Mercurial > repos > davidvanzessen > shm_csr

changeset 16:4e596473c25c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Wed, 23 Nov 2016 09:05:40 -0500
parents 61d0a6318711
children b95fa7e426c3
files merge_and_filter.r shm_csr.py wrapper.sh
diffstat 3 files changed, 57 insertions(+), 44 deletions(-) [+]
line wrap: on
line diff
--- a/merge_and_filter.r	Thu Nov 17 07:33:21 2016 -0500
+++ b/merge_and_filter.r	Wed Nov 23 09:05:40 2016 -0500
@@ -96,6 +96,8 @@
 result$JGene = gsub("^Homsap ", "", result$J.GENE.and.allele)
 result$JGene = gsub("[*].*", "", result$JGene)
 
+print(result[result$Sequence.ID == "JY8QFUQ01C310D",c("Sequence.ID","best_match")])
+
 splt = strsplit(class.filter, "_")[[1]]
 chunk_hit_threshold = as.numeric(splt[1])
 nt_hit_threshold = as.numeric(splt[2])
@@ -110,6 +112,8 @@
 	result$best_match = "all"
 }
 
+print(result[result$Sequence.ID == "JY8QFUQ01C310D",c("Sequence.ID","best_match")])
+
 write.table(x=result, file=gsub("merged.txt$", "before_filters.txt", output), sep="\t",quote=F,row.names=F,col.names=T)
 
 print(paste("Number of empty CDR1 sequences:", sum(result$CDR1.IMGT.seq == "")))
@@ -135,6 +139,8 @@
 	filtering.steps = rbind(filtering.steps, c("After empty CDR2, FR3 filter", nrow(result)))
 }
 
+print(result[result$Sequence.ID == "JY8QFUQ01C310D",c("Sequence.ID","best_match")])
+
 if(empty.region.filter == "leader"){
 	result = result[!(grepl("n|N", result$FR1.IMGT.seq) | grepl("n|N", result$FR2.IMGT.seq) | grepl("n|N", result$FR3.IMGT.seq) | grepl("n|N", result$CDR1.IMGT.seq) | grepl("n|N", result$CDR2.IMGT.seq) | grepl("n|N", result$CDR3.IMGT.seq)),]
 } else if(empty.region.filter == "FR1"){
@@ -145,6 +151,9 @@
 	result = result[!(grepl("n|N", result$FR3.IMGT.seq) | grepl("n|N", result$CDR2.IMGT.seq) | grepl("n|N", result$CDR3.IMGT.seq)),]
 }
 
+print(result[result$Sequence.ID == "JY8QFUQ01C310D",c("Sequence.ID","best_match")])
+print(result[result$Sequence.ID == "JY8QFUQ01BNS72",c("Sequence.ID","best_match")])
+
 print(paste("Number of sequences in result after n filtering:", nrow(result)))
 filtering.steps = rbind(filtering.steps, c("After N filter", nrow(result)))
 
@@ -183,6 +192,9 @@
 	result = result[!duplicated(result$unique.def),]
 }
 
+print(result[result$Sequence.ID == "JY8QFUQ01C310D",c("Sequence.ID","best_match")])
+print(result[result$Sequence.ID == "JY8QFUQ01BNS72",c("Sequence.ID","best_match")])
+
 write.table(result, gsub("before_unique_filter.txt", "after_unique_filter.txt", before.unique.file), sep="\t", quote=F,row.names=F,col.names=T)
 
 filtering.steps = rbind(filtering.steps, c("After filter unique sequences", nrow(result)))
@@ -207,7 +219,7 @@
 
 
 
-
+print(result[result$Sequence.ID == "JY8QFUQ01C310D",c("Sequence.ID","best_match")])
 
 
 result = result[,!(names(result) %in% c("past", "best_match_class"))]
--- a/shm_csr.py	Thu Nov 17 07:33:21 2016 -0500
+++ b/shm_csr.py	Wed Nov 23 09:05:40 2016 -0500
@@ -284,4 +284,5 @@
 with open(seq_motif_file, 'w') as o:
 	o.write("ID\tRGYWC\tWRCY\tWA\tTW\n")
 	for ID in IDlist:
-		o.write(ID + "\t" + str(round(RGYWCount[ID], 2)) + "\t" + str(round(WRCYCount[ID], 2)) + "\t" + str(round(WACount[ID], 2)) + "\t" + str(round(TWCount[ID], 2)) + "\n")
+		#o.write(ID + "\t" + str(round(RGYWCount[ID], 2)) + "\t" + str(round(WRCYCount[ID], 2)) + "\t" + str(round(WACount[ID], 2)) + "\t" + str(round(TWCount[ID], 2)) + "\n")
+		o.write(ID + "\t" + str(RGYWCount[ID]) + "\t" + str(WRCYCount[ID]) + "\t" + str(WACount[ID]) + "\t" + str(TWCount[ID]) + "\n")
--- a/wrapper.sh	Thu Nov 17 07:33:21 2016 -0500
+++ b/wrapper.sh	Wed Nov 23 09:05:40 2016 -0500
@@ -447,58 +447,58 @@
 
