Submission commit: reformatted scripts for filename and heading consi…

…stency, updated real data and related figures, added YAML files for all 360 models

Figure_2.R

@@ -1,5 +1,14 @@
 #!/usr/bin/env Rscript
 
+# Figure_2.R
+# Generate the plots (but not the tree diagram) for Figure 2 as a PDF file
+
+# Written for "Evaluating statistics for the identification of introgressed loci"
+# by Simon H. Martin, John W. Davey and Chris D. Jiggins
+# Simon Martin: [email protected]
+# John Davey:   [email protected]
+# November-December 2013
+
 library(optparse)
 suppressMessages(library(ggplot2))
 suppressMessages(library(reshape))

plot_sim_accuracy.r → Figure_3.R

@@ -1,15 +1,16 @@
 #!/usr/bin/env Rscript
-# plot_sim_accuracy.r
-# Plot accuracy for all models with oldest split at 2MYA
+
+# Figure_3.R
+# Plot accuracy for all models with oldest split at 2 MYA for Figure 3 as PDF file
 
 # Written for "Evaluating statistics for the identification of introgressed loci"
 # by Simon H. Martin, John W. Davey and Chris D. Jiggins
-# John Davey:   [email protected]
 # Simon Martin: [email protected]
+# John Davey:   [email protected]
 # November-December 2013
 
 
-models<-read.delim("model_files_win10000_size5000_ne1000000_2013-11-29.partition.summary.tsv")
+models<-read.delim("model_files_win10000_size5000.partition.summary.tsv")
 
 
 mf_models <- subset(models, Stat == "mfD0")
@@ -28,7 +29,7 @@ splits <- round(seq(0.2,2,0.2),1)
 for (i in 1:length(splits))  gradCols[i] <- rgb(1-(splits[i]/2),1-(splits[i]/2),1-(splits[i]/2),1)
 
 
-pdf(file = "model_accuracy_plots.pdf", width = 7, height = 10)
+pdf(file = "Figure_3.pdf", width = 7, height = 10)
 
 par(mfrow = c(3,2), mar = c(5.5,4,1.5,1))
 

plot_ABBABABBA_pattern_loci.r → Figure_4.R

@@ -1,25 +1,25 @@
 #!/usr/bin/env Rscript
 
-# plot_ABBABABA_pattern_loci.r
-# generate plots across BD and Yb bac walk regions - Figure 4.
+# Figure_4.R
+# Generate plots across BD and Yb bac walk regions for Figure 4 as a PDF file
 
 # Written for "Evaluating statistics for the identification of introgressed loci"
 # by Simon H. Martin, John W. Davey and Chris D. Jiggins
-# John Davey:   [email protected]
 # Simon Martin: [email protected]
+# John Davey:   [email protected]
 # November-December 2013
 
 
 #input data
 
-yb <- read.csv("Yb.ABBABABA_dxy_S.minExD0.5.w5m1s1000.csv")
+yb <- read.csv("Heliconius_HmB_windows.csv")
 yb <- subset(yb, is.na(D) == F & is.na(mf) == F & sitesOverMinExD >= 1000)
 
 
-bd <- read.csv("BD.ABBABABA_dxy_S.minExD0.5.w5m1s1000.csv")
+bd <- read.csv("Heliconius_HmYb_windows.csv")
 bd <- subset(bd, is.na(D) == F & is.na(mf) == F & sitesOverMinExD >= 1000)
 
-pdf(file = "/home/simon/Images/ABBABABA_sim_paper/plots_acrosss_BD_Yb_filtered.pdf", width = 12, height = 7)
+pdf("Figure_4.pdf", width = 12, height = 7)
 
 
 par(mfrow = c(4,2), mar = c(2.5,2,0.5,1))

plot_D_and_f_by_S_WG.r → Figure_5.R

@@ -1,15 +1,16 @@
 #!/usr/bin/env Rscript
 
-# plot_D_and_f_by_S.r
-# Plots for whole genome Heliconius data - Figure 5
+# Figure_5.R
+# Plots for whole genome Heliconius data for Figure 5 as a PDF file
 
 # Written for "Evaluating statistics for the identification of introgressed loci"
 # by Simon H. Martin, John W. Davey and Chris D. Jiggins
-# John Davey:   [email protected]
 # Simon Martin: [email protected]
+# John Davey:   [email protected]
 # November-December 2013
 
-
+# This script requires the file Hmel1-1_hox_RAD_matepair_chromosomes_Zupdated.agp
+# Available in Data Dryad repository http://datadryad.org/resource/doi:10.5061/dryad.dk712
 
