Merge pull request #14 from PF2-pasteur-fr/development

Development
PF2-pasteur-fr · Jun 13, 2016 · 6fbc38b · 6fbc38b
2 parents 94bd77b + b1da000
commit 6fbc38b
Show file tree

Hide file tree

Showing 59 changed files with 70 additions and 51 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,13 +1,13 @@
 Package: SARTools
 Type: Package
 Title: Statistical Analysis of RNA-Seq Tools
-Version: 1.3.0
-Date: 2016-05-09
+Version: 1.3.1
+Date: 2016-06-13
 Author: Marie-Agnes Dillies and Hugo Varet
 Maintainer: Hugo Varet <[email protected]>
 Depends: R (>= 3.3.0), DESeq2 (>= 1.12.0), edgeR (>= 3.12.0), xtable
 Imports: stats, utils, graphics, grDevices, knitr, SummarizedExperiment, S4Vectors, limma, genefilter (>= 1.44.0)
 VignetteBuilder: knitr
 Encoding: latin1
-Description: SARTools provides R tools and an environment for the statistical analysis of RNA-Seq projects: load and clean data, produce figures, perform statistical analysis/testing with DESeq2 or edgeR, export results and create final report.
+Description: Provide R tools and an environment for the statistical analysis of RNA-Seq projects: load and clean data, produce figures, perform statistical analysis/testing with DESeq2 or edgeR, export results and create final report.
 License: GPL-2
diff --git a/NEWS b/NEWS
@@ -1,3 +1,9 @@
+CHANGES IN VERSION 1.3.1
+------------------------
+	o Increased plot resolution to 300ppi
+	o New instructions to install SARTools with Conda
+	o Update of the citation of SARTools (PLoS One 2016)
+
 CHANGES IN VERSION 1.3.0
 ------------------------
 	o Adapted the package to the new Bioconductor release (April 2016)

diff --git a/R/BCVPlot.R b/R/BCVPlot.R
@@ -8,7 +8,7 @@
 #' @author Marie-Agnes Dillies and Hugo Varet
 
 BCVPlot <- function(dge, outfile=TRUE){	
-  if (outfile) png(filename="figures/BCV.png", width=400, height=400)
+  if (outfile) png(filename="figures/BCV.png", width=1800, height=1800, res=300)
     plotBCV(dge, las = 1, main = "BCV plot")
   if (outfile) dev.off()	
 }
diff --git a/R/MAPlot.R b/R/MAPlot.R
@@ -11,7 +11,7 @@
 MAPlot <- function(complete, alpha=0.05, outfile=TRUE){
   nrow <- ceiling(sqrt(length(complete)))
   ncol <- ceiling(length(complete)/nrow)
-  if (outfile) png(filename="figures/MAPlot.png", width=400*max(ncol,nrow), height=400*min(ncol,nrow))
+  if (outfile) png(filename="figures/MAPlot.png", width=1800*max(ncol,nrow), height=1800*min(ncol,nrow), res=300)
     par(mfrow=sort(c(nrow,ncol)))
       for (name in names(complete)){
         complete.name <- complete[[name]]

diff --git a/R/MDSPlot.R b/R/MDSPlot.R
@@ -13,7 +13,7 @@
 
 MDSPlot <- function(dge, group, n=min(500,nrow(dge$counts)), gene.selection=c("pairwise", "common"),
                     col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE){
-  if (outfile) png(filename="figures/MDS.png", width=400, height=400)
+  if (outfile) png(filename="figures/MDS.png", width=1800, height=1800, res=300)
     coord <- plotMDS(dge, top=n, method="logFC", gene.selection=gene.selection[1])
     abs=range(coord$x); abs=abs(abs[2]-abs[1])/25;
     ord=range(coord$y); ord=abs(ord[2]-ord[1])/25;

diff --git a/R/NAMESPACE.R b/R/NAMESPACE.R
diff --git a/R/PCAPlot.R b/R/PCAPlot.R
@@ -20,7 +20,7 @@ PCAPlot <- function(counts.trans, group, n=min(500,nrow(counts.trans)),
   prp <- round(prp[1:3],2)
 
