| Title: | RBM: a R package for microarray and RNA-Seq data analysis |
|---|---|
| Description: | Use A Resampling-Based Empirical Bayes Approach to Assess Differential Expression in Two-Color Microarrays and RNA-Seq data sets. |
| Authors: | Dongmei Li and Chin-Yuan Liang |
| Maintainer: | Dongmei Li <[email protected]> |
| License: | GPL (>= 2) |
| Version: | 1.37.0 |
| Built: | 2024-07-01 05:31:34 UTC |
| Source: | https://github.com/bioc/RBM |
Use A Resampling-Based Empirical Bayes Approach to Assesse Differential Expression or Identifying differntially methylated loci in Two-Color Microarrays and RNA-Seq data sets. Significant features selected through RBM_T or RBM_F functions could be further used as input for pathway analysis or experimental vilidations.
| Package: | RBM |
| Type: | Package |
| Version: | 0.99.0 |
| Date: | 2014-10-05 |
| Depends: | R (>= 3.0.0), limma, marray |
| License: | GPL (>= 2) |
Dongmei Li and Chin-Yuan Liang Maintainer: Dongmei Li <[email protected]> and Chin-Yuan Liang <[email protected]>
Li D, Le Pape MA, Parikh NI, Chen WX, Dye TD (2013) Assessing Differential Expression in Two-Color Microarrays: A Resampling-Based Empirical Bayes Approach. PLoS ONE 8(11): e80099. doi: 10.1371/journal.pone.0080099
The RBM_T and RBM_F functions defined in this package.
The limma and marray packages.
normal_data <- matrix(rnorm(200*6), 200, 6) mydesign <- c(0,0,0,1,1,1) norm_result <- RBM_T(normal_data,mydesign,50,0.05) unif_data <- matrix(runif(200*7, 0.10, 0.95), 200, 7) mydesign2 <- c(0,0,0, 1,1,1,1) unif_result <- RBM_T(unif_data,mydesign2,100,0.05) normdata_F <- matrix(rnorm(200*9, 0, 2), 200, 9) mydesign_F <- c(0, 0, 0, 1, 1, 1, 2, 2, 2) aContrast <- c("X1-X0", "X2-X1", "X2-X0") normresult_F <- RBM_F(normdata_F, mydesign_F, aContrast, 100, 0.05) unifdata_F <- matrix(runif(200*18, 0.15, 0.98), 200, 18) mydesign2_F <- c(rep(0, 6), rep(1, 6), rep(2, 6)) aContrast <- c("X1-X0", "X2-X1", "X2-X0") unifresult_F <- RBM_F(unifdata_F, mydesign2_F, aContrast, 100, 0.05)normal_data <- matrix(rnorm(200*6), 200, 6) mydesign <- c(0,0,0,1,1,1) norm_result <- RBM_T(normal_data,mydesign,50,0.05) unif_data <- matrix(runif(200*7, 0.10, 0.95), 200, 7) mydesign2 <- c(0,0,0, 1,1,1,1) unif_result <- RBM_T(unif_data,mydesign2,100,0.05) normdata_F <- matrix(rnorm(200*9, 0, 2), 200, 9) mydesign_F <- c(0, 0, 0, 1, 1, 1, 2, 2, 2) aContrast <- c("X1-X0", "X2-X1", "X2-X0") normresult_F <- RBM_F(normdata_F, mydesign_F, aContrast, 100, 0.05) unifdata_F <- matrix(runif(200*18, 0.15, 0.98), 200, 18) mydesign2_F <- c(rep(0, 6), rep(1, 6), rep(2, 6)) aContrast <- c("X1-X0", "X2-X1", "X2-X0") unifresult_F <- RBM_F(unifdata_F, mydesign2_F, aContrast, 100, 0.05)
This data set contains DNA methylation level from 1000 DNA methylation loci in 8 randomly selected women with 4 ovarian cancer cases (pre-treatment) and 4 age-matched healthy controls.
ovarian_cancer_methylationovarian_cancer_methylation
A matrix containing 1000 rows and 8 columns with each row denoting a methyaltion locus and each column denoting a subject.
The ovarian cancer methylation example data set contains the following information:
IlmnID |
Name of DNA methylation loci |
case |
Ovarian cancer patients |
control |
Healthy controls |
NCBI GEO website with access number GSE19711
Teschendorff AE, Menon U, Gentry-Maharaj A, Ramus SJ et al. Age-dependent DNA methylation of genes that are suppressed in stem cells is a hallmark of cancer. Genome Res 2010 Apr;20(4):440-6. PMID: 20219944
Use A Resampling-Based Empirical Bayes Approach to Assess Differential Expression in Two-Color Microarrays and RNA-Seq data sets for designs with more than two groups.
