by Keith Baggerly
Jun 23, 2013
We want to examine the joint distribution of FABP4 and ADH1B in the TCGA, Tothill, Bonome, and CCLE cohorts, and to assess how much RD rates increase with expression levels.
We use the array and clinical data prepared in the various “assembleData” and “assembleClinical” scripts. We produce plots for each dataset, using high/low cutoffs assessed by eye. We measure the RD rates when both genes are high for the TCGA and Tothill cohorts.
We produce figures named fabp4VsAdh1b(dataset).
The TCGA RD rates are 97/107 in the high expression group, vs 281/384 in the complement.
The Tothill RD rates are 59/63 in the high expression group, vs 80/126 in the complement.
load(file.path("RDataObjects", "tcgaExpression.RData"))
load(file.path("RDataObjects", "tcgaFilteredSamples.RData"))
load(file.path("RDataObjects", "tcgaClinical.RData"))
fabp4.ps <- "203980_at"
adh1b.ps <- "209612_s_at"
bgColors <- rep("grey", length(tcgaSampleRD))
bgColors[tcgaSampleRD == "RD"] <- "red"
tcgaUsed <- tcgaFilteredSamples[, "sampleUse"] == "Used"
plot(tcgaExpression[fabp4.ps, tcgaUsed], tcgaExpression[adh1b.ps, tcgaUsed],
pch = 21, bg = bgColors[tcgaUsed], xlab = "FABP4 Expression (203980_at)",
ylab = "ADH1B Expression (209612_s_at)", main = "FABP4 and ADH1B in TCGA Ovarian Samples")
abline(v = 3.5, h = 3.5)
legend("topleft", c("Yes", "No"), pch = 19, col = c("red", "grey"), bty = "n",
title = "RD Status")
## pdf
## 2
Now we check the RD to No RD ratios by subgroup.
table(tcgaSampleRD[tcgaUsed], tcgaExpression[fabp4.ps, tcgaUsed] > 3.5)
##
## FALSE TRUE
## No RD 94 19
## RD 254 124
table(tcgaSampleRD[tcgaUsed], tcgaExpression[adh1b.ps, tcgaUsed] > 3.5)
##
## FALSE TRUE
## No RD 97 16
## RD 266 112
table(tcgaSampleRD[tcgaUsed], (tcgaExpression[fabp4.ps, tcgaUsed] > 3.5) & (tcgaExpression[adh1b.ps,
tcgaUsed] > 3.5))
##
## FALSE TRUE
## No RD 103 10
## RD 281 97
When both gene levels are high (above 3.5), the RD rate is 97/107 (90.6%), as opposed to 281/384 (73.2%).
rm(tcgaExpression, tcgaFilteredSamples, tcgaSampleInfo, fabp4.ps, adh1b.ps,
bgColors, tcgaDataDirs, tcgaFiles, tcgaSampleClinicalMapping, tcgaSampleRD,
tcgaUsed)
load(file.path("RDataObjects", "tothillExpression.RData"))
load(file.path("RDataObjects", "tothillFilteredSamples.RData"))
load(file.path("RDataObjects", "tothillClinical.RData"))
tothillExpression <- tothillExpression[, rownames(tothillFilteredSamples)]
all(rownames(tothillFilteredSamples) == names(tothillRD))
## [1] TRUE
fabp4.ps <- "203980_at"
adh1b.ps <- "209612_s_at"
bgColors <- rep("grey", length(tothillRD))
bgColors[tothillRD == "RD"] <- "red"
tothillUsed <- tothillFilteredSamples[, "sampleUse"] == "Used"
plot(tothillExpression[fabp4.ps, tothillUsed], tothillExpression[adh1b.ps, tothillUsed],
pch = 21, bg = bgColors[tothillUsed], xlab = "FABP4 Expression (203980_at)",
ylab = "ADH1B Expression (209612_s_at)", main = "FABP4 and ADH1B in Tothill Ovarian Samples")
abline(v = 5.25, h = 4.25)
legend("topleft", c("Yes", "No"), pch = 19, col = c("red", "grey"), bty = "n",
title = "RD Status")
## pdf
## 2
Now we check the RD to No RD ratios by subgroup.
