In MarzyUnicz/MMRFBiolinks:

library(MMRFBiolinks)

library(TCGAbiolinks)
library(SummarizedExperiment)
library(dplyr)
library(DT)
library(png)
library(grid)

Analyze data from MMRF-COMMPASS database available at GDC Data Portal

You can easily analyze data using following functions:

MMRFanalyzeGDC_Preprocessing: Preprocessing of Gene Expression data

You can easily search TCGA samples, download and prepare a matrix of gene expression.

# You can define a list of samples to query and download providing relative TCGA barcodes.
listSamples <- c("MMRF_2473","MMRF_2111",
                 "MMRF_2362","MMRF_1824",
                 "MMRF_1458","MRF_1361",
                 "MMRF_2203","MMRF_2762",
                 "MMRF_2680","MMRF_1797")

# Query platform Illumina HiSeq with a list of barcode 
query <- GDCquery(project = "MMRF-COMMPASS", 
                  data.category = "Transcriptome Profiling",
                  data.type = "Gene Expression Quantification",
                  experimental.strategy = "RNA-Seq",
                  workflow.type="HTSeq - FPKM",
                  barcode = listSamples)

# Download 
GDCdownload(query)

# Prepare expression matrix with geneID in the rows and samples (barcode) in the columns

MMRnaseqSE <- MMRFGDC_prepare(query,
                              save = TRUE ,
                              save.filename = "RNASeqSE.rda" ,
                              directory = "GDCdata",
                              summarizedExperiment = TRUE)

MMmatrix <- assays(MMRnaseqSE,"raw_count") 
# For gene expression if you need to see a boxplot correlation and AAIC plot to define outliers you can run
MMRnaseq_CorOutliers <- MMRFanalyze_Preprocessing(MMRnaseqSE)

The result from MMRFanalyzeGDC_Preprocessing is shown below:

img <- readPNG("MMRF_PreprocessingOutput.png")
grid.raster(img)

TCGAanalyzeGDC_SurvivalKM: Correlating gene expression and Survival Analysis

#library(TCGAbiolinks)
# Survival Analysis SA
clinical_patient_Cancer <- MMRFquery_clinic(type = "clinical")
dataMMcomplete <- log2(dataMM)
tokenStop<- 1
tabSurvKMcomplete <- NULL
for( i in 1: round(nrow(dataMMcomplete)/100)){
    message( paste( i, "of ", round(nrow(dataMMcomplete)/100)))
    tokenStart <- tokenStop
    tokenStop <-100*i
    tabSurvKM<-TCGAanalyze_SurvivalKM(clinical_patient_Cancer,
                                      dataMMcomplete,
                                      Genelist = rownames(dataMMcomplete)[tokenStart:tokenStop],
                                      Survresult = F,
                                      ThreshTop=0.67,
                                      ThreshDown=0.33)

    tabSurvKMcomplete <- rbind(tabSurvKMcomplete,tabSurvKM)
}
tabSurvKMcomplete <- tabSurvKMcomplete[tabSurvKMcomplete$pvalue < 0.01,]
tabSurvKMcomplete <- tabSurvKMcomplete[order(tabSurvKMcomplete$pvalue, decreasing=F),]
tabSurvKMcompleteDEGs <- tabSurvKMcomplete[
    rownames(tabSurvKMcomplete) %in% dataDEGsFiltLevel$mRNA,
    ]

The result is shown below:

tabSurvKMcompleteDEGs$pvalue <- format(tabSurvKMcompleteDEGs$pvalue, scientific = TRUE)
knitr::kable(tabSurvKMcompleteDEGs[1:5,1:4], 
             digits = 2,
             caption = "Table KM-survival genes after SA",
             row.names = TRUE)
knitr::kable(tabSurvKMcompleteDEGs[1:5,5:7], 
             digits = 2,
             row.names = TRUE)

Analyze clinical data downloaded from MMRF-Commpass Researcher Gateway

You can easily analyze data using following functions:

MMRFgetGateway_BestOverallResponsePlot: draw plot of the Best Overall Response to the Treatment

MMRFgetGateway_BestOverallResponsePlot(clinMMGateway)

img <- readPNG("MMRF_TreatResp.png")
grid.raster(img)

MMRFgetGateway_BestOverallResponsePlot(clinMMGateway,"Bortezomib")

img <- readPNG("MMRF_TreatRespFilt.png")
grid.raster(img)

MarzyUnicz/MMRFBiolinks documentation built on May 28, 2020, 4:08 a.m.