Mercurial > repos > davidvanzessen > clonal_sequences_in_paired_samples

comparison RScript.r @ 24:6904186d13b9 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Tue, 24 Feb 2015 09:12:28 -0500
parents b662fdc7eff4
children 99020e5ce46c
comparison
equal deleted inserted replaced
23:0940835d259c 24:6904186d13b9
263 patientMerge13 = merge(patient1, patient3, by="merge") 263 patientMerge13 = merge(patient1, patient3, by="merge")
264 patientMerge13$thresholdValue = pmax(patientMerge13[,onx], patientMerge13[,ony]) 264 patientMerge13$thresholdValue = pmax(patientMerge13[,onx], patientMerge13[,ony])
265 patientMerge23 = merge(patient2, patient3, by="merge") 265 patientMerge23 = merge(patient2, patient3, by="merge")
266 patientMerge23$thresholdValue = pmax(patientMerge23[,onx], patientMerge23[,ony]) 266 patientMerge23$thresholdValue = pmax(patientMerge23[,onx], patientMerge23[,ony])
267 267
268 scatterplot_data_columns = c("Clone_Sequence", "Frequency", "normalized_read_count") 268 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]) 269 scatterplot_data = rbind(patient1[,scatterplot_data_columns], patient2[,scatterplot_data_columns], patient3[,scatterplot_data_columns])
270 scatterplot_data = scatterplot_data[!duplicated(scatterplot_data$Clone_Sequence),] 270 scatterplot_data = scatterplot_data[!duplicated(scatterplot_data$Clone_Sequence),]
271 scatterplot_data$type = factor(x="single", levels=c("In one", "In two", "In three")) 271 scatterplot_data$type = factor(x="single", levels=c("In one", "In two", "In three"))
272 272
273 res1 = vector() 273 res1 = vector()
288 threshhold = product[iter,threshholdIndex] 288 threshhold = product[iter,threshholdIndex]
289 V_Segment = paste(".*", as.character(product[iter,V_SegmentIndex]), ".*", sep="") 289 V_Segment = paste(".*", as.character(product[iter,V_SegmentIndex]), ".*", sep="")
290 J_Segment = paste(".*", as.character(product[iter,J_SegmentIndex]), ".*", sep="") 290 J_Segment = paste(".*", as.character(product[iter,J_SegmentIndex]), ".*", sep="")
291 #all = (grepl(V_Segment, patientMerge$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge$J_Segment_Major_Gene.x) & patientMerge[,onx] > threshhold & patientMerge[,ony] > threshhold & patientMerge[,onz] > threshhold) 291 #all = (grepl(V_Segment, patientMerge$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge$J_Segment_Major_Gene.x) & patientMerge[,onx] > threshhold & patientMerge[,ony] > threshhold & patientMerge[,onz] > threshhold)
292 all = (grepl(V_Segment, patientMerge$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge$J_Segment_Major_Gene.x) & patientMerge$thresholdValue > threshhold) 292 all = (grepl(V_Segment, patientMerge$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge$J_Segment_Major_Gene.x) & patientMerge$thresholdValue > threshhold)
293 one = (grepl(V_Segment, patient1$V_Segment_Major_Gene) & grepl(J_Segment, patient1$J_Segment_Major_Gene) & patient1[,on] > threshhold & !(patient1$Clone_Sequence %in% patientMerge[all,]$merge))
294 two = (grepl(V_Segment, patient2$V_Segment_Major_Gene) & grepl(J_Segment, patient2$J_Segment_Major_Gene) & patient2[,on] > threshhold & !(patient2$Clone_Sequence %in% patientMerge[all,]$merge))
295 three = (grepl(V_Segment, patient3$V_Segment_Major_Gene) & grepl(J_Segment, patient3$J_Segment_Major_Gene) & patient3[,on] > threshhold & !(patient3$Clone_Sequence %in% patientMerge[all,]$merge))
296 293
297 one_two = (grepl(V_Segment, patientMerge12$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge12$J_Segment_Major_Gene.x) & patientMerge12$thresholdValue > threshhold) 294 one_two = (grepl(V_Segment, patientMerge12$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge12$J_Segment_Major_Gene.x) & patientMerge12$thresholdValue > threshhold & !(patientMerge12$Clone_Sequence %in% patientMerge[all,]$merge))
298 one_three = (grepl(V_Segment, patientMerge13$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge13$J_Segment_Major_Gene.x) & patientMerge13$thresholdValue > threshhold) 295 one_three = (grepl(V_Segment, patientMerge13$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge13$J_Segment_Major_Gene.x) & patientMerge13$thresholdValue > threshhold & !(patientMerge13$Clone_Sequence %in% patientMerge[all,]$merge))
299 two_three = (grepl(V_Segment, patientMerge23$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge23$J_Segment_Major_Gene.x) & patientMerge23$thresholdValue > threshhold) 296 two_three = (grepl(V_Segment, patientMerge23$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge23$J_Segment_Major_Gene.x) & patientMerge23$thresholdValue > threshhold & !(patientMerge23$Clone_Sequence %in% patientMerge[all,]$merge))
297
