Mercurial > repos > davidvanzessen > prisca

changeset 6:a9d2ed661541 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Thu, 05 Oct 2017 09:06:21 -0400
parents bcf1469e8feb
children 7ce82833977c
files RScript.r
diffstat 1 files changed, 21 insertions(+), 25 deletions(-) [+]
line wrap: on
line diff
--- a/RScript.r	Mon Oct 02 09:24:25 2017 -0400
+++ b/RScript.r	Thu Oct 05 09:06:21 2017 -0400
@@ -399,33 +399,29 @@
         filenameTwo = paste(twoSample, "_", product[iter, "Titles"], "_", threshhold, sep="")
         write.table(dfTwo, file=paste(filenameTwo, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
       }
-    } else {
-      scatterplot_locus_data = scatterplot_data[grepl(V_Segment, scatterplot_data$V_Segment_Major_Gene) & grepl(J_Segment, scatterplot_data$J_Segment_Major_Gene),]
-      if(nrow(scatterplot_locus_data) > 0){
-        scatterplot_locus_data$Rearrangement = product[iter, "Titles"]
+    }
+	scatterplot_locus_data = scatterplot_data[grepl(V_Segment, scatterplot_data$V_Segment_Major_Gene) & grepl(J_Segment, scatterplot_data$J_Segment_Major_Gene),]
+	if(nrow(scatterplot_locus_data) > 0){
+		scatterplot_locus_data$Rearrangement = product[iter, "Titles"]
+	}
+	p = NULL
+    #print(paste("nrow scatterplot_locus_data", nrow(scatterplot_locus_data)))
+    if(nrow(scatterplot_locus_data) != 0){
+      if(on == "normalized_read_count"){
+        write.table(scatterplot_locus_data, file=paste(oneSample, twoSample, product[iter, "Titles"], "scatterplot_locus_data.txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
+        scales = 10^(0:6) #(0:ceiling(log10(max(scatterplot_locus_data$normalized_read_count))))
+        p = ggplot(scatterplot_locus_data, aes(factor(reorder(type, type.order)), normalized_read_count, group=link)) + geom_line() + scale_y_log10(breaks=scales,labels=scales, limits=c(1,1e6)) + scale_x_discrete(breaks=levels(scatterplot_data$type), labels=levels(scatterplot_data$type), drop=FALSE)
+      } else {
+        p = ggplot(scatterplot_locus_data, aes(factor(reorder(type, type.order)), Frequency, group=link)) + geom_line() + scale_y_log10(limits=c(0.0001,100), breaks=c(0.0001, 0.001, 0.01, 0.1, 1, 10, 100), labels=c("0.0001", "0.001", "0.01", "0.1", "1", "10", "100")) + scale_x_discrete(breaks=levels(scatterplot_data$type), labels=levels(scatterplot_data$type), drop=FALSE)
       }
-      
-      
-      
-      p = NULL
-      #print(paste("nrow scatterplot_locus_data", nrow(scatterplot_locus_data)))
-      if(nrow(scatterplot_locus_data) != 0){
-        if(on == "normalized_read_count"){
-          write.table(scatterplot_locus_data, file=paste(oneSample, twoSample, product[iter, "Titles"], "scatterplot_locus_data.txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
-          scales = 10^(0:6) #(0:ceiling(log10(max(scatterplot_locus_data$normalized_read_count))))
-          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, limits=c(1,1e6)) + scale_x_discrete(breaks=levels(scatterplot_data$type), labels=levels(scatterplot_data$type), drop=FALSE)
-        } else {
-          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="dodge")
-        p = p + xlab("In one or both samples") + ylab(onShort) + ggtitle(paste(patient1[1,"Patient"], patient1[1,"Sample"], patient2[1,"Sample"], onShort, product[iter, "Titles"]))
-      } else {
-        p = ggplot(NULL, aes(x=c("In one", "In Both"),y=0)) + geom_blank(NULL) + xlab("In one or both of the samples") + ylab(onShort) + ggtitle(paste(patient1[1,"Patient"], patient1[1,"Sample"], patient2[1,"Sample"], onShort, product[iter, titleIndex]))
-      }
-      png(paste(patient1[1,"Patient"], "_", patient1[1,"Sample"], "_", patient2[1,"Sample"], "_", onShort, "_", product[iter, "Titles"],"_scatter.png", sep=""))
-      print(p)
-      dev.off()
+      p = p + geom_point(aes(colour=type), position="dodge")
+      p = p + xlab("In one or both samples") + ylab(onShort) + ggtitle(paste(patient1[1,"Patient"], patient1[1,"Sample"], patient2[1,"Sample"], onShort, product[iter, "Titles"]))
+    } else {
+      p = ggplot(NULL, aes(x=c("In one", "In Both"),y=0)) + geom_blank(NULL) + xlab("In one or both of the samples") + ylab(onShort) + ggtitle(paste(patient1[1,"Patient"], patient1[1,"Sample"], patient2[1,"Sample"], onShort, product[iter, "Titles"]))
     }
+    png(paste(patient1[1,"Patient"], "_", patient1[1,"Sample"], "_", patient2[1,"Sample"], "_", onShort, "_", product[iter, "Titles"],"_scatter.png", sep=""))
+    print(p)
+    dev.off()
     if(sum(both) > 0){
       dfBoth = patientMerge[both,c("V_Segment_Major_Gene.x", "J_Segment_Major_Gene.x", "normalized_read_count.x", "Frequency.x", "Related_to_leukemia_clone.x", "Clone_Sequence.x", "V_Segment_Major_Gene.y", "J_Segment_Major_Gene.y", "normalized_read_count.y", "Frequency.y", "Related_to_leukemia_clone.y")]
       colnames(dfBoth) = c(paste("Proximal segment", oneSample), paste("Distal segment", oneSample), paste("Normalized_Read_Count", oneSample), paste("Frequency", oneSample), paste("Related_to_leukemia_clone", oneSample),"Clone Sequence", paste("Proximal segment", twoSample), paste("Distal segment", twoSample), paste("Normalized_Read_Count", twoSample), paste("Frequency", twoSample), paste("Related_to_leukemia_clone", twoSample))