lwaldron

library(curatedTCGAData)
curatedTCGAData("OV")
mae <- curatedTCGAData("OV", assays=c("mRNAArray", "RNASeq2GeneNorm", "RNASeqGene"), dry.run = FALSE)
library(TCGAutils)
keep <- TCGAsampleSelect(colnames(mae), 11)
mae <- mae[, keep, ]
mae <- intersectColumns(mae)
mae <- intersectRows(mae)

library(org.Hs.eg.db)

lwaldron

.cMAE <- function(mae, x, name="newelement"){
  el <- ExperimentList(tmp=x)
  names(el)[1] <- name
  c(mae, el)
}

.hasSymbols <- function(x){
  mean(c(FALSE, grepl("^[A-Z0-9]{1,6}|^C[0-9]orf[0-9]{1,4}", rownames(x))), na.rm=TRUE) > 0.9
}
.isSummarizedExperiment <- function(x){

lwaldron

simplifyTCGAData <- function(obj, removeRaggedExperiments=TRUE){
##This function will convert mutations to a genes x samples RangedSummarizedExperiment of 1 for non-silent mutations, 1 for silent or no mutation
##It will convert segmented copy number to copy number per gene, using a weighted average if there are non-disjunct ranges  
  suppressPackageStartupMessages({
    library(TxDb.Hsapiens.UCSC.hg19.knownGene)
    library(org.Hs.eg.db)
    library(GenomeInfoDb)
  })
  gn <- genes(TxDb.Hsapiens.UCSC.hg19.knownGene)
  gn <- keepStandardChromosomes(granges(gn), pruning.mode="coarse")

lwaldron

metaphlanToPhyloseq <- function(
  metaphlandir,
  metadat=NULL,
  simplify=TRUE){
  ## tax is a matrix or data.frame with the table of taxonomic abundances, rows are taxa, columns are samples
  ## metadat is an optional data.frame of specimen metadata, rows are samples, columns are variables
  ## if simplify=TRUE, use only the most detailed level of taxa names in the final object
  ## metaphlanToPhyloseq("~/Downloads/metaphlan_bugs_list")
  .getMetaphlanTree <- function(removeGCF=TRUE, simplify=TRUE){
    if (!requireNamespace("ape")) {

lwaldron

fracwithin <- function(n){
  sam1 <- rnorm(n)
  ci <- t.test(sam1)$conf.int
  means <- replicate(100, mean(rnorm(n)))
  mean(means > ci[1] & means < ci[2])
}

set.seed(2)
n <- seq(5, 10000, by=2)
fraction <- sapply(n, function(i) fracwithin(i))

lwaldron

---
title: "OVC single-cell analysis"
author: "Levi Waldron"
date: "5/29/2018"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

lwaldron

# Before starting, install the NCBI SRA Tookit:
# Debian/Ubuntu: 
#     apt install sra-toolkit 
# macOS: 
#     brew install sratoolkit 
# Windows: 
#     see https://tinyurl.com/y845ppaa 
# Get your dbGaP repository from https://dbgap.ncbi.nlm.nih.gov/aa/wga.cgi?page=list_wishlists
# Click "get dbGaP repository key"
library(HMP16SData)

lwaldron

library(curatedMetagenomicData)
library(SummarizedExperiment)
library(tidyr)
library(ape)

simplifynodes <- TRUE

makeTaxTable <- function(fullnames){
  taxonomic.ranks <- c("Kingdom", "Phylum", "Class", "Order", 
                       "Family", "Genus", "Species", "Strain")

lwaldron

## A big SE

library(curatedMetagenomicData)
library(SummarizedExperiment)
library(tidyr)
library(ape)

simplifynodes <- TRUE

makeTaxTable <- function(fullnames){

lwaldron

url1 <- "https://support.illumina.com/content/dam/illumina-support/documents/documentation/chemistry_documentation/samplepreps_nextera/nexterarapidcapture/nexterarapidcapture_exome_targetedregions.bed"
url2 <- "https://support.illumina.com/content/dam/illumina-support/documents/documentation/chemistry_documentation/samplepreps_nextera/nexterarapidcapture/nexterarapidcapture_expandedexome_targetedregions.bed"

library(rtracklayer)
rapidgr <- import(url1, genome="hg19")
expandedgr <- import(url2, genome="hg19")

library(GenomicRanges)

table(countOverlaps(rapidgr, expandedgr))