Added a scatter plot

public/biopet-framework/src/main/resources/nl/lumc/sasc/biopet/extensions/rscript/plotScatter.R

+library(reshape2)
+library(ggplot2)
+library(argparse)
+
+parser <- ArgumentParser(description='Process some integers')
+parser$add_argument('--input', dest='input', type='character', help='Input tsv file', required=TRUE)
+parser$add_argument('--output', dest='output', type='character', help='Output png file', required=TRUE)
+parser$add_argument('--width', dest='width', type='integer', default = 500)
+parser$add_argument('--height', dest='height', type='integer', default = 500)
+parser$add_argument('--xlabel', dest='xlabel', type='character')
+parser$add_argument('--ylabel', dest='ylabel', type='character', required=TRUE)
+parser$add_argument('--llabel', dest='llabel', type='character')
+parser$add_argument('--title', dest='title', type='character')
+parser$add_argument('--removeZero', dest='removeZero', type='character', default="false")
+
+arguments <- parser$parse_args()
+
+png(filename = arguments$output, width = arguments$width, height = arguments$height)
+
+DF <- read.table(arguments$input, header=TRUE)
+
+if (is.null(arguments$xlabel)) xlab <- colnames(DF)[1] else xlab <- arguments$xlabel
+
+colnames(DF)[1] <- "Rank"
+
+DF1 <- melt(DF, id.var="Rank")
+
+if (arguments$removeZero == "true") DF1 <- DF1[DF1$value > 0, ]
+if (arguments$removeZero == "true") print("Removed 0 values")
+
+ggplot(DF1, aes(x = Rank, y = value, group = variable, color = variable)) +
+  xlab(xlab) +
+  ylab(arguments$ylabel) +
+  guides(fill=guide_legend(title=arguments$llabel)) +
+  theme(axis.text.x = element_text(angle = 90, hjust = 1, size = 8)) +
+  ggtitle(arguments$title) +
+  theme_bw() +
+  geom_point()
+
+dev.off()

public/biopet-framework/src/main/scala/nl/lumc/sasc/biopet/extensions/rscript/ScatterPlot.scala

+/**
+ * Biopet is built on top of GATK Queue for building bioinformatic
+ * pipelines. It is mainly intended to support LUMC SHARK cluster which is running
+ * SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
+ * should also be able to execute Biopet tools and pipelines.
+ *
+ * Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
+ *
+ * Contact us at: sasc@lumc.nl
+ *
+ * A dual licensing mode is applied. The source code within this project that are
+ * not part of GATK Queue is freely available for non-commercial use under an AGPL
+ * license; For commercial users or users who do not want to follow the AGPL
+ * license, please contact us to obtain a separate license.
+ */
+package nl.lumc.sasc.biopet.extensions.rscript
+
+import java.io.File
+
+import nl.lumc.sasc.biopet.core.config.Configurable
+import nl.lumc.sasc.biopet.extensions.RscriptCommandLineFunction
+import org.broadinstitute.gatk.utils.commandline.{Input, Output}
+
+/**
+ * Extension for en general line plot with R
+ *
+ * Created by pjvan_thof on 4/29/15.
+ */
+class ScatterPlot(val root: Configurable) extends RscriptCommandLineFunction {
+  protected var script: File = config("script", default = "plotScatter.R")
+
+  @Input
+  var input: File = _
+
+  @Output
+  var output: File = _
+
+  var width: Option[Int] = config("width")
+  var height: Option[Int] = config("height")
+  var xlabel: Option[String] = config("xlabel")
+  var ylabel: Option[String] = config("ylabel")
+  var llabel: Option[String] = config("llabel")
+  var title: Option[String] = config("title")
+  var removeZero: Boolean = config("removeZero", default = false)
+
+  override def cmdLine: String = super.cmdLine +
+    required("--input", input) +
+    required("--output", output) +
+    optional("--width", width) +
+    optional("--height", height) +
+    optional("--xlabel", xlabel) +
+    required("--ylabel", ylabel) +
+    optional("--llabel", llabel) +
+    optional("--title", title) +
+    optional("--removeZero", removeZero)
+}