# HG changeset patch
# User davidvanzessen
# Date 1463052907 14400
# Node ID 0513b46178c45c5469a60cee02307dee7a873087
# Parent  b523ce95d85714d7caab9377553de057ec5caf72
Uploaded

diff -r b523ce95d857 -r 0513b46178c4 merge_and_filter.r
--- a/merge_and_filter.r	Wed May 11 10:29:33 2016 -0400
+++ b/merge_and_filter.r	Thu May 12 07:35:07 2016 -0400
@@ -69,7 +69,7 @@
 if(any(higher_than)){
 	#summ = summ[higher_than,]
 }
-print(paste("Number of matched sequences:", nrow(summ)))
+print(paste("Number of matched sequences:", sum(!grepl("^unmatched", summ$best_match))))
 
 if(nrow(summ) == 0){
 	stop("No data remaining after filter")
diff -r b523ce95d857 -r 0513b46178c4 mutation_analysis.xml
--- a/mutation_analysis.xml	Wed May 11 10:29:33 2016 -0400
+++ b/mutation_analysis.xml	Thu May 12 07:35:07 2016 -0400
@@ -33,7 +33,7 @@
 			<option value="AA.JUNCTION">AA.JUNCTION</option>
 			<option value="none">Don't remove duplicates</option>
 		</param>
-		<param name="class_filter" type="select" label="Class/Sublass filter" help="" >
+		<param name="class_filter" type="select" label="Class/Subclass filter" help="" >
 			<option value="70_70" selected="true">>70% class and >70% subclass</option>
 			<option value="70_0">>70% class</option>
 			<option value="60_0">>60% class</option>
diff -r b523ce95d857 -r 0513b46178c4 sequence_overview.r
--- a/sequence_overview.r	Wed May 11 10:29:33 2016 -0400
+++ b/sequence_overview.r	Thu May 12 07:35:07 2016 -0400
@@ -21,11 +21,11 @@
 
 #dat = data.frame(data.table(dat)[, list(freq=.N), by=c("best_match", "seq_conc")])
 
-dat = data.frame(table(dat$best_match, dat$seq_conc))
+dat = data.frame(table(dat$best_match, dat$seq_conc, dat$Functionality))
 
 dat = dat[dat$Freq > 1,]
 
-names(dat) = c("best_match", "seq_conc", "Freq")
+names(dat) = c("best_match", "seq_conc", "Functionality", "Freq")
 
 dat$seq_conc = factor(dat$seq_conc)
 
@@ -39,7 +39,7 @@
 
 cat("<table border='1'>", file=main.html, append=F)
 cat("<caption>CDR1+CDR2+CDR3+FR2+FR3 sequences that show up more than once</caption>", file=main.html, append=T)
-cat("<tr><th>Sequence</th><th>ca1</th><th>ca2</th><th>cg1</th><th>cg2</th><th>cg3</th><th>cg4</th><th>cm</th></tr>", file=main.html, append=T)
+cat("<tr><th>Sequence</th><th>Functionality</th><th>ca1</th><th>ca2</th><th>cg1</th><th>cg2</th><th>cg3</th><th>cg4</th><th>cm</th></tr>", file=main.html, append=T)
 
 for(i in 1:nrow(dat)){
 	ca1 = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "ca1",]
@@ -53,6 +53,8 @@
 	cm = IDs[IDs$seq_conc == dat[i,c("seq_conc")] & IDs$best_match == "cm",]
 	
 	id = as.numeric(dat[i,"seq_conc"])
+	
+	functionality = dat[i,"Functionality"]
 
 	if(nrow(ca1) > 0){
 		cat(tbl(ca1), file=paste("ca1_", id, ".html", sep=""))
@@ -92,7 +94,7 @@
 	
 	cm.html = make.link(id, "cm", nrow(cm))
 	
-	rw = c(as.character(dat[i,"seq_conc"]), ca1.html, ca2.html, cg1.html, cg2.html, cg3.html, cg4.html, cm.html)
+	rw = c(as.character(dat[i,"seq_conc"]), as.character(functionality), ca1.html, ca2.html, cg1.html, cg2.html, cg3.html, cg4.html, cm.html)
 
 	cat(tr(rw), file=main.html, append=T)
 }
diff -r b523ce95d857 -r 0513b46178c4 wrapper.sh
--- a/wrapper.sh	Wed May 11 10:29:33 2016 -0400
+++ b/wrapper.sh	Thu May 12 07:35:07 2016 -0400
@@ -142,7 +142,7 @@
 	done
 	
 	tmp=`cat $outdir/unmatched_${func}_n.txt`
-	echo "<th><a href='unmatched.txt'>unmatched (N = $tmp)</a></th>" >> $output
+	echo "<th><a href='unmatched.txt'>unmatched (N = ${unmatched_count})</a></th>" >> $output
 	tmp=`cat $outdir/all_${func}_n.txt`
 	echo "<th><a href='matched_${func}_all.txt'>all (N = $tmp)</a></th>" >> $output