Mercurial > repos > davidvanzessen > clonal_sequences_in_paired_samples

changeset 15:d137974763b3 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Thu, 05 Feb 2015 07:57:21 -0500
parents 1735e91a8f4b
children 95c9d82b3cd4
files RScript.r
diffstat 1 files changed, 23 insertions(+), 22 deletions(-) [+]
line wrap: on
line diff
--- a/RScript.r	Thu Feb 05 06:20:36 2015 -0500
+++ b/RScript.r	Thu Feb 05 07:57:21 2015 -0500
@@ -20,6 +20,7 @@
 dat$Related_to_leukemia_clone = F
 
 setwd(outDir)
+write(paste("TMP='", outDir, "'"), file=file.path(Sys.getenv('R_USER'), '.Renviron'))
 cat("<tr><td>Selecting first V/J Genes</td></tr>", file=logfile, append=T)
 dat$V_Segment_Major_Gene = as.factor(as.character(lapply(strsplit(as.character(dat$V_Segment_Major_Gene), "; "), "[[", 1)))
 dat$J_Segment_Major_Gene = as.factor(as.character(lapply(strsplit(as.character(dat$J_Segment_Major_Gene), "; "), "[[", 1)))
@@ -123,8 +124,8 @@
     V_Segment = paste(".*", as.character(product[iter,V_SegmentIndex]), ".*", sep="")
     J_Segment = paste(".*", as.character(product[iter,J_SegmentIndex]), ".*", sep="")
     both = (grepl(V_Segment, patientMerge$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge$J_Segment_Major_Gene.x) & patientMerge[,paste(on, ".x", sep="")] > threshhold & patientMerge[,paste(on, ".y", sep="")] > threshhold)
-    one = (grepl(V_Segment, patient1$V_Segment_Major_Gene) & grepl(J_Segment, patient1$J_Segment_Major_Gene) & patient1[,on] > threshhold & !(patient1$CDR3_Sense_Sequence %in% patientMerge[both,]$CDR3_Sense_Sequence.x))
-    two = (grepl(V_Segment, patient2$V_Segment_Major_Gene) & grepl(J_Segment, patient2$J_Segment_Major_Gene) & patient2[,on] > threshhold & !(patient2$CDR3_Sense_Sequence %in% patientMerge[both,]$CDR3_Sense_Sequence.x))
+    one = (grepl(V_Segment, patient1$V_Segment_Major_Gene) & grepl(J_Segment, patient1$J_Segment_Major_Gene) & patient1[,on] > threshhold & !(patient1$Clone_Sequence %in% patientMerge[both,]$Clone_Sequence.x))
+    two = (grepl(V_Segment, patient2$V_Segment_Major_Gene) & grepl(J_Segment, patient2$J_Segment_Major_Gene) & patient2[,on] > threshhold & !(patient2$Clone_Sequence %in% patientMerge[both,]$Clone_Sequence.x))
     read1Count = append(read1Count, sum(patient1[one,]$normalized_read_count))
     read2Count = append(read2Count, sum(patient2[two,]$normalized_read_count))
     res1 = append(res1, sum(one))
@@ -135,21 +136,21 @@
     #threshhold = 0
     if(threshhold != 0){
       if(sum(one) > 0){
-        dfOne = patient1[one,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "CDR3_Sense_Sequence", "Related_to_leukemia_clone")]
-        colnames(dfOne) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "CDR3 Sequence", "Related_to_leukemia_clone")
+        dfOne = patient1[one,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "Clone_Sequence", "Related_to_leukemia_clone")]
+        colnames(dfOne) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "Clone Sequence", "Related_to_leukemia_clone")
         filenameOne = paste(oneSample, "_", product[iter, titleIndex], "_", threshhold, sep="")
         write.table(dfOne, file=paste(filenameOne, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
       }
       if(sum(two) > 0){
-        dfTwo = patient2[two,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "CDR3_Sense_Sequence", "Related_to_leukemia_clone")]
-        colnames(dfTwo) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "CDR3 Sequence", "Related_to_leukemia_clone")
+        dfTwo = patient2[two,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "Clone_Sequence", "Related_to_leukemia_clone")]
+        colnames(dfTwo) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "Clone Sequence", "Related_to_leukemia_clone")
         filenameTwo = paste(twoSample, "_", product[iter, titleIndex], "_", threshhold, sep="")
         write.table(dfTwo, file=paste(filenameTwo, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
       }
     }
     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", "CDR3_Sense_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),"CDR3 Sequence", paste("Proximal segment", twoSample), paste("Distal segment", twoSample), paste("Normalized_Read_Count", twoSample), paste("Frequency", twoSample), paste("Related_to_leukemia_clone", twoSample))
+      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))
       filenameBoth = paste(oneSample, "_", twoSample, "_", product[iter, titleIndex], "_", threshhold, sep="")
       write.table(dfBoth, file=paste(filenameBoth, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
     }
@@ -242,9 +243,9 @@
   #patient2$merge = paste(patient2$V_Segment_Major_Gene, patient2$J_Segment_Major_Gene, patient2$CDR3_Sense_Sequence)
   #patient3$merge = paste(patient3$V_Segment_Major_Gene, patient3$J_Segment_Major_Gene, patient3$CDR3_Sense_Sequence)
   