table(tothillRD[tothillUsed], tothillExpression[fabp4.ps, tothillUsed] > 5.25)
##
## FALSE TRUE
## No RD 44 6
## RD 78 61
table(tothillRD[tothillUsed], tothillExpression[adh1b.ps, tothillUsed] > 4.25)
##
## FALSE TRUE
## No RD 44 6
## RD 70 69
table(tothillRD[tothillUsed], (tothillExpression[fabp4.ps, tothillUsed] > 5.25) &
(tothillExpression[adh1b.ps, tothillUsed] > 4.25))
##
## FALSE TRUE
## No RD 46 4
## RD 80 59
When both gene levels are high, the RD rate is 59/63 (93.7%), as opposed to 80/126 (63.5%).
rm(tothillClinical, tothillExpression, tothillFilteredSamples, tothillOSMos,
tothillPFSMos, fabp4.ps, adh1b.ps, bgColors, tothillRD, tothillUsed)
load(file.path("RDataObjects", "bonomeExpression.RData"))
load(file.path("RDataObjects", "bonomeClinical.RData"))
bonomeExpression <- bonomeExpression[, rownames(bonomeClinical)]
fabp4.ps <- "203980_at"
adh1b.ps <- "209612_s_at"
bgColors <- rep("grey", nrow(bonomeClinical))
bgColors[bonomeClinical[, "SurgeryOutcome"] == "Suboptimal"] <- "red"
bonomeUsed <- bonomeClinical[, "SurgeryOutcome"] != "" ## omit 10 normal samples
plot(bonomeExpression[fabp4.ps, bonomeUsed], bonomeExpression[adh1b.ps, bonomeUsed],
pch = 21, bg = bgColors[bonomeUsed], xlab = "FABP4 Expression (203980_at)",
ylab = "ADH1B Expression (209612_s_at)", main = "FABP4 and ADH1B in Bonome Ovarian Samples")
abline(v = 5.25, h = 4.9)
legend("topleft", c("Subopt", "Optimal"), pch = 19, col = c("red", "grey"),
bty = "n", title = "Debulking")
## pdf
## 2
Now we check the Optimal to Suboptimal ratios by subgroup.
table(bonomeClinical[bonomeUsed, "SurgeryOutcome"], bonomeExpression[fabp4.ps,
bonomeUsed] > 5.25)
##
## FALSE TRUE
## 0 0
## Optimal 60 30
## Suboptimal 65 30
table(bonomeClinical[bonomeUsed, "SurgeryOutcome"], bonomeExpression[adh1b.ps,
bonomeUsed] > 4.9)
##
## FALSE TRUE
## 0 0
## Optimal 69 21
## Suboptimal 72 23
table(bonomeClinical[bonomeUsed, "SurgeryOutcome"], (bonomeExpression[fabp4.ps,
bonomeUsed] > 5.25) & (bonomeExpression[adh1b.ps, bonomeUsed] > 4.9))
##
## FALSE TRUE
## 0 0
## Optimal 74 16
## Suboptimal 76 19
rm(bonomeClinical, bonomeExpression, fabp4.ps, adh1b.ps, bgColors, bonomeOSYrs,
bonomeUsed)
load(file.path("RDataObjects", "ccleExpression.RData"))
load(file.path("RDataObjects", "ccleClinical.RData"))
all(rownames(ccleClinical) == colnames(ccleExpression))
## [1] TRUE
fabp4.ps <- "203980_at"
adh1b.ps <- "209612_s_at"
bgColors <- rep("grey", nrow(ccleClinical))
bgColors[ccleClinical[, "primarySite"] == "ovary"] <- "pink"
bgColors[ccleClinical[, "primarySite"] == "breast"] <- "blue"
plot(ccleExpression[fabp4.ps, ], ccleExpression[adh1b.ps, ], pch = 21, bg = bgColors,
xlab = "FABP4 Expression (203980_at)", ylab = "ADH1B Expression (209612_s_at)",
main = "FABP4 and ADH1B in CCLE Samples")
abline(v = 5, h = 4.5)
legend("topright", c("Ovary", "Breast", "Other"), pch = 19, col = c("pink",
"blue", "grey"), bty = "n", title = "Tissue")
## pdf
## 2
rm(ccleClinical, ccleExpression, fabp4.ps, adh1b.ps, bgColors)
getwd()
## [1] "/Users/kabagg/TCGA/RDPaper"
sessionInfo()
## R version 3.0.0 (2013-04-03)
## Platform: x86_64-apple-darwin10.8.0 (64-bit)
##
## 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] knitr_1.1
##
## loaded via a namespace (and not attached):
## [1] digest_0.6.3 evaluate_0.4.3 formatR_0.7 stringr_0.6.2
## [5] tools_3.0.0