Mercurial > repos > davidvanzessen > clonal_sequences_in_paired_samples

comparison RScript.r @ 69:c532b3f8dc97 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Wed, 06 Jan 2016 11:00:00 -0500
parents ef13f0a3f4d6
children 9643b1fd9c45
comparison
equal deleted inserted replaced
68:ef13f0a3f4d6 69:c532b3f8dc97
339 } 339 }
340 link.count = link.count + 1 340 link.count = link.count + 1
341 } 341 }
342 patient.merge.list[[patient]] <<- patientMerge 342 patient.merge.list[[patient]] <<- patientMerge
343 patient.merge.list.second[[patient]] <<- merge.list[["second"]] 343 patient.merge.list.second[[patient]] <<- merge.list[["second"]]
344
345 sample.order = data.frame(type = c(oneSample, twoSample, paste(c(oneSample, twoSample), "In Both")),type.order = 1:4)
346 scatterplot_data = merge(scatterplot_data, sample.order, by="type")
347
344 scatter_locus_data_list[[patient]] <<- scatterplot_data 348 scatter_locus_data_list[[patient]] <<- scatterplot_data
345 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) 349 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)
346 } 350 }
347 351
348 patient1 = patient1[!(patient1$Clone_Sequence %in% patient.merge.list.second[[patient]]),] 352 patient1 = patient1[!(patient1$Clone_Sequence %in% patient.merge.list.second[[patient]]),]
389 filenameTwo = paste(twoSample, "_", product[iter, titleIndex], "_", threshhold, sep="") 393 filenameTwo = paste(twoSample, "_", product[iter, titleIndex], "_", threshhold, sep="")
390 write.table(dfTwo, file=paste(filenameTwo, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T) 394 write.table(dfTwo, file=paste(filenameTwo, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
391 } 395 }
392 } else { 396 } else {
393 scatterplot_locus_data = scatterplot_data[grepl(V_Segment, scatterplot_data$V_Segment_Major_Gene) & grepl(J_Segment, scatterplot_data$J_Segment_Major_Gene),] 397 scatterplot_locus_data = scatterplot_data[grepl(V_Segment, scatterplot_data$V_Segment_Major_Gene) & grepl(J_Segment, scatterplot_data$J_Segment_Major_Gene),]
394 #scatterplot_locus_data = scatterplot_locus_data[!(scatterplot_locus_data$merge %in% merge.list[[twoSample]]),]
395 #scatterplot_locus_data = scatterplot_locus_data[!(scatterplot_locus_data$merge %in% merge.list[["second"]]),]
396 if(nrow(scatterplot_locus_data) > 0){ 398 if(nrow(scatterplot_locus_data) > 0){
397 scatterplot_locus_data$Rearrangement = product[iter, titleIndex] 399 scatterplot_locus_data$Rearrangement = product[iter, titleIndex]
398 } 400 }
399 401
400 402
401 403
402 #in_one = (scatterplot_locus_data$merge %in% patient1$merge)
403 #in_two = (scatterplot_locus_data$merge %in% patient2$merge)
404 #if(any(in_two)){
405 # scatterplot_locus_data[in_two,]$type = twoSample
406 #}
407 #in_both = (scatterplot_locus_data$merge %in% patientMerge$merge)
408 ##merge.list.filter = (scatterplot_locus_data$merge %in% merge.list[[oneSample]])
409 ##exact.matches.filter = (scatterplot_locus_data$merge %in% cs.exact.matches)
410 #if(any(in_both)){
411 # scatterplot_locus_data[in_both,]$type = "In Both"
412 #}
413 #if(type == "single" & (nrow(scatterplot_locus_data) > 0 | !any(scatterplot_locus_data$Patient %in% single_patients$Patient))){
414 # single_patients <<- rbind(single_patients, scatterplot_locus_data)
415 #}
416
417
418 p = NULL 404 p = NULL
419 print(paste("nrow scatterplot_locus_data", nrow(scatterplot_locus_data))) 405 print(paste("nrow scatterplot_locus_data", nrow(scatterplot_locus_data)))
420 if(nrow(scatterplot_locus_data) != 0){ 406 if(nrow(scatterplot_locus_data) != 0){
421 if(on == "normalized_read_count"){ 407 if(on == "normalized_read_count"){
422 scales = 10^(0:6) #(0:ceiling(log10(max(scatterplot_locus_data$normalized_read_count)))) 408 scales = 10^(0:6) #(0:ceiling(log10(max(scatterplot_locus_data$normalized_read_count))))
423 #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) 409 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)
424 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)
425 } else { 410 } else {
426 #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) 411 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)
427 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)
428 } 412 }
429 #p = p + geom_point(aes(colour=type), position="jitter")
430 p = p + geom_point(aes(colour=type), position="dodge") 413 p = p + geom_point(aes(colour=type), position="dodge")
431 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])) 414 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]))
432 } else { 415 } else {
433 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,patientIndex], patient1[1,sampleIndex], patient2[1,sampleIndex], onShort, product[iter, titleIndex])) 416 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,patientIndex], patient1[1,sampleIndex], patient2[1,sampleIndex], onShort, product[iter, titleIndex]))
434 } 417 }