Last updated: 2017-12-21
Code version: 6e42447
Re-analyze Smemo et al 2014’s mouse heart RNA-seq data after discussion with Matthew.
counts.mat = read.table("../data/smemo.txt", header = T, row.name = 1)
counts.mat = counts.mat[, -5]
Only use genes with total counts of \(4\) samples \(\geq 5\).
counts = counts.mat[rowSums(counts.mat) >= 5, ]
design = model.matrix(~c(0, 0, 1, 1))
Number of selected genes: 17191
source("../code/count_to_summary.R")
summary <- count_to_summary(counts, design)
betahat <- summary$betahat
sebetahat <- summary$sebetahat
z <- summary$z
With stretch GD can fit \(z\) scores, but it seems there should be signals.
GD Coefficients:
0 : 1 ; 1 : 0.0112765123515518 ; 2 : 1.60751487400088 ; 3 : 0.361378958092878 ; 4 : 1.6578925761474 ; 5 : 0.670189379060511 ; 6 : 0.759975038796516 ; 7 : 0.557659272292095 ; 8 : -0.0586994517222567 ; 9 : 0.175073181131895 ; 10 : -0.132350826272878 ;
BH
and ASH
Feeding summary statistics to BH
and ASH
, both give thousands of discoveries.
fit.BH = p.adjust((1 - pnorm(abs(z))) * 2, method = "BH")
## Number of discoveries by BH
sum(fit.BH <= 0.05)
[1] 2541
fit.ash = ashr::ash(betahat, sebetahat, method = "fdr")
## Number of discoveries by ASH
sum(get_svalue(fit.ash) <= 0.05)
[1] 6440
ASH
first or Gaussian derivatives firstUsing default setting \(L = 10\), \(\lambda = 10\), \(\rho = 0.5\), compare the GD-ASH
results by fitting ASH
first vs fitting GD
first. They indeed arrive at different local minima.
fit.gdash.ASH <- gdash(betahat, sebetahat,
gd.priority = FALSE)
## Regularized log-likelihood by fitting ASH first
fit.gdash.ASH$loglik
[1] -12483.86
fit.gdash.GD <- gdash(betahat, sebetahat)
## Regularized log-likelihood by fitting GD first
fit.gdash.GD$loglik
[1] -22136.92
GD-ASH
with larger penalties on \(w\)Using \(\lambda = 50\), \(\rho = 0.1\), fitting ASH
first and GD
first give the same result, and produce 1400+ discoveries with \(q\) values \(\leq 0.05\), all of which are discovered by BH
.
L = 10
lambda = 50
rho = 0.1
fit.gdash.ASH <- gdash(betahat, sebetahat,
gd.ord = L, w.lambda = lambda, w.rho = rho,
gd.priority = FALSE)
## Regularized log-likelihood by fitting ASH first
fit.gdash.ASH$loglik
[1] -13651.59
## Number of discoveries
sum(fit.gdash.ASH$qvalue <= 0.05)
[1] 1431
fit.gdash.GD <- gdash(betahat, sebetahat,
gd.ord = L, w.lambda = lambda, w.rho = rho,
gd.priority = TRUE)
## Regularized log-likelihood by fitting GD first
fit.gdash.GD$loglik
[1] -13651.59
## Number of discoveries
sum(fit.gdash.GD$qvalue <= 0.05)
[1] 1431
GD Coefficients:
0 : 1 ; 1 : -0.0475544308510135 ; 2 : 0.707888470469342 ; 3 : 0.149489828947119 ; 4 : -8.97499076623316e-14 ; 5 : 0.109281416075664 ; 6 : -3.00530934822662e-13 ; 7 : 0.0783545592042359 ; 8 : -2.99572304462426e-13 ; 9 : 0.0911488252640105 ; 10 : -2.99578347875936e-13 ;
sessionInfo()
R version 3.4.3 (2017-11-30)
Platform: x86_64-apple-darwin15.6.0 (64-bit)
Running under: macOS High Sierra 10.13.2
Matrix products: default
BLAS: /Library/Frameworks/R.framework/Versions/3.4/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/3.4/Resources/lib/libRlapack.dylib
locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] ashr_2.2-2 Rmosek_8.0.69 PolynomF_1.0-1 CVXR_0.94-4
[5] REBayes_1.2 Matrix_1.2-12 SQUAREM_2017.10-1 EQL_1.0-0
[9] ttutils_1.0-1
loaded via a namespace (and not attached):
[1] gmp_0.5-13.1 Rcpp_0.12.14 compiler_3.4.3
[4] git2r_0.20.0 R.methodsS3_1.7.1 R.utils_2.6.0
[7] iterators_1.0.9 tools_3.4.3 digest_0.6.13
[10] bit_1.1-12 evaluate_0.10.1 lattice_0.20-35
[13] foreach_1.4.4 yaml_2.1.16 parallel_3.4.3
[16] Rmpfr_0.6-1 ECOSolveR_0.3-2 stringr_1.2.0
[19] knitr_1.17 locfit_1.5-9.1 rprojroot_1.3-1
[22] bit64_0.9-7 grid_3.4.3 R6_2.2.2
[25] rmarkdown_1.8 limma_3.34.4 edgeR_3.20.2
[28] magrittr_1.5 MASS_7.3-47 backports_1.1.2
[31] codetools_0.2-15 htmltools_0.3.6 scs_1.1-1
[34] assertthat_0.2.0 stringi_1.1.6 pscl_1.5.2
[37] doParallel_1.0.11 truncnorm_1.0-7 R.oo_1.21.0
This R Markdown site was created with workflowr