 	PWD="$tmp"
 
-echo "<div class='tabbertab' title='Clonality'>" >> $output #clonality tab
+	echo "<div class='tabbertab' title='Clonality'>" >> $output #clonality tab
 
-function clonality_table {
-	local infile=$1
-	local outfile=$2
-	
-	echo "<table class='pure-table pure-table-striped'>" >> $outfile
-	echo "<thead><tr><th>Clone size</th><th>Nr of clones</th><th>Nr of sequences</th></tr></thead>" >> $outfile
-	
-	first='true'
-	
-	while read size clones seqs
-	do
-		if [[ "$first" == "true" ]]; then
-			first="false"
-			continue
-		fi
-		echo "<tr><td>$size</td><td>$clones</td><td>$seqs</td></tr>" >> $outfile
-	done < $infile
-	
-	echo "</table>" >> $outfile
-}
-echo "<div class='tabber'>" >> $output
+	function clonality_table {
+		local infile=$1
+		local outfile=$2
+		
+		echo "<table class='pure-table pure-table-striped'>" >> $outfile
+		echo "<thead><tr><th>Clone size</th><th>Nr of clones</th><th>Nr of sequences</th></tr></thead>" >> $outfile
+		
+		first='true'
+		
+		while read size clones seqs
+		do
+			if [[ "$first" == "true" ]]; then
+				first="false"
+				continue
+			fi
+			echo "<tr><td>$size</td><td>$clones</td><td>$seqs</td></tr>" >> $outfile
+		done < $infile
+		
+		echo "</table>" >> $outfile
+	}
+	echo "<div class='tabber'>" >> $output
 
-echo "<div class='tabbertab' title='All'>" >> $output
-clonality_table $outdir/change_o/change-o-defined_clones-summary.txt $output
-echo "</div>" >> $output
+	echo "<div class='tabbertab' title='All'>" >> $output
+	clonality_table $outdir/change_o/change-o-defined_clones-summary.txt $output
+	echo "</div>" >> $output
 
-echo "<div class='tabbertab' title='IGA'>" >> $output
-clonality_table $outdir/change_o/change-o-defined_clones-summary-IGA.txt $output
-echo "</div>" >> $output
+	echo "<div class='tabbertab' title='IGA'>" >> $output
+	clonality_table $outdir/change_o/change-o-defined_clones-summary-IGA.txt $output
+	echo "</div>" >> $output
 
-echo "<div class='tabbertab' title='IGG'>" >> $output
-clonality_table $outdir/change_o/change-o-defined_clones-summary-IGG.txt $output
-echo "</div>" >> $output
+	echo "<div class='tabbertab' title='IGG'>" >> $output
+	clonality_table $outdir/change_o/change-o-defined_clones-summary-IGG.txt $output
+	echo "</div>" >> $output
 
-echo "<div class='tabbertab' title='IGM'>" >> $output
-clonality_table $outdir/change_o/change-o-defined_clones-summary-IGM.txt $output
-echo "</div>" >> $output
+	echo "<div class='tabbertab' title='IGM'>" >> $output
+	clonality_table $outdir/change_o/change-o-defined_clones-summary-IGM.txt $output
+	echo "</div>" >> $output
 
-echo "<div class='tabbertab' title='IGE'>" >> $output
-clonality_table $outdir/change_o/change-o-defined_clones-summary-IGM.txt $output
-echo "</div>" >> $output
+	echo "<div class='tabbertab' title='IGE'>" >> $output
+	clonality_table $outdir/change_o/change-o-defined_clones-summary-IGM.txt $output
+	echo "</div>" >> $output
 
-echo "<div class='tabbertab' title='Overview'>" >> $output
-cat "$outdir/sequence_overview/index.html" >> $output
-echo "</div>" >> $output
+	echo "<div class='tabbertab' title='Overview'>" >> $output
+	cat "$outdir/sequence_overview/index.html" >> $output
+	echo "</div>" >> $output
 
 
-echo "</div>" >> $output #clonality tabber end
+	echo "</div>" >> $output #clonality tabber end
 
-echo "</div>" >> $output #clonality tab end
+	echo "</div>" >> $output #clonality tab end
 
 fi