jnpaulson

################################################################################
#' Convert dataframe objects to biom-format \code{biom-class} objects.
#'
#' Wrapper to convert dataframe objects to \code{biom-class} objects. Currently cannot
#' create sparse biom-format objects. The user can then export their previously
#' prepared files using \code{write_biom}.
#' \href{http://biom-format.org/documentation/biom_format.html}{the
#' biom-format definition}.
#'
#' #' The BIOM file format (canonically pronounced biome) is designed to be a general-use format for representing biological sample by observation contingency tables. BIOM is a recognized standard for the \href{http://www.earthmicrobiome.org/}{Earth Microbiome Project} and is a \href{http://gensc.org/}{Genomics Standards Consortium} candidate project. Please see \href{http://biom-format.org/}{the biom-format home page} for more details.

jnpaulson

make_biom2<-function (data, sample_metadata = NULL, observation_metadata = NULL, 
    id = NULL,matrix_element_type="int") 
{
    if (!is.null(observation_metadata)) {
        rows = mapply(list, SIMPLIFY = FALSE, id = as.list(rownames(data)), 
            metadata = alply(as.matrix(observation_metadata), 
                1, .expand = FALSE, .dims = TRUE))
    }
    else {
        rows = mapply(list, id = as.list(rownames(data)), metadata = NA, 

jnpaulson

bubblePlot<-function(yvector,xvector,sigvector=NULL,nbreaks=10,ret=FALSE,scale=1,...){
	#if(names(yvector)%in%names(xvector)){
	#	stop("Name the y and x vectors -- ideally the same name ;-)")
	#}
	ybreaks = cut(yvector,breaks=quantile(yvector,p=seq(0,1,length.out=nbreaks)),include.lowest=T)
	xbreaks = cut(xvector,breaks=quantile(xvector,p=seq(0,1,length.out=nbreaks)),include.lowest=T)
	numFeatures = lapply(levels(xbreaks),function(i){
		k = which(xbreaks==i)
		sapply(levels(ybreaks),function(j){
			length(which(ybreaks[k]==j))

jnpaulson

source("http://bioconductor.org/biocLite.R")
biocLite(c("rhdf5","biom"))
library(rhdf5)
library(biom)

# This generates the matrix columns-wise
generate_matrix <- function(x){
	indptr  = x$sample$matrix$indptr+1
	indices = x$sample$matrix$indices+1
	data    = x$sample$matrix$data

jnpaulson

---
title: "metagenomeSeq"
author: "jpaulson"
date: "October 22, 2014"
output: html_document
runtime: shiny
---

This R Markdown document is made interactive using Shiny and allows you to explore MRexperiment objects.
Replace 

jnpaulson

jnpaulson

jnpaulson

#!/bin/bash

# grab the biom data
wget https://github.com/biocore/American-Gut/raw/master/data/PGP/PGP_100nt.biom.gz
wget https://github.com/biocore/American-Gut/raw/master/data/HMP/HMPv35_100nt.biom.gz
wget https://github.com/biocore/American-Gut/raw/master/data/GG/GG_100nt.biom.gz
wget https://github.com/biocore/American-Gut/raw/master/data/AG/AG_100nt.biom.gz
gunzip *

# grab the phenodata

jnpaulson

require(vegan)
require(biom)
require(metagenomeSeq)

files = grep(".biom$",list.files(),value=TRUE)
files2= grep(".txt",list.files(),value=TRUE)
files3 = sprintf("%s_MRexperiment.rdata",files)

# This generates the data - only run once.
for(i in 1:length(files)){

jnpaulson

j = unlist(locals[2:3])
obj2 = obj[,j]
sampleID2 = sampleID[j]

mat = MRcounts(obj2,norm=TRUE,log=TRUE)
otusToKeep <- which(rowSums(mat)>0)
otuVars<-rowSds(mat[otusToKeep,])
otuIndices<-otusToKeep[order(otuVars,decreasing=TRUE)[1:1000]]
mat <- mat[otuIndices,]
mat = t(mat)