# HG changeset patch
# User davidvanzessen
# Date 1443442113 14400
# Node ID 1b5b862b055b9042b9c4dc233def5a6b73582f71
# Parent  2cf89b8652024c2359a14eea82602034a1c262b1
Uploaded

diff -r 2cf89b865202 -r 1b5b862b055b RScript.r
--- a/RScript.r	Thu Sep 17 11:01:20 2015 -0400
+++ b/RScript.r	Mon Sep 28 08:08:33 2015 -0400
@@ -159,8 +159,11 @@
     #patient1.fuzzy$merge = paste(patient1.fuzzy$V_Segment_Major_Gene, patient1.fuzzy$J_Segment_Major_Gene, patient1.fuzzy$CDR3_Sense_Sequence)
     #patient2.fuzzy$merge = paste(patient2.fuzzy$V_Segment_Major_Gene, patient2.fuzzy$J_Segment_Major_Gene, patient2.fuzzy$CDR3_Sense_Sequence)
     
-    patient1.fuzzy$merge = paste(patient1.fuzzy$locus_V, patient1.fuzzy$locus_J, patient1.fuzzy$CDR3_Sense_Sequence)
-    patient2.fuzzy$merge = paste(patient2.fuzzy$locus_V, patient2.fuzzy$locus_J, patient2.fuzzy$CDR3_Sense_Sequence)
+    #patient1.fuzzy$merge = paste(patient1.fuzzy$locus_V, patient1.fuzzy$locus_J, patient1.fuzzy$CDR3_Sense_Sequence)
+    #patient2.fuzzy$merge = paste(patient2.fuzzy$locus_V, patient2.fuzzy$locus_J, patient2.fuzzy$CDR3_Sense_Sequence)
+    
+    patient1.fuzzy$merge = paste(patient1.fuzzy$locus_V, patient1.fuzzy$locus_J)
+    patient2.fuzzy$merge = paste(patient2.fuzzy$locus_V, patient2.fuzzy$locus_J)
     
     merge.freq.table = data.frame(table(c(patient1.fuzzy[!duplicated(patient1.fuzzy$merge),"merge"], patient2.fuzzy[!duplicated(patient2.fuzzy$merge),"merge"])))
     merge.freq.table.gt.1 = merge.freq.table[merge.freq.table$Freq > 1,]
@@ -181,8 +184,10 @@
       
       sample.filter = patient.fuzzy[1,"Sample"] != patient.fuzzy$Sample
       
+      sequence.filter = grepl(paste("^", first.clone.sequence, sep=""), patient.fuzzy$Clone_Sequence)
+      
       #match.filter = merge.filter & grepl(first.clone.sequence, patient.fuzzy$Clone_Sequence) & length.filter & sample.filter
-      match.filter = merge.filter & grepl(first.clone.sequence, patient.fuzzy$Clone_Sequence) & sample.filter
+      match.filter = merge.filter & sequence.filter & sample.filter
       
       if(sum(match.filter) == 1){
         second.match = which(match.filter)[1]
@@ -190,64 +195,59 @@
         first.sample = patient.fuzzy[1,"Sample"]
         second.sample = patient.fuzzy[second.match,"Sample"]
         