   # create figure
-  if (outfile) png(filename="figures/PCA.png",width=400*2,height=400)
+  if (outfile) png(filename="figures/PCA.png",width=1800*2,height=1800,res=300)
     par(mfrow=c(1,2))
 	# axes 1 et 2
 	abs=range(pca$x[,1]); abs=abs(abs[2]-abs[1])/25;

diff --git a/R/SARTools-package.r b/R/SARTools-package.r
@@ -1,4 +1,4 @@
-#' SARTools provides R tools and an environment for the statistical analysis of RNA-Seq projects: load and clean data, produce figures, perform statistical analysis/testing with DESeq2 or edgeR, export results and create final report
+#' Provide R tools and an environment for the statistical analysis of RNA-Seq projects: load and clean data, produce figures, perform statistical analysis/testing with DESeq2 or edgeR, export results and create final report
 #' @title Statistical Analysis of RNA-Seq Tools
 #' @author Marie-Agnes Dillies and Hugo Varet
 #' @docType package

diff --git a/R/SERE.r b/R/SERE.r
diff --git a/R/barplotNull.R b/R/barplotNull.R
@@ -10,7 +10,7 @@
 #' @author Marie-Agnes Dillies and Hugo Varet
 
 barplotNull <- function(counts, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE){
-  if (outfile) png(filename="figures/barplotNull.png",width=min(800,400+200*ncol(counts)/10),height=400)
+  if (outfile) png(filename="figures/barplotNull.png",width=min(3600,1800+800*ncol(counts)/10),height=1800,res=300)
     percentage <- apply(counts, 2, function(x){sum(x == 0)})*100/nrow(counts)
     percentage.allNull <- (nrow(counts) - nrow(removeNull(counts)))*100/nrow(counts)
     barplot(percentage, las = 2,

diff --git a/R/barplotTotal.R b/R/barplotTotal.R
@@ -10,11 +10,12 @@
 #' @author Marie-Agnes Dillies and Hugo Varet
 
 barplotTotal <- function(counts, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE){
-  if (outfile) png(filename="figures/barplotTotal.png",width=min(800,400+200*ncol(counts)/10),height=400)
-  barplot(colSums(counts),
-          main = "Total read count per sample",
-		  ylab = "Total read count",
-		  ylim = c(0, max(colSums(counts))*1.2),
+  if (outfile) png(filename="figures/barplotTotal.png",width=min(3600,1800+800*ncol(counts)/10),height=1800,res=300)
+  libsize <- colSums(counts)/1e6
+  barplot(libsize,
+          main = "Total read count per sample (million)",
+		  ylab = "Total read count (million)",
+		  ylim = c(0, max(libsize)*1.2),
 		  col = col[as.integer(group)],
 		  las = 2)
   legend("topright", levels(group), fill=col[1:nlevels(group)], bty="n")

diff --git a/R/checkParameters.DESeq2.r b/R/checkParameters.DESeq2.r
diff --git a/R/checkParameters.edgeR.r b/R/checkParameters.edgeR.r
diff --git a/R/clusterPlot.R b/R/clusterPlot.R
@@ -10,7 +10,7 @@
 
 clusterPlot <- function(counts.trans, group, outfile=TRUE){
   hc <- hclust(dist(t(counts.trans)), method="ward.D")
-  if (outfile) png(filename="figures/cluster.png",width=400,height=400) 
+  if (outfile) png(filename="figures/cluster.png",width=1800,height=1800,res=300) 
     plot(hc, hang=-1, ylab="Height", las=2, xlab="Method: Euclidean distance - Ward criterion", main="Cluster dendrogram")
   if (outfile) dev.off()
 }
diff --git a/R/countsBoxplots.R b/R/countsBoxplots.R
@@ -25,7 +25,7 @@ countsBoxplots <- function(object, group, col = c("lightblue","orange","MediumVi
     norm.counts <- removeNull(norm.counts)    
   }
 
