mlDNA (version 1.1)

PSOL_NegativeExpansion: Negative expansion

Description

This function expands the negative sample set using PSOL algorithm.

Usage

PSOL_NegativeExpansion(featureMat, positives, negatives, unlabels, cpus = 1,  iterator = 50, cross = 5, TPR = 0.98, method = "randomForest",  plot = TRUE, trace = TRUE, PSOLResDic, ...)

Arguments

featureMat

a feature matrix recording the feature values for all samples.

positives

a character string recording the positive samples.

negatives

a character string recording the negative samples.

unlabels

a character string recording the unlabeled samples.

cpus

an integer value, cpu number

iterator

an integer value, iterator times.

cross

an integer value, cross-times cross validation.

TPR

a numeric value ranged from 0 to 1.0, used to select the prediction score cutoff.

method

a character string, machine learing method

plot

a logic value specifies whether the score distribution of positive and unlabeled samples will be plotted.

trace

logic. TRUE: the intermediate results will be saved as ".RData" format.

PSOLResDic

a character string, PSOL Result directory

...

Further parameters used in PSOL_ExpandSelection. see the further parameters in function classifier.

Value

The PSOL-related results are output in the "resultDic" directory.

Examples

## Not run: 
# 
#    ##generate expression feature matrix
#    sampleVec1 <- c(1, 2, 3, 4, 5, 6)
#    sampleVec2 <- c(1, 2, 3, 4, 5, 6)
#    featureMat <- expFeatureMatrix( expMat1 = ControlExpMat, 
#                                    sampleVec1 = sampleVec1, 
#                                    expMat2 = SaltExpMat, 
#                                    sampleVec2 = sampleVec2, 
#                                    logTransformed = TRUE, 
#                                    base = 2,
#                                    features = c("zscore", 
#                                    "foldchange", "cv", 
#                                    "expression"))
# 
#    ##positive samples
#    positiveSamples <- as.character(sampleData$KnownSaltGenes)
#    ##unlabeled samples
#    unlabelSamples <- setdiff( rownames(featureMat), positiveSamples )
#   
#    ##selecting an intial set of negative samples 
#    ##for building ML-based classification model
#    ##suppose the PSOL results will be stored in:
#    PSOLResDic <- "/home/wanglab/mlDNA/PSOL/"
#    res <- PSOL_InitialNegativeSelection(featureMatrix = featureMat, 
#                                         positives = positiveSamples, 
#                                         unlabels = unlabelSamples, 
#                                         negNum = length(positiveSamples), 
#                                         cpus = 6, PSOLResDic = PSOLResDic)
# 
#    ##initial negative samples extracted from unlabelled samples with PSOL algorithm
#    negatives <- res$negatives
# 
#    ##negative sample expansion
#    PSOL_NegativeExpansion(featureMat = featureMat, positives = positiveSamples, 
#                           negatives = res$negatives, unlabels = res$unlabels, 
#                           cpus = 2, iterator = 50, cross = 5, TPR = 0.98, 
#                           method = "randomForest", plot = TRUE, trace = TRUE, 
#                           PSOLResDic = PSOLResDic,
#                           ntrees = 200 ) # parameters for ML-based classifier 
# 
# ## End(Not run)