Last data update: 2014.03.03
|
R: Negative expansion
PSOL_NegativeExpansion | R Documentation |
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.
Author(s)
Chuang Ma, Xiangfeng Wang.
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)
Results
|