adomingues

# install the Rsamtools package if necessary
source("http://bioconductor.org/biocLite.R")
biocLite("Rsamtools")
 
# load the library
library(Rsamtools)

# specify the bam file you want to import
bamFile <- "test.bam"

adomingues

# resource: http://seqanswers.com/forums/showthread.php?t=4914
# Calculate length for each transcript for a GTF file
awk -F"\t" '
$3=="exon" 
    {
        ID=substr($9, length($9)-16, 15); 
        L[ID]+=$5-$4+1
    } 
END{
    for(i in L)

adomingues

## RNA-seq analysis with DESeq2
## Stephen Turner, @genetics_blog

# RNA-seq data from GSE52202
# http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=gse52202. All patients with
# ALS, 4 with C9 expansion ("exp"), 4 controls without expansion ("ctl")

# Import & pre-process ----------------------------------------------------

# Import data from featureCounts

adomingues

# A function (borrowed from the Sleuth documentation) for connecting Ensembl transcript names to common gene names
convert_tx_to_gene <- function(dat="drerio_gene_ensembl"){
    mart <- biomaRt::useMart(
        biomart = "ensembl",
        dataset = dat
    )
    t2g <- biomaRt::getBM(
        attributes = c("ensembl_transcript_id", "ensembl_gene_id", "external_gene_name"),
        mart = mart

adomingues

@SQ	SN:chrM	LN:16571
@SQ	SN:chr1	LN:249250621
@SQ	SN:chr2	LN:243199373
@SQ	SN:chr3	LN:198022430
@SQ	SN:chr4	LN:191154276
@SQ	SN:chr5	LN:180915260
@SQ	SN:chr6	LN:171115067
@SQ	SN:chr7	LN:159138663
@SQ	SN:chr8	LN:146364022
@SQ	SN:chr9	LN:141213431

adomingues

### My favourite ggplot2 themes, always accessible ###
## just source this gist from any project ##


#####################################################################################

# Noam's default ggplot2 styling #####
# Source: https://github.com/noamross/noamtools/blob/master/R/theme_nr.R
theme_nr <-theme(text=element_text(family="Helvetica", size=14),
                 panel.grid.major.x=element_blank(),

adomingues

# Multiple plot function
#
# ggplot objects can be passed in ..., or to plotlist (as a list of ggplot objects)
# - cols:   Number of columns in layout
# - layout: A matrix specifying the layout. If present, 'cols' is ignored.
#
# If the layout is something like matrix(c(1,2,3,3), nrow=2, byrow=TRUE),
# then plot 1 will go in the upper left, 2 will go in the upper right, and
# 3 will go all the way across the bottom.
#

adomingues

swatch <- function(x) {
  # x: a vector of colours (hex, numeric, or string)
  par(mai=c(0.2, max(strwidth(x, "inch") + 0.4, na.rm = TRUE), 0.2, 0.4))
  barplot(rep(1, length(x)), col=rev(x), space = 0.1, axes=FALSE, 
          names.arg=rev(x), cex.names=0.8, horiz=T, las=1)  
}
 
# Example:
# swatch(colours()[1:10])
# swatch(iwanthue(5))