 ############## Functions ###############
 
@@ -53,7 +54,8 @@ as.chromosomes <- function(table,agp,chromNames,gap = 0) {
 
 ########### input data ################
 
-#agp file carrys chromosome information for mapped scaffolds
+# agp file carries chromosome information for mapped scaffolds
+# Available in Data Dryad repository http://datadryad.org/resource/doi:10.5061/dryad.dk712
 agp <- read.delim("Hmel1-1_hox_RAD_matepair_chromosomes_Zupdated.agp", as.is = T, sep = "\t", header = F)
 
 names(agp) = c("chromosome", "start", "end", "order", "DN", "scaffold", "one", "length", "ori", "rec")
@@ -65,11 +67,10 @@ chromNames <- c("chr1","chr2","chr3","chr4","chr5","chr6","chr7","chr8","chr9","
 
 #input data
 
-ABBA_table <- read.csv("set31.Zupdated.autoscafs.union.SPiDxyDf.w5m1s5.csv", as.is = T)
-ABBA_table_Z <- read.csv("set31.Zupdated.chrZscafs.union.SPiDxyDf.w5m1s5.csv", as.is = T)
+ABBA_table <- read.csv("Heliconius_autosome_windows.csv", as.is = T)
+ABBA_table_Z <- read.csv("Heliconius_Zchromosome_windows.csv", as.is = T)
 ABBA_table <- rbind(ABBA_table, ABBA_table_Z)
 
-
 #filter for windows with enough sites above the minimum data cutoff
 ABBA_table <- subset(ABBA_table, sitesOverMinExD >= 1000)
 
@@ -84,7 +85,7 @@ bdsub <- subset(ABBA_table, scaffold == "HE670865" & position >= 300000 & positi
 ###### plotting D and f against number of segregating sites
 
 
-pdf(file = "D_and_f_against_s.pdf", width = 3.3, height = 9.5)
+pdf(file = "Figure_5.pdf", width = 3.3, height = 9.5)
 
 par(mfrow = c(3,1), mar = c(3,3,1,1))
 

Figure_6_S5.R

@@ -1,5 +1,14 @@
 #!/usr/bin/env Rscript
 
+# Figure_6_S5.R
+# Generate the plots for Figure 6 and Figure S5 as PDF files
+
+# Written for "Evaluating statistics for the identification of introgressed loci"
+# by Simon H. Martin, John W. Davey and Chris D. Jiggins
+# Simon Martin: [email protected]
+# John Davey:   [email protected]
+# November-December 2013
+
 suppressMessages(library(ggplot2))
 suppressMessages(library(reshape))
 library(plyr)
@@ -143,7 +152,7 @@ grid.text("D",x=0.025,y=0.99,just=c("left","top"),vp=viewport(layout.pos.row=2,l
 dev.off()
 
 # Figure S5 - real data
-real<-read.delim("Heliconius_genome_windows.dxy.summary.tsv",stringsAsFactors=FALSE)
+real<-read.delim("Heliconius_autosome_windows.dxy.summary.tsv",stringsAsFactors=FALSE)
 
 real.dxy<-get.dxy.df(real)
 real.dxy$Stat<-factor(real.dxy$Stat,levels=c("D","mfD0"))

Figure_7.R

@@ -1,5 +1,14 @@
 #!/usr/bin/env Rscript
 
+# Figure_7.R
+# Generate the plot for Figure 7 as a PDF file
+
+# Written for "Evaluating statistics for the identification of introgressed loci"
+# by Simon H. Martin, John W. Davey and Chris D. Jiggins
+# Simon Martin: [email protected]
+# John Davey:   [email protected]
+# November-December 2013
+
 library(optparse)
 suppressMessages(library(ggplot2))
 library(plyr)

Figure_S1_S2.R

@@ -1,5 +1,15 @@
 #!/usr/bin/env Rscript
 
+# Figure_S1_S2.R
+# Generate the plots for Figures S1 and S2 as PDF files
+
+# Written for "Evaluating statistics for the identification of introgressed loci"
+# by Simon H. Martin, John W. Davey and Chris D. Jiggins
+# Simon Martin: [email protected]
+# John Davey:   [email protected]
+# November-December 2013
+
+
 library(optparse)
 suppressMessages(library(ggplot2))
 library(plyr)

Figure_S3_S4.R

@@ -1,5 +1,14 @@
 #!/usr/bin/env Rscript
 
+# Figure_S3_S4.R
+# Generate the plots for Figures S3 and S4 as PDF files
+
+# Written for "Evaluating statistics for the identification of introgressed loci"
+# by Simon H. Martin, John W. Davey and Chris D. Jiggins
+# Simon Martin: [email protected]
+# John Davey:   [email protected]
+# November-December 2013
+
 suppressMessages(library(ggplot2))
 suppressMessages(library(reshape))
 library(plyr)