-  if (outfile) png(filename="figures/countsBoxplots.png",width=2*min(500,400+200*ncol(norm.counts)/10),height=400)
+  if (outfile) png(filename="figures/countsBoxplots.png",width=2*min(2200,1800+800*ncol(norm.counts)/10),height=1800,res=300)
     par(mfrow=c(1,2))
 	# raw counts
     boxplot(log2(counts+1), col = col[as.integer(group)], las = 2,

diff --git a/R/densityPlot.R b/R/densityPlot.R
@@ -10,7 +10,7 @@
 #' @author Marie-Agnes Dillies and Hugo Varet
 
 densityPlot <- function(counts, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE){
-  if (outfile) png(filename="figures/densplot.png",width=400,height=400)
+  if (outfile) png(filename="figures/densplot.png",width=1800,height=1800,res=300)
     counts <- removeNull(counts)
     plot(density(log2(counts[,1]+1)), las = 1, lwd = 2,
          main = "Density of counts distribution",

diff --git a/R/descriptionPlots.r b/R/descriptionPlots.r
diff --git a/R/diagSizeFactorsPlots.R b/R/diagSizeFactorsPlots.R
@@ -13,7 +13,7 @@ diagSizeFactorsPlots <- function(dds, outfile=TRUE, plots=c("diag","sf_libsize")
   if ("diag" %in% plots){
     nrow <- ceiling(sqrt(ncol(counts(dds))))
     ncol <- ceiling(ncol(counts(dds))/nrow)
-    if (outfile) png(filename="figures/diagSizeFactorsHist.png", width=300*max(ncol,nrow), height=300*min(ncol,nrow))
+    if (outfile) png(filename="figures/diagSizeFactorsHist.png", width=1400*max(ncol,nrow), height=1400*min(ncol,nrow), res=300)
     par(mfrow=sort(c(nrow,ncol)))
     geomeans <- exp(rowMeans(log(counts(dds))))
     samples <- colnames(counts(dds))
@@ -30,7 +30,7 @@ diagSizeFactorsPlots <- function(dds, outfile=TRUE, plots=c("diag","sf_libsize")
 
   # total read counts vs size factors
   if ("sf_libsize" %in% plots){
-    if (outfile) png(filename="figures/diagSizeFactorsTC.png",width=400,height=400)  
+    if (outfile) png(filename="figures/diagSizeFactorsTC.png",width=1800,height=1800,res=300)  
     plot(sizeFactors(dds), colSums(counts(dds)), pch=19, las=1, xlab="Size factors",
 	 ylab="Total number of reads",main="Diagnostic: size factors vs total number of reads")
     abline(lm(colSums(counts(dds)) ~ sizeFactors(dds) + 0), lty=2, col="grey")

diff --git a/R/dispersionsPlot.R b/R/dispersionsPlot.R
@@ -14,7 +14,7 @@ dispersionsPlot <- function(dds, outfile=TRUE){
   disp <- log(disp)
   mean.disp <- mean(disp,na.rm=TRUE)
   sd.disp <- sd(disp,na.rm=TRUE)
-  if (outfile) png(filename="figures/dispersionsPlot.png",width=800,height=400)
+  if (outfile) png(filename="figures/dispersionsPlot.png",width=3600,height=1800,res=300)
 	par(mfrow=c(1,2))
     # dispersions plot
 	plotDispEsts(dds, main="Dispersions", las=1, xlab="Mean of normalized counts", ylab="Dispersion")

diff --git a/R/exploreCounts.R b/R/exploreCounts.R
diff --git a/R/exportResults.DESeq2.R b/R/exportResults.DESeq2.R
diff --git a/R/exportResults.edgeR.R b/R/exportResults.edgeR.R
diff --git a/R/loadCountData.R b/R/loadCountData.R
diff --git a/R/loadTargetFile.R b/R/loadTargetFile.R
diff --git a/R/majSequences.R b/R/majSequences.R
@@ -20,7 +20,7 @@ majSequences <- function(counts, n=3, group, col=c("lightblue","orange","MediumV
   sum <- matrix(sum,nrow(counts),ncol(counts),byrow=TRUE)
   p <- round(100*counts/sum,digits=3)
 
