aepSVM) classification methods
predictHubc

Predicting the test data using hubc trained model
calc.diffusionKernelp

Computing the Random Walk Kernel matrix of network
probeset2pathwayTst

Applied CROG to testing data
probeset2pathwayTrain

Search CROG in training data
cv.aep

Cross validation for aepSVM (aepSVM)