epic-demo.rmd

```{r epic-demo-init, echo=FALSE, message=F}
library(knitr)
library(Cairo)
opts_chunk$set(warning=FALSE, fig.width=6, fig.height=6, dev="CairoPNG", stop=TRUE)

```

# Normalize an EPIC dataset

## Download example data set 

```{r child = 'dataset-epic-demo.rmd'}
```

```{r}
path <- download.epic.demo.dataset()
```

## Normalize dataset 

Create samplesheet
```{r}
library(meffil)
samplesheet <- meffil.read.samplesheet(base=path, pattern="Demo_SampleSheet.csv")
```

Parameters.
```{r}
qc.file <- "epic-demo/qc-report.html"
author <- "Illumina, et al."
study <- "EPIC demo dataset"
number.pcs <- 2
norm.file <- "epic-demo/normalization-report.html"
```

Generate QC objects.
```{r epic-demo-qc, cache=T}
qc.objects <- meffil.qc(samplesheet, cell.type.reference="blood gse35069 complete", verbose=T)
```

QC report.
```{r}
qc.summary <- meffil.qc.summary(qc.objects, verbose=T)
meffil.qc.report(qc.summary,
                 output.file=qc.file,
                 author=author,
                 study=study)
```

Normalization dataset.
```{r epic-demo-norm, cache=T}
norm.objects <- meffil.normalize.quantiles(qc.objects, number.pcs=number.pcs, verbose=T)

norm.dataset <- meffil.normalize.samples(norm.objects,
                                         just.beta=F, 
                                         cpglist.remove=qc.summary$bad.cpgs$name,
                                         verbose=T)
```

```{r}
beta.meffil <- meffil.get.beta(norm.dataset$M, norm.dataset$U)
```

Compute principal components of the normalized methylation matrix.
```{r epic-demo-pcs, cache=T}
pcs <- meffil.methylation.pcs(beta.meffil, sites=meffil.get.autosomal.sites("epic"), verbose=T)
```

Normalization report.
```{r}
parameters <- meffil.normalization.parameters(norm.objects)
parameters$batch.threshold <- 0.01
norm.summary <- meffil.normalization.summary(norm.objects=norm.objects,
                                             pcs=pcs,
                                             parameters=parameters, verbose=T)

meffil.normalization.report(norm.summary,
                            output.file=norm.file,
                            author=author,
                            study=study)
```


## Horvath's clock and the EPIC microarray

```{r}
#require(RCurl)
#clock <- read.csv(textConnection(getURL("https://labs.genetics.ucla.edu/horvath/dnamage/AdditionalFile3.csv")), comment.char="#", stringsAsFactors=F)
clock <- read.csv("AdditionalFile3.csv", comment.char="#", stringsAsFactors=F)
length(setdiff(clock$CpGmarker, rownames(beta.meffil)))
nrow(clock)
length(intersect(clock$CpGmarker, rownames(beta.meffil)))/nrow(clock)
```

20 of the 'clock' sites are missing.

## Hannum predictor CpG sites and the EPIC microarray

71 CpG sites were used in the Hannum et al. age predictor:

> Hannum G, et al.
> Genome-wide methylation profiles reveal quantitative views of human aging rates.
> Mol Cell. 2013 Jan 24;49(2):359-67.

The list can be obtained from here:
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3780611/bin/NIHMS418935-supplement-02.xlsx

```{r}
hannum.sites <- readLines("hannum.txt")
length(hannum.sites)
length(setdiff(hannum.sites, rownames(beta.meffil)))
length(intersect(hannum.sites, rownames(beta.meffil)))/length(hannum.sites)
```

6 of the 71 sites are missing.