Merge pull request #77 from PF2-pasteur-fr/development

Development

DESCRIPTION

@@ -1,14 +1,14 @@
 Package: SARTools
 Type: Package
 Title: Statistical Analysis of RNA-Seq Tools
-Version: 1.7.2
-Date: 2020-01-13
+Version: 1.7.3
+Date: 2020-04-29
 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),
-	ggplot2,
+	ggplot2 (>= 3.3.0),
 	kableExtra
 Imports: genefilter (>= 1.44.0),
 	GGally,
@@ -33,4 +33,4 @@ VignetteBuilder: knitr, rmarkdown
 Encoding: latin1
 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
-RoxygenNote: 7.0.0
+RoxygenNote: 7.1.0

NEWS

@@ -1,3 +1,10 @@
+CHANGES IN VERSION 1.7.3
+------------------------
+	o added some parameters to change the ggplot theme
+	o use breaks instead of binwidth for the raw p-values histogram
+	o updated vignette with ggplot2 figures
+	o now requires ggplot2 >= 3.3.0 (cf issue #76 on GitHub)
+
 CHANGES IN VERSION 1.7.2
 ------------------------
 	o the levels of the variable of interest are now ordered as they appear in the target file (after the reference level set as parameter)

R/BCVPlot.R

@@ -4,10 +4,11 @@
 #'
 #' @param dge a \code{DGEList} object
 #' @param outfile TRUE to export the figure in a png file
+#' @param ggplot_theme ggplot2 theme function (\code{theme_gray()} by default)
 #' @return A file named BCV.png in the figures directory with a BCV plot produced by the \code{plotBCV()} function of the edgeR package
 #' @author Marie-Agnes Dillies and Hugo Varet
 
-BCVPlot <- function(dge, outfile=TRUE){	
+BCVPlot <- function(dge, outfile=TRUE, ggplot_theme=theme_gray()){	
   if (outfile) png(filename="figures/BCV.png", width=2100, height=1800, res=300)
   A <- dge$AveLogCPM
   if (is.null(A)) A <- aveLogCPM(dge$counts, offset = getOffset(dge))
@@ -26,6 +27,7 @@ BCVPlot <- function(dge, outfile=TRUE){
           geom_hline(data=d, aes(yintercept=.data$sqrtcommon, color="c")) +
           xlab("Average log CPM") +
           ylab("Biological coefficient of variation") +
-          ggtitle("BCV plot"))
+          ggtitle("BCV plot") +
+          ggplot_theme)
   if (outfile) dev.off()	
 }

R/MAPlot.R

@@ -6,10 +6,11 @@
 #' @param alpha cut-off to apply on each adjusted p-value
 #' @param outfile TRUE to export the figure in a png file
 #' @param log2FClim numeric vector containing both upper and lower y-axis limits for all the MA-plots produced (NULL by default to set them automatically)
+#' @param ggplot_theme ggplot2 theme function (\code{theme_gray()} by default)
 #' @return A file named MAPlot.png in the figures directory containing one MA-plot per comparison
 #' @author Marie-Agnes Dillies and Hugo Varet
 
-MAPlot <- function(complete, alpha=0.05, outfile=TRUE, log2FClim=NULL){
+MAPlot <- function(complete, alpha=0.05, outfile=TRUE, log2FClim=NULL, ggplot_theme=theme_gray()){
   ncol <- min(2, length(complete))
   nrow <- ceiling(length(complete)/ncol)
   if (outfile) png(filename="figures/MAPlot.png", width=cairoSizeWrapper(1800*ncol), height=cairoSizeWrapper(1800*nrow), res=300)
@@ -34,10 +35,11 @@ MAPlot <- function(complete, alpha=0.05, outfile=TRUE, log2FClim=NULL){
       scale_colour_manual(values=c("no"="black", "yes"="red"), drop=FALSE) +
       scale_shape_manual(values=c("bottom"=25, "in"=21, "top"=24), drop=FALSE) +
       scale_fill_manual(values=c("no"="black", "yes"="red"), drop=FALSE) +
-      scale_y_continuous(expand=expand_scale(mult=c(0.03, 0.03))) +
+      scale_y_continuous(expand=expansion(mult=c(0.03, 0.03))) +
       xlab("Mean of normalized counts") +
       ylab(expression(log[2]~fold~change)) +
-      ggtitle(paste0("MA-plot - ", gsub("_"," ",name)))
+      ggtitle(paste0("MA-plot - ", gsub("_"," ",name))) +
+      ggplot_theme
   }
   tmpfun <- function(...) grid.arrange(..., nrow=nrow, ncol=ncol)
   do.call(tmpfun, p)

