changeset 1:b360a373835f draft

Uploaded

--- a/imgt_concatenate.sh	Mon Aug 29 05:46:28 2016 -0400
+++ b/imgt_concatenate.sh	Thu Nov 24 10:27:14 2016 -0500
@@ -32,37 +32,43 @@
 	indir=$1
 	outdir=$2
 	start_line=$3 #line # to start at, 2 to skip header
-	cat `find $indir/ -name "1_*"` | tail -n+${start_line} >> "$outdir/1_Summary.txt"
-	cat `find $indir/ -name "2_*"` | tail -n+${start_line} >> "$outdir/2_IMGT-gapped-nt-sequences.txt"
-	cat `find $indir/ -name "3_*"` | tail -n+${start_line} >> "$outdir/3_Nt-sequences.txt"
-	cat `find $indir/ -name "4_*"` | tail -n+${start_line} >> "$outdir/4_IMGT-gapped-AA-sequences.txt"
-	cat `find $indir/ -name "5_*"` | tail -n+${start_line} >> "$outdir/5_AA-sequences.txt"
-	cat `find $indir/ -name "6_*"` | tail -n+${start_line} >> "$outdir/6_Junction.txt"
-	cat `find $indir/ -name "7_*"` | tail -n+${start_line} >> "$outdir/7_V-REGION-mutation-and-AA-change-table.txt"
-	cat `find $indir/ -name "8_*"` | tail -n+${start_line} >> "$outdir/8_V-REGION-nt-mutation-statistics.txt"
-	cat `find $indir/ -name "9_*"` | tail -n+${start_line} >> "$outdir/9_V-REGION-AA-change-statistics.txt"
-	cat `find $indir/ -name "10_*"` | tail -n+${start_line} >> "$outdir/10_V-REGION-mutation-hotspots.txt"
+	id=$4
+	cat `find $indir/ -name "1_*"` | tail -n+${start_line} | awk -v id=$id '{ if($1 !~ /^header/) {$2=$2id; } print}' >> "$outdir/1_Summary.txt"
+	cat `find $indir/ -name "2_*"` | tail -n+${start_line} | awk -v id=$id '{ if($1 !~ /^header/) {$2=$2id; } print}' >> "$outdir/2_IMGT-gapped-nt-sequences.txt"
+	cat `find $indir/ -name "3_*"` | tail -n+${start_line} | awk -v id=$id '{ if($1 !~ /^header/) {$2=$2id; } print}' >> "$outdir/3_Nt-sequences.txt"
+	cat `find $indir/ -name "4_*"` | tail -n+${start_line} | awk -v id=$id '{ if($1 !~ /^header/) {$2=$2id; } print}' >> "$outdir/4_IMGT-gapped-AA-sequences.txt"
+	cat `find $indir/ -name "5_*"` | tail -n+${start_line} | awk -v id=$id '{ if($1 !~ /^header/) {$2=$2id; } print}' >> "$outdir/5_AA-sequences.txt"
+	cat `find $indir/ -name "6_*"` | tail -n+${start_line} | awk -v id=$id '{ if($1 !~ /^header/) {$2=$2id; } print}' >> "$outdir/6_Junction.txt"
+	cat `find $indir/ -name "7_*"` | tail -n+${start_line} | awk -v id=$id '{ if($1 !~ /^header/) {$2=$2id; } print}' >> "$outdir/7_V-REGION-mutation-and-AA-change-table.txt"
+	cat `find $indir/ -name "8_*"` | tail -n+${start_line} | awk -v id=$id '{ if($1 !~ /^header/) {$2=$2id; } print}' >> "$outdir/8_V-REGION-nt-mutation-statistics.txt"
+	cat `find $indir/ -name "9_*"` | tail -n+${start_line} | awk -v id=$id '{ if($1 !~ /^header/) {$2=$2id; } print}' >> "$outdir/9_V-REGION-AA-change-statistics.txt"
+	cat `find $indir/ -name "10_*"` | tail -n+${start_line} | awk -v id=$id '{ if($1 !~ /^header/) {$2=$2id; } print}' >> "$outdir/10_V-REGION-mutation-hotspots.txt"
 }
 
 echo "Unpacking IMGT file 1.."
 imgt_unpack ${inputs[0]} "$workdir/input1"
 
 echo "Concatenating IMGT file 1..."
-concat_imgt_files "$workdir/input1" "$workdir/output" 1
+id=${inputs[1]}
+concat_imgt_files "$workdir/input1" "$workdir/output" 1 $id
 