-  if (outfile) png(filename="figures/majSeq.png",width=min(800,400+200*ncol(counts)/10),height=400)
+  if (outfile) png(filename="figures/majSeq.png",width=min(3600,1800+800*ncol(counts)/10),height=1800,res=300)
     maj <- apply(p, 2, max)
     seqname <- rownames(p)[apply(p, 2, which.max)]
     x <- barplot(maj, col=col[as.integer(group)], main="Proportion of reads from most expressed sequence",

diff --git a/R/nDiffTotal.r b/R/nDiffTotal.r
diff --git a/R/pairwiseScatterPlots.R b/R/pairwiseScatterPlots.R
@@ -10,7 +10,7 @@
 
 pairwiseScatterPlots <- function(counts, group, outfile=TRUE){
   ncol <- ncol(counts)
-  if (outfile) png(filename="figures/pairwiseScatter.png",width=150*ncol,height=150*ncol)
+  if (outfile) png(filename="figures/pairwiseScatter.png",width=800*ncol,height=800*ncol,res=300)
     # defining panel and lower.panel functions
 	panel <- function(x,y,...){points(x, y, pch=".");abline(a=0,b=1,lty=2);}
 	lower.panel <- function(x,y,...){

diff --git a/R/rawpHist.R b/R/rawpHist.R
@@ -10,7 +10,7 @@
 rawpHist <- function(complete, outfile=TRUE){
   nrow <- ceiling(sqrt(length(complete)))
   ncol <- ceiling(length(complete)/nrow)
-  if (outfile) png(filename="figures/rawpHist.png", width=400*max(ncol,nrow), height=400*min(ncol,nrow))
+  if (outfile) png(filename="figures/rawpHist.png", width=1800*max(ncol,nrow), height=1800*min(ncol,nrow), res=300)
     par(mfrow=sort(c(nrow,ncol)))
     for (name in names(complete)){
       hist(complete[[name]][,"pvalue"], nclass=50, xlab="Raw p-value", 

diff --git a/R/removeNull.R b/R/removeNull.R
diff --git a/R/run.DESeq2.r b/R/run.DESeq2.r
diff --git a/R/run.edgeR.r b/R/run.edgeR.r
diff --git a/R/summarizeResults.DESeq2.r b/R/summarizeResults.DESeq2.r
diff --git a/R/summarizeResults.edgeR.r b/R/summarizeResults.edgeR.r
diff --git a/R/tabIndepFiltering.R b/R/tabIndepFiltering.R
diff --git a/R/tabSERE.R b/R/tabSERE.R
diff --git a/R/volcanoPlot.r b/R/volcanoPlot.r
@@ -11,7 +11,7 @@
 volcanoPlot <- function(complete, alpha=0.05, outfile=TRUE){
   nrow <- ceiling(sqrt(length(complete)))
   ncol <- ceiling(length(complete)/nrow)
-  if (outfile) png(filename="figures/volcanoPlot.png", width=400*max(ncol,nrow), height=400*min(ncol,nrow))
+  if (outfile) png(filename="figures/volcanoPlot.png", width=1800*max(ncol,nrow), height=1800*min(ncol,nrow), res=300)
     par(mfrow=sort(c(nrow,ncol)))
     for (name in names(complete)){
       complete.name <- complete[[name]]

diff --git a/R/welcome.R b/R/welcome.R
diff --git a/R/writeReport.DESeq2.r b/R/writeReport.DESeq2.r
diff --git a/R/writeReport.edgeR.r b/R/writeReport.edgeR.r
diff --git a/README.md b/README.md
@@ -8,23 +8,34 @@ SARTools is distributed with two R script templates (`template_script_DESeq2.r`
 How to install SARTools?
 ------------------------
 
+### Within R
+
 In addition to the SARTools package itself, the workflow requires the installation of several packages: DESeq2, edgeR, genefilter, xtable and knitr (all available online, see the dedicated webpages). SARTools needs R version 3.3.0 or higher, DESeq2 1.12.0 or higher and edgeR 3.12.0 or higher: old versions of DESeq2 or edgeR may be incompatible with SARTools.
 
