Add an option to turn off the region filter.

CHANGELOG.md

@@ -1,5 +1,6 @@
 version 1.9.0-dev
 -----------------
++ Add a no filter region filter. 
 + Fix a bug where tar would not open certain filenames.
 
 version 1.8.1

merge_and_filter.r

@@ -183,6 +183,7 @@ if(empty.region.filter == "leader"){
 } else if(empty.region.filter == "FR2"){
 	result = result[result$CDR2.IMGT.seq != "" & result$FR3.IMGT.seq != "", ]
 }
+# If empty region filter is None, nothing happens.
 
 print(paste("After removal sequences that are missing a gene region:", nrow(result)))
 filtering.steps = rbind(filtering.steps, c("After removal sequences that are missing a gene region", nrow(result)))
@@ -219,7 +220,7 @@ if(filter.unique != "no"){
 	clmns = names(result)
 	if(filter.unique == "remove_vjaa"){
 		result$unique.def = paste(result$VGene, result$JGene, result$CDR3.IMGT.AA)
-	} else if(empty.region.filter == "leader"){
+	} else if(empty.region.filter == "leader" || empty.region.filter == "None"){
 		result$unique.def = paste(result$FR1.IMGT.seq, result$CDR1.IMGT.seq, result$FR2.IMGT.seq, result$CDR2.IMGT.seq, result$FR3.IMGT.seq, result$CDR3.IMGT.seq)
 	} else if(empty.region.filter == "FR1"){
 		result$unique.def = paste(result$CDR1.IMGT.seq, result$FR2.IMGT.seq, result$CDR2.IMGT.seq, result$FR3.IMGT.seq, result$CDR3.IMGT.seq)

nt_overview.r

@@ -17,7 +17,7 @@ hotspot.analysis.sum = read.table(hotspot.analysis.sum.file, header=F, sep=",",
 
 NToverview = merged
 
-if(empty.region.filter == "leader"){
+if(empty.region.filter == "leader" || empty.region.filter == "None"){
 	NToverview$seq = paste(NToverview$FR1.IMGT.seq, NToverview$CDR1.IMGT.seq, NToverview$FR2.IMGT.seq, NToverview$CDR2.IMGT.seq, NToverview$FR3.IMGT.seq)
 } else if(empty.region.filter == "FR1"){
 	NToverview$seq = paste(NToverview$CDR1.IMGT.seq, NToverview$FR2.IMGT.seq, NToverview$CDR2.IMGT.seq, NToverview$FR3.IMGT.seq)

sequence_overview.py

@@ -101,7 +101,7 @@ def sequence_overview(before_unique: str,
     sequence_columns = [
         "FR1.IMGT.seq", "CDR1.IMGT.seq", "FR2.IMGT.seq", "CDR2.IMGT.seq",
         "FR3.IMGT.seq", "CDR3.IMGT.seq"]
-    if empty_region_filter == "leader":
+    if empty_region_filter == "leader" or empty_region_filter == "None":
         sequence_columns = sequence_columns
     elif empty_region_filter == "FR1":
         sequence_columns = sequence_columns[1:]

shm_csr.py

@@ -2,14 +2,21 @@
 import logging
 import sys
 import os
+import traceback
 import typing
 from typing import Optional
 
 from collections import defaultdict
 
-REGION_FILTERS = ("leader", "FR1", "CDR1", "FR2", "CDR2")
+REGION_FILTERS = ("leader", "FR1", "CDR1", "FR2", "CDR2", "None")
 
 
+def int_or_zero(value: typing.Any):
+	try:
+		return int(value)
+	except ValueError:
+		return 0
+
 class Mutation(typing.NamedTuple):
 	"""Represent a mutation type as a tuple"""
 	frm: str  # 'from' is a reserved python keyword.
@@ -177,15 +184,15 @@ def main():
 			mutationList += mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"]
 			mutationListByID[ID] = mutationdic[ID + "_FR1"] + mutationdic[ID + "_CDR1"] + mutationdic[ID + "_FR2"] + mutationdic[ID + "_CDR2"] + mutationdic[ID + "_FR3"]
 
-			fr1Length = int(linesplt[fr1LengthIndex])
-			fr2Length = int(linesplt[fr2LengthIndex])
-			fr3Length = int(linesplt[fr3LengthIndex])
-			cdr1Length = int(linesplt[cdr1LengthIndex])
-			cdr2Length = int(linesplt[cdr2LengthIndex])
+			fr1Length = int_or_zero(linesplt[fr1LengthIndex])
+			fr2Length = int_or_zero(linesplt[fr2LengthIndex])
+			fr3Length = int_or_zero(linesplt[fr3LengthIndex])
+			cdr1Length = int_or_zero(linesplt[cdr1LengthIndex])
+			cdr2Length = int_or_zero(linesplt[cdr2LengthIndex])
 			LengthDic[ID] = (fr1Length, cdr1Length, fr2Length, cdr2Length, fr3Length)
 
-			cdr1AALengthDic[ID] = int(linesplt[cdr1AALengthIndex])
-			cdr2AALengthDic[ID] = int(linesplt[cdr2AALengthIndex])
+			cdr1AALengthDic[ID] = int_or_zero(linesplt[cdr1AALengthIndex])
+			cdr2AALengthDic[ID] = int_or_zero(linesplt[cdr2AALengthIndex])
 
 			IDlist += [ID]
 	print("len(mutationdic) =", len(mutationdic))
@@ -222,6 +229,8 @@ def main():
 		# We determine the position to start summing below.
 		# This returns 0 for leader, 1 for FR1 etc.
 		length_start_pos = REGION_FILTERS.index(empty_region_filter)
+		if empty_region_filter == "None":
+			length_start_pos = 0
 
 		o.write("Sequence.ID\tnumber_of_mutations\tnumber_of_tandems\tregion_length\texpected_tandems\tlongest_tandem\ttandems\n")
 		for ID in IDlist:

shm_csr.xml

@@ -59,6 +59,7 @@
 			<option value="FR1" selected="true">FR1: include CDR1,FR2,CDR2,FR3 in filters</option>
 			<option value="CDR1">CDR1: include FR2,CDR2,FR3 in filters</option>
 			<option value="FR2">FR2: include CDR2,FR3 in filters</option>
+			<option value="None">No filter: sequences with mission regions are not filtered.</option>
 		</param>
 		<param name="functionality" type="select" label="Functionality filter" help="" >
 			<option value="productive" selected="true">Productive (Productive and Productive see comment)</option>

wrapper.sh

@@ -31,7 +31,7 @@ NEW_IMGT_PREFIX=${NEW_IMGT_PREFIX// /_}
 #exec 5> debug_output.txt
 #BASH_XTRACEFD="5"
 ## Busybox date does not support '+%s.%N'. So use a custom program. Can be
-## Compiled with cc -Os show_time_as_float.c -o show_time_as_float
+## Compiled with cc -static -Os show_time_as_float.c -o show_time_as_float
 #PS4='$(${dir}/show_time_as_float) $LINENO: '
 #set -x