R/MDSPlot.R

@@ -8,24 +8,24 @@
 #' @param gene.selection \code{"pairwise"} to choose the top features separately for each pairwise comparison between the samples or \code{"common"} to select the same features for all comparisons. Only used when \code{method="logFC"}
 #' @param col colors to use (one per biological condition)
 #' @param outfile TRUE to export the figure in a png file
+#' @param ggplot_theme ggplot2 theme function (\code{theme_gray()} by default)
 #' @return A file named MDS.png in the figures directory
 #' @author Marie-Agnes Dillies and Hugo Varet
 
-MDSPlot <- function(dge, group, n=min(500, nrow(dge$counts)), gene.selection=c("pairwise", "common"),
-                    col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE){
+MDSPlot <- function(dge, group, n=min(500, nrow(dge$counts)), gene.selection=c("pairwise", "common", ggplot_theme=theme_gray()),
+                    col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE, ggplot_theme=theme_gray()){
   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], plot=FALSE)
-    coord <- as.data.frame(coord)
-    d <- data.frame(coord[,c("x", "y")], 
-                    group=group, 
-                    sample=factor(row.names(coord), levels=row.names(coord)))
+    d <- data.frame(x=coord$x, y=coord$y, group = group, 
+                    sample = factor(names(coord$x), levels = names(coord$x)))
     print(ggplot(data=d, aes(x=.data$x, y=.data$y, color=group, label=sample)) + 
       geom_point(show.legend=TRUE, size=3) +
       labs(color="") +
       scale_colour_manual(values=col) +
       geom_text_repel(show.legend=FALSE, size=5, point.padding=0.2) +
       xlab("Leading logFC dimension 1") +
       ylab("Leading logFC dimension 2") +
-      ggtitle("Multi-Dimensional Scaling plot"))
+      ggtitle("Multi-Dimensional Scaling plot") +
+      ggplot_theme)
   if (outfile) dev.off()      
 }

R/PCAPlot.R

@@ -7,12 +7,13 @@
 #' @param n number of features to keep among the most variant
 #' @param col colors to use (one per biological condition)
 #' @param outfile TRUE to export the figure in a png file
+#' @param ggplot_theme ggplot2 theme function (\code{theme_gray()} by default)
 #' @return A file named PCA.png in the figures directory with a pairwise plot of the three first principal components
 #' @author Marie-Agnes Dillies and Hugo Varet
 
 PCAPlot <- function(counts.trans, group, n=min(500, nrow(counts.trans)), 
                     col=c("lightblue","orange","MediumVioletRed","SpringGreen"),
-                    outfile=TRUE){
+                    outfile=TRUE, ggplot_theme=theme_gray()){
   # PCA on the 500 most variables features
   rv = apply(counts.trans, 1, var, na.rm=TRUE)
   pca = prcomp(t(counts.trans[order(rv, decreasing = TRUE), ][1:n,]))
@@ -33,7 +34,8 @@ PCAPlot <- function(counts.trans, group, n=min(500, nrow(counts.trans)),
       scale_colour_manual(values=col) +
       geom_text_repel(show.legend=FALSE, size=5, point.padding=0.2) +
       xlab(paste0("PC", index1, " (",prp[index1],"%)")) +
-      ylab(paste0("PC", index2, " (",prp[index2],"%)"))
+      ylab(paste0("PC", index2, " (",prp[index2],"%)")) +
+      ggplot_theme
   }
   p1 <- tmpFunction(c(1, 2))
   p2 <- tmpFunction(c(1, 3))

R/barplotNull.R

@@ -6,10 +6,11 @@
 #' @param group factor vector of the condition from which each sample belongs
 #' @param col colors of the bars (one color per biological condition)
 #' @param outfile TRUE to export the figure in a png file
+#' @param ggplot_theme ggplot2 theme function (\code{theme_gray()} by default)
 #' @return A file named barplotNull.png in the figures directory
 #' @author Marie-Agnes Dillies and Hugo Varet
 