-  patient1$merge = paste(patient1$CDR3_Sense_Sequence)
-  patient2$merge = paste(patient2$CDR3_Sense_Sequence)
-  patient3$merge = paste(patient3$CDR3_Sense_Sequence)
+  patient1$merge = paste(patient1$Clone_Sequence)
+  patient2$merge = paste(patient2$Clone_Sequence)
+  patient3$merge = paste(patient3$Clone_Sequence)
   
   patientMerge = merge(patient1, patient2, by="merge")
   patientMerge = merge(patientMerge, patient3, by="merge")
@@ -265,9 +266,9 @@
     V_Segment = paste(".*", as.character(product[iter,V_SegmentIndex]), ".*", sep="")
     J_Segment = paste(".*", as.character(product[iter,J_SegmentIndex]), ".*", sep="")
     all = (grepl(V_Segment, patientMerge$V_Segment_Major_Gene.x) & grepl(J_Segment, patientMerge$J_Segment_Major_Gene.x) & patientMerge[,paste(on, ".x", sep="")] > threshhold & patientMerge[,paste(on, ".y", sep="")] > threshhold & patientMerge[,paste(on, ".z", sep="")] > threshhold)
-    one = (grepl(V_Segment, patient1$V_Segment_Major_Gene) & grepl(J_Segment, patient1$J_Segment_Major_Gene) & patient1[,on] > threshhold & !(patient1$CDR3_Sense_Sequence %in% patientMerge[all,]$CDR3_Sense_Sequence.x))
-    two = (grepl(V_Segment, patient2$V_Segment_Major_Gene) & grepl(J_Segment, patient2$J_Segment_Major_Gene) & patient2[,on] > threshhold & !(patient2$CDR3_Sense_Sequence %in% patientMerge[all,]$CDR3_Sense_Sequence.x))
-    three = (grepl(V_Segment, patient3$V_Segment_Major_Gene) & grepl(J_Segment, patient3$J_Segment_Major_Gene) & patient3[,on] > threshhold & !(patient3$CDR3_Sense_Sequence %in% patientMerge[all,]$CDR3_Sense_Sequence.x))
+    one = (grepl(V_Segment, patient1$V_Segment_Major_Gene) & grepl(J_Segment, patient1$J_Segment_Major_Gene) & patient1[,on] > threshhold & !(patient1$Clone_Sequence %in% patientMerge[all,]$Clone_Sequence.x))
+    two = (grepl(V_Segment, patient2$V_Segment_Major_Gene) & grepl(J_Segment, patient2$J_Segment_Major_Gene) & patient2[,on] > threshhold & !(patient2$Clone_Sequence %in% patientMerge[all,]$Clone_Sequence.x))
+    three = (grepl(V_Segment, patient3$V_Segment_Major_Gene) & grepl(J_Segment, patient3$J_Segment_Major_Gene) & patient3[,on] > threshhold & !(patient3$Clone_Sequence %in% patientMerge[all,]$Clone_Sequence.x))
     
