data(thermo)
## basic examples of get.protein
# amino acid composition of two proteins
get.protein(c("YML020W","YBR051W"),"SGD")
# average composition of proteins
get.protein(c("YML020W","YBR051W"),"SGD",
abundance=1,pname="PROT1_NEW")
# 1 of one and 1/2 of the other
get.protein(c("YML020W","YBR051W"),"SGD",
abundance=c(1,0.5),average=FALSE,pname="PROT2_NEW")
# compositions of proteins induced in carbon limitation
get.protein("low.C","SGD")
## overall composition of proteins exclusively localized
## to cytoplasm of S. cerevisiae with reported expression levels
y <- yeastgfp("cytoplasm")
p <- get.protein(y$yORF,"SGD",y$abundance,"cytoplasm")
# add the protein and calculate its properties
i <- add.protein(p)
protein(i)
## speciation diagram for ER.to.Golgi proteins (COPII coat
## proteins) as a function of logfO2, after Dick, 2009
y <- yeastgfp("ER.to.Golgi")
# take out proteins with NA experimental abundance
ina <- which(is.na(y$abundance))
y$yORF <- y$yORF[-ina]
y$abundance <- y$abundance[-ina]
# get the amino acid compositions of the proteins
p <- get.protein(y$yORF,"SGD")
ip <- add.protein(p)
# use logarithms of activities of proteins such
# that total activity of residues is unity
pl <- protein.length(-ip)
logact <- unitize(rep(1,length(ip)),pl)
# load the proteins
basis("CHNOS+")
a <- affinity(O2=c(-80,-73),iprotein=ip,loga.protein=logact)
# make a speciation diagram
diagram(a,ylim=c(-4.9,-2.9))
# where we are closest to experimental log activity
logfO2 <- rep(-78,length(ip))
abline(v=logfO2[1],lty=3)
# scale experimental abundances such that
# total activity of residues is unity
logact.expt <- unitize(log10(y$abundance),pl)
# plot experimental log activity
points(logfO2,logact.expt,pch=16)
text(logfO2+0.5,logact.expt,y$yORF)
# add title
title(main=paste("ER.to.Golgi; points - relative abundances",
"from YeastGFP. Figure after Dick, 2009",sep=""))
## Chemical activities of model subcellular proteins
# speciation diagram as a function of logfO2, after Dick, 2009
basis("CHNOS+")
names <- yeastgfp()
# calculate amino acid compositions using "get.protein" function
for(i in 1:length(names)) {
y <- yeastgfp(names[i])
p <- get.protein(y$yORF,"SGD",y$abundance,names[i])
add.protein(p)
}
species(names,"SGD")
# set unit activity of residues
pl <- protein.length(thermo$species$name)
species(NULL,unitize(thermo$species$logact,pl))
res <- 200
a <- affinity(O2=c(-82,-65,res))
mycolor <- topo.colors(6)[1:4]
mycolor <- rep(mycolor,times=rep(6,4))
logact <- diagram(a,balance="PBB",names=names,ylim=c(-5,-3),legend.x=NULL,
col=mycolor,lwd=2)$logact
# so far good, but how about labels on the plot?
for(i in 1:length(logact)) {
myloga <- as.numeric(logact[[i]])
# don't take values that lie above the plot (vacuole in this example)
myloga[myloga > -3.1] <- -999
imax <- which.max(myloga)
adj <- 0.5
if(imax > 180) adj <- 1
if(imax < 20) adj <- 0
text(seq(-82,-65,length.out=res)[imax],logact[[i]][imax],
labels=names[i],adj=adj)
}
title(main=paste("Subcellular proteins of S. cerevisiae, after Dick, 2009",
describe(thermo$basis[-5,]),sep="\n"),col.main=par("fg"),cex.main=0.9)
## Oxygen fugacity - activity of H2O predominance
## diagrams for proteologs for 23 YeastGFP localizations
# arranged by decreasing metastability:
# order of this list of locations is based on the
# (dis)appearance of species on the current set of diagrams
names <- c("vacuole","early.Golgi","ER","lipid.particle",
"cell.periphery","ambiguous","Golgi","mitochondrion",
"bud","actin","cytoplasm","late.Golgi",
"endosome","nucleus","vacuolar.membrane","punctate.composite",
"peroxisome","ER.to.Golgi","nucleolus","spindle.pole",
"nuclear.periphery","bud.neck","microtubule")
nloc <- c(4,5,3,4,4,3)
inames <- 1:length(names)
# define the system
basis("CHNOS+")
# calculate amino acid compositions using "get.protein" function
for(i in 1:length(names)) {
y <- yeastgfp(names[i])
p <- get.protein(y$yORF,"SGD",y$abundance,names[i])
add.protein(p)
}
species(names,"SGD")
a <- affinity(H2O=c(-5,0,256),O2=c(-80,-66,256))
# setup the plot
layout(matrix(c(1,1,2:7),byrow=TRUE,nrow=4),heights=c(0.7,3,3,3))
