Mercurial > repos > davidvanzessen > clonal_sequences_in_paired_samples

comparison RScript.r @ 28:a63ccc36f5a4 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Tue, 19 May 2015 08:13:49 -0400
parents dd8518ea23dd
children 5ab17bdf2530
comparison
equal deleted inserted replaced
27:dd8518ea23dd 28:a63ccc36f5a4
59 Titles = c("Total", "IGH-Vh-Jh", "IGH-Dh-Jh", "Vk-Jk", "Vk-Kde" , "Intron-Kde", "TCRG", "TCRD-Vd-Dd", "TCRD-Dd-Dd", "TCRB-Vb-Jb") 59 Titles = c("Total", "IGH-Vh-Jh", "IGH-Dh-Jh", "Vk-Jk", "Vk-Kde" , "Intron-Kde", "TCRG", "TCRD-Vd-Dd", "TCRD-Dd-Dd", "TCRB-Vb-Jb")
60 Titles = factor(Titles, levels=Titles) 60 Titles = factor(Titles, levels=Titles)
61 TitlesOrder = data.frame("Title"=Titles, "TitlesOrder"=1:length(Titles)) 61 TitlesOrder = data.frame("Title"=Titles, "TitlesOrder"=1:length(Titles))
62 62
63 patientCountOnColumn <- function(x, product, interval, on, appendtxt=F){ 63 patientCountOnColumn <- function(x, product, interval, on, appendtxt=F){
64 if (!is.data.frame(x) & is.list(x)){
65 x = x[[1]]
66 }
64 x$Sample = factor(x$Sample, levels=unique(x$Sample)) 67 x$Sample = factor(x$Sample, levels=unique(x$Sample))
65 onShort = "reads" 68 onShort = "reads"
66 if(on == "Frequency"){ 69 if(on == "Frequency"){
67 onShort = "freq" 70 onShort = "freq"
68 } 71 }
253 patient2$merge = paste(patient2$Clone_Sequence) 256 patient2$merge = paste(patient2$Clone_Sequence)
254 patient3$merge = paste(patient3$Clone_Sequence) 257 patient3$merge = paste(patient3$Clone_Sequence)
255 258
256 patientMerge = merge(patient1, patient2, by="merge") 259 patientMerge = merge(patient1, patient2, by="merge")
257 patientMerge = merge(patientMerge, patient3, by="merge") 260 patientMerge = merge(patientMerge, patient3, by="merge")
258 colnames(patientMerge)[30:length(colnames(patientMerge))] = paste(colnames(patientMerge)[30:length(colnames(patientMerge))], ".z", sep="") 261 colnames(patientMerge)[which(!grepl("(\\.x$)|(\\.y$)|(merge)", names(patientMerge)))] = paste(colnames(patientMerge)[which(!grepl("(\\.x$)|(\\.y$)|(merge)", names(patientMerge), perl=T))], ".z", sep="")
259 patientMerge$thresholdValue = pmax(patientMerge[,onx], patientMerge[,ony], patientMerge[,onz]) 262 patientMerge$thresholdValue = pmax(patientMerge[,onx], patientMerge[,ony], patientMerge[,onz])
260
261 patientMerge12 = merge(patient1, patient2, by="merge") 263 patientMerge12 = merge(patient1, patient2, by="merge")
262 patientMerge12$thresholdValue = pmax(patientMerge12[,onx], patientMerge12[,ony]) 264 patientMerge12$thresholdValue = pmax(patientMerge12[,onx], patientMerge12[,ony])
263 patientMerge13 = merge(patient1, patient3, by="merge") 265 patientMerge13 = merge(patient1, patient3, by="merge")
264 patientMerge13$thresholdValue = pmax(patientMerge13[,onx], patientMerge13[,ony]) 266 patientMerge13$thresholdValue = pmax(patientMerge13[,onx], patientMerge13[,ony])
265 patientMerge23 = merge(patient2, patient3, by="merge") 267 patientMerge23 = merge(patient2, patient3, by="merge")
266 patientMerge23$thresholdValue = pmax(patientMerge23[,onx], patientMerge23[,ony]) 268 patientMerge23$thresholdValue = pmax(patientMerge23[,onx], patientMerge23[,ony])
269
267 270
268 scatterplot_data_columns = c("Clone_Sequence", "Frequency", "normalized_read_count", "V_Segment_Major_Gene", "J_Segment_Major_Gene") 271 scatterplot_data_columns = c("Clone_Sequence", "Frequency", "normalized_read_count", "V_Segment_Major_Gene", "J_Segment_Major_Gene")
269 scatterplot_data = rbind(patient1[,scatterplot_data_columns], patient2[,scatterplot_data_columns], patient3[,scatterplot_data_columns]) 272 scatterplot_data = rbind(patient1[,scatterplot_data_columns], patient2[,scatterplot_data_columns], patient3[,scatterplot_data_columns])
270 scatterplot_data = scatterplot_data[!duplicated(scatterplot_data$Clone_Sequence),] 273 scatterplot_data = scatterplot_data[!duplicated(scatterplot_data$Clone_Sequence),]
271 scatterplot_data$type = factor(x="In one", levels=c("In one", "In two", "In three", "In multiple")) 274 scatterplot_data$type = factor(x="In one", levels=c("In one", "In two", "In three", "In multiple"))
356 in_three = (scatterplot_locus_data$Clone_Sequence %in% patientMerge[all,]$Clone_Sequence.x) 359 in_three = (scatterplot_locus_data$Clone_Sequence %in% patientMerge[all,]$Clone_Sequence.x)
357 if(sum(in_three)> 0){ 360 if(sum(in_three)> 0){
358 scatterplot_locus_data[in_three,]$type = "In three" 361 scatterplot_locus_data[in_three,]$type = "In three"
359 } 362 }
360 not_in_one = scatterplot_locus_data$type != "In one" 363 not_in_one = scatterplot_locus_data$type != "In one"
361 print(not_in_one)
362 if(sum(not_in_one) > 0){ 364 if(sum(not_in_one) > 0){
363 scatterplot_locus_data[not_in_one,]$type = "In multiple" 365 scatterplot_locus_data[not_in_one,]$type = "In multiple"
364 } 366 }
365 p = NULL 367 p = NULL
366 if(nrow(scatterplot_locus_data) != 0){ 368 if(nrow(scatterplot_locus_data) != 0){