# HG changeset patch
# User davidvanzessen
# Date 1452096000 18000
# Node ID c532b3f8dc972a9258289c1fc3a8db58efe76b8a
# Parent  ef13f0a3f4d6c238c4625a608a173eddd9322738
Uploaded

diff -r ef13f0a3f4d6 -r c532b3f8dc97 RScript.r
--- a/RScript.r	Tue Jan 05 10:49:40 2016 -0500
+++ b/RScript.r	Wed Jan 06 11:00:00 2016 -0500
@@ -341,6 +341,10 @@
     }
     patient.merge.list[[patient]] <<- patientMerge
     patient.merge.list.second[[patient]] <<- merge.list[["second"]]
+    
+    sample.order = data.frame(type = c(oneSample, twoSample, paste(c(oneSample, twoSample), "In Both")),type.order = 1:4)
+    scatterplot_data = merge(scatterplot_data, sample.order, by="type")
+    
     scatter_locus_data_list[[patient]] <<- scatterplot_data
     cat(paste("<td>", nrow(patient1), " in ", oneSample, " and ", nrow(patient2), " in ", twoSample, ", ", nrow(patientMerge), " in both (finding both took ", (proc.time() - start.time)[[3]], "s)</td></tr>", sep=""), file=logfile, append=T)
   }
@@ -391,42 +395,21 @@
       }
     } else {
       scatterplot_locus_data = scatterplot_data[grepl(V_Segment, scatterplot_data$V_Segment_Major_Gene) & grepl(J_Segment, scatterplot_data$J_Segment_Major_Gene),]
-      #scatterplot_locus_data = scatterplot_locus_data[!(scatterplot_locus_data$merge %in% merge.list[[twoSample]]),]
-      #scatterplot_locus_data = scatterplot_locus_data[!(scatterplot_locus_data$merge %in% merge.list[["second"]]),]
       if(nrow(scatterplot_locus_data) > 0){
         scatterplot_locus_data$Rearrangement = product[iter, titleIndex]
       }
       
       
-      
-      #in_one = (scatterplot_locus_data$merge %in% patient1$merge)
-      #in_two = (scatterplot_locus_data$merge %in% patient2$merge)
-      #if(any(in_two)){
-      #  scatterplot_locus_data[in_two,]$type = twoSample
-      #}
-      #in_both = (scatterplot_locus_data$merge %in% patientMerge$merge)
-      ##merge.list.filter = (scatterplot_locus_data$merge %in% merge.list[[oneSample]])
-      ##exact.matches.filter = (scatterplot_locus_data$merge %in% cs.exact.matches)
-      #if(any(in_both)){
-      #  scatterplot_locus_data[in_both,]$type = "In Both"
-      #}
-      #if(type == "single" & (nrow(scatterplot_locus_data) > 0 | !any(scatterplot_locus_data$Patient %in% single_patients$Patient))){
-      #  single_patients <<- rbind(single_patients, scatterplot_locus_data)
-      #}
-      
-      
+            
       p = NULL
       print(paste("nrow scatterplot_locus_data", nrow(scatterplot_locus_data)))
       if(nrow(scatterplot_locus_data) != 0){
         if(on == "normalized_read_count"){
           scales = 10^(0:6) #(0:ceiling(log10(max(scatterplot_locus_data$normalized_read_count))))
-          #p = ggplot(scatterplot_locus_data, aes(type, normalized_read_count)) + scale_y_log10(breaks=scales,labels=scales) + expand_limits(y=10^6) + scale_x_discrete(breaks=levels(scatterplot_data$type), labels=levels(scatterplot_data$type), drop=FALSE)
-          p = ggplot(scatterplot_locus_data, aes(type, normalized_read_count, group=link)) + geom_line() + scale_y_log10(breaks=scales,labels=scales) + expand_limits(y=c(0,10^6)) + scale_x_discrete(breaks=levels(scatterplot_data$type), labels=levels(scatterplot_data$type), drop=FALSE)
+          p = ggplot(scatterplot_locus_data, aes(factor(reorder(type, type.order)), normalized_read_count, group=link)) + geom_line() + scale_y_log10(breaks=scales,labels=scales) + expand_limits(y=c(0,10^6)) + scale_x_discrete(breaks=levels(scatterplot_data$type), labels=levels(scatterplot_data$type), drop=FALSE)
         } else {
-          #p = ggplot(scatterplot_locus_data, aes(type, Frequency)) + scale_y_continuous(limits = c(0, 100)) + expand_limits(y=c(0,100)) + scale_x_discrete(breaks=levels(scatterplot_data$type), labels=levels(scatterplot_data$type), drop=FALSE)
-          p = ggplot(scatterplot_locus_data, aes(type, Frequency, group=link)) + geom_line() + scale_y_log10(limits=c(0.0001,100), breaks=c(0.0001, 0.001, 0.01, 0.1, 1, 10, 100), labels=c("0.0001", "0.001", "0.01", "0.1", "1", "10", "100")) + scale_x_discrete(breaks=levels(scatterplot_data$type), labels=levels(scatterplot_data$type), drop=FALSE)
+          p = ggplot(scatterplot_locus_data, aes(factor(reorder(type, type.order)), Frequency, group=link)) + geom_line() + scale_y_log10(limits=c(0.0001,100), breaks=c(0.0001, 0.001, 0.01, 0.1, 1, 10, 100), labels=c("0.0001", "0.001", "0.01", "0.1", "1", "10", "100")) + scale_x_discrete(breaks=levels(scatterplot_data$type), labels=levels(scatterplot_data$type), drop=FALSE)
         }
-        #p = p + geom_point(aes(colour=type), position="jitter")
         p = p + geom_point(aes(colour=type), position="dodge")
         p = p + xlab("In one or both samples") + ylab(onShort) + ggtitle(paste(patient1[1,patientIndex], patient1[1,sampleIndex], patient2[1,sampleIndex], onShort, product[iter, titleIndex]))
       } else {