298 one = (grepl(V_Segment, patient1$V_Segment_Major_Gene) & grepl(J_Segment, patient1$J_Segment_Major_Gene) & patient1[,on] > threshhold & !(patient1$Clone_Sequence %in% patientMerge[all,]$merge) & !(patientMerge12$Clone_Sequence %in% patientMerge[all,]$merge) & !(patientMerge13$Clone_Sequence %in% patientMerge[all,]$merge))
299 two = (grepl(V_Segment, patient2$V_Segment_Major_Gene) & grepl(J_Segment, patient2$J_Segment_Major_Gene) & patient2[,on] > threshhold & !(patient2$Clone_Sequence %in% patientMerge[all,]$merge) & !(patientMerge12$Clone_Sequence %in% patientMerge[all,]$merge) & !(patientMerge23$Clone_Sequence %in% patientMerge[all,]$merge))
300 three = (grepl(V_Segment, patient3$V_Segment_Major_Gene) & grepl(J_Segment, patient3$J_Segment_Major_Gene) & patient3[,on] > threshhold & !(patient3$Clone_Sequence %in% patientMerge[all,]$merge) & !(patientMerge13$Clone_Sequence %in% patientMerge[all,]$merge) & !(patientMerge23$Clone_Sequence %in% patientMerge[all,]$merge))
300 301
301 read1Count = append(read1Count, sum(patient1[one,]$normalized_read_count) + sum(patientMerge[all,]$normalized_read_count.x)) 302 read1Count = append(read1Count, sum(patient1[one,]$normalized_read_count) + sum(patientMerge[all,]$normalized_read_count.x))
302 read2Count = append(read2Count, sum(patient2[two,]$normalized_read_count) + sum(patientMerge[all,]$normalized_read_count.y)) 303 read2Count = append(read2Count, sum(patient2[two,]$normalized_read_count) + sum(patientMerge[all,]$normalized_read_count.y))
303 read3Count = append(read3Count, sum(patient3[three,]$normalized_read_count) + sum(patientMerge[all,]$normalized_read_count.z)) 304 read3Count = append(read3Count, sum(patient3[three,]$normalized_read_count) + sum(patientMerge[all,]$normalized_read_count.z))
304 res1 = append(res1, sum(one)) 305 res1 = append(res1, sum(one))
345 colnames(dfTwo_three) = c(paste("Proximal segment", twoSample), paste("Distal segment", twoSample), paste("Normalized_Read_Count", twoSample), paste("Frequency", twoSample), paste("Related_to_leukemia_clone", twoSample),"Clone_Sequence", paste("Proximal segment", threeSample), paste("Distal segment", threeSample), paste("Normalized_Read_Count", threeSample), paste("Frequency", threeSample), paste("Related_to_leukemia_clone", threeSample)) 346 colnames(dfTwo_three) = c(paste("Proximal segment", twoSample), paste("Distal segment", twoSample), paste("Normalized_Read_Count", twoSample), paste("Frequency", twoSample), paste("Related_to_leukemia_clone", twoSample),"Clone_Sequence", paste("Proximal segment", threeSample), paste("Distal segment", threeSample), paste("Normalized_Read_Count", threeSample), paste("Frequency", threeSample), paste("Related_to_leukemia_clone", threeSample))
346 filenameTwo_three = paste(label2, "_", label3, "_", product[iter, titleIndex], "_", threshhold, onShort, sep="") 347 filenameTwo_three = paste(label2, "_", label3, "_", product[iter, titleIndex], "_", threshhold, onShort, sep="")
347 write.table(dfTwo_three, file=paste(filenameTwo_three, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T) 348 write.table(dfTwo_three, file=paste(filenameTwo_three, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
348 } 349 }
349 } else { #scatterplot data 350 } else { #scatterplot data
350 scatterplot_locus_data = scatterplot_data 351 scatterplot_locus_data = scatterplot_data[grepl(V_Segment, scatterplot_data$V_Segment_Major_Gene) & grepl(J_Segment, scatterplot_data$J_Segment_Major_Gene),]
351 scatterplot_locus_data$type = ifelse(scatterplot_locus_data$Clone_Sequence %in% patientMerge12[one_two,]$Clone_Sequence.x, "In two", "In one") 352 scatterplot_locus_data$type = ifelse(scatterplot_locus_data$Clone_Sequence %in% patientMerge12[one_two,]$Clone_Sequence.x, "In two", "In one")
352 scatterplot_locus_data$type = ifelse(scatterplot_locus_data$Clone_Sequence %in% patientMerge13[one_three,]$Clone_Sequence.x, "In two", "In one") 353 scatterplot_locus_data$type = ifelse(scatterplot_locus_data$Clone_Sequence %in% patientMerge13[one_three,]$Clone_Sequence.x, "In two", "In one")
353 scatterplot_locus_data$type = ifelse(scatterplot_locus_data$Clone_Sequence %in% patientMerge23[two_three,]$Clone_Sequence.x, "In two", "In one") 354 scatterplot_locus_data$type = ifelse(scatterplot_locus_data$Clone_Sequence %in% patientMerge23[two_three,]$Clone_Sequence.x, "In two", "In one")
354 scatterplot_locus_data$type = ifelse(scatterplot_locus_data$type == "In two", ifelse(scatterplot_locus_data$Clone_Sequence %in% patientMerge[all,]$Clone_Sequence.x, "In three", "In two"), "In one") 355 scatterplot_locus_data$type = ifelse(scatterplot_locus_data$type == "In two", ifelse(scatterplot_locus_data$Clone_Sequence %in% patientMerge[all,]$Clone_Sequence.x, "In three", "In two"), "In one")
355 scatterplot_locus_data$type = ifelse(scatterplot_locus_data$type == "In one", "In one", "In multiple") 356 scatterplot_locus_data$type = ifelse(scatterplot_locus_data$type == "In one", "In one", "In multiple")