-        if(((nchar(second.clone.sequence) - nchar(first.clone.sequence)) <= 9) & (first.sample != second.sample)){
-          first.match.row = patient.fuzzy[1,]
-          second.match.row = patient.fuzzy[second.match,]
-          print(paste(first.merge, first.match.row$normalized_read_count, second.match.row$normalized_read_count, first.clone.sequence, second.clone.sequence))
-          patientMerge.new.row = data.frame(merge=first.clone.sequence,
-                                            min_cell_paste.x=first.match.row[1,"min_cell_paste"],
-                                            Patient.x=first.match.row[1,"Patient"],
-                                            Receptor.x=first.match.row[1,"Receptor"],
-                                            Sample.x=first.match.row[1,"Sample"],
-                                            Cell_Count.x=first.match.row[1,"Cell_Count"],
-                                            Clone_Molecule_Count_From_Spikes.x=first.match.row[1,"Clone_Molecule_Count_From_Spikes"],
-                                            Log10_Frequency.x=first.match.row[1,"Log10_Frequency"],
-                                            Total_Read_Count.x=first.match.row[1,"Total_Read_Count"],
-                                            dsPerM.x=first.match.row[1,"dsPerM"],
-                                            J_Segment_Major_Gene.x=first.match.row[1,"J_Segment_Major_Gene"],
-                                            V_Segment_Major_Gene.x=first.match.row[1,"V_Segment_Major_Gene"],
-                                            Clone_Sequence.x=first.match.row[1,"Clone_Sequence"],
-                                            CDR3_Sense_Sequence.x=first.match.row[1,"CDR3_Sense_Sequence"],
-                                            Related_to_leukemia_clone.x=first.match.row[1,"Related_to_leukemia_clone"],
-                                            Frequency.x=first.match.row[1,"Frequency"],
-                                            locus_V.x=first.match.row[1,"locus_V"],
-                                            locus_J.x=first.match.row[1,"locus_J"],
-                                            min_cell_count.x=first.match.row[1,"min_cell_count"],
-                                            normalized_read_count.x=first.match.row[1,"normalized_read_count"],
-                                            paste.x=first.match.row[1,"paste"],
-                                            min_cell_paste.y=second.match.row[1,"min_cell_paste"],
-                                            Patient.y=second.match.row[1,"Patient"],
-                                            Receptor.y=second.match.row[1,"Receptor"],
-                                            Sample.y=second.match.row[1,"Sample"],
-                                            Cell_Count.y=second.match.row[1,"Cell_Count"],
-                                            Clone_Molecule_Count_From_Spikes.y=second.match.row[1,"Clone_Molecule_Count_From_Spikes"],
-                                            Log10_Frequency.y=second.match.row[1,"Log10_Frequency"],
-                                            Total_Read_Count.y=second.match.row[1,"Total_Read_Count"],
-                                            dsPerM.y=second.match.row[1,"dsPerM"],
-                                            J_Segment_Major_Gene.y=second.match.row[1,"J_Segment_Major_Gene"],
-                                            V_Segment_Major_Gene.y=second.match.row[1,"V_Segment_Major_Gene"],
-                                            Clone_Sequence.y=second.match.row[1,"Clone_Sequence"],
-                                            CDR3_Sense_Sequence.y=second.match.row[1,"CDR3_Sense_Sequence"],
-                                            Related_to_leukemia_clone.y=second.match.row[1,"Related_to_leukemia_clone"],
-                                            Frequency.y=second.match.row[1,"Frequency"],
-                                            locus_V.y=second.match.row[1,"locus_V"],
-                                            locus_J.y=second.match.row[1,"locus_J"],
-                                            min_cell_count.y=second.match.row[1,"min_cell_count"],
-                                            normalized_read_count.y=second.match.row[1,"normalized_read_count"],
-                                            paste.y=first.match.row[1,"paste"])
-          
-          
-          patientMerge = rbind(patientMerge, patientMerge.new.row)