-barplotNull <- function(counts, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE){
+barplotNull <- function(counts, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE, ggplot_theme=theme_gray()){
   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)
@@ -20,9 +21,10 @@ barplotNull <- function(counts, group, col=c("lightblue","orange","MediumVioletR
             scale_fill_manual(values=col) +
             xlab("Samples") + 
             ylab("Percentage of null counts") +
-            scale_y_continuous(expand=expand_scale(mult=c(0.01, 0.05))) +
             ggtitle("Percentage of null counts per sample") +
+            ggplot_theme +
             theme(axis.text.x=element_text(angle=90, hjust=1, vjust=0.5)) +
+            scale_y_continuous(expand=expansion(mult=c(0.01, 0.05))) +
             geom_hline(yintercept=percentage.allNull, linetype="dashed", color="black", size=1))
   if (outfile) dev.off()
 }

R/barplotTotal.R

@@ -6,10 +6,11 @@
 #' @param group factor vector of the condition from which each sample belongs
 #' @param col colors of the bars (one color per biological condition)
 #' @param outfile TRUE to export the figure in a png file
+#' @param ggplot_theme ggplot2 theme function (\code{theme_gray()} by default)
 #' @return A file named barplotTotal.png in the figures directory
 #' @author Marie-Agnes Dillies and Hugo Varet
 
-barplotTotal <- function(counts, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE){
+barplotTotal <- function(counts, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE, ggplot_theme=theme_gray()){
   if (outfile) png(filename="figures/barplotTotal.png", width=min(3600, 1800+800*ncol(counts)/10), height=1800, res=300)
   d <- data.frame(tc=colSums(counts)/1e6, sample=factor(colnames(counts), colnames(counts)), group)
   print(ggplot(d, aes(x=.data$sample, y=.data$tc, fill=.data$group)) +
@@ -18,8 +19,9 @@ barplotTotal <- function(counts, group, col=c("lightblue","orange","MediumViolet
           scale_fill_manual(values=col) +
           xlab("Samples") + 
           ylab("Total read count (million)") +
-          scale_y_continuous(expand=expand_scale(mult=c(0.01, 0.05))) +
           ggtitle("Total read count per sample (million)") +
-          theme(axis.text.x=element_text(angle=90, hjust=1, vjust=0.5)))
+          ggplot_theme +
+          theme(axis.text.x=element_text(angle=90, hjust=1, vjust=0.5)) +
+          scale_y_continuous(expand=expansion(mult=c(0.01, 0.05))))
   if (outfile) dev.off()
 }

R/clusterPlot.R

@@ -5,18 +5,20 @@
 #' @param counts.trans a matrix a transformed counts (VST- or rlog-counts if use of DESeq2 or cpm-counts if use of edgeR)
 #' @param group factor vector of the condition from which each sample belongs
 #' @param outfile TRUE to export the figure in a png file
+#' @param ggplot_theme ggplot2 theme function (\code{theme_gray()} by default)
 #' @return A file named cluster.png in the figures directory with the dendrogram of the clustering
 #' @author Marie-Agnes Dillies and Hugo Varet
 
-clusterPlot <- function(counts.trans, group, outfile=TRUE){
+clusterPlot <- function(counts.trans, group, outfile=TRUE, ggplot_theme=theme_gray()){
   hc <- hclust(dist(t(counts.trans)), method="ward.D")
   if (outfile) png(filename="figures/cluster.png", width=1800, height=1800, res=300) 
   print(ggdendrogram(hc, theme_dendro=FALSE) +
           xlab("Samples") +
           ylab("Height") +
           ggtitle("Cluster dendrogram\nEuclidean distance, Ward criterion") +
+          ggplot_theme +
           theme(axis.text.x=element_text(angle=90, hjust=1, vjust=0.5),
                 axis.text.y=element_text(angle=0)) +
-          scale_y_continuous(expand=expand_scale(mult=c(0.01, 0.05))))
+          scale_y_continuous(expand=expansion(mult=c(0.01, 0.05))))
   if (outfile) dev.off()
 }