 To install the SARTools package from GitHub, open a R session and:
 - install DESeq2, edgeR and genefilter with `source("http://bioconductor.org/biocLite.R")` and `biocLite(c("DESeq2", "edgeR", "genefilter"))` (if not installed yet)
 - install devtools with `install.packages("devtools")` (if not installed yet)
-- Note: Ubuntu users may have to install some libraries (libxml2-dev, libcurl4-dev and libssl-dev) to be able to install DESeq2 and devtools
+- Note: Ubuntu users may have to install some libraries (libxml2-dev, libcurl4-openssl-dev and libssl-dev) to be able to install DESeq2 and devtools
 - for Windows users only, install [Rtools](http://cran.r-project.org/bin/windows/Rtools/) or check that it is already installed (needed to build the package)
 - load the devtools R package with `library(devtools)`
 - run `install_github("PF2-pasteur-fr/SARTools", build_vignettes=TRUE)`
 
-Please read the NEWS file to see the latest improvements!
+### Using Conda
+
+[![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg?style=flat-square)](http://bioconda.github.io/recipes/r-sartools/README.html)
+
+1. Install miniconda2 http://conda.pydata.org/miniconda.html
+2. Install the SARTools R library and its dependencies using conda `conda install r-sartools`
+
+Note: if you want to set a dedicated conda environment for SARTools, use `conda create -n sartools r-sartools` and follow the instructions to activate it.
 
 How to use SARTools?
 --------------------
 
 A HTML vignette is available within the vignettes folder on GitHub and provides extensive information on the use of SARTools. The user can also open it with `vignette("SARTools")` if it has been generated during the installation of the package.
 
+Please read the NEWS file to see the latest improvements!
+
 About SARTools
 --------------
-The SARTools package has been developped at PF2 - Institut Pasteur by M.-A. Dillies and H. Varet ([email protected]). Thanks to cite H. Varet, J.-Y. Coppee and M.-A. Dillies, _SARTools: a DESeq2- and edgeR-based R pipeline for comprehensive differential analysis of RNA-seq data_, bioRxiv, 2015, doi: http://dx.doi.org/10.1101/021741 when using this tool for any analysis published.
+The SARTools package has been developped at PF2 - Institut Pasteur by M.-A. Dillies and H. Varet ([email protected]). Thanks to cite H. Varet, L. Brillet-Guéguen, J.-Y. Coppee and M.-A. Dillies, _SARTools: A DESeq2- and EdgeR-Based R Pipeline for Comprehensive Differential Analysis of RNA-Seq Data_, PLoS One, 2016, doi: http://dx.doi.org/10.1371/journal.pone.0157022 when using this tool for any analysis published.
diff --git a/inst/CITATION b/inst/CITATION
@@ -1,14 +1,15 @@
 citEntry(entry = "article",
-         title = "SARTools: a DESeq2- and edgeR-based R pipeline for comprehensive differential analysis of RNA-seq data",
+         title = "SARTools: A DESeq2- and EdgeR-Based R Pipeline for Comprehensive Differential Analysis of RNA-Seq Data",
          author = personList( as.person("Hugo Varet"),
+                              as.person("Loraine Brillet-Guéguen"),
                               as.person("Jean-Yves Coppée"),
                               as.person("Marie-Agnès Dillies")),
-         year = 2015,
-         journal = "bioRxiv",
-         doi = "10.1101/021741",
-         url = "http://biorxiv.org/content/early/2015/06/30/021741",
+         year = 2016,
+         journal = "PLoS One",
+         doi = "10.1371/journal.pone.0157022",
+         url = "http://dx.doi.org/10.1371/journal.pone.0157022",
          textVersion = 
-         paste("Hugo Varet, Jean-Yves Coppée and Marie-Agnès Dillies (2015):", 
-               "SARTools: a DESeq2- and edgeR-based R pipeline for comprehensive differential analysis of RNA-seq data.",
-                "bioRxiv, 2015, doi: http://dx.doi.org/10.1101/021741"))
+         paste("Hugo Varet, Loraine Brillet-Guéguen, Jean-Yves Coppée and Marie-Agnès Dillies (2016):", 
+               "SARTools: A DESeq2- and EdgeR-Based R Pipeline for Comprehensive Differential Analysis of RNA-Seq Data.",
+                "PLoS One, 2016, doi: http://dx.doi.org/10.1371/journal.pone.0157022"))
 
diff --git a/inst/raw/KO1.htseq.out b/inst/raw/KO1.htseq.out
diff --git a/inst/raw/KO2.htseq.out b/inst/raw/KO2.htseq.out
diff --git a/inst/raw/WT1.htseq.out b/inst/raw/WT1.htseq.out
diff --git a/inst/raw/WT2.htseq.out b/inst/raw/WT2.htseq.out
diff --git a/inst/report_DESeq2.rmd b/inst/report_DESeq2.rmd
@@ -8,7 +8,7 @@ Author: `r author`
 
