## ----knitrSetup, include=FALSE-------------------------------------------
library(knitr)
opts_chunk$set(out.extra='style="display:block; margin: auto"', fig.align="center", tidy=FALSE)


## ----install, eval=FALSE-------------------------------------------------
## source("http://bioconductor.org/biocLite.R")
## biocLite("rcellminer")
## biocLite("rcellminerData")


## ----loadLibrary, message=FALSE, warning=FALSE---------------------------
library(rcellminer)
library(rcellminerData)


## ----searchHelp, eval=FALSE, tidy=FALSE----------------------------------
## help.search("rcellminer")


## ----plotCellminer-------------------------------------------------------
# Get Cellminer data
drugAct <- exprs(getAct(rcellminerData::drugData))
molData <- getMolDataMatrices()

# Two drugs 
nsc <- c("3284", "739")
plots <- c("drug", "drug") 
plotCellMiner(drugAct, molData, plots, nsc, NULL)

# Just drug
nsc <- "94600"
plots <- c("drug") 
plotCellMiner(drugAct, molData, plots, nsc, NULL)

# Just expression
gene <- "TP53"
plots <- c("exp") 
plotCellMiner(drugAct, molData, plots, NULL, gene)

# Two genes 
# NOTE: subscript out of bounds Errors likely mean the gene is not present for that data type
gene <- c("TP53", "MDM2")
plots <- c("exp", "mut", "exp") 
plotCellMiner(drugAct, molData, plots, NULL, gene)

# Gene and drug to plot 
nsc <- "94600"
gene <- "TP53"
plots <- c("mut", "drug", "cop") 
plotCellMiner(drugAct, molData, plots, nsc, gene)


## ----plotDrugSets--------------------------------------------------------
# Get CellMiner data
drugAct <- exprs(getAct(rcellminerData::drugData))

# Select drugs using NSC IDs
drugs <- "26273 39367 39368 105546 120958 255523 284751 289900 736740 743891 752330"

drugs <- strsplit(drugs, " ")[[1]]
drugAct <- drugAct[drugs,]
mainLabel <- paste("Drug Set: 1, Drugs:", length(drugs), sep=" ")

plotDrugSets(drugAct, drugs, mainLabel) 


## ----plotStructures------------------------------------------------------
plotStructuresFromNscs("Topotecan", getSmiles("609699"))


## ----compareFingerPrints, results='hide', message=FALSE, warning=FALSE----
# Load sqldf
library(sqldf)

# Set up necessary data
## Compound annotations
df <- as(featureData(getAct(rcellminerData::drugData)), "data.frame")
## Drug activities 
drugAct <- exprs(getAct(rcellminerData::drugData))
## Molecular profiling data
molData <- getMolDataMatrices() 

# Example filter on particular properties of the compounds
tmpDf <- sqldf("SELECT NSC, SMILES 
							 FROM df 
							 WHERE SMILES != ''")

# Compare against the 100 NSCs for demonstration
ids <- head(tmpDf$NSC, 100)
smiles <- head(tmpDf$SMILES, 100)

# All public
#ids <- tmpDf$nsc
#smiles <- tmpDf$smiles

drugOfInterest <- "MK2206"
smilesOfInterest <- "C1CC(C1)(C2=CC=C(C=C2)C3=C(C=C4C(=N3)C=CN5C4=NNC5=O)C6=CC=CC=C6)N"

# Make a vector of all the compounds to be pairwise compared 
ids <- c(drugOfInterest, ids)
smiles <- c(smilesOfInterest, smiles)


## ----runComparison, results='hide', message=FALSE------------------------
# Run fingerprint comparison 
results <- compareFingerprints(ids, smiles)


## ----plotSimilarStructures-----------------------------------------------
# Plot top 2 results 
resultsIdx <- sapply(names(results)[2:3], function(x) { which(tmpDf$NSC == x) })
resultsIds <- names(results)[2:3]
resultsSmiles <- tmpDf$SMILES[resultsIdx]

resultsIds <- c(drugOfInterest, resultsIds)
resultsSmiles <- c(smilesOfInterest, resultsSmiles)

plotStructuresFromNscs(resultsIds, resultsSmiles, 
											 titleCex=0.5, mainLabel="Fingerprint Results")


## ----plotCellMiner-------------------------------------------------------
nscs <- names(results)[2:3]
plotCellMiner(drugAct=drugAct, molData=molData, plots=rep("drug", length(nscs)), nscs, NULL)


## ----makeDrugInfoTable, results='hide', message=FALSE--------------------
drugAnnot <- as(featureData(getAct(rcellminerData::drugData)), "data.frame")

knownMoaDrugs <- unique(c(getMoaToCompounds(), recursive = TRUE))

knownMoaDrugInfo <- data.frame(NSC=knownMoaDrugs, stringsAsFactors = FALSE)

knownMoaDrugInfo$Name <- drugAnnot[knownMoaDrugInfo$NSC, "NAME"]

knownMoaDrugInfo$MOA <- vapply(knownMoaDrugInfo$NSC, getMoaStr, character(1))

# Order drugs by mechanism of action.
knownMoaDrugInfo <- knownMoaDrugInfo[order(knownMoaDrugInfo$MOA), ]


## ----computeGI50Data, results='hide', message=FALSE----------------------
negLogGI50Data <- getDrugActivityData(nscSet = knownMoaDrugInfo$NSC)

gi50Data <- 10^(-negLogGI50Data)


## ----makeIntegratedTable, results='hide', message=FALSE------------------
knownMoaDrugAct <- as.data.frame(cbind(knownMoaDrugInfo, gi50Data), stringsAsFactors = FALSE)

# This table can be written out to a file
#write.table(knownMoaDrugAct, file="knownMoaDrugAct.txt", quote=FALSE, sep="\t", row.names=FALSE, col.names=TRUE, na="NA")


## ----sessionInfo---------------------------------------------------------
sessionInfo()