R Packages Developed Based Upon BRB-ArrayTools Modules
Several R packages are developed based upon selected modules in BRB-ArrayTools, an integrated package for the visualization and statistical analysis of Microarray gene expression, copy number, methylation and RNA-Seq data (Simon et al, 2007). Please download each binary package and install it from its local zip file. You also need to pre-install required R packages if they are listed. Please feel free to contact us at email@example.com if you have any questions.
classpredict R package
This R package is developed based on the class prediction module with multiple methods in BRB-ArrayTools, a tool creating a multivariate predictor for determining to which of multiple classes a given sample belongs. Several multivariate classification algorithms are available, including the Compound Covariate Predictor, Diagonal Linear Discriminant Analysis, Nearest Neighbor Predictor, Nearest Centroid Predictor, and Support Vector Machine Predictor methods. For each class prediction method requested, this package provides an estimate of how accurately the classes can be predicted by the multivariate class predictor. The whole procedure is evaluated by the cross-validation methods including leave-one-out cross-validation, k-fold validation and 0.632+ bootstrap validation. The cross-validated estimate of misclassification rate is computed, and the performance of each classifier is provided. New samples can be further classified based on specified classifiers and the multivariate predictor from the full dataset.
survriskpred R package
This R package implements the survival risk group prediction analysis tool in BRB-ArrayTools. It provides an assessment of whether the association of expression data to survival data is statistically significant. It also lets the user evaluate whether the expression data provide more accurate predictions than those provided by standard clinical covariates alone. The principal components or penalized Cox regression method is employed to select a gene list for fitting the Cox proportional harzards model. When no clinical covariates are provided, the model with gene expression alone will be used. If any covariates are provided, models with covariates alone and with both gene expression and covariates will be considered. Kaplan-Meier curves are plotted for 2-/3-risk groups obtained by leave-one-our or 10-fold cross validation, and prognostic indices are computed to predict risk groups for new samples.
dynamicHeatmap R package
This package creates a Dynamic Heatmap based on the Hierarchical Clustering method for visualizing microarray expression data. You can easily zoom in and out, change the color preferences, and mark genes and sample classes of the heatmap.
Last updated on August 16, 2019