R/countsBoxplots.R

@@ -6,10 +6,11 @@
 #' @param group factor vector of the condition from which each sample belongs
 #' @param col colors of the boxplots (one per biological condition)
 #' @param outfile TRUE to export the figure in a png file
+#' @param ggplot_theme ggplot2 theme function (\code{theme_gray()} by default)
 #' @return A file named countsBoxplots.png in the figures directory containing boxplots of the raw and normalized counts
 #' @author Marie-Agnes Dillies and Hugo Varet
 
-countsBoxplots <- function(object, group, col = c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE){
+countsBoxplots <- function(object, group, col = c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE, ggplot_theme=theme_gray()){
   if (class(object)=="DESeqDataSet"){
     counts <- counts(object)
     counts <- removeNull(counts)
@@ -31,28 +32,30 @@ countsBoxplots <- function(object, group, col = c("lightblue","orange","MediumVi
   p1 <- ggplot(d) + 
     geom_boxplot(aes(x=.data$ind, y=.data$values+1, fill=.data$group), show.legend=TRUE) +
     labs(fill="") +
-    scale_y_continuous(trans = log10_trans(),
-                       breaks = trans_breaks("log10", function(x) 10^x),
-                       labels = trans_format("log10", math_format(~10^.x))) +
     scale_fill_manual(values=col) +
     xlab("Samples") +
     ylab("Raw counts") +
     ggtitle("Raw counts distribution") +
-    theme(axis.text.x=element_text(angle=90, hjust=1, vjust=0.5))
+    ggplot_theme +
+    theme(axis.text.x=element_text(angle=90, hjust=1, vjust=0.5)) +
+    scale_y_continuous(trans = log10_trans(),
+                       breaks = trans_breaks("log10", function(x) 10^x),
+                       labels = trans_format("log10", math_format(~10^.x)))
 
   d <- stack(as.data.frame(norm.counts))
   d$group <- rep(group, each=nrow(norm.counts))
   p2 <- ggplot(d) + 
     geom_boxplot(aes(x=.data$ind, y=.data$values+1, fill=.data$group), show.legend=TRUE) +
     labs(fill="") +
-    scale_y_continuous(trans = log10_trans(),
-                       breaks = trans_breaks("log10", function(x) 10^x),
-                       labels = trans_format("log10", math_format(~10^.x))) +
     scale_fill_manual(values=col) +
     xlab("Samples") +
     ylab("Normalized counts") +
     ggtitle("Normalized counts distribution") +
-    theme(axis.text.x=element_text(angle=90, hjust=1, vjust=0.5))
+    ggplot_theme +
+    theme(axis.text.x=element_text(angle=90, hjust=1, vjust=0.5)) +
+    scale_y_continuous(trans = log10_trans(),
+                       breaks = trans_breaks("log10", function(x) 10^x),
+                       labels = trans_format("log10", math_format(~10^.x)))
 
   grid.arrange(p1, p2, nrow=1, ncol=2)
   if (outfile) dev.off()

R/densityPlot.R

@@ -6,10 +6,11 @@
 #' @param group factor vector of the condition from which each sample belongs
 #' @param col colors of the curves (one per biological condition)
 #' @param outfile TRUE to export the figure in a png file
+#' @param ggplot_theme ggplot2 theme function (\code{theme_gray()} by default)
 #' @return A file named densplot.png in the figures directory
 #' @author Marie-Agnes Dillies and Hugo Varet
 
-densityPlot <- function(counts, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE){
+densityPlot <- function(counts, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen"), outfile=TRUE, ggplot_theme=theme_gray()){
   if (outfile) png(filename="figures/densplot.png", width=2000, height=1800, res=300)
     counts <- removeNull(counts)
     d <- stack(data.frame(counts))
@@ -23,6 +24,7 @@ densityPlot <- function(counts, group, col=c("lightblue","orange","MediumVioletR
             scale_colour_manual(values=col) +
             xlab("Raw counts") +
             ylab("Density") +
-            ggtitle("Density of counts distribution"))
+            ggtitle("Density of counts distribution") +
+            ggplot_theme)
   if (outfile) dev.off()
 }

R/descriptionPlots.r

@@ -5,29 +5,30 @@
 #' @param counts \code{matrix} of counts
 #' @param group factor vector of the condition from which each sample belongs
 #' @param col colors for the plots (one per biological condition)
+#' @param ggplot_theme ggplot2 theme function (\code{theme_gray()} by default)
 #' @return PNG files in the "figures" directory and the matrix of the most expressed sequences
 #' @author Hugo Varet
 
