RNA_SEQ_prophetic.r

possibleDrugs <- c("A.443654", "A.770041", "ABT.263", "ABT.888", "AG.014699", "AICAR", "AKT.inhibitor.VIII", "AMG.706", "AP.24534", "AS601245", "ATRA", "AUY922", "Axitinib", "AZ628", "AZD.0530", "AZD.2281", "AZD6244", "AZD6482", "AZD7762", "AZD8055", "BAY.61.3606", "Bexarotene", "BI.2536", "BIBW2992", "Bicalutamide", "BIRB.0796", "Bleomycin", "BMS.509744", "BMS.536924", "BMS.708163", "BMS.754807", "Bortezomib", "Bosutinib", "Bryostatin.1", "BX.795", "Camptothecin", "CCT007093", "CCT018159", "CEP.701", "CGP.082996", "CGP.60474", "CHIR.99021", "CI.1040", "Cisplatin", "CMK", "Cyclopamine", "Cytarabine", "Dasatinib", "DMOG", "Docetaxel", "Doxorubicin", "EHT.1864", "Elesclomol", "Embelin", "Epothilone.B", "Erlotinib", "Etoposide", "FH535", "FTI.277", "GDC.0449", "GDC0941", "Gefitinib", "Gemcitabine", "GNF.2", "GSK269962A", "GSK.650394", "GW.441756", "GW843682X", "Imatinib", "IPA.3", "JNJ.26854165", "JNK.9L", "JNK.Inhibitor.VIII", "JW.7.52.1", "KIN001.135", "KU.55933", "Lapatinib", "Lenalidomide", "LFM.A13", "Methotrexate", "MG.132", "Midostaurin", "Mitomycin.C", "MK.2206", "MS.275", "Nilotinib", "NSC.87877", "NU.7441", "Nutlin.3a", "NVP.BEZ235", "NVP.TAE684", "Obatoclax.Mesylate", "OSI.906", "PAC.1", "Paclitaxel", "Parthenolide", "Pazopanib", "PD.0325901", "PD.0332991", "PD.173074", "PF.02341066", "PF.4708671", "PF.562271", "PHA.665752", "PLX4720", "Pyrimethamine", "QS11", "Rapamycin", "RDEA119", "RO.3306", "Roscovitine", "Salubrinal", "SB.216763", "SB590885", "Shikonin", "SL.0101.1", "Sorafenib", "S.Trityl.L.cysteine", "Sunitinib", "Temsirolimus", "Thapsigargin", "Tipifarnib", "TW.37", "Vinblastine", "Vinorelbine", "Vorinostat", "VX.680", "VX.702", "WH.4.023","WZ.1.84", "X17.AAG", "X681640", "XMD8.85", "Z.LLNle.CHO", "ZM.447439")
diseaseAbbrvs <- c("ACC", "BLCA", "BRCA", "CESC", "CHOL", "COAD", "DLBC", "GBM", "HNSC", "KICH", "KIRC", "KIRP", "LAML", "LGG", "LIHC", "LUAD", "LUSC", "MESO", "OV", "PAAD", "PCPG", "PRAD", "READ", "SARC", "SKCM", "STAD", "TGCT", "THCA", "THYM", "UCEC", "UCS", "UVM")


#### code to "load" package #####
library(car)
library(genefilter)
library(preprocessCore)
library(ridge)
library(sva)
setwd("C:/Users/fwang1/Desktop/mRNA-Seq")
load("C:/Users/fwang1/Desktop/Lari/Logistic/drugAndPhenoCgp.RData")
files <- dir("C:/Users/fwang1/Downloads/pRRophetic_0.5.tar.gz/pRRophetic_0.5.tar/pRRophetic/R") # <- contents of R.zip
sapply(files, source)


## Loading the data
setwd("C:/Users/fwang1/Desktop/mRNA-Seq") # set working directory

tpmDatMat_bc <- read.delim("GBM.rnaseqv2__illuminahiseq_rnaseqv2__unc_edu__Level_3__RSEM_genes__data.data.txt", as.is=T) ##download the right file
tpmDatMat_bc_tpm <- apply(tpmDatMat_bc[-1,which(tpmDatMat_bc[1,] == "scaled_estimate")], 2, as.numeric) # pull out relevant columns
tpmDatMat_bc_tpm <- tpmDatMat_bc[-1,which(tpmDatMat_bc[1,] == "scaled_estimate")] 
tpmDatMat_bc_tpm <- apply(tpmDatMat_bc_tpm, 2, as.numeric)
geneNames <- do.call(cbind, strsplit(tpmDatMat_bc[, "Hybridization.REF"], "|", fixed=TRUE))[1,][-1] # get the actual gene symbols
rownames(tpmDatMat_bc_tpm) <- geneNames
colnames(tpmDatMat_bc_tpm) <- substr(colnames(tpmDatMat_bc_tpm), 1, 28)
tpmDatMat_bc_tpm_logged <- log((tpmDatMat_bc_tpm*1000000)+1) # scale and log transform the data

#### Code to run prediction function #####
allExprData <- tpmDatMat_bc_tpm_logged


LL <- lapply(possibleDrugs,
             function(i) {
               predicted <- pRRopheticLogisticPredict(allExprData, i, selection=1, batchCorrect="standardize")
               
               assign(paste('b',i,sep=''),predicted)
             }
)
result <- do.call(cbind, LL)
write.csv(result, file="predicted-rna_seq.csv") ## contains the sensitivity score for every patient, every drug