par(mar=c(0,0,0,0))
plot.new()
text(0.5,0.5,paste("Subcellular proteins of S. cerevisiae,",
"after Dick, 2009\n",describe(thermo$basis[-c(2,5),])),cex=1.5)
opar <- par(mar=c(3,4,1,1),xpd=TRUE)
for(i in 1:length(nloc)) {
cex.axis <- 0.75
# uncomment the following and dev.off() below to generate png files
#png(paste(i,"png",sep="."),width=300,height=250); cex.axis <- 1
diagram(a,balance="PBB",names=names[inames],
ispecies=inames,cex.axis=cex.axis)
label.plot(letters[i])
title(main=paste(length(inames),"locations"))
#dev.off()
# take out the stable species
inames <- inames[-(1:nloc[i])]
}
# make an animated gif from png files (with ImageMagick convert tool)
#system(paste("convert -delay 100 1.png 1.png 1.png 2.png",
# "3.png 4.png 5.png 6.png 6.png 6.png yeast.gif"))
# return to plot defaults
layout(matrix(1))
par(opar)
## Compare calculated and experimenal relative abundances
## of proteins in a subcellular location, after Dick, 2009
# get the amino acid composition of the proteins
loc <- "vacuolar.membrane"
y <- yeastgfp(loc)
ina <- which(is.na(y$abundance))
p <- get.protein(y$yORF[-ina],"SGD")
add.protein(p)
# set up the system
basis("CHNOS+")
# this is the logfO2 value that gives the best fit (see paper)
basis("O2",-74)
is <- species(p$protein,p$organism)
np <- length(is)
pl <- protein.length(species()$name)
# we use unitize so total activity of residues is unity
loga <- rep(0,np)
species(1:np,unitize(loga,pl))
a <- affinity()
d <- diagram(a,do.plot=FALSE)
calc.loga <- as.numeric(d$logact)
expt.loga <- unitize(log10(y$abundance[-ina]),pl)
# which ones are outliers
rmsd <- sqrt(sum((expt.loga-calc.loga)^2)/np)
residuals <- abs(expt.loga - calc.loga)
iout <- which(residuals > rmsd)
pch <- rep(16,length(is))
pch[iout] <- 1
# the colors reflect average oxidation number of carbon
# corrects misassigned colors in Figs. 5 and 6 of Dick 2009
ZC <- ZC(thermo$obigt$formula[species()$ispecies])
col <- rgb(0.15-ZC,0,0.35+ZC,max=0.5)
# there is a color-plotting error on line 567 of the plot.R file
# of Dick, 2009 that can be reproduced with
#col <- rep(col,length.out=9)
xlim <- ylim <- extendrange(c(calc.loga,expt.loga))
thermo.plot.new(xlim=xlim,ylim=ylim,xlab=expression(list("log"*italic(a),
"calc")),ylab=expression(list("log"*italic(a),"expt")))
points(calc.loga,expt.loga,pch=pch,col=col)
lines(xlim,ylim+rmsd,lty=2)
lines(xlim,ylim-rmsd,lty=2)
title(main=paste("Calculated and experimental relative abundances of\n",
"proteins in ",loc,", after Dick, 2009",sep=""),cex.main=0.95)
### examples for stress response experiments
## predominance fields for overall protein compositions induced by
## carbon, sulfur and nitrogen limitation
## (experimental data from Boer et al., 2003)
expt <- c("low.C","low.N","low.S")
for(i in 1:length(expt)) {
p <- get.protein(expt[i],"SGD",abundance=1)
add.protein(p)
}
basis("CHNOS+")
basis("O2",-75.29)
species(expt,"SGD")
a <- affinity(CO2=c(-5,0),H2S=c(-10,0))
diagram(a,balance="PBB",names=expt,color=NULL)
title(main=paste("Proteins induced by",
"carbon, sulfur and nitrogen limitation",sep="\n"))
## predominance fields for overall protein compositions
## induced and repressed in an/aerobic carbon limitation
## (experiments of Tai et al., 2005)
# the activities of glucose, ammonium and sulfate
# are similar to the non-growth-limiting concentrations
# used by Boer et al., 2003
basis(c("glucose","H2O","NH4+","hydrogen","SO4-2","H+"),
c(-1,0,-1.3,999,-1.4,-7))
# the names of the experiments in thermo$stress
expt <- c("Clim.aerobic.down","Clim.aerobic.up",
"Clim.anaerobic.down","Clim.anaerobic.up")
# here we use abundance to indicate that the protein
# compositions should be summed together in equal amounts
for(i in 1:length(expt)) {
p <- get.protein(expt[i],"SGD",abundance=1)
add.protein(p)
}
species(expt,"SGD")
a <- affinity(C6H12O6=c(-35,-20),H2=c(-20,0))
diagram(a,color=NULL,as.residue=TRUE)
title(main=paste("Average protein residue composition in",
"an/aerobic carbon limitation in yeast",sep="\n"))Run the code above in your browser using DataLab