arraytools

# Optional parameters for the console and the pager
# The system-wide copy is in rwxxxx/etc.
# A user copy can be installed in `R_USER'.

## Style
# This can be `yes' (for MDI) or `no' (for SDI).
MDI = yes
# the next two are only relevant for MDI
toolbar = yes
statusbar = no

arraytools

# This is a note about import rsem-generated file for DESeq2 package

# As described by the tximport's vignette, the method below uses the gene-level estimated counts from the quantification tools, and additionally to use the transcript-level abundance estimates to calculate a gene-level offset that corrects for changes to the average transcript length across samples.
# This approach corrects for potential changes in gene length across samples (e.g. from differential isoform usage)

# References:
# 1. http://bioconductor.org/packages/release/bioc/vignettes/tximport/inst/doc/tximport.html#rsem
# 2. https://bioconductor.org/packages/release/bioc/vignettes/DESeq2/inst/doc/DESeq2.html#differential-expression-analysis

arraytools

x <- read.delim("GX_datab31.txt")
dim(x)
# [1] 1579  463
sum(x)
sum(x[1, ])
options(digits = 20)
sum(x)
# [1] 12589441.434223400429
sum(x[1,])
# [1] 4787.087760000000344

arraytools

library(glmnet) 

# Binary data
n = 1000
p = 100
nzc = trunc(p/10)
for(i in 1:100) {
  cat(i, " ")
  if (i %% 10 == 0) cat("\n")
  x = matrix(rnorm(n * p), n, p)

arraytools

set.seed(1234)
junk <- biospear::simdata(n=500, p=500, q.main = 10, q.inter = 10, 
                          prob.tt = .5, m0=1, alpha.tt= -.5, 
                          beta.main= -.5, beta.inter= -.5, b.corr = .7, b.corr.by=25, 
                          wei.shape = 1, recr=3, fu=2, timefactor=1)
## Method 1: MASS::mvrnorm()
## This is simdata() has used. It gives different numbers on different OS.
## 
library(MASS)
set.seed(1234)

arraytools

#include <Rembedded.h>
#include <Rdefines.h>

static void doSplinesExample();
int
main(int argc, char *argv[])
{
    Rf_initEmbeddedR(argc, argv);
    doSplinesExample();
    Rf_endEmbeddedR(0);

arraytools

library(glmnet)
x <- dget(url("https://gist.githubusercontent.com/arraytools/238e812555d69cb0213adaf99353c25f/raw/911bd4c6810fff6483521808cd1dfa1833891eb7/glmnet_surv_x"))
y <- dget(url("https://gist.githubusercontent.com/arraytools/238e812555d69cb0213adaf99353c25f/raw/911bd4c6810fff6483521808cd1dfa1833891eb7/glmnet_surv_y"))
lambda <- dget(url("https://gist.githubusercontent.com/arraytools/238e812555d69cb0213adaf99353c25f/raw/911bd4c6810fff6483521808cd1dfa1833891eb7/glmnet_surv_lambda"))

cvfit <- cv.glmnet(x, y, family = "cox", nfolds=10)
fit <- glmnet(x, y, family = "cox", lambda = lambda)
coef.cv <- coef(cvfit, s = lambda)
coef.fit <- coef(fit)
length(coef.cv[coef.cv != 0]) # 31

arraytools

df <-
structure(list(muc6 = c(0.65991920232772827, 12.234284400939941,
7.5393352508544922, 13.921844482421875, 4.8508410453796387, 0,
6.7801151275634766, 5.5127406120300293, 1.030299186706543, 3.5845346450805664,
0.98191821575164795, 0, 0, 1.052558422088623, 0, 0, 2.5294754505157471,
0.59700602293014526, 0, 0, 7.0485143661499023, 0, 0, 0, 1.1008850336074829,
5.777961254119873, 6.1289887428283691, 0, 4.9814505577087402,
0, 5.4703717231750488, 8.0720577239990234, 0), tumortype = c("Carcinoma",
"sarcoma", "Carcinoma", "Carcinoma", "sarcoma", "sarcoma", "Carcinoma",
"Carcinoma", "sarcoma", "sarcoma", "Carcinoma", "Carcinoma",

arraytools

x <- readxl::read_excel("~/Downloads/EMset.xlsx")
x %>% drop_na() %>% write.table("~/Downloads/EMset.txt", quote=F, row.names = F)
x2 <- read.table("~/Downloads/EMset.txt")
dim(x2) # 218 x 2
epi <- x2[1:170, 2]
mes <- x2[171:218, 2]
x3 <- data.frame(symbol=x2[,2], epimes=c(rep("epi", 170), rep("mes", 48)))
x3[, 1] <- gsub(substr(x3[1,1], 1, 1), "", x3[,1]) # rm "white space'?
write.table(x3, file="~/Downloads/EMgenes_cellline.txt", quote=F, row.names = F, sep="\t")

arraytools

KRT19	E
AGR2	E
RAB25	E
CDH1	E
ERBB3	E
FXYD3	E
SLC44A4	E
S100P	E
SCNN1A	E
GALNT3	E