Mercurial > repos > davidvanzessen > argalaxy_tools

changeset 38:b6936fb52ab9 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Wed, 19 Apr 2017 10:21:01 -0400
parents f37e072affc0
children bad6a9a53ae7
files report_clonality/RScript.r report_clonality/r_wrapper.sh
diffstat 2 files changed, 17 insertions(+), 22 deletions(-) [+]
line wrap: on
line diff
--- a/report_clonality/RScript.r	Wed Apr 19 08:05:01 2017 -0400
+++ b/report_clonality/RScript.r	Wed Apr 19 10:21:01 2017 -0400
@@ -768,7 +768,7 @@
                                                Total.Del=mean(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
                                                Total.N=mean(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)),
                                                Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
-                                               Median.CDR3.l=as.double(median(as.numeric(.SD$CDR3.Length, na.rm=T)))),
+                                               Median.CDR3.l=as.double(median(as.numeric(.SD$CDR3.Length), na.rm=T))),
                                          by=c("Sample")])
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
   write.table(newData, "junctionAnalysisProd_mean_wD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
@@ -787,7 +787,7 @@
 											   Total.Del=num_median(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
 											   Total.N=num_median(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)),
 											   Total.P=num_median(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
-											   Median.CDR3.l=as.double(median(as.numeric(.SD$CDR3.Length, na.rm=T)))),
+											   Median.CDR3.l=as.double(median(as.numeric(.SD$CDR3.Length), na.rm=T))),
                                          by=c("Sample")])
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
   write.table(newData, "junctionAnalysisProd_median_wD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
@@ -806,7 +806,7 @@
                                                 Total.Del=mean(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
                                                 Total.N=mean(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)),
                                                 Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
-                                                Median.CDR3.l=as.double(as.numeric(median(.SD$CDR3.Length, na.rm=T)))),
+                                                Median.CDR3.l=as.double(median(as.numeric(.SD$CDR3.Length), na.rm=T))),
                                           by=c("Sample")])
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
   write.table(newData, "junctionAnalysisUnProd_mean_wD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
@@ -825,7 +825,7 @@
                                                 Total.Del=num_median(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
                                                 Total.N=num_median(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)),
                                                 Total.P=num_median(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
-                                                Median.CDR3.l=as.double(as.numeric(median(.SD$CDR3.Length, na.rm=T)))),
+                                                Median.CDR3.l=as.double(median(as.numeric(.SD$CDR3.Length), na.rm=T))),
 															by=c("Sample")])
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
   write.table(newData, "junctionAnalysisUnProd_median_wD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
@@ -841,7 +841,7 @@
                                                Total.Del=mean(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
                                                Total.N=mean(.SD$N.REGION.nt.nb, na.rm=T),
                                                Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
-                                               Median.CDR3.l=as.double(as.numeric(median(.SD$CDR3.Length, na.rm=T)))),
+                                               Median.CDR3.l=as.double(median(as.numeric(.SD$CDR3.Length), na.rm=T))),
                                          by=c("Sample")])
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
   write.table(newData, "junctionAnalysisProd_mean_nD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
@@ -855,13 +855,11 @@
 											   Total.Del=num_median(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
 											   Total.N=num_median(.SD$N.REGION.nt.nb, na.rm=T),
 											   Total.P=num_median(rowSums(.SD[,c("P3V.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
-											   Median.CDR3.l=as.double(as.numeric(median(.SD$CDR3.Length, na.rm=T)))),
+											   Median.CDR3.l=as.double(median(as.numeric(.SD$CDR3.Length), na.rm=T))),
                                          by=c("Sample")])
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
   write.table(newData, "junctionAnalysisProd_median_nD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
   
-  print(paste("mean N:", mean(UNPROD.no.D$N.REGION.nt.nb, na.rm=T)))
-  
   newData = data.frame(data.table(UNPROD.no.D)[,list(unique=.N, 
                                                 VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T),
                                                 P1=mean(.SD$P3V.nt.nb, na.rm=T),
@@ -871,12 +869,11 @@
                                                 Total.Del=mean(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
                                                 Total.N=mean(.SD$N.REGION.nt.nb, na.rm=T),
                                                 Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
-                                                Median.CDR3.l=as.double(as.numeric(median(.SD$CDR3.Length, na.rm=T)))),
+                                                Median.CDR3.l=as.double(median(as.numeric(.SD$CDR3.Length), na.rm=T))),
                                           by=c("Sample")])
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
   write.table(newData, "junctionAnalysisUnProd_mean_nD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
   
