Mercurial > repos > davidvanzessen > prisca

comparison RScript.r @ 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
comparison
equal deleted inserted replaced
5:bcf1469e8feb 6:a9d2ed661541
397 dfTwo = patient2[two,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "Clone_Sequence", "Related_to_leukemia_clone")] 397 dfTwo = patient2[two,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "Clone_Sequence", "Related_to_leukemia_clone")]
398 colnames(dfTwo) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "Clone Sequence", "Related_to_leukemia_clone") 398 colnames(dfTwo) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "Clone Sequence", "Related_to_leukemia_clone")
399 filenameTwo = paste(twoSample, "_", product[iter, "Titles"], "_", threshhold, sep="") 399 filenameTwo = paste(twoSample, "_", product[iter, "Titles"], "_", threshhold, sep="")
400 write.table(dfTwo, file=paste(filenameTwo, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T) 400 write.table(dfTwo, file=paste(filenameTwo, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
401 } 401 }
402 }
403 scatterplot_locus_data = scatterplot_data[grepl(V_Segment, scatterplot_data$V_Segment_Major_Gene) & grepl(J_Segment, scatterplot_data$J_Segment_Major_Gene),]
404 if(nrow(scatterplot_locus_data) > 0){
405 scatterplot_locus_data$Rearrangement = product[iter, "Titles"]
406 }
407 p = NULL
408 #print(paste("nrow scatterplot_locus_data", nrow(scatterplot_locus_data)))
409 if(nrow(scatterplot_locus_data) != 0){
410 if(on == "normalized_read_count"){
411 write.table(scatterplot_locus_data, file=paste(oneSample, twoSample, product[iter, "Titles"], "scatterplot_locus_data.txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
412 scales = 10^(0:6) #(0:ceiling(log10(max(scatterplot_locus_data$normalized_read_count))))
413 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)
414 } else {
415 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)
416 }
417 p = p + geom_point(aes(colour=type), position="dodge")
418 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"]))
402 } else { 419 } else {
403 scatterplot_locus_data = scatterplot_data[grepl(V_Segment, scatterplot_data$V_Segment_Major_Gene) & grepl(J_Segment, scatterplot_data$J_Segment_Major_Gene),] 420 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"]))
404 if(nrow(scatterplot_locus_data) > 0){
405 scatterplot_locus_data$Rearrangement = product[iter, "Titles"]
406 }
407
408
409
410 p = NULL
411 #print(paste("nrow scatterplot_locus_data", nrow(scatterplot_locus_data)))
412 if(nrow(scatterplot_locus_data) != 0){
413 if(on == "normalized_read_count"){
414 write.table(scatterplot_locus_data, file=paste(oneSample, twoSample, product[iter, "Titles"], "scatterplot_locus_data.txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
415 scales = 10^(0:6) #(0:ceiling(log10(max(scatterplot_locus_data$normalized_read_count))))
416 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)
417 } else {
418 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)
419 }
420 p = p + geom_point(aes(colour=type), position="dodge")
421 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"]))
422 } else {
423 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]))
424 }
425 png(paste(patient1[1,"Patient"], "_", patient1[1,"Sample"], "_", patient2[1,"Sample"], "_", onShort, "_", product[iter, "Titles"],"_scatter.png", sep=""))
426 print(p)
427 dev.off()
428 } 421 }
422 png(paste(patient1[1,"Patient"], "_", patient1[1,"Sample"], "_", patient2[1,"Sample"], "_", onShort, "_", product[iter, "Titles"],"_scatter.png", sep=""))
423 print(p)
424 dev.off()
429 if(sum(both) > 0){ 425 if(sum(both) > 0){
430 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")] 426 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")]
431 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)) 427 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))
432 filenameBoth = paste(oneSample, "_", twoSample, "_", product[iter, "Titles"], "_", threshhold, sep="") 428 filenameBoth = paste(oneSample, "_", twoSample, "_", product[iter, "Titles"], "_", threshhold, sep="")
433 write.table(dfBoth, file=paste(filenameBoth, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T) 429 write.table(dfBoth, file=paste(filenameBoth, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)