-          patient.fuzzy = patient.fuzzy[-match.filter,]
-          
-          patient1 = patient1[!(patient1$Clone_Sequence %in% c(first.clone.sequence, second.clone.sequence)),]
-          patient2 = patient2[!(patient2$Clone_Sequence %in% c(first.clone.sequence, second.clone.sequence)),]
-          
-          scatterplot_data = scatterplot_data[scatterplot_data$merge != second.clone.sequence,]
-          
-        } else {
-					patient.fuzzy = patient.fuzzy[-1,]
-        }
+				first.match.row = patient.fuzzy[1,]
+				second.match.row = patient.fuzzy[second.match,]
+				print(paste(first.merge, first.match.row$normalized_read_count, second.match.row$normalized_read_count, first.clone.sequence, second.clone.sequence))
+				patientMerge.new.row = data.frame(merge=first.clone.sequence,
+																					min_cell_paste.x=first.match.row[1,"min_cell_paste"],
+																					Patient.x=first.match.row[1,"Patient"],
+																					Receptor.x=first.match.row[1,"Receptor"],
+																					Sample.x=first.match.row[1,"Sample"],
+																					Cell_Count.x=first.match.row[1,"Cell_Count"],
+																					Clone_Molecule_Count_From_Spikes.x=first.match.row[1,"Clone_Molecule_Count_From_Spikes"],
+																					Log10_Frequency.x=first.match.row[1,"Log10_Frequency"],
+																					Total_Read_Count.x=first.match.row[1,"Total_Read_Count"],
+																					dsPerM.x=first.match.row[1,"dsPerM"],
+																					J_Segment_Major_Gene.x=first.match.row[1,"J_Segment_Major_Gene"],
+																					V_Segment_Major_Gene.x=first.match.row[1,"V_Segment_Major_Gene"],
+																					Clone_Sequence.x=first.match.row[1,"Clone_Sequence"],
+																					CDR3_Sense_Sequence.x=first.match.row[1,"CDR3_Sense_Sequence"],
+																					Related_to_leukemia_clone.x=first.match.row[1,"Related_to_leukemia_clone"],
+																					Frequency.x=first.match.row[1,"Frequency"],
+																					locus_V.x=first.match.row[1,"locus_V"],
+																					locus_J.x=first.match.row[1,"locus_J"],
+																					min_cell_count.x=first.match.row[1,"min_cell_count"],
+																					normalized_read_count.x=first.match.row[1,"normalized_read_count"],
+																					paste.x=first.match.row[1,"paste"],
+																					min_cell_paste.y=second.match.row[1,"min_cell_paste"],
+																					Patient.y=second.match.row[1,"Patient"],
+																					Receptor.y=second.match.row[1,"Receptor"],
+																					Sample.y=second.match.row[1,"Sample"],
+																					Cell_Count.y=second.match.row[1,"Cell_Count"],
+																					Clone_Molecule_Count_From_Spikes.y=second.match.row[1,"Clone_Molecule_Count_From_Spikes"],
+																					Log10_Frequency.y=second.match.row[1,"Log10_Frequency"],
+																					Total_Read_Count.y=second.match.row[1,"Total_Read_Count"],
+																					dsPerM.y=second.match.row[1,"dsPerM"],
+																					J_Segment_Major_Gene.y=second.match.row[1,"J_Segment_Major_Gene"],
+																					V_Segment_Major_Gene.y=second.match.row[1,"V_Segment_Major_Gene"],
+																					Clone_Sequence.y=second.match.row[1,"Clone_Sequence"],
+																					CDR3_Sense_Sequence.y=second.match.row[1,"CDR3_Sense_Sequence"],
+																					Related_to_leukemia_clone.y=second.match.row[1,"Related_to_leukemia_clone"],
+																					Frequency.y=second.match.row[1,"Frequency"],
+																					locus_V.y=second.match.row[1,"locus_V"],
+																					locus_J.y=second.match.row[1,"locus_J"],
+																					min_cell_count.y=second.match.row[1,"min_cell_count"],
+																					normalized_read_count.y=second.match.row[1,"normalized_read_count"],
+																					paste.y=first.match.row[1,"paste"])
+				
+				
+				patientMerge = rbind(patientMerge, patientMerge.new.row)
+				patient.fuzzy = patient.fuzzy[-match.filter,]
+				
+				patient1 = patient1[!(patient1$Clone_Sequence %in% c(first.clone.sequence, second.clone.sequence)),]
+				patient2 = patient2[!(patient2$Clone_Sequence %in% c(first.clone.sequence, second.clone.sequence)),]
+				
+				scatterplot_data = scatterplot_data[scatterplot_data$merge != second.clone.sequence,]
 				
       } else if (sum(match.filter) > 1){
 				cat(paste("<tr><td>", "Multiple matches (", sum(match.filter), ") found for", first.merge, "in", patient, "</td></tr>", sep=" "), file=logfile, append=T)