-  print(paste("median N:", num_median(UNPROD.no.D$N.REGION.nt.nb, na.rm=T)))
   
     newData = data.frame(data.table(UNPROD.no.D)[,list(unique=.N, 
                                                 VH.DEL=num_median(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T),
@@ -887,7 +884,7 @@
                                                 Total.Del=num_median(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
                                                 Total.N=num_median(.SD$N.REGION.nt.nb, na.rm=T),
                                                 Total.P=num_median(rowSums(.SD[,c("P3V.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
-                                                Median.CDR3.l=as.double(as.numeric(median(.SD$CDR3.Length, na.rm=T)))),
+                                                Median.CDR3.l=as.double(median(as.numeric(.SD$CDR3.Length), na.rm=T))),
 															by=c("Sample")])
   newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
   write.table(newData, "junctionAnalysisUnProd_median_nD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
@@ -927,7 +924,6 @@
 
 ggsave("DReadingFrame.pdf", D.REGION.reading.frame)
 
-
 # ---------------------- AA composition in CDR3 ----------------------
 
 AACDR3 = PRODF[,c("Sample", "CDR3.Seq")]
@@ -977,6 +973,7 @@
 
 #generate the "Sequences that are present in more than one replicate" dataset
 clonaltype.in.replicates = inputdata
+clonaltype.in.replicates = clonaltype.in.replicates[clonaltype.in.replicates$Functionality %in% c("productive (see comment)","productive"),]
 clonaltype.in.replicates = na.omit(clonaltype.in.replicates)
 clonaltype = unlist(strsplit(clonaltype, ","))
 
@@ -1023,5 +1020,3 @@
 
 
 
-
-
--- a/report_clonality/r_wrapper.sh	Wed Apr 19 08:05:01 2017 -0400
+++ b/report_clonality/r_wrapper.sh	Wed Apr 19 10:21:01 2017 -0400
@@ -273,28 +273,28 @@
 	echo "<img src='IGH_junctie_analyse.png' />" >> $outputFile
 	
 	echo "<center><p style='font-size: 20;'>Unique rearrangements with a V, D and J gene assigned</p></center>" >> $outputFile
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>CDR3.Length</th><thead></tr><tbody>" >> $outputFile
 	while read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
 	done < $outputDir/junctionAnalysisProd_mean_wD.txt
 	echo "</tbody></table>" >> $outputFile
 	
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>CDR3.Length</th><thead></tr><tbody>" >> $outputFile
 	while read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>-</td></tr>" >> $outputFile
 	done < $outputDir/junctionAnalysisUnProd_mean_wD.txt
 	echo "</tbody></table>" >> $outputFile
 	
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive median</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive median</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>CDR3.Length</th><thead></tr><tbody>" >> $outputFile
 	while read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
 	done < $outputDir/junctionAnalysisProd_median_wD.txt
 	echo "</tbody></table>" >> $outputFile
 	
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive median</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive median</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>CDR3.Length</th><thead></tr><tbody>" >> $outputFile
 	while read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>-</td></tr>" >> $outputFile
@@ -303,28 +303,28 @@
 	
 	# again for no-d
 	echo "<center><p style='font-size: 20;'>Unique rearrangements with only a V and J gene assigned</p></center>" >> $outputFile
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>CDR3.Length</th><thead></tr><tbody>" >> $outputFile
 	while read Sample unique VDEL P1 N1 P2 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
 	done < $outputDir/junctionAnalysisProd_mean_nD.txt
 	echo "</tbody></table>" >> $outputFile
 	
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>CDR3.Length</th><thead></tr><tbody>" >> $outputFile
 	while read Sample unique VDEL P1 N1 P2 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>-</td></tr>" >> $outputFile
 	done < $outputDir/junctionAnalysisUnProd_mean_nD.txt
 	echo "</tbody></table>" >> $outputFile
 	
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive median</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive median</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>CDR3.Length</th><thead></tr><tbody>" >> $outputFile
 	while read Sample unique VDEL P1 N1 P2 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
 	done < $outputDir/junctionAnalysisProd_median_nD.txt
 	echo "</tbody></table>" >> $outputFile
 	
-	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive median</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive median</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>CDR3.Length</th><thead></tr><tbody>" >> $outputFile
 	while read Sample unique VDEL P1 N1 P2 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>-</td></tr>" >> $outputFile