-remaining_inputs=("${inputs[@]:1}")
+remaining_inputs=("${inputs[@]:2}")
 
-i="2"
-for input in "${remaining_inputs[@]}"
-do
-	echo "Unpacking IMGT file $i.."
+i="0"
+while [ $i -lt ${#remaining_inputs[@]} ]; do
+	j=$((i+1))
+	input="${remaining_inputs[$i]}"
+	id="${remaining_inputs[$j]}"
+	
+	echo "Unpacking IMGT file $j.."
 	current_dir="$workdir/input${i}"
 	imgt_unpack "${input}" "${current_dir}"
 	echo "Concatenating IMGT file $1..."
-	concat_imgt_files "${current_dir}" "$workdir/output" 2
-	i=$((i+1))
+	concat_imgt_files "${current_dir}" "$workdir/output" 2 $id
+	i=$((i+2))
 done
 
+
 echo "Creating new IMGT zip"
 cd "$workdir/output"
 tar cfJ "$output" *
@@ -70,3 +76,17 @@
 #awk to fix the sequence numbers repeating?
 
 echo "Done"
+
+exit 0
+
+i="1"
+for input in "${remaining_inputs[@]}"
+do
+	echo "Unpacking IMGT file $i.."
+	current_dir="$workdir/input${i}"
+	imgt_unpack "${input}" "${current_dir}"
+	echo "Concatenating IMGT file $1..."
+	concat_imgt_files "${current_dir}" "$workdir/output" 2 $id
+	i=$((i+1))
+done
+

--- a/imgt_concatenate.xml	Mon Aug 29 05:46:28 2016 -0400
+++ b/imgt_concatenate.xml	Thu Nov 24 10:27:14 2016 -0500
@@ -2,16 +2,40 @@
 	<description> </description>
 	<command interpreter="bash">
 		imgt_concatenate.sh $out_file 
-#for $i, $f in enumerate($files)
- "$f.file"
-#end for
+#if str( $with_id.with_id_selector ) == "true":
+	#for $i, $f in enumerate($with_id.files)
+	 "$f.file"
+	 "$f.id"
+	#end for
+#else
+	#for $i, $f in enumerate($with_id.files)
+	 "$f.file"
+	 ""
+	#end for
+#end if
 	</command>
 	<inputs>
-		<repeat name="files" title="Sample" min="2" default="2">
-			<param name="file" format="peptideshaker_archive" type="data" label="IMGT zip file" />
-		</repeat>
+		<conditional name="with_id">
+			<param name="with_id_selector" type="select" label="Add a file ID to the sequence ID">
+				<option value="true">Add file ID to SequenceID to identify the origin file</option>
+				<option value="false" selected="True">Keep SequenceID as is</option>
+			</param>
+			<when value='true'>
+				<repeat name="files" title="Sample" min="2" default="2">
+					<param name="file" format="peptideshaker_archive" type="data" label="IMGT zip file" />
+					<param name="id" type="text" label="ID for dataset" size="25">
+						<validator type="regex" message="Fill in an ID">.+</validator>
+					</param>
+				</repeat>
+			</when>
+			<when value='false'>
+				<repeat name="files" title="Sample" min="2" default="2">
+					<param name="file" format="peptideshaker_archive" type="data" label="IMGT zip file" />
+				</repeat>
+			</when>
+		</conditional>
 		<param name="label" type="text" label="A name for the new dataset" size="25">
-			<validator type="length" message="Fill in a name for the new dataset" min="1" />
+			<validator type="regex" message="Fill in a name for the new dataset">.+</validator>
 		</param>
 	</inputs>
 	<outputs>