mw55309

x <- data.frame(d=runif(12), g=rep(1:4, each =3)) 

my.col <- c("deepskyblue3","darkorange2","darkgray","gold")

spacer <- c(1, 0.1, 0.1, 1, 0.1, 0.1, 1, 0.1, 0.1, 1, 0.1, 0.1)

bw <- 0.8

xmax <- (sum(spacer) * bw) + (nrow(x) * bw)

mw55309

sync; echo 1 > /proc/sys/vm/drop_caches

mw55309

# data from https://twitter.com/LukeTurnerEsq/status/738308821207142400
d <- data.frame(min=c(18,30,40,50,60), max=c(29,39,49,59,85), remain=c(73,64,46,45,35), stringsAsFactors=FALSE)

# calc mid-points
mid <- d$min + ((d$max - d$min) / 2)

# fit model and plot
lmfit <- lm(d$remain~mid)
plot(mid, d$remain, pch=16, xlab="Age", ylab="% who support REMAIN in EURef")
abline(lmfit)

mw55309

YAPYAP  first uniquely mapped primary;second uniquely mapped primary    152876366
YAPYAP  first uniquely mapped primary;second uniquely mapped primary soft-clipped       7347030
YAPYAP  first uniquely mapped primary soft-clipped;second uniquely mapped primary soft-clipped  3420363
YAPYAP  first uniquely mapped primary soft-clipped;second uniquely mapped primary       2772544
YAPYAP  first unmapped;second unmapped  579939
YAPYAP  first uniquely mapped primary;second unmapped   522762
YAPYAP  first uniquely mapped primary;second multi-mapped one primary   228682
YAPYAP  first multi-mapped one primary;second uniquely mapped primary soft-clipped      183838
YAPYAP  first uniquely mapped primary soft-clipped;second multi-mapped one primary      175894
YAPYAP  first multi-mapped one primary;second uniquely mapped primary   148302

mw55309

d <- read.csv("http://www.electoralcommission.org.uk/__data/assets/file/0014/212135/EU-referendum-result-data.csv")

vec <- rep(1, nrow(d))
vec[d$Region=="Scotland"] <- 1
vec[d$Region=="North East"] <- 2
vec[d$Region=="North West"] <- 3
vec[d$Region=="East Midlands"] <- 4
vec[d$Region=="West Midlands"] <- 5
vec[d$Region=="Yorkshire and The Humber"] <- 6
vec[d$Region=="Northern Ireland"] <- 7

mw55309

mydir <- "/data2/minion/R7/Ebola/PRJEB10571_ERR1014225/014370/pass/"

meta <- read.meta.info(dir=mydir, path.t="/Analyses/Basecall_2D_000/", path.c="Analyses/Basecall_2D_000/")

yield <- plot.cumulative.yield(meta)

plot.length.histogram(meta)

meta.s <- summarise.by.channel(meta)

mw55309

# Polyester (https://github.com/alyssafrazee/polyester) simulates RNA-Seq reads
# Output is FASTA and sorted by input transcript ID
# Some tools don't like this e.g. Salmon, and want a more random order

# Here is a one-liner for shuffling the reads from sample 1 in output directory test.out

cat test.out/sample_01.fasta | paste - - | shuf | awk '{print $1"\n"$2}' > test.out/sample_01.shuf.fasta

mw55309

par(mar=c(2,2,1,1))
plot(sqrt, bty="n", xaxt="n", yaxt="n", xlab="", ylab="")

axis(side=1, at=seq(0,1,by=0.2), las=1, labels=FALSE)
axis(side=2, at=seq(0,1,by=0.2), las=2, labels=FALSE)

axis(side=1, at=seq(0,1,by=0.2), las=1, labels=TRUE, tick=FALSE, line=-0.5, cex.axis=0.8)
axis(side=2, at=seq(0,1,by=0.2), las=2, labels=TRUE, tick=FALSE, line=-0.5, cex.axis=0.8)

axis(side=1, at=0.5, labels="x", tick=FALSE, line=0)

mw55309

## functions

plot.histograms <- function(cname="", flip=FALSE, xlim) {

	dse <- density(setosa[, cname])
	dve <- density(versicolor[, cname])
	dvi <- density(virginica[, cname])

	ymax <- max(c(dse$y, dve$y, dvi$y))

mw55309

Download Miniconda

Main env (python 3.5):
	- snakemake
	- Ete3?
	- CheckM
	- HMMER
	- pplacer
	- FastTree
	- Prodigal