-descriptionPlots <- function(counts, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen")){
+descriptionPlots <- function(counts, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen"), ggplot_theme=theme_gray()){
   # create the figures directory if does not exist
   if (!I("figures" %in% dir())) dir.create("figures", showWarnings=FALSE)
 
   # total number of reads per sample
-  barplotTotal(counts=counts, group=group, col=col)
+  barplotTotal(counts=counts, group=group, col=col, ggplot_theme=ggplot_theme)
 
   # percentage of null counts per sample
-  barplotNull(counts=counts, group=group, col=col)
+  barplotNull(counts=counts, group=group, col=col, ggplot_theme=ggplot_theme)
 
   # distribution of counts per sample
-  densityPlot(counts=counts, group=group, col=col)
+  densityPlot(counts=counts, group=group, col=col, ggplot_theme=ggplot_theme)
 
   # features which catch the most important number of reads
-  majSequences <- majSequences(counts=counts, group=group, col=col)
+  majSequences <- majSequences(counts=counts, group=group, col=col, ggplot_theme=ggplot_theme)
 
   # SERE and pairwise scatter plots
   cat("Matrix of SERE statistics:\n")
   print(tabSERE(counts))
-  pairwiseScatterPlots(counts=counts)
+  pairwiseScatterPlots(counts=counts, ggplot_theme=ggplot_theme)
 
   return(majSequences)
 }

R/diagSizeFactorsPlots.R

@@ -7,11 +7,12 @@
 #' @param col colors for the plots
 #' @param outfile TRUE to export the figure in a png file
 #' @param plots vector of plots to generate
+#' @param ggplot_theme ggplot2 theme function (\code{theme_gray()} by default)
 #' @return Two files in the figures directory: diagSizeFactorsHist.png containing one histogram per sample and diagSizeFactorsTC.png for a plot of the size factors vs the total number of reads
 #' @author Marie-Agnes Dillies and Hugo Varet
 
 diagSizeFactorsPlots <- function(dds, group, col=c("lightblue","orange","MediumVioletRed","SpringGreen"), 
-                                 outfile=TRUE, plots=c("diag","sf_libsize")){
+                                 outfile=TRUE, plots=c("diag","sf_libsize"), ggplot_theme=theme_gray()){
   # histograms
   if ("diag" %in% plots){
     ncol <- 2
@@ -26,11 +27,12 @@ diagSizeFactorsPlots <- function(dds, group, col=c("lightblue","orange","MediumV
       d <- data.frame(x=counts.trans[,j])
       p[[j]] <- ggplot(data=d, aes(x=.data$x)) +
         geom_histogram(bins=100) +
-        scale_y_continuous(expand=expand_scale(mult=c(0.01, 0.05))) +
+        scale_y_continuous(expand=expansion(mult=c(0.01, 0.05))) +
         xlab(expression(log[2]~(counts/geometric~mean))) +
         ylab("") +
         ggtitle(paste0("Size factor diagnostic - ", samples[j])) +
-        geom_vline(xintercept=log2(sizeFactors(dds)[j]), linetype="dashed", color="red", size=1)
+        geom_vline(xintercept=log2(sizeFactors(dds)[j]), linetype="dashed", color="red", size=1) +
+        ggplot_theme
     }
     tmpfun <- function(...) grid.arrange(..., nrow=nrow, ncol=ncol)
     do.call(tmpfun, p)
@@ -50,9 +52,8 @@ diagSizeFactorsPlots <- function(dds, group, col=c("lightblue","orange","MediumV
             xlab("Size factors") +
             ylab("Total number of reads (millions)") +
             ggtitle("Diagnostic: size factors vs total number of reads") +
-            geom_abline(slope=coefficients(lm(libsize ~ sf + 0, data=d)), intercept=0, show.legend=FALSE, linetype="dashed", color="grey"))
+            geom_abline(slope=coefficients(lm(libsize ~ sf + 0, data=d)), intercept=0, show.legend=FALSE, linetype="dashed", color="grey") +
+            ggplot_theme)
     if (outfile) dev.off()
   }
 }
-
-