 Date: `r Sys.Date()`
 
-The SARTools R package which generated this report has been developped at PF2 - Institut Pasteur by M.-A. Dillies and H. Varet ([email protected]). Thanks to cite H. Varet, J.-Y. Coppee and M.-A. Dillies, _SARTools: a DESeq2- and edgeR-based R pipeline for comprehensive differential analysis of RNA-seq data_, bioRxiv, 2015, doi: http://dx.doi.org/10.1101/021741 when using this tool for any analysis published.
+The SARTools R package which generated this report has been developped at PF2 - Institut Pasteur by M.-A. Dillies and H. Varet ([email protected]). Thanks to cite H. Varet, L. Brillet-Guéguen, J.-Y. Coppee and M.-A. Dillies, _SARTools: A DESeq2- and EdgeR-Based R Pipeline for Comprehensive Differential Analysis of RNA-Seq Data_, PLoS One, 2016, doi: http://dx.doi.org/10.1371/journal.pone.0157022 when using this tool for any analysis published.
 
 --------------------------------------------------------------------------------------------------------------------------
 
@@ -66,7 +66,7 @@ Figure 1 shows the total number of mapped reads for each sample. Reads that map
 
 <figure>
 <center>
-    <img src="figures/barplotTotal.png" alt="Barplot total counts" />
+    <img src="figures/barplotTotal.png" alt="Barplot total counts" width=600 />
 	<figcaption> Figure 1: Number of mapped reads per sample. Colors refer to the biological condition of the sample. </figcaption>
 </center>
 </figure>
@@ -75,7 +75,7 @@ Figure 2 shows the proportion of features with no read count in each sample. We
 
 <figure>
 <center>
-    <img src="figures/barplotNull.png" alt="Barplot null counts" />
+    <img src="figures/barplotNull.png" alt="Barplot null counts" width=600 />
 	<figcaption> Figure 2: Proportion of features with null read counts in each sample. </figcaption>
 </center>
 </figure>
@@ -84,7 +84,7 @@ Figure 3 shows the distribution of read counts for each sample. For sake of read
 
 <figure>
 <center>
-    <img src="figures/densplot.png" alt="Estimated densities of raw counts" />
+    <img src="figures/densplot.png" alt="Estimated densities of raw counts" width="60%" />
 	<figcaption> Figure 3: Density distribution of read counts. </figcaption>
 </center>
 </figure>
@@ -93,7 +93,7 @@ It may happen that one or a few features capture a high proportion of reads (up
 
 <figure>
 <center>
-    <img src="figures/majSeq.png" alt="Most represented sequences" />
+    <img src="figures/majSeq.png" alt="Most represented sequences" width=600 />
 	<figcaption> Figure 4: Percentage of reads associated with the sequence having the highest count (provided in each box on the graph) for each sample. </figcaption>
 </center>
 </figure>
@@ -127,7 +127,7 @@ Figure 6 shows the dendrogram obtained from `r typeTrans`-transformed data. An e
 
 <figure>
 <center>
-    <img src="figures/cluster.png" alt="Clustering" />
+    <img src="figures/cluster.png" alt="Clustering" width="60%" />
 	<figcaption> Figure 6: Sample clustering based on normalized data. </figcaption>
 </center>
 </figure>
@@ -170,7 +170,7 @@ The figure 9 shows that the scaling factors of DESeq2 and the total count normal
 
 <figure>
 <center>
-    <img src="figures/diagSizeFactorsTC.png" alt="Size factors vs total counts" />
+    <img src="figures/diagSizeFactorsTC.png" alt="Size factors vs total counts" width="60%" />
 	<figcaption> Figure 9: Plot of the estimated size factors and the total number of reads per sample. </figcaption>
 </center>
 </figure>