     read1Count = append(read1Count, sum(patient1[one,]$normalized_read_count))
     read2Count = append(read2Count, sum(patient2[two,]$normalized_read_count))
@@ -279,27 +280,27 @@
     #threshhold = 0
     if(threshhold != 0){
       if(sum(one) > 0){
-        dfOne = patient1[one,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "CDR3_Sense_Sequence", "Related_to_leukemia_clone")]
-        colnames(dfOne) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "Sequence", "Related_to_leukemia_clone")
+        dfOne = patient1[one,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "Clone_Sequence", "Related_to_leukemia_clone")]
+        colnames(dfOne) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "Clone Sequence", "Related_to_leukemia_clone")
         filenameOne = paste(label1, "_", product[iter, titleIndex], "_", threshhold, sep="")
         write.table(dfOne, file=paste(filenameOne, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
       }
       if(sum(two) > 0){
-        dfTwo = patient2[two,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "CDR3_Sense_Sequence", "Related_to_leukemia_clone")]
-        colnames(dfTwo) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "Sequence", "Related_to_leukemia_clone")
+        dfTwo = patient2[two,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "Clone_Sequence", "Related_to_leukemia_clone")]
+        colnames(dfTwo) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "Clone Sequence", "Related_to_leukemia_clone")
         filenameTwo = paste(label2, "_", product[iter, titleIndex], "_", threshhold, sep="")
         write.table(dfTwo, file=paste(filenameTwo, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
       }
       if(sum(three) > 0){
-        dfThree = patient3[three,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "CDR3_Sense_Sequence", "Related_to_leukemia_clone")]
-        colnames(dfThree) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "Sequence", "Related_to_leukemia_clone")
+        dfThree = patient3[three,c("V_Segment_Major_Gene", "J_Segment_Major_Gene", "normalized_read_count", "Frequency", "Clone_Sequence", "Related_to_leukemia_clone")]
+        colnames(dfThree) = c("Proximal segment", "Distal segment", "normalized_read_count", "Frequency", "Clone Sequence", "Related_to_leukemia_clone")
         filenameThree = paste(label3, "_", product[iter, titleIndex], "_", threshhold, sep="")
         write.table(dfThree, file=paste(filenameThree, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
       }
     }
     if(sum(all) > 0){
-      dfAll = patientMerge[all,c("V_Segment_Major_Gene.x", "J_Segment_Major_Gene.x", "normalized_read_count.x", "Frequency.x", "Related_to_leukemia_clone.x", "CDR3_Sense_Sequence.x", "V_Segment_Major_Gene.y", "J_Segment_Major_Gene.y", "normalized_read_count.y", "Frequency.y", "Related_to_leukemia_clone.y", "V_Segment_Major_Gene.z", "J_Segment_Major_Gene.z", "normalized_read_count.z", "Frequency.z", "Related_to_leukemia_clone.z")]
-      colnames(dfAll) = c(paste("Proximal segment", oneSample), paste("Distal segment", oneSample), paste("Normalized_Read_Count", oneSample), paste("Frequency", oneSample), paste("Related_to_leukemia_clone", oneSample),"CDR3_Sense_Sequence", paste("Proximal segment", twoSample), paste("Distal segment", twoSample), paste("Normalized_Read_Count", twoSample), paste("Frequency", twoSample), paste("Related_to_leukemia_clone", twoSample), paste("Proximal segment", threeSample), paste("Distal segment", threeSample), paste("Normalized_Read_Count", threeSample), paste("Frequency", threeSample), paste("Related_to_leukemia_clone", threeSample))
+      dfAll = patientMerge[all,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", "V_Segment_Major_Gene.z", "J_Segment_Major_Gene.z", "normalized_read_count.z", "Frequency.z", "Related_to_leukemia_clone.z")]
+      colnames(dfAll) = 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), paste("Proximal segment", threeSample), paste("Distal segment", threeSample), paste("Normalized_Read_Count", threeSample), paste("Frequency", threeSample), paste("Related_to_leukemia_clone", threeSample))
       filenameAll = paste(label1, "_", label2, "_", label3, "_", product[iter, titleIndex], "_", threshhold, sep="")
       write.table(dfAll, file=paste(filenameAll, ".txt", sep=""), quote=F, sep="\t", dec=",", row.names=F, col.names=T)
     }