lwaldron

# I create and discuss this code at https://youtu.be/nU_GEPKVXU8

library(dplyr)
#> 
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag
#> The following objects are masked from 'package:base':
#> 

lwaldron

system("gsutil cp gs://biocbbs_2020a/cmd3out/uploads/GuptaA_2019.metaphlan_bugs_list.stool.rda .")
load("GuptaA_2019.metaphlan_bugs_list.stool.rda")
head(rownames(GuptaA_2019.metaphlan_bugs_list.stool)) #first 3 look wrong
grep("CIBIO", rownames(GuptaA_2019.metaphlan_bugs_list.stool)) #there are 60 with CIBIO in the rowname

lwaldron

# to run this using Docker from the command line on the stock Bioconductor image:
# docker run -it bioconductor/bioconductor_docker:latest R

BiocManager::install("cBioPortalData")
library(cBioPortalData)

#acc_tcga full data pack
system.time(accpack <- cBioDataPack("acc_tcga")) #~10 seconds
accpack

lwaldron

# docker run -it bioconductor/bioconductor_docker:latest R
BiocManager::install("cBioPortalData")
library(cBioPortalData)
cBio <- cBioPortal()
system.time(acc <- cBioPortalData(cBio, studyId = "acc_tcga", genePanelId = "IMPACT341"))
acc

lwaldron

# docker run -it bioconductor/bioconductor_docker:latest R
BiocManager::install("cBioPortalData")
library(cBioPortalData)
cBio <- cBioPortal()
system.time(gbm <- cBioPortalData(cBio, studyId = "gbm_tcga", genePanelId = "IMPACT341"))
gbm
# again
system.time(gbm <- cBioPortalData(cBio, studyId = "gbm_tcga", genePanelId = "IMPACT341"))

lwaldron

source("https://raw.githubusercontent.com/waldronlab/bugSigSimple/master/R/simple.R")
x=readCurationSheet("https://github.com/waldronlab/bugSigSimple/blob/master/inst/extdata/Microbial%20signatures%20curation%20-%20signatures.tsv?raw=true")
length(unique(x$PMID))
writeLines(unique(x$PMID), file("signaturesPMID.txt"))

lwaldron

library(BiocManager)

dir.create("~/packagefiles")
unlink("installationresults.txt")

pkgs <- available.packages(contrib.url(BiocManager::repositories()["BioCsoft"]))
pkgs <- rownames(pkgs)
set.seed(1)
pkgs <- sample(pkgs)
## pkgs <- pkgs[!pkgs %in% installed.packages()]

lwaldron

if( Biobase::package.version("curatedTCGAData") < "1.5.6" ){
  BiocManager::install("waldronlab/curatedTCGAData")
}
stopifnot(BiocManager::version() >= "3.9")

library(curatedTCGAData) #requires >=1.5.6 and bioc-devel
mae <- curatedTCGAData("UCEC", "Methylation_methyl27", dry.run = FALSE) #~2 seconds from cache
dm <- assay(mae, 1)

# benchmarking showing cubic increase with # rows

lwaldron

# Masseroli et al 2018, https://doi.org/10.1093/bioinformatics/bty688
# "In TCGA data of BRCA patients, find the DNA somatic mutations 
# within the first 2000 bp outside of the genes that are both 
# expressed with FPKM > 3 and have at least a methylation in the same patient
# biospecimen, and extract these mutations of the top 5% patients
# with the highest number of such mutations."

library(curatedTCGAData)
system.time(mae <- curatedTCGAData("ACC", c("Mutation", "RNASeq2GeneNorm", "Methylation"), dry.run = FALSE))

lwaldron

## ------------------------------------------------------------------------
library(GenomicRanges)
library(RaggedExperiment)
sample1 <- GRanges(
    c(A = "chr1:1-10:-", B = "chr1:8-14:+", C = "chr2:15-18:+"),
    score = 3:5)
sample2 <- GRanges(
    c(D = "chr1:1-10:-", E = "chr2:11-18:+"),
    score = 1:2)
colDat <- DataFrame(id = 1:2)