RBM_F(aData, vec_trt, aContrast, repetition, alpha)RBM_F(aData, vec_trt, aContrast, repetition, alpha)
aData |
The input data set with rows and columns denoting features and samples, respectively |
vec_trt |
A vector for group notation such as 1s denote treatment group and 0s denote control group |
aContrast |
A vector for contrast. For example: if we want to compare group 1 with group 0, group 2 with group 1, and group 2 with group 0, then the contrast vector will be ("X1-X0", "X2"-"X1", "X2-X0") |
repetition |
The number of resamplings used in the analysis. You could use 1000 or higher number |
alpha |
The signifiance level |
Combine resampling with empirical Bayes approach for Microarrays and RNA-Seq data analysis.
RBM_F produces a named list with the following components:
ordfit_t |
orignal t statistics |
ordfit_pvalue |
original p-values from lmFit and eBayes |
ordfit_beta0 |
estimated mean for the control group |
ordfit_beta1 |
estimated mean difference between treatment and control group |
permutation_p |
calculated p-values from permutation method based on resampled test statistics |
bootstrap_p |
calculated p-values from bootstrap method based on resampled test statistics |
Dongmei Li and Chin-Yuan Liang
Li D, Le Pape MA, Parikh NI, Chen WX, Dye TD (2013) Assessing Differential Expression in Two-Color Microarrays: A Resampling-Based Empirical Bayes Approach. PLoS ONE 8(11): e80099. doi: 10.1371/journal.pone.0080099
The RBM_T function defined in this package.
The limma and marray packages.
normdata_F <- matrix(rnorm(200*9, 0, 2), 200, 9) mydesign_new <- c(0, 0, 0, 1, 1, 1, 2, 2, 2) aContrast <- c("X1-X0", "X2-X1", "X2-X0") normresult_F <- RBM_F(normdata_F, mydesign_new, aContrast, 100, 0.05) unifdata_F <- matrix(runif(200*18, 0.15, 0.98), 200, 18) mydesign2_new <- c(rep(0, 6), rep(1, 6), rep(2, 6)) aContrast <- c("X1-X0", "X2-X1", "X2-X0") unifresult_F <- RBM_F(unifdata_F, mydesign2_new, aContrast, 100, 0.05)normdata_F <- matrix(rnorm(200*9, 0, 2), 200, 9) mydesign_new <- c(0, 0, 0, 1, 1, 1, 2, 2, 2) aContrast <- c("X1-X0", "X2-X1", "X2-X0") normresult_F <- RBM_F(normdata_F, mydesign_new, aContrast, 100, 0.05) unifdata_F <- matrix(runif(200*18, 0.15, 0.98), 200, 18) mydesign2_new <- c(rep(0, 6), rep(1, 6), rep(2, 6)) aContrast <- c("X1-X0", "X2-X1", "X2-X0") unifresult_F <- RBM_F(unifdata_F, mydesign2_new, aContrast, 100, 0.05)
Use A Resampling-Based Empirical Bayes Approach to Assess Differential Expression or Identify differntially methylated loci in Two-Color Microarrays and RNA-Seq data sets.
RBM_T(aData, vec_trt, repetition, alpha)RBM_T(aData, vec_trt, repetition, alpha)
aData |
The input data set with rows and columns denoting features and samples, respectively |
vec_trt |
A vector for group notation such as 1s denote treatment group and 0s denote control group |
repetition |
The number of resamplings used in the analysis. You could use 1000 or higher number |
alpha |
The signifiance level |
Combine resampling with empirical Bayes approach for Microarrays and RNA-Seq data analysis.
RBM_T produces a named list with the following components:
ordfit_t |
orignal t statistics |
ordfit_pvalue |
original p-values from lmFit and eBayes |
ordfit_beta0 |
estimated mean for the control group |
ordfit_beta1 |
estimated mean difference between treatment and control group |
permutation_p |
calculated p-values from permutation method based on resampled test statistics |
bootstrap_p |
calculated p-values from bootstrap method based on resampled test statistics |
Dongmei Li and Chin-Yuan Liang
Li D, Le Pape MA, Parikh NI, Chen WX, Dye TD (2013) Assessing Differential Expression in Two-Color Microarrays: A Resampling-Based Empirical Bayes Approach. PLoS ONE 8(11): e80099. doi: 10.1371/journal.pone.0080099
The RBM_F function defined in this package.
The limma and marray packages.
normal_data <- matrix(rnorm(200*6), 200, 6) mydesign <- c(0,0,0,1,1,1) norm_result <- RBM_T(normal_data,mydesign,50,0.05) unif_data <- matrix(runif(200*7, 0.10, 0.95), 200, 7) mydesign2 <- c(0,0,0, 1,1,1,1) unif_result <- RBM_T(unif_data,mydesign2,100,0.05)normal_data <- matrix(rnorm(200*6), 200, 6) mydesign <- c(0,0,0,1,1,1) norm_result <- RBM_T(normal_data,mydesign,50,0.05) unif_data <- matrix(runif(200*7, 0.10, 0.95), 200, 7) mydesign2 <- c(0,0,0, 1,1,1,1) unif_result <- RBM_T(unif